From 4ebf780868a5b4dd425534816cfd32bcc618237b Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:10:26 +0100 Subject: [PATCH 01/23] docs(telemetry): drop the plan-folder pointer from the trace_state note The trace_state comment pointed at a planning document that is not part of the shipped tree, so the reference would dangle for any reader of the repository. State the reserved-and-inert fact on its own. --- include/xrpl/proto/xrpl.proto | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/xrpl/proto/xrpl.proto b/include/xrpl/proto/xrpl.proto index b13c3d0b16..56fb3d0056 100644 --- a/include/xrpl/proto/xrpl.proto +++ b/include/xrpl/proto/xrpl.proto @@ -95,9 +95,8 @@ message TMPublicKey { // Older peers that do not understand field 1001 will simply ignore it // per protobuf wire-format rules, preserving backwards compatibility. // -// trace_state is reserved for future use (secure tracing pipeline, -// OpenTelemetryPlan/secure-OTel.md). It is currently neither populated -// on inject nor read on extract; consumers must not rely on it. +// trace_state is reserved for future use. It is currently neither +// populated on inject nor read on extract; consumers must not rely on it. message TraceContext { optional bytes trace_id = 1; // 16-byte trace identifier optional bytes span_id = 2; // 8-byte parent span identifier From 6ac68abfb56d629367bbb3b5ae26e54d4e03186c Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:11:07 +0100 Subject: [PATCH 02/23] docs(telemetry): drop plan-document pointers from consensus tracing comments These comments pointed at a planning folder and at its rollout phase numbering, neither of which is part of the shipped tree, so the references would dangle for any reader of the repository. Each comment now states the fact it was pointing at. --- include/xrpl/telemetry/TraceContextPropagator.h | 11 ++++------- src/xrpld/app/consensus/RCLConsensus.cpp | 6 +++--- src/xrpld/app/consensus/RCLConsensus.h | 6 +++--- src/xrpld/telemetry/ConsensusReceiveTracing.h | 3 ++- 4 files changed, 12 insertions(+), 14 deletions(-) diff --git a/include/xrpl/telemetry/TraceContextPropagator.h b/include/xrpl/telemetry/TraceContextPropagator.h index e8d851e53e..9933e79292 100644 --- a/include/xrpl/telemetry/TraceContextPropagator.h +++ b/include/xrpl/telemetry/TraceContextPropagator.h @@ -101,13 +101,10 @@ injectToProtobuf(opentelemetry::context::Context const& ctx, protocol::TraceCont // Serialize flags proto.set_trace_flags(spanCtx.trace_flags().flags()); - // TODO(observability/secure-OTel): the protobuf TraceContext message - // also carries `trace_state` (field 4), which is currently neither - // populated here nor read by extractFromProtobuf above. The field is - // reserved for the secure tracing pipeline outlined in - // OpenTelemetryPlan/secure-OTel.md, where an authenticated token in - // tracestate will let receivers reject spoofed/poisoned trace context. - // Wire trace_state through inject/extract once the consumer lands. + // TODO: the protobuf TraceContext message also carries `trace_state` + // (field 4), which is currently neither populated here nor read by + // extractFromProtobuf above. The field is reserved for future use; + // wire it through inject/extract once a consumer lands. } } // namespace xrpl::telemetry diff --git a/src/xrpld/app/consensus/RCLConsensus.cpp b/src/xrpld/app/consensus/RCLConsensus.cpp index 35f5ed2131..5d8fb2ae5f 100644 --- a/src/xrpld/app/consensus/RCLConsensus.cpp +++ b/src/xrpld/app/consensus/RCLConsensus.cpp @@ -274,9 +274,9 @@ RCLConsensus::Adaptor::propose(RCLCxPeerPos::Proposal const& proposal) app_.getHashRouter().addSuppression(suppression); - // Inject the current thread's active span context (e.g. the - // consensus round span from Phase 4) so receiving peers can link - // their proposal.receive span as a child of this trace. + // Inject the current thread's active span context (e.g. the consensus + // round span) so receiving peers can link their proposal.receive span + // as a child of this trace. telemetry::SpanGuard::injectCurrentContextToProtobuf(*prop.mutable_trace_context()); app_.getOverlay().broadcast(prop); diff --git a/src/xrpld/app/consensus/RCLConsensus.h b/src/xrpld/app/consensus/RCLConsensus.h index 1ada9e7ee9..a7057e2f3a 100644 --- a/src/xrpld/app/consensus/RCLConsensus.h +++ b/src/xrpld/app/consensus/RCLConsensus.h @@ -127,9 +127,9 @@ class RCLConsensus * * Captured in makeAcceptSpan() and consumed by createValidationSpan() * on the jtACCEPT worker thread so the validation.send span can be - * follows-from linked to consensus.accept (matching the design doc - * and span hierarchy diagram). Reset on each startRoundTracing() - * to prevent a stale prior-round context from being linked. + * follows-from linked to consensus.accept. Reset on each + * startRoundTracing() to prevent a stale prior-round context from + * being linked. * * Thread safety: same model as roundSpanContext_. The write in * makeAcceptSpan happens on the main consensus thread under diff --git a/src/xrpld/telemetry/ConsensusReceiveTracing.h b/src/xrpld/telemetry/ConsensusReceiveTracing.h index 03974c5473..0a1a4458dc 100644 --- a/src/xrpld/telemetry/ConsensusReceiveTracing.h +++ b/src/xrpld/telemetry/ConsensusReceiveTracing.h @@ -34,7 +34,8 @@ * * @note Span names come from the canonical constants in * ConsensusSpanNames.h (consensus::span::proposalReceive / - * validationReceive) so they stay in sync with the rest of Phase 4. + * validationReceive) so they stay in sync with the rest of the + * consensus tracing surface. */ #include From c4888dd066c810a152d33a2e89768955218dca63 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:11:14 +0100 Subject: [PATCH 03/23] test(telemetry): label the native-metrics section by what it verifies The label carried a rollout phase number defined only in a planning folder outside the shipped tree. The descriptive half already identifies the section. --- docker/telemetry/integration-test.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/telemetry/integration-test.sh b/docker/telemetry/integration-test.sh index 3e9ac410f2..9b9a7ab3b6 100755 --- a/docker/telemetry/integration-test.sh +++ b/docker/telemetry/integration-test.sh @@ -543,7 +543,7 @@ fi # Step 10b: Verify native OTel metrics in Prometheus (beast::insight) # --------------------------------------------------------------------------- log "" -log "--- Phase 7: Native OTel Metrics (beast::insight via OTLP) ---" +log "--- Native OTel Metrics (beast::insight via OTLP) ---" log "Waiting 20s for OTLP metric export + Prometheus scrape..." sleep 20 From 2bac88e67cc5da97345e5bf2d7a2b4171c3e73f1 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:11:54 +0100 Subject: [PATCH 04/23] test(telemetry): label integration-test sections by what they verify The section labels carried rollout phase numbers that are defined only in a planning folder outside the shipped tree, so they meant nothing to a reader of the repository. The descriptive half of each label already identifies the section. --- docker/telemetry/integration-test.sh | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/docker/telemetry/integration-test.sh b/docker/telemetry/integration-test.sh index f8263df63a..ba0974f2f4 100755 --- a/docker/telemetry/integration-test.sh +++ b/docker/telemetry/integration-test.sh @@ -409,7 +409,7 @@ for attempt in $(seq 1 60); do done # --------------------------------------------------------------------------- -# Step 7: Exercise RPC spans (Phase 2) +# Step 7: Exercise RPC spans # --------------------------------------------------------------------------- log "Exercising RPC spans..." @@ -424,7 +424,7 @@ log "RPC commands sent. Waiting 5s for batch export..." sleep 5 # --------------------------------------------------------------------------- -# Step 8: Submit transaction (Phase 3) +# Step 8: Submit transaction # --------------------------------------------------------------------------- log "Submitting Payment transaction..." @@ -477,7 +477,7 @@ else fi log "" -log "--- Phase 2: RPC Spans ---" +log "--- RPC Spans ---" check_span "rpc.request" check_span "rpc.process" check_span "rpc.command.server_info" @@ -485,26 +485,26 @@ check_span "rpc.command.server_state" check_span "rpc.command.ledger" log "" -log "--- Phase 3: Transaction Spans ---" +log "--- Transaction Spans ---" check_span "tx.process" check_span "tx.receive" check_span "tx.apply" log "" -log "--- Phase 4: Consensus Spans ---" +log "--- Consensus Spans ---" check_span "consensus.proposal.send" check_span "consensus.ledger_close" check_span "consensus.accept" check_span "consensus.validation.send" log "" -log "--- Phase 5: Ledger Spans ---" +log "--- Ledger Spans ---" check_span "ledger.build" check_span "ledger.validate" check_span "ledger.store" log "" -log "--- Phase 5: Peer Spans (trace_peer=1) ---" +log "--- Peer Spans (trace_peer=1) ---" check_span "peer.proposal.receive" check_span "peer.validation.receive" @@ -512,7 +512,7 @@ check_span "peer.validation.receive" # Step 10: Verify Prometheus spanmetrics # --------------------------------------------------------------------------- log "" -log "--- Phase 5: Spanmetrics ---" +log "--- Spanmetrics ---" log "Waiting 20s for Prometheus scrape cycle..." sleep 20 @@ -543,7 +543,7 @@ fi # Step 10b: Verify StatsD metrics in Prometheus # --------------------------------------------------------------------------- log "" -log "--- Phase 6: StatsD Metrics (beast::insight) ---" +log "--- StatsD Metrics (beast::insight) ---" log "Waiting 20s for StatsD aggregation + Prometheus scrape..." sleep 20 From 68b94e625c7fc594e3bde8d686694718d1e4e7c5 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:13:59 +0100 Subject: [PATCH 05/23] docs(telemetry): name log-trace correlation instead of its phase number These comments and headings identified the feature by a rollout phase number defined only in a planning folder outside the shipped tree, so the label meant nothing to a reader of the repository. --- docker/telemetry/TESTING.md | 10 +++++----- docker/telemetry/docker-compose.yml | 2 +- docker/telemetry/integration-test.sh | 2 +- docker/telemetry/otel-collector-config.yaml | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/docker/telemetry/TESTING.md b/docker/telemetry/TESTING.md index 21fb098d27..a1f21dded7 100644 --- a/docker/telemetry/TESTING.md +++ b/docker/telemetry/TESTING.md @@ -472,9 +472,9 @@ Pre-configured datasources: --- -## Test 3: Log-Trace Correlation (Phase 8) +## Test 3: Log-Trace Correlation -Phase 8 injects `trace_id` and `span_id` into xrpld's log output when +xrpld injects `trace_id` and `span_id` into its log output when a log line is emitted within an active OTel span. This test verifies the end-to-end log-trace correlation pipeline. @@ -591,7 +591,7 @@ Expected: > 0 results. 2. Check submit response for error codes 3. In standalone mode, remember to call `ledger_accept` after submitting -### No trace_id in log output (Phase 8) +### No trace_id in log output 1. Verify xrpld was built with `telemetry=ON` (`-Dtelemetry=ON` in CMake) 2. Verify `enabled=1` in the `[telemetry]` config section @@ -600,7 +600,7 @@ Expected: > 0 results. `trace_id`/`span_id`. 4. Ensure the trace category is enabled (e.g., `trace_rpc=1` for RPC logs) -### No logs in Loki (Phase 8) +### No logs in Loki 1. Verify the log file mount in docker-compose.yml: ```yaml @@ -621,7 +621,7 @@ Expected: > 0 results. 4. Verify the filelog receiver glob pattern matches your log files: The default pattern is `/var/log/xrpld/*/debug.log` -### Grafana trace-log links not working (Phase 8) +### Grafana trace-log links not working 1. Verify `tracesToLogs` is configured in the Tempo datasource provisioning (`docker/telemetry/grafana/provisioning/datasources/tempo.yaml`) diff --git a/docker/telemetry/docker-compose.yml b/docker/telemetry/docker-compose.yml index 51c1993eed..44709c4ca8 100644 --- a/docker/telemetry/docker-compose.yml +++ b/docker/telemetry/docker-compose.yml @@ -8,7 +8,7 @@ # - tempo: Grafana Tempo tracing backend, queryable via Grafana Explore # on port 3000. Recommended for production (S3/GCS storage, TraceQL). # - loki: Grafana Loki log aggregation backend for centralized log -# ingestion and log-trace correlation (Phase 8). +# ingestion and log-trace correlation. # - grafana: dashboards on port 3000, pre-configured with Tempo, # Prometheus, and Loki datasources. # diff --git a/docker/telemetry/integration-test.sh b/docker/telemetry/integration-test.sh index dd209a53ad..c24bc55fc3 100755 --- a/docker/telemetry/integration-test.sh +++ b/docker/telemetry/integration-test.sh @@ -562,7 +562,7 @@ check_span "peer.proposal.receive" check_span "peer.validation.receive" # --------------------------------------------------------------------------- -# Step 9b: Verify log-trace correlation (Phase 8) +# Step 9b: Verify log-trace correlation # --------------------------------------------------------------------------- log "" log "--- Log-Trace Correlation ---" diff --git a/docker/telemetry/otel-collector-config.yaml b/docker/telemetry/otel-collector-config.yaml index 1c8e214c0e..8025232113 100644 --- a/docker/telemetry/otel-collector-config.yaml +++ b/docker/telemetry/otel-collector-config.yaml @@ -3,7 +3,7 @@ # Pipelines: # traces: OTLP receiver -> batch processor -> debug + Tempo + spanmetrics # metrics: OTLP receiver + spanmetrics connector -> Prometheus exporter -# logs: filelog receiver -> batch processor -> otlphttp/Loki (Phase 8) +# logs: filelog receiver -> batch processor -> otlphttp/Loki # # xrpld sends traces via OTLP/HTTP to port 4318. The collector batches # them, forwards to Tempo, and derives RED metrics via the spanmetrics From 8670e31d6c0f12af68a24cbf729c17d750a537d4 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:17:02 +0100 Subject: [PATCH 06/23] docs(telemetry): drop rollout phase numbers from the span catalog The catalog tagged every span with a rollout phase number defined only in a planning folder outside the shipped tree, so the column meant nothing to a reader of the repository. The span name and source file identify each entry. --- docker/telemetry/TESTING.md | 42 ++++++++++++++++++------------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/docker/telemetry/TESTING.md b/docker/telemetry/TESTING.md index 2a6cfac9f2..723371a888 100644 --- a/docker/telemetry/TESTING.md +++ b/docker/telemetry/TESTING.md @@ -372,28 +372,28 @@ See the "Verification Queries" section below. ## Expected Span Catalog -All 16 production span names instrumented across Phases 2-5: +All 16 production span names: -| Span Name | Source File | Phase | Key Attributes | How to Trigger | -| --------------------------- | ----------------- | ----- | ---------------------------------------------------------------------------------------- | ------------------------- | -| `rpc.http_request` | ServerHandler.cpp | 2 | -- | Any HTTP RPC call | -| `rpc.ws_upgrade` | ServerHandler.cpp | 2 | -- | WebSocket upgrade | -| `rpc.ws_message` | ServerHandler.cpp | 2 | -- | WebSocket RPC message | -| `rpc.process` | ServerHandler.cpp | 2 | -- | RPC processing | -| `rpc.command.` | RPCHandler.cpp | 2 | `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role` | Any RPC command | -| `tx.process` | NetworkOPs.cpp | 3 | `xrpl.tx.hash`, `xrpl.tx.local`, `xrpl.tx.path` | Submit transaction | -| `tx.receive` | PeerImp.cpp | 3 | `xrpl.peer.id` | Peer relays transaction | -| `consensus.proposal.send` | RCLConsensus.cpp | 4 | `xrpl.consensus.round` | Consensus proposing phase | -| `consensus.ledger_close` | RCLConsensus.cpp | 4 | `xrpl.consensus.ledger.seq`, `xrpl.consensus.mode` | Ledger close event | -| `consensus.accept` | RCLConsensus.cpp | 4 | `xrpl.consensus.proposers`, `xrpl.consensus.round_time_ms` | Ledger accepted | -| `consensus.validation.send` | RCLConsensus.cpp | 4 | `xrpl.consensus.ledger.seq`, `xrpl.consensus.proposing` | Validation sent | -| `consensus.accept.apply` | RCLConsensus.cpp | 4 | `xrpl.consensus.close_time`, `close_time_correct`, `close_resolution_ms`, `state` | Ledger apply + close time | -| `tx.apply` | BuildLedger.cpp | 5 | `xrpl.ledger.tx_count`, `xrpl.ledger.tx_failed` | Ledger close (tx set) | -| `ledger.build` | BuildLedger.cpp | 5 | `xrpl.ledger.seq`, `xrpl.ledger.close_time`, `close_time_correct`, `close_resolution_ms` | Ledger build | -| `ledger.validate` | LedgerMaster.cpp | 5 | `xrpl.ledger.seq`, `xrpl.ledger.validations` | Ledger validated | -| `ledger.store` | LedgerMaster.cpp | 5 | `xrpl.ledger.seq` | Ledger stored | -| `peer.proposal.receive` | PeerImp.cpp | 5 | `xrpl.peer.id`, `xrpl.peer.proposal.trusted` | Peer sends proposal | -| `peer.validation.receive` | PeerImp.cpp | 5 | `xrpl.peer.id`, `xrpl.peer.validation.trusted` | Peer sends validation | +| Span Name | Source File | Key Attributes | How to Trigger | +| --------------------------- | ----------------- | ---------------------------------------------------------------------------------------- | ------------------------- | +| `rpc.http_request` | ServerHandler.cpp | -- | Any HTTP RPC call | +| `rpc.ws_upgrade` | ServerHandler.cpp | -- | WebSocket upgrade | +| `rpc.ws_message` | ServerHandler.cpp | -- | WebSocket RPC message | +| `rpc.process` | ServerHandler.cpp | -- | RPC processing | +| `rpc.command.` | RPCHandler.cpp | `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role` | Any RPC command | +| `tx.process` | NetworkOPs.cpp | `xrpl.tx.hash`, `xrpl.tx.local`, `xrpl.tx.path` | Submit transaction | +| `tx.receive` | PeerImp.cpp | `xrpl.peer.id` | Peer relays transaction | +| `consensus.proposal.send` | RCLConsensus.cpp | `xrpl.consensus.round` | Consensus proposing phase | +| `consensus.ledger_close` | RCLConsensus.cpp | `xrpl.consensus.ledger.seq`, `xrpl.consensus.mode` | Ledger close event | +| `consensus.accept` | RCLConsensus.cpp | `xrpl.consensus.proposers`, `xrpl.consensus.round_time_ms` | Ledger accepted | +| `consensus.validation.send` | RCLConsensus.cpp | `xrpl.consensus.ledger.seq`, `xrpl.consensus.proposing` | Validation sent | +| `consensus.accept.apply` | RCLConsensus.cpp | `xrpl.consensus.close_time`, `close_time_correct`, `close_resolution_ms`, `state` | Ledger apply + close time | +| `tx.apply` | BuildLedger.cpp | `xrpl.ledger.tx_count`, `xrpl.ledger.tx_failed` | Ledger close (tx set) | +| `ledger.build` | BuildLedger.cpp | `xrpl.ledger.seq`, `xrpl.ledger.close_time`, `close_time_correct`, `close_resolution_ms` | Ledger build | +| `ledger.validate` | LedgerMaster.cpp | `xrpl.ledger.seq`, `xrpl.ledger.validations` | Ledger validated | +| `ledger.store` | LedgerMaster.cpp | `xrpl.ledger.seq` | Ledger stored | +| `peer.proposal.receive` | PeerImp.cpp | `xrpl.peer.id`, `xrpl.peer.proposal.trusted` | Peer sends proposal | +| `peer.validation.receive` | PeerImp.cpp | `xrpl.peer.id`, `xrpl.peer.validation.trusted` | Peer sends validation | --- From 974835589ae22f6b6022d552fe105e24fcefbca8 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:19:49 +0100 Subject: [PATCH 07/23] docs(telemetry): drop the plan task reference from a StatsD panel note Two panel descriptions pointed at a rollout phase and task number defined only in a planning folder outside the shipped tree. The note still names the file and the change it is waiting on, which is the part a reader can act on. --- .../telemetry/grafana/dashboards/statsd-rpc-pathfinding.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json b/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json index a30a3aa82b..fb417c40a0 100644 --- a/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json +++ b/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json @@ -287,7 +287,7 @@ }, { "title": "Resource Warnings Rate", - "description": "Rate of resource warning events from the Resource Manager. Sourced from the warn meter (Logic.h) which increments when a consumer (peer or RPC client) exceeds the warning threshold for resource usage. A rising rate indicates aggressive clients that may need throttling. NOTE: This panel will show no data until the |m -> |c fix is applied in StatsDCollector.cpp (Phase 6 Task 6.1).", + "description": "Rate of resource warning events from the Resource Manager. Sourced from the warn meter (Logic.h) which increments when a consumer (peer or RPC client) exceeds the warning threshold for resource usage. A rising rate indicates aggressive clients that may need throttling. NOTE: This panel will show no data until the |m -> |c fix is applied in StatsDCollector.cpp.", "type": "stat", "gridPos": { "h": 8, @@ -335,7 +335,7 @@ }, { "title": "Resource Drops Rate", - "description": "Rate of resource drop events from the Resource Manager. Sourced from the drop meter (Logic.h) which increments when a consumer is disconnected or blocked due to excessive resource usage. Non-zero values mean the node is actively rejecting abusive connections. NOTE: This panel will show no data until the |m -> |c fix is applied in StatsDCollector.cpp (Phase 6 Task 6.1).", + "description": "Rate of resource drop events from the Resource Manager. Sourced from the drop meter (Logic.h) which increments when a consumer is disconnected or blocked due to excessive resource usage. Non-zero values mean the node is actively rejecting abusive connections. NOTE: This panel will show no data until the |m -> |c fix is applied in StatsDCollector.cpp.", "type": "stat", "gridPos": { "h": 8, From be8f987b39bce4aca140b1aa0db8ff83da96933b Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:21:25 +0100 Subject: [PATCH 08/23] docs(telemetry): drop the phase number from a node-health row title The row was titled after the rollout phase its metrics came from, a number defined only in a planning folder outside the shipped tree. Grafana shows this title to operators, so it named something no reader could look up. --- docker/telemetry/grafana/dashboards/node-health.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/telemetry/grafana/dashboards/node-health.json b/docker/telemetry/grafana/dashboards/node-health.json index 00e04b9b84..c01f5b4301 100644 --- a/docker/telemetry/grafana/dashboards/node-health.json +++ b/docker/telemetry/grafana/dashboards/node-health.json @@ -441,7 +441,7 @@ "id": 8 }, { - "title": "--- Extended Metrics (Recovered from Phase 6) ---", + "title": "--- Extended Metrics ---", "type": "row", "gridPos": { "h": 1, From ddda820591e69acda3c393f6098e43e7591673c4 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:44:19 +0100 Subject: [PATCH 09/23] fix(perflog): record OTel metrics outside the counter locks rpcStart, jobQueue, jobStart and jobFinish each acquired a lock without braces, so it stayed held to the end of the function and covered the OTel recording calls this branch added. counters_.jobsMutex and counters_.methodsMutex are process-wide, so every worker thread starting or finishing a job serialised on the SDK's work. That work is not a bare atomic add: each record builds a map-backed attribute set and takes a spin lock inside the SDK, whose backoff reaches a millisecond-scale sleep under contention. Brace the lock plus the state it guards, then record after it releases. None of the metric calls read lock-protected state, so this is semantics-preserving, and rpcEnd() in the same file already had this shape. --- src/xrpld/perflog/detail/PerfLogImp.cpp | 44 +++++++++++++++++-------- 1 file changed, 30 insertions(+), 14 deletions(-) diff --git a/src/xrpld/perflog/detail/PerfLogImp.cpp b/src/xrpld/perflog/detail/PerfLogImp.cpp index f43464dd1d..106c36f157 100644 --- a/src/xrpld/perflog/detail/PerfLogImp.cpp +++ b/src/xrpld/perflog/detail/PerfLogImp.cpp @@ -331,10 +331,15 @@ PerfLogImp::rpcStart(std::string const& method, std::uint64_t const requestId) std::scoped_lock const lock(counter->second.mutex); ++counter->second.value.started; } - std::scoped_lock const lock(counters_.methodsMutex); - counters_.methods[requestId] = {counter->first.c_str(), steady_clock::now()}; + { + std::scoped_lock const lock(counters_.methodsMutex); + counters_.methods[requestId] = {counter->first.c_str(), steady_clock::now()}; + } - // Task 9.4: Record RPC start in OTel metrics pipeline. + // Task 9.4: Record RPC start in OTel metrics pipeline. Recorded after the + // locks above are released: the OTel call path allocates and takes locks + // inside the SDK, so holding methodsMutex across it would widen a + // process-wide critical section for no reason. Mirrors rpcEnd(). if (auto* mr = app_.getMetricsRegistry()) mr->recordRpcStarted(method); @@ -424,10 +429,13 @@ PerfLogImp::jobQueue(JobType const type, std::string const& name) return; // LCOV_EXCL_STOP } - std::scoped_lock const lock(counter->second.mutex); - ++counter->second.value.queued; + { + std::scoped_lock const lock(counter->second.mutex); + ++counter->second.value.queued; + } - // Task 9.5: Record job enqueue in OTel metrics pipeline. + // Task 9.5: Record job enqueue in OTel metrics pipeline, after the lock + // above is released so the SDK's work stays outside the critical section. if (auto* mr = app_.getMetricsRegistry()) mr->recordJobQueued(JobTypes::name(type), name); } @@ -454,11 +462,16 @@ PerfLogImp::jobStart( ++counter->second.value.started; counter->second.value.queuedDuration += dur; } - std::scoped_lock const lock(counters_.jobsMutex); - if (instance >= 0 && instance < counters_.jobs.size()) - counters_.jobs[instance] = {type, startTime}; + { + std::scoped_lock const lock(counters_.jobsMutex); + if (instance >= 0 && instance < counters_.jobs.size()) + counters_.jobs[instance] = {type, startTime}; + } - // Task 9.5: Record job start in OTel metrics pipeline. + // Task 9.5: Record job start in OTel metrics pipeline, after the locks + // above are released. jobsMutex is process-wide and taken by every worker + // thread on every job, so the SDK's allocation and internal locking must + // not run inside it. if (auto* mr = app_.getMetricsRegistry()) mr->recordJobStarted(JobTypes::name(type), name, dur.count()); } @@ -480,11 +493,14 @@ PerfLogImp::jobFinish(JobType const type, std::string const& name, microseconds ++counter->second.value.finished; counter->second.value.runningDuration += dur; } - std::scoped_lock const lock(counters_.jobsMutex); - if (instance >= 0 && instance < counters_.jobs.size()) - counters_.jobs[instance] = {JtInvalid, steady_time_point()}; + { + std::scoped_lock const lock(counters_.jobsMutex); + if (instance >= 0 && instance < counters_.jobs.size()) + counters_.jobs[instance] = {JtInvalid, steady_time_point()}; + } - // Task 9.5: Record job finish in OTel metrics pipeline. + // Task 9.5: Record job finish in OTel metrics pipeline, after the locks + // above are released, for the same reason as jobStart(). if (auto* mr = app_.getMetricsRegistry()) mr->recordJobFinished(JobTypes::name(type), name, dur.count()); } From b4ee0b2f4457bfca1e021c335453dc2c20035569 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:44:23 +0100 Subject: [PATCH 10/23] feat(ledger): mark abandoned ledger acquisitions on the acquire span An InboundLedger destroyed while !isDone() recorded recordAbort() in the metrics but left ledger.acquire carrying only the attributes set at construction, so an abandoned acquisition was indistinguishable from one still in flight. Set outcome=aborted plus timeouts on that path, and add the val::aborted constant. peer_count is deliberately omitted: reading it goes through Overlay, and a destructor must not depend on Overlay still existing. The status stays Unset for an abort, because InboundLedgers::stop() clears every in-flight acquisition, so a clean shutdown would otherwise report errors. done() now sets Error when failed_, which is an unambiguous failure of the operation. Success is left Unset rather than Ok, per the OpenTelemetry guidance that instrumentation should not assert Ok. --- src/xrpld/app/ledger/detail/InboundLedger.cpp | 31 +++++++++++++++++++ src/xrpld/app/ledger/detail/LedgerSpanNames.h | 6 ++++ 2 files changed, 37 insertions(+) diff --git a/src/xrpld/app/ledger/detail/InboundLedger.cpp b/src/xrpld/app/ledger/detail/InboundLedger.cpp index 742313f915..fbe129b37e 100644 --- a/src/xrpld/app/ledger/detail/InboundLedger.cpp +++ b/src/xrpld/app/ledger/detail/InboundLedger.cpp @@ -227,6 +227,27 @@ InboundLedger::~InboundLedger() // the whole acquisition has to start over. That is the expensive case, // so it is counted apart from a cheap abort that had nothing yet. app_.getAcquireStats().recordAbort(haveHeader_ || haveState_ || haveTransactions_); + + // Mark the span so an abandoned acquisition is distinguishable from one + // that was still in flight when the trace was read. Without this the + // span still ends (the guard's destructor calls End()) but carries only + // the attributes set at construction, and the collector's spanmetrics + // `outcome` dimension has nothing to group these under. + // + // peer_count is deliberately NOT recorded here, unlike done(): reading + // it goes through getPeerCount() -> app_.getOverlay(), and a destructor + // must not depend on Overlay still existing. InboundLedgers::stop() + // normally clears the map while Overlay is alive, but a shared_ptr held + // past that point would destroy this object after Overlay is gone. + if (acquireSpan_ && *acquireSpan_) + { + using namespace telemetry; + acquireSpan_->setAttribute( + ledger_span::attr::outcome, std::string_view(ledger_span::val::aborted)); + acquireSpan_->setAttribute( + ledger_span::attr::timeouts, static_cast(timeouts_)); + } + JLOG(journal_.debug()) << "Acquire " << hash_ << " abort " << ((timeouts_ == 0) ? std::string() : (std::string("timeouts:") + @@ -513,6 +534,16 @@ InboundLedger::done() ledger_span::attr::timeouts, static_cast(timeouts_)); acquireSpan_->setAttribute( ledger_span::attr::peerCount, static_cast(getPeerCount())); + + // Only the failure path gets an Error status. Success is left Unset + // rather than Ok: per the OpenTelemetry spec, Ok is reserved for an + // application deliberately asserting verified success, and + // instrumentation should not set it. The abort path in the + // destructor is also left Unset, because a clean shutdown clears + // every in-flight acquisition and would otherwise report an error + // on every stop. + if (failed_) + acquireSpan_->setError("ledger acquisition gave up"); } JLOG(journal_.debug()) << "Acquire " << hash_ << (failed_ ? " fail " : " ") diff --git a/src/xrpld/app/ledger/detail/LedgerSpanNames.h b/src/xrpld/app/ledger/detail/LedgerSpanNames.h index 4de4d24824..361313c4bf 100644 --- a/src/xrpld/app/ledger/detail/LedgerSpanNames.h +++ b/src/xrpld/app/ledger/detail/LedgerSpanNames.h @@ -65,6 +65,12 @@ namespace val { */ inline constexpr auto complete = makeStr("complete"); inline constexpr auto failed = makeStr("failed"); +/** + * Set when the acquisition is abandoned before it finishes, i.e. the + * InboundLedger is destroyed while !isDone(). Distinct from `failed`, which + * means the fetch ran to its retry limit and gave up. + */ +inline constexpr auto aborted = makeStr("aborted"); /** * ledger.acquire reason values (mirror InboundLedger::Reason). */ From 74db74a7793a97134625edd0df54c5050e4f4e03 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:44:27 +0100 Subject: [PATCH 11/23] fix(telemetry): drop the duplicate protobuf include The test carried both and the bare . Both resolve to the same generated header, because the proto helper puts the generated tree and its prefixed subdirectory on the target, so the second include expanded to nothing behind the header guard. The bare form arrived from merging two same-day clang-tidy commits that added the include with different spellings. Keep the prefixed spelling, which is what the telemetry headers and the upstream phase branches use. --- src/tests/libxrpl/telemetry/TraceContextPropagator.cpp | 2 -- 1 file changed, 2 deletions(-) diff --git a/src/tests/libxrpl/telemetry/TraceContextPropagator.cpp b/src/tests/libxrpl/telemetry/TraceContextPropagator.cpp index fdc6c443cb..aa0bbf8903 100644 --- a/src/tests/libxrpl/telemetry/TraceContextPropagator.cpp +++ b/src/tests/libxrpl/telemetry/TraceContextPropagator.cpp @@ -17,8 +17,6 @@ #include #include -#include - #include #include From 19f49cf9613e56cb148ec34df8304c8d374c5217 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:45:09 +0100 Subject: [PATCH 12/23] docs(telemetry): explain the telemetry dependency loop and the Compose floor Two comment-only notes. MetricsRegistry.cpp: record why the app and overlay includes exist and what they cost. They are what makes loops.txt carry xrpld.app <-> xrpld.telemetry and xrpld.overlay <-> xrpld.telemetry, where ordering.txt previously had telemetry strictly below both. The observable gauges are pull-model, so their callbacks need the concrete types to sample live state. The cycle is confined to this translation unit: no telemetry header includes app or overlay, and all of src/xrpld builds into one target, so there is no header or link cycle. Inverting it needs a metrics-source interface below overlay, which is left as follow-up. Also note loops.txt is generated and must never be hand-edited. docker-compose.yml: state the Compose >= 2.24.0 floor. The grafana service uses the long-form env_file mapping, which older Compose cannot parse, and it fails for the whole file rather than that one service. The long form is required because .env.alerting is gitignored and absent in a fresh clone, and the short form treats a missing env file as an error. --- docker/telemetry/docker-compose.yml | 6 ++++++ src/xrpld/telemetry/MetricsRegistry.cpp | 17 +++++++++++++++++ 2 files changed, 23 insertions(+) diff --git a/docker/telemetry/docker-compose.yml b/docker/telemetry/docker-compose.yml index 8aa2c3df64..7e3d01d182 100644 --- a/docker/telemetry/docker-compose.yml +++ b/docker/telemetry/docker-compose.yml @@ -12,6 +12,12 @@ # - grafana: dashboards on port 3000, pre-configured with Tempo, # Prometheus, and Loki datasources. # +# Requires Docker Compose >= 2.24.0. The grafana service uses the long-form +# `env_file` mapping (`path:` / `required:`), which older Compose cannot parse — +# and it fails for the whole file, not just that service. The long form is +# needed: `.env.alerting` is gitignored and absent in a fresh clone, and the +# short form treats a missing env file as an error. +# # Usage: # docker compose -f docker/telemetry/docker-compose.yml up -d # diff --git a/src/xrpld/telemetry/MetricsRegistry.cpp b/src/xrpld/telemetry/MetricsRegistry.cpp index 73af238945..40e434416d 100644 --- a/src/xrpld/telemetry/MetricsRegistry.cpp +++ b/src/xrpld/telemetry/MetricsRegistry.cpp @@ -24,6 +24,23 @@ #ifdef XRPL_ENABLE_TELEMETRY +// The app and overlay includes below are why +// .github/scripts/levelization/results/loops.txt records +// `xrpld.app <-> xrpld.telemetry` and `xrpld.overlay <-> xrpld.telemetry`, where +// ordering.txt previously had telemetry strictly below both. The observable +// gauges are pull-model: their callbacks sample live state when the reader +// thread fires, so they need the concrete types to call getJqTransOverflow(), +// size(), getPeerDisconnectCharges(), foreach() and txMetrics(). +// +// The cycle is confined to this translation unit. No telemetry header includes +// app or overlay (MetricsRegistry.h forward-declares what it needs and takes a +// ServiceRegistry&), and all of src/xrpld builds into a single CMake target, so +// there is no header cycle and no link cycle to break. +// +// Inverting it properly means declaring a metrics-source interface below overlay +// and implementing it there, which is deliberately left as follow-up rather than +// widening this change. Note loops.txt is generated: it can only change as a +// consequence of changing these includes, never by editing the baseline. #include #include #include From 004b8e92aba60b133dabd7c7052defd4ff667231 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:47:20 +0100 Subject: [PATCH 13/23] fix(telemetry): keep the work item in ledger-data-sync aggregations Nine targets across four panels filtered on xrpl_work_item while leaving it out of their sum by() grouping. PromQL keeps only the labels listed in by(), so the label was dropped from the result and the xrpl_ident legend these panels build from it lost that segment. Perf-iac runs stamp xrpl_work_item and give each work item its own set of nodes, so service_instance_id already separates the runs; the visible effect is the legend rather than merged series. Adding the label makes the work item identifiable, which is the comparison these panels exist for. NuDB Read Latency and NuDB Read Found Ratio each divide two aggregations. Both sides get the label so their label sets stay equal and vector matching still works. --- .../grafana/dashboards/ledger-data-sync.json | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/ledger-data-sync.json b/docker/telemetry/grafana/dashboards/ledger-data-sync.json index 86b41bd488..3650fb9d35 100644 --- a/docker/telemetry/grafana/dashboards/ledger-data-sync.json +++ b/docker/telemetry/grafana/dashboards/ledger-data-sync.json @@ -1225,42 +1225,42 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_ledgerdata_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"ledgerdata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(jobq_ledgerdata_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"ledgerdata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_acceptledger_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"acceptledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(jobq_acceptledger_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"acceptledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_fetchtxndata_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"fetchtxndata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(jobq_fetchtxndata_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"fetchtxndata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_transaction_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"transaction q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(jobq_transaction_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"transaction q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_advanceledger_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"advanceledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(jobq_advanceledger_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"advanceledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_ledgerrequest_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"ledgerrequest q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(jobq_ledgerrequest_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"ledgerrequest q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1305,7 +1305,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_duration_us\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"NuDB us/read\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_duration_us\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"NuDB us/read\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1350,7 +1350,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(ios_latency_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"IO Service p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(ios_latency_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"IO Service p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1395,7 +1395,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_hit\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"NuDB Found Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_hit\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"NuDB Found Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { From 87812650844283ba611929348a43c481133cc041 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:47:57 +0100 Subject: [PATCH 14/23] fix(telemetry): keep the work item in the two phase-9 sync aggregations LedgerReq Wait by Handler and NodeStore Read Latency (Bottleneck Discriminator) filter on xrpl_work_item but left it out of their sum by() grouping, so PromQL dropped the label and the xrpl_ident legend lost that segment. These two targets took their current form on this branch, so they are fixed here. The other nine in this file predate it and were fixed on pratik/otel-phase7-native-metrics, which merges forward. The discriminator panel divides two aggregations; both sides carry the label so their label sets stay equal for vector matching. --- docker/telemetry/grafana/dashboards/ledger-data-sync.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/ledger-data-sync.json b/docker/telemetry/grafana/dashboards/ledger-data-sync.json index e6e3fae3ad..9878f0ccdf 100644 --- a/docker/telemetry/grafana/dashboards/ledger-data-sync.json +++ b/docker/telemetry/grafana/dashboards/ledger-data-sync.json @@ -1703,7 +1703,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, handler, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"ledgerRequest\", handler=~\"$handler\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"$1 q-wait p99\", \"handler\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, handler, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"ledgerRequest\", handler=~\"$handler\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"$1 q-wait p99\", \"handler\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1768,7 +1768,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_duration_us\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"Read Mean (Windowed)\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_duration_us\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"Read Mean (Windowed)\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { From 8a6ecb80937edc881226ee14897258a2d84f4eaf Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:57:50 +0100 Subject: [PATCH 15/23] fix(telemetry): carry the work item through dashboard aggregations Every aggregation that filtered on xrpl_work_item left it out of its sum by() grouping, so PromQL dropped the label and the xrpl_ident legend these panels build from it rendered without the work item. 217 clauses across the touched boards. Perf-iac gives each work item its own set of nodes, so service_instance_id already separates the runs and the visible effect is the legend rather than merged series. Four clauses are the exception and aggregate across nodes, where the grouping does real work: Convergence, Lag Behind Network Tip and Build Version now measure spread, lag and version distribution within one work item instead of smearing two independent clusters together. Lag Behind Network Tip also needed its on() join key extended to match, or two coexisting work items would fail the query outright. The five heatmap inner by (le) clauses are deliberately untouched: an extra grouping label would superimpose several distributions. Also in this change: - transaction-overview gains per-type-per-stage rate and failure-rate panels, so all three requested dimensions exist rather than latency alone, and its stage-rate panel picks up the filters and legend its siblings already had. - The acquire-duration panel splits by outcome. An aborted acquisition is open until the sweep reaps it, so mixing it into one percentile conflated fetch latency with time-to-abandon. - Ledger Acquire Rate by Outcome gets the same Title Case value mapping as its neighbour, and node-health gains the $outcome variable the two panels now need. --- .../grafana/dashboards/consensus-health.json | 36 ++-- .../grafana/dashboards/fee-market.json | 4 +- .../grafana/dashboards/ledger-operations.json | 18 +- .../grafana/dashboards/network-traffic.json | 4 +- .../grafana/dashboards/node-health.json | 90 ++++++---- .../dashboards/overlay-traffic-detail.json | 16 +- .../grafana/dashboards/peer-network.json | 8 +- .../grafana/dashboards/rpc-pathfinding.json | 26 +-- .../grafana/dashboards/rpc-performance.json | 38 ++--- .../dashboards/transaction-overview.json | 157 ++++++++++++++---- .../grafana/dashboards/validator-health.json | 2 +- 11 files changed, 260 insertions(+), 139 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/consensus-health.json b/docker/telemetry/grafana/dashboards/consensus-health.json index 00579d9736..20d1b9613c 100644 --- a/docker/telemetry/grafana/dashboards/consensus-health.json +++ b/docker/telemetry/grafana/dashboards/consensus-health.json @@ -61,7 +61,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.validation.send\"}[$__rate_interval])), \"series\", \"Validations / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.validation.send\"}[$__rate_interval])), \"series\", \"Validations / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -99,7 +99,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (consensus_mode, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[$__rate_interval])), \"series\", \"$1\", \"consensus_mode\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (consensus_mode, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[$__rate_interval])), \"series\", \"$1\", \"consensus_mode\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -157,7 +157,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.proposal.send\"}[$__rate_interval])), \"series\", \"Proposals / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.proposal.send\"}[$__rate_interval])), \"series\", \"Proposals / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -202,14 +202,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\"}[$__rate_interval])), \"series\", \"Accepts / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\"}[$__rate_interval])), \"series\", \"Accepts / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.ledger_close\"}[$__rate_interval])), \"series\", \"Closes / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.ledger_close\"}[$__rate_interval])), \"series\", \"Closes / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -254,14 +254,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.validation.send\"}[$__rate_interval])), \"series\", \"Validations / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.validation.send\"}[$__rate_interval])), \"series\", \"Validations / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.ledger_close\"}[$__rate_interval])), \"series\", \"Closes / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.ledger_close\"}[$__rate_interval])), \"series\", \"Closes / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -663,7 +663,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.update_positions\"}[5m]))), \"series\", \"P95 Update\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.update_positions\"}[5m]))), \"series\", \"P95 Update\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -708,7 +708,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.round\"}[5m]))), \"series\", \"P95 Close (consensus.round)\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.round\"}[5m]))), \"series\", \"P95 Close (consensus.round)\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -746,7 +746,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept.apply\"}[5m]))), \"series\", \"P95 Apply Duration\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept.apply\"}[5m]))), \"series\", \"P95 Apply Duration\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -840,7 +840,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (close_time_correct, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{span_name=\"consensus.accept.apply\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"$1\", \"close_time_correct\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (close_time_correct, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{span_name=\"consensus.accept.apply\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"$1\", \"close_time_correct\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1005,7 +1005,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, consensus_state, xrpl_branch, xrpl_node_role) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state!=\"\"}[$__rate_interval])), \"series\", \"$1\", \"consensus_state\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, consensus_state, xrpl_branch, xrpl_node_role, xrpl_work_item) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state!=\"\"}[$__rate_interval])), \"series\", \"$1\", \"consensus_state\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1040,14 +1040,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state=\"moved_on\"}[$__rate_interval])), \"series\", \"moved_on\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state=\"moved_on\"}[$__rate_interval])), \"series\", \"moved_on\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state=\"expired\"}[$__rate_interval])), \"series\", \"expired\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state=\"expired\"}[$__rate_interval])), \"series\", \"expired\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1092,14 +1092,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.check\", consensus_stalled=\"true\"}[$__rate_interval])), \"series\", \"Stalled\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.check\", consensus_stalled=\"true\"}[$__rate_interval])), \"series\", \"Stalled\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.check\", consensus_stalled=\"false\"}[$__rate_interval])), \"series\", \"Not Stalled\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.check\", consensus_stalled=\"false\"}[$__rate_interval])), \"series\", \"Not Stalled\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1144,7 +1144,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (mode_new, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.mode_change\"}[$__rate_interval])), \"series\", \"$1\", \"mode_new\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (mode_new, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.mode_change\"}[$__rate_interval])), \"series\", \"$1\", \"mode_new\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -1189,7 +1189,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (reason, service_instance_id, xrpl_branch, xrpl_node_role) (rate(ledger_history_mismatch_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"$1\", \"reason\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (reason, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(ledger_history_mismatch_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"$1\", \"reason\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/fee-market.json b/docker/telemetry/grafana/dashboards/fee-market.json index 2d572f454c..71dd0ba6ed 100644 --- a/docker/telemetry/grafana/dashboards/fee-market.json +++ b/docker/telemetry/grafana/dashboards/fee-market.json @@ -427,7 +427,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(txq_expired_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Expired / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(txq_expired_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Expired / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -472,7 +472,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (reason, service_instance_id, xrpl_branch, xrpl_node_role) (rate(txq_dropped_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"$1\", \"reason\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (reason, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(txq_dropped_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"$1\", \"reason\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/ledger-operations.json b/docker/telemetry/grafana/dashboards/ledger-operations.json index 27ca03f666..9cc7726cb0 100644 --- a/docker/telemetry/grafana/dashboards/ledger-operations.json +++ b/docker/telemetry/grafana/dashboards/ledger-operations.json @@ -74,7 +74,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[$__rate_interval])), \"series\", \"Builds / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[$__rate_interval])), \"series\", \"Builds / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -112,7 +112,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.validate\"}[$__rate_interval])), \"series\", \"Validations / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.validate\"}[$__rate_interval])), \"series\", \"Validations / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -150,7 +150,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[5m]))), \"series\", \"P95 Build Duration\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[5m]))), \"series\", \"P95 Build Duration\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -257,7 +257,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[5m]))), \"series\", \"P95 tx.apply\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[5m]))), \"series\", \"P95 tx.apply\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -302,7 +302,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[$__rate_interval])), \"series\", \"tx.apply / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[$__rate_interval])), \"series\", \"tx.apply / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -360,7 +360,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.store\"}[$__rate_interval])), \"series\", \"Stores / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.store\"}[$__rate_interval])), \"series\", \"Stores / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -398,14 +398,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[5m]))), \"series\", \"P95 ledger.build\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[5m]))), \"series\", \"P95 ledger.build\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.round\"}[5m]))), \"series\", \"P95 Close (consensus.round)\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.round\"}[5m]))), \"series\", \"P95 Close (consensus.round)\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -457,7 +457,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(1 / sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Close Interval\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(1 / sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Close Interval\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/network-traffic.json b/docker/telemetry/grafana/dashboards/network-traffic.json index aa2ed62610..f258ff8db1 100644 --- a/docker/telemetry/grafana/dashboards/network-traffic.json +++ b/docker/telemetry/grafana/dashboards/network-traffic.json @@ -482,7 +482,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(topk(10, label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(proposals_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(validations_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(overhead_overlay_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_overlay_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ping_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ping_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(status_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"status_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(havetxset_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"havetxset_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledgerdata_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledgerdata_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_set_candidate_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_set_candidate_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"set_get_bytes_in\",\"\",\"\")), \"series\", \"$1\", \"__name__\", \"(.*)\")" + "expr": "label_replace(topk(10, label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(proposals_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(validations_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(overhead_overlay_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_overlay_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ping_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ping_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(status_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"status_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(havetxset_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"havetxset_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledgerdata_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledgerdata_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_set_candidate_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_set_candidate_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"set_get_bytes_in\",\"\",\"\")), \"series\", \"$1\", \"__name__\", \"(.*)\")" } ], "fieldConfig": { @@ -877,7 +877,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(topk(15, label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_cas_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_cas_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_cas_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_cas_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_fetch_pack_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_fetch_pack_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_fetch_pack_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_ledger_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_ledger_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_transaction_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_transaction_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(getobject_transactions_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transactions_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(have_transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"have_transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_set_candidate_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_set_candidate_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_set_candidate_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_set_candidate_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(overhead_cluster_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_cluster_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(overhead_manifest_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_manifest_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(overhead_overlay_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_overlay_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(proof_path_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proof_path_request_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(proof_path_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proof_path_response_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(proposals_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(proposals_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_duplicate_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(proposals_untrusted_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_untrusted_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(replay_delta_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"replay_delta_request_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(replay_delta_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"replay_delta_response_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(requested_transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"requested_transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"set_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(set_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"set_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(squelch_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"squelch_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(squelch_ignored_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"squelch_ignored_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(squelch_suppressed_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"squelch_suppressed_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(transactions_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"transactions_duplicate_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(unknown_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"unknown_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(validations_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(validations_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_duplicate_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(validations_untrusted_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_untrusted_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role)(rate(validator_lists_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validator_lists_bytes_in\",\"\",\"\")), \"series\", \"$1\", \"__name__\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(topk(15, label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_cas_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_cas_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_cas_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_cas_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_fetch_pack_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_fetch_pack_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_fetch_pack_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_ledger_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_ledger_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_transaction_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_transaction_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transaction_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(getobject_transactions_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"getobject_transactions_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(have_transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"have_transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_account_state_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_set_candidate_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_data_transaction_set_candidate_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_node_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_node_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_set_candidate_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"ledger_transaction_set_candidate_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(overhead_cluster_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_cluster_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(overhead_manifest_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_manifest_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(overhead_overlay_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"overhead_overlay_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(proof_path_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proof_path_request_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(proof_path_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proof_path_response_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(proposals_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(proposals_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_duplicate_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(proposals_untrusted_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"proposals_untrusted_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(replay_delta_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"replay_delta_request_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(replay_delta_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"replay_delta_response_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(requested_transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"requested_transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"set_get_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(set_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"set_share_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(squelch_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"squelch_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(squelch_ignored_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"squelch_ignored_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(squelch_suppressed_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"squelch_suppressed_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(transactions_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"transactions_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(transactions_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"transactions_duplicate_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(unknown_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"unknown_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(validations_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(validations_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_duplicate_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(validations_untrusted_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validations_untrusted_bytes_in\",\"\",\"\") or label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item)(rate(validator_lists_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])),\"__name__\",\"validator_lists_bytes_in\",\"\",\"\")), \"series\", \"$1\", \"__name__\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/node-health.json b/docker/telemetry/grafana/dashboards/node-health.json index 6791aaa147..5fcde759cd 100644 --- a/docker/telemetry/grafana/dashboards/node-health.json +++ b/docker/telemetry/grafana/dashboards/node-health.json @@ -574,7 +574,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(ios_latency_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 I/O Latency\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(ios_latency_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 I/O Latency\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" } ], @@ -2100,7 +2100,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"acceptLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Accept Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"acceptLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Accept Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" }, { @@ -2108,7 +2108,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"advanceLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Advance Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"advanceLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Advance Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "B" }, { @@ -2116,7 +2116,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"transaction\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Transaction\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"transaction\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Transaction\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "C" }, { @@ -2124,7 +2124,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"writeObjects\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Write Objects\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"writeObjects\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Write Objects\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "D" }, { @@ -2132,7 +2132,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"heartbeat\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Heartbeat\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"heartbeat\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Heartbeat\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "E" }, { @@ -2140,7 +2140,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"sweep\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Sweep\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"sweep\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Sweep\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "F" }, { @@ -2148,7 +2148,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"trustedValidation\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Validation\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"trustedValidation\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Validation\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "G" }, { @@ -2156,7 +2156,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"trustedProposal\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Proposal\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"trustedProposal\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Proposal\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "H" }, { @@ -2164,7 +2164,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"publishNewLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Publish New Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"publishNewLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Publish New Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "I" }, { @@ -2172,7 +2172,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"clientRPC\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Client RPC\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"clientRPC\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Client RPC\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "J" }, { @@ -2180,7 +2180,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"ledgerData\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Ledger Data\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{job_type=\"ledgerData\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Ledger Data\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "K" } ], @@ -2283,7 +2283,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"acceptLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Accept Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"acceptLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Accept Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" }, { @@ -2291,7 +2291,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"advanceLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Advance Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"advanceLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Advance Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "B" }, { @@ -2299,7 +2299,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"transaction\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Transaction\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"transaction\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Transaction\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "C" }, { @@ -2307,7 +2307,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"writeObjects\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Write Objects\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"writeObjects\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Write Objects\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "D" }, { @@ -2315,7 +2315,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"heartbeat\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Heartbeat\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"heartbeat\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Heartbeat\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "E" }, { @@ -2323,7 +2323,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"sweep\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Sweep\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"sweep\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Sweep\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "F" }, { @@ -2331,7 +2331,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"trustedValidation\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Validation\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"trustedValidation\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Validation\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "G" }, { @@ -2339,7 +2339,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"trustedProposal\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Proposal\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"trustedProposal\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Proposal\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "H" }, { @@ -2347,7 +2347,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"publishNewLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Publish New Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"publishNewLedger\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Publish New Ledger\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "I" }, { @@ -2355,7 +2355,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"clientRPC\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Client RPC\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"clientRPC\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Client RPC\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "J" }, { @@ -2363,7 +2363,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"ledgerData\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Ledger Data\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{job_type=\"ledgerData\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Ledger Data\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "K" } ], @@ -2466,7 +2466,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (service_instance_id, le, job_type, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"$1\", \"job_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (service_instance_id, le, job_type, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"$1\", \"job_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" } ], @@ -2569,7 +2569,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (service_instance_id, le, job_type, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"$1\", \"job_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(histogram_quantile($quantile, sum by (service_instance_id, le, job_type, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"$1\", \"job_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" } ], @@ -3503,9 +3503,9 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "max by (xrpl_network_type) (server_info{metric=\"validated_ledger_seq\",service_name=~\"$service_name\",service_instance_id=~\"$node\",xrpl_network_type=~\"$xrpl_network_type\",xrpl_branch=~\"$xrpl_branch\",xrpl_node_role=~\"$xrpl_node_role\",deployment_environment=~\"$deployment_environment\",xrpl_work_item=~\"$xrpl_work_item\"}) - min by (xrpl_network_type) (server_info{metric=\"validated_ledger_seq\",service_name=~\"$service_name\",service_instance_id=~\"$node\",xrpl_network_type=~\"$xrpl_network_type\",xrpl_branch=~\"$xrpl_branch\",xrpl_node_role=~\"$xrpl_node_role\",deployment_environment=~\"$deployment_environment\",xrpl_work_item=~\"$xrpl_work_item\"})", + "expr": "max by (xrpl_network_type, xrpl_work_item) (server_info{metric=\"validated_ledger_seq\",service_name=~\"$service_name\",service_instance_id=~\"$node\",xrpl_network_type=~\"$xrpl_network_type\",xrpl_branch=~\"$xrpl_branch\",xrpl_node_role=~\"$xrpl_node_role\",deployment_environment=~\"$deployment_environment\",xrpl_work_item=~\"$xrpl_work_item\"}) - min by (xrpl_network_type, xrpl_work_item) (server_info{metric=\"validated_ledger_seq\",service_name=~\"$service_name\",service_instance_id=~\"$node\",xrpl_network_type=~\"$xrpl_network_type\",xrpl_branch=~\"$xrpl_branch\",xrpl_node_role=~\"$xrpl_node_role\",deployment_environment=~\"$deployment_environment\",xrpl_work_item=~\"$xrpl_work_item\"})", "instant": true, - "legendFormat": "Spread [{{xrpl_network_type}}]", + "legendFormat": "Spread [{{xrpl_network_type}}] [{{xrpl_work_item}}]", "queryType": "instant", "range": false, "refId": "A" @@ -3572,9 +3572,9 @@ "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", - "expr": "sort_desc(max by (xrpl_network_type) (server_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"validated_ledger_seq\"}) - on(xrpl_network_type) group_right() server_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"validated_ledger_seq\"})", + "expr": "sort_desc(max by (xrpl_network_type, xrpl_work_item) (server_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"validated_ledger_seq\"}) - on(xrpl_network_type, xrpl_work_item) group_right() server_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"validated_ledger_seq\"})", "instant": true, - "legendFormat": "{{service_instance_id}} [{{xrpl_network_type}}]", + "legendFormat": "{{service_instance_id}} [{{xrpl_network_type}}] [{{xrpl_work_item}}]", "queryType": "instant", "range": false, "refId": "A" @@ -3636,9 +3636,9 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "count by (version) (build_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"})", + "expr": "count by (version, xrpl_work_item) (build_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"})", "instant": false, - "legendFormat": "{{version}}", + "legendFormat": "{{version}} [{{xrpl_work_item}}]", "queryType": "range", "range": true, "refId": "A" @@ -3987,7 +3987,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(1 / sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Close Interval\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(1 / sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Close Interval\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "B" } ], @@ -5001,7 +5001,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "description": "###### What this is:\n*Time to fetch a missing ledger from peers, at the 95th percentile.*\n\n###### How it's computed:\n*Per-acquire durations aggregated to their 95th percentile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; populated mainly during sync or back-fill.*\n\n###### Healthy range:\n*Low when synced; higher and more active while catching up.*\n\n###### Watch for:\n*A spike signals the node is falling behind or recovering from a fork.*\n\n###### Keywords:\n- **Ledger acquire (inbound fetch)** *(per node)* \u2014 fetching a specific missing ledger from peers; tracked by duration and outcome (complete/failed).\n- **Back-fill / catch-up** *(per node)* \u2014 fetching missing historical ledgers from peers to fill gaps or reach the network tip.\n- **Fork** *(network-wide)* \u2014 when nodes validate divergent ledger chains instead of a single agreed history.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::init`\n\n###### References:\n[Fork](https://xrpl.org/docs/concepts/consensus-protocol) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#ledger-acquire-inbound-fetch)", + "description": "###### What this is:\n*Time to fetch a missing ledger from peers, at the 95th percentile, with a separate line per acquisition outcome.*\n\n###### How it's computed:\n*Per-acquire durations aggregated to their 95th percentile per node over a 5-minute window, grouped by outcome, so complete, failed and aborted acquisitions are never mixed into one percentile.*\n\n###### Reading it:\n*Read the Complete line as the real fetch latency; lower is better, and it is populated mainly during sync or back-fill. Aborted means the acquisition was abandoned before it finished, so its span also covers the idle time it spent waiting to be reaped (at least a minute when swept, or any age when a shutdown or an admin fetch_info clear drops it) and is not comparable to a fetch time.*\n\n###### Healthy range:\n*Complete is low when synced, and higher and more active while catching up. Failed and Aborted are normally absent.*\n\n###### Watch for:\n*A spike in Complete signals the node is falling behind or recovering from a fork. A persistent Aborted line means acquisitions are routinely abandoned before they finish, so its height reflects how long they sat unfinished, not how slow the network is.*\n\n###### Keywords:\n- **Ledger acquire (inbound fetch)** *(per node)* \u2014 fetching a specific missing ledger from peers; tracked by duration and outcome \u2014 complete, failed (gave up after its retry limit, or hit unusable ledger data), or aborted (abandoned before finishing).\n- **Back-fill / catch-up** *(per node)* \u2014 fetching missing historical ledgers from peers to fill gaps or reach the network tip.\n- **Fork** *(network-wide)* \u2014 when nodes validate divergent ledger chains instead of a single agreed history.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::init ; InboundLedger::done ; InboundLedger::~InboundLedger`\n\n###### References:\n[Fork](https://xrpl.org/docs/concepts/consensus-protocol) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#ledger-acquire-inbound-fetch)", "fieldConfig": { "defaults": { "color": { @@ -5092,7 +5092,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.acquire\"}[5m]))), \"series\", \"P95 Acquire\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(histogram_quantile(0.95, sum by (le, outcome, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", outcome=~\"$outcome\", span_name=\"ledger.acquire\"}[5m]))), \"outcome\", \"Complete\", \"outcome\", \"complete\"), \"outcome\", \"Failed\", \"outcome\", \"failed\"), \"outcome\", \"Aborted\", \"outcome\", \"aborted\"), \"series\", \"P95 Acquire $1\", \"outcome\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" } ], @@ -5195,7 +5195,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (outcome, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.acquire\"}[$__rate_interval])), \"series\", \"$1\", \"outcome\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(sum by (outcome, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", outcome=~\"$outcome\", span_name=\"ledger.acquire\"}[$__rate_interval])), \"outcome\", \"Complete\", \"outcome\", \"complete\"), \"outcome\", \"Failed\", \"outcome\", \"failed\"), \"outcome\", \"Aborted\", \"outcome\", \"aborted\"), \"series\", \"$1\", \"outcome\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" } ], @@ -5491,6 +5491,26 @@ "refresh": 2, "sort": 1 }, + { + "name": "outcome", + "label": "Acquire Outcome", + "description": "Filter ledger acquire (inbound fetch) attempts by outcome [complete / failed / aborted]", + "type": "query", + "query": "label_values(span_calls_total{span_name=\"ledger.acquire\"}, outcome)", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, { "name": "quantile", "label": "Quantile", diff --git a/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json b/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json index 0617cd703a..df48858eab 100644 --- a/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json +++ b/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json @@ -664,19 +664,19 @@ "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{handler=\"RcvGetObjByHash\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Queue Wait p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{handler=\"RcvGetObjByHash\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Queue Wait p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{handler=\"RcvGetObjByHash\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Handler Total p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{handler=\"RcvGetObjByHash\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Handler Total p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(getobject_lookup_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"NodeStore Lookup p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(getobject_lookup_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"NodeStore Lookup p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -773,7 +773,7 @@ "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(sum by (result, service_instance_id, xrpl_branch, xrpl_node_role) (rate(getobject_lookups_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", result=~\"$result\"}[$__rate_interval])), \"series\", \"$1\", \"result\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (result, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(getobject_lookups_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", result=~\"$result\"}[$__rate_interval])), \"series\", \"$1\", \"result\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -817,7 +817,7 @@ "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(sum by (reason, service_instance_id, xrpl_branch, xrpl_node_role) (rate(getobject_rejected_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", reason=~\"$reason\"}[$__rate_interval])), \"series\", \"$1\", \"reason\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (reason, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(getobject_rejected_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", reason=~\"$reason\"}[$__rate_interval])), \"series\", \"$1\", \"reason\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -861,19 +861,19 @@ "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.5, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(getobject_charge_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Charge p50\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.5, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(getobject_charge_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Charge p50\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.9, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(getobject_charge_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Charge p90\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.9, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(getobject_charge_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Charge p90\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(getobject_charge_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Charge p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(getobject_charge_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"Charge p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/peer-network.json b/docker/telemetry/grafana/dashboards/peer-network.json index efbb2fbca5..ca4d55239a 100644 --- a/docker/telemetry/grafana/dashboards/peer-network.json +++ b/docker/telemetry/grafana/dashboards/peer-network.json @@ -75,7 +75,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"peer.proposal.receive\"}[$__rate_interval])), \"series\", \"Proposals Received / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"peer.proposal.receive\"}[$__rate_interval])), \"series\", \"Proposals Received / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -120,7 +120,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"peer.validation.receive\"}[$__rate_interval])), \"series\", \"Validations Received / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"peer.validation.receive\"}[$__rate_interval])), \"series\", \"Validations Received / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -178,7 +178,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (proposal_trusted, service_instance_id, xrpl_branch, xrpl_node_role) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[$__rate_interval])), \"series\", \"Trusted = $1\", \"proposal_trusted\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (proposal_trusted, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[$__rate_interval])), \"series\", \"Trusted = $1\", \"proposal_trusted\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -213,7 +213,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (validation_trusted, service_instance_id, xrpl_branch, xrpl_node_role) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[$__rate_interval])), \"series\", \"Trusted = $1\", \"validation_trusted\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (validation_trusted, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[$__rate_interval])), \"series\", \"Trusted = $1\", \"validation_trusted\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/rpc-pathfinding.json b/docker/telemetry/grafana/dashboards/rpc-pathfinding.json index e649350953..b751c16959 100644 --- a/docker/telemetry/grafana/dashboards/rpc-pathfinding.json +++ b/docker/telemetry/grafana/dashboards/rpc-pathfinding.json @@ -113,7 +113,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Response Time\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Response Time\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -158,7 +158,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_size_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Response Size\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_size_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Response Size\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -203,21 +203,21 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.9, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P90\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.9, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P90\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -383,7 +383,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(pathfind_fast_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Fast Pathfind\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(pathfind_fast_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Fast Pathfind\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -428,7 +428,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(pathfind_full_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Full Pathfind\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(pathfind_full_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m]))), \"series\", \"P95 Full Pathfind\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -486,7 +486,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (method, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[$__rate_interval])), \"series\", \"$1\", \"method\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (method, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[$__rate_interval])), \"series\", \"$1\", \"method\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -531,7 +531,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, method, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m]))), \"series\", \"$1\", \"method\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, method, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m]))), \"series\", \"$1\", \"method\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -576,7 +576,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (grpc_status, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[$__rate_interval])), \"series\", \"$1\", \"grpc_status\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (grpc_status, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[$__rate_interval])), \"series\", \"$1\", \"grpc_status\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -621,7 +621,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.compute\"}[5m]))), \"series\", \"P95 Compute\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.compute\"}[5m]))), \"series\", \"P95 Compute\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -666,14 +666,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.request\"}[$__rate_interval])), \"series\", \"Requests / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.request\"}[$__rate_interval])), \"series\", \"Requests / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.discover\"}[$__rate_interval])), \"series\", \"Discoveries / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.discover\"}[$__rate_interval])), \"series\", \"Discoveries / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/rpc-performance.json b/docker/telemetry/grafana/dashboards/rpc-performance.json index 3ab073879d..8228c9283b 100644 --- a/docker/telemetry/grafana/dashboards/rpc-performance.json +++ b/docker/telemetry/grafana/dashboards/rpc-performance.json @@ -74,7 +74,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (command, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval])) / sum by (command, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])) * 100, \"series\", \"$1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (command, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval])) / sum by (command, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])) * 100, \"series\", \"$1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -128,7 +128,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(topk(10, sum by (command, service_instance_id, xrpl_branch, xrpl_node_role) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval]))), \"series\", \"$1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(topk(10, sum by (command, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval]))), \"series\", \"$1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -166,7 +166,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.ws_message\"}[$__rate_interval])), \"series\", \"WS Messages / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.ws_message\"}[$__rate_interval])), \"series\", \"WS Messages / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -204,7 +204,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (command, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])), \"series\", \"$1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (command, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])), \"series\", \"$1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -249,7 +249,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, command, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m]))), \"series\", \"P95 $1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, command, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m]))), \"series\", \"P95 $1\", \"command\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -343,14 +343,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.http_request\"}[$__rate_interval])), \"series\", \"rpc.http_request / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.http_request\"}[$__rate_interval])), \"series\", \"rpc.http_request / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.process\"}[$__rate_interval])), \"series\", \"rpc.process / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.process\"}[$__rate_interval])), \"series\", \"rpc.process / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -395,14 +395,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_OK\"}[$__rate_interval])), \"series\", \"Success\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_OK\"}[$__rate_interval])), \"series\", \"Success\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval])), \"series\", \"Error\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval])), \"series\", \"Error\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -452,7 +452,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, load_type, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"rpc.command.*\", load_type!=\"\"}[$__rate_interval])), \"series\", \"$1\", \"load_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, load_type, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"rpc.command.*\", load_type!=\"\"}[$__rate_interval])), \"series\", \"$1\", \"load_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -497,14 +497,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"rpc.process\", is_batch=\"true\"}[$__rate_interval])), \"series\", \"Batch\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"rpc.process\", is_batch=\"true\"}[$__rate_interval])), \"series\", \"Batch\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"rpc.process\", is_batch=\"false\"}[$__rate_interval])), \"series\", \"Single\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"rpc.process\", is_batch=\"false\"}[$__rate_interval])), \"series\", \"Single\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -566,7 +566,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (service_instance_id, le, xrpl_branch, xrpl_node_role) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m]))), \"series\", \"p99 Latency\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (service_instance_id, le, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m]))), \"series\", \"p99 Latency\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -622,21 +622,21 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[$__rate_interval])), \"series\", \"Started/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[$__rate_interval])), \"series\", \"Started/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_method_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[$__rate_interval])), \"series\", \"Finished/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_method_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[$__rate_interval])), \"series\", \"Finished/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[$__rate_interval])), \"series\", \"Errored/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[$__rate_interval])), \"series\", \"Errored/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -793,14 +793,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.75, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m]))), \"series\", \"p75\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.75, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m]))), \"series\", \"p75\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m]))), \"series\", \"p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m]))), \"series\", \"p99\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -854,7 +854,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(topk(10, histogram_quantile(0.99, sum by (le, method, service_instance_id, xrpl_branch, xrpl_node_role) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m])))), \"series\", \"$1\", \"method\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(topk(10, histogram_quantile(0.99, sum by (le, method, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m])))), \"series\", \"$1\", \"method\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/transaction-overview.json b/docker/telemetry/grafana/dashboards/transaction-overview.json index a7d2ad429a..f5e6820a81 100644 --- a/docker/telemetry/grafana/dashboards/transaction-overview.json +++ b/docker/telemetry/grafana/dashboards/transaction-overview.json @@ -61,7 +61,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.transactor\", stage=\"apply\", ter_result!~\"tesSUCCESS|\"}[$__rate_interval])), \"series\", \"Failed / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.transactor\", stage=\"apply\", ter_result!~\"tesSUCCESS|\"}[$__rate_interval])), \"series\", \"Failed / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -120,7 +120,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, tx_type, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, tx_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -183,7 +183,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (tx_type, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (tx_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -233,7 +233,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (tx_type, ter_result, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\", ter_result=~\"$ter_result\", ter_result!=\"tesSUCCESS\"}[$__rate_interval])), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"ter_result\", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (tx_type, ter_result, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\", ter_result=~\"$ter_result\", ter_result!=\"tesSUCCESS\"}[$__rate_interval])), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"ter_result\", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -278,7 +278,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (suppressed, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{span_name=\"tx.receive\", tx_type=~\"$tx_type\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Suppressed $1\", \"suppressed\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (suppressed, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{span_name=\"tx.receive\", tx_type=~\"$tx_type\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Suppressed $1\", \"suppressed\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -323,14 +323,14 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"tx.process / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"tx.process / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.receive\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"tx.receive / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.receive\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"tx.receive / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -382,7 +382,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (local, service_instance_id, xrpl_branch, xrpl_node_role) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", local=~\"$tx_origin\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"Local $1\", \"local\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (local, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", local=~\"$tx_origin\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"Local $1\", \"local\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "id": 8 @@ -464,7 +464,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, tx_type, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.transactor\", tx_type=~\"$tx_type\"}[5m]))), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, tx_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.transactor\", tx_type=~\"$tx_type\"}[5m]))), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -518,9 +518,9 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "sum by (service_instance_id, xrpl_network_type) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.accept_tx\", txq_status=\"applied\"}[$__rate_interval]))\n/\nsum by (service_instance_id, xrpl_network_type) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.accept_tx\", txq_status=~\"applied|failed\"}[$__rate_interval]))", + "expr": "sum by (service_instance_id, xrpl_network_type, xrpl_work_item) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.accept_tx\", txq_status=\"applied\"}[$__rate_interval]))\n/\nsum by (service_instance_id, xrpl_network_type, xrpl_work_item) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.accept_tx\", txq_status=~\"applied|failed\"}[$__rate_interval]))", "interval": "15s", - "legendFormat": "{{service_instance_id}} [{{xrpl_network_type}}]" + "legendFormat": "{{service_instance_id}} [{{xrpl_network_type}}] [{{xrpl_work_item}}]" } ], "fieldConfig": { @@ -560,7 +560,7 @@ }, { "title": "Tx Apply Pipeline Rate by Stage", - "description": "**What:** Throughput of each apply-pipeline stage (preflight, preclaim, apply), showing where transactions drop out.\n**How it's computed:** Per-second rate per stage over a 5-minute window, per node.\n**Reading it:** A decline from earlier to later stages shows where transactions are filtered.\n**Healthy range:** Workload-dependent; later stages sit at or below earlier ones.\n**Watch for:** A large early-stage drop means many transactions fail basic checks, consistent with malformed floods.\n**Source:** src/libxrpl/tx/Transactor.cpp:Transactor::operator()", + "description": "###### What this is:\n*Throughput of each apply-pipeline stage (preflight, preclaim, apply), showing where transactions drop out.*\n\n###### How it's computed:\n*Per-second rate of stage spans over the rate interval, grouped by stage and node.*\n\n###### Reading it:\n*A decline from earlier to later stages shows where transactions are filtered.*\n\n###### Healthy range:\n*Workload-dependent; later stages sit at or below earlier ones.*\n\n###### Watch for:\n*A large early-stage drop, meaning many transactions fail basic checks, consistent with malformed floods.*\n\n###### Keywords:\n- **Apply pipeline stages** *(per node)* \u2014 the ordered checks a transaction passes \u2014 preflight (stateless), preclaim (stateful), then apply.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`\n\n###### References:\n[Apply pipeline stages](https://xrpl.org/docs/concepts/transactions) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#apply-pipeline-stages)", "type": "timeseries", "gridPos": { "h": 10, @@ -583,15 +583,16 @@ "targets": [ { "datasource": { - "type": "prometheus" + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" }, - "expr": "sum by (stage, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[$__rate_interval]))", - "interval": "15s", - "legendFormat": "{{stage}} [{{service_instance_id}}]" + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(sum by (stage, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[$__rate_interval])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"stage\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "interval": "15s" } ], "fieldConfig": { "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", "unit": "ops", "custom": { "axisLabel": "Spans / Sec", @@ -649,7 +650,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(histogram_quantile(0.95, sum by (le, stage, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[5m]))), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"stage\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(histogram_quantile(0.95, sum by (le, stage, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[5m]))), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"stage\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -699,7 +700,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(sum by (stage, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\", ter_result!~\"tesSUCCESS|\"}[$__rate_interval])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"stage\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(sum by (stage, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\", ter_result!~\"tesSUCCESS|\"}[$__rate_interval])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"stage\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -749,7 +750,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(histogram_quantile(0.95, sum by (le, tx_type, stage, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", tx_type=~\"$tx_type\", stage=~\"$stage\"}[5m]))), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"stage\", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(histogram_quantile(0.95, sum by (le, tx_type, stage, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", tx_type=~\"$tx_type\", stage=~\"$stage\"}[5m]))), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"stage\", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -771,6 +772,106 @@ }, "id": 16 }, + { + "title": "Tx Apply Pipeline Rate by Type and Stage", + "description": "###### What this is:\n*Throughput of each apply-pipeline stage broken down by both transaction type and pipeline stage.*\n\n###### How it's computed:\n*Per-second rate of stage spans over the rate interval, grouped by transaction type, stage and node; higher cardinality than the by-stage view.*\n\n###### Reading it:\n*A decline from earlier to later stages shows where each transaction type is filtered out.*\n\n###### Healthy range:\n*Workload-dependent; for every type the later stages sit at or below the earlier ones.*\n\n###### Watch for:\n*One type's early-stage rate dwarfing its later stages, consistent with a malformed flood of that type.*\n\n###### Keywords:\n- **Transaction type** *(network-wide)* \u2014 the kind of transaction (Payment, OfferCreate, TrustSet, AMM*, NFToken*, etc.), used as a breakdown dimension.\n- **Apply pipeline stages** *(per node)* \u2014 the ordered checks a transaction passes \u2014 preflight (stateless), preclaim (stateful), then apply.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`\n\n###### References:\n[Transaction type](https://xrpl.org/docs/references/protocol/transactions/types) \u00b7 [Apply pipeline stages](https://xrpl.org/docs/concepts/transactions) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#transaction-type)", + "type": "timeseries", + "gridPos": { + "h": 10, + "w": 24, + "x": 0, + "y": 122 + }, + "options": { + "tooltip": { + "mode": "multi", + "sort": "desc", + "maxHeight": 600 + }, + "legend": { + "displayMode": "table", + "placement": "right", + "calcs": ["mean", "max"] + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(sum by (tx_type, stage, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", tx_type=~\"$tx_type\", stage=~\"$stage\"}[$__rate_interval])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"stage\", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "unit": "ops", + "custom": { + "axisLabel": "Spans / Sec", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}" + }, + "overrides": [] + }, + "id": 22 + }, + { + "title": "Tx Apply Pipeline Failure Rate by Type and Stage", + "description": "###### What this is:\n*How many transactions fail at each apply-pipeline stage per second, broken down by transaction type.*\n\n###### How it's computed:\n*Per-second rate of non-success outcomes over the rate interval, grouped by transaction type, stage and node; higher cardinality than the by-stage view.*\n\n###### Reading it:\n*Shows which transaction type is being rejected and at which stage \u2014 preflight, preclaim, or apply.*\n\n###### Healthy range:\n*Workload-dependent; a modest background of expected rejections is normal for every type.*\n\n###### Watch for:\n*A failure spike concentrated in one type and stage pair, consistent with malformed or spam submissions of that type.*\n\n###### Keywords:\n- **Transaction type** *(network-wide)* \u2014 the kind of transaction (Payment, OfferCreate, TrustSet, AMM*, NFToken*, etc.), used as a breakdown dimension.\n- **Apply pipeline stages** *(per node)* \u2014 the ordered checks a transaction passes \u2014 preflight (stateless), preclaim (stateful), then apply.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`\n\n###### References:\n[Transaction type](https://xrpl.org/docs/references/protocol/transactions/types) \u00b7 [Apply pipeline stages](https://xrpl.org/docs/concepts/transactions) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#transaction-type)", + "type": "timeseries", + "gridPos": { + "h": 10, + "w": 24, + "x": 0, + "y": 132 + }, + "options": { + "tooltip": { + "mode": "multi", + "sort": "desc", + "maxHeight": 600 + }, + "legend": { + "displayMode": "table", + "placement": "right", + "calcs": ["mean", "max"] + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(label_replace(label_replace(label_replace(sum by (tx_type, stage, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", tx_type=~\"$tx_type\", stage=~\"$stage\", ter_result!~\"tesSUCCESS|\"}[$__rate_interval])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\"), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"stage\", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "unit": "suffix: failures/s", + "custom": { + "axisLabel": "Failures / Sec", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}" + }, + "overrides": [] + }, + "id": 23 + }, { "title": "Transaction Apply Duration per Ledger", "description": "###### What this is:\n*The 95th-percentile time to apply the agreed transaction set into each new ledger.*\n\n###### How it's computed:\n*95th-percentile of transaction-apply durations over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; a major component of ledger build time.*\n\n###### Healthy range:\n*A few to tens of milliseconds; scales with transactions per ledger.*\n\n###### Watch for:\n*Rising durations during heavy or expensive transaction sets.*\n\n###### Keywords:\n- **Transaction apply phase** *(per node)* \u2014 the step that executes the agreed transaction set into the new ledger during a close.\n- **Ledger build** *(per node)* \u2014 constructing the new ledger by applying the agreed transaction set to the prior ledger.\n- **In-ledger vs target count** *(per node)* \u2014 transactions already in the open ledger versus the soft target that triggers fee escalation.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp)\n\n###### Function:\n`applyTransactions`\n\n###### References:\n[Transaction apply phase](https://xrpl.org/docs/concepts/ledgers/open-closed-validated-ledgers) \u00b7 [In-ledger vs target count](https://xrpl.org/docs/concepts/transactions/transaction-cost#open-ledger-cost) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#transaction-apply-phase)", @@ -779,7 +880,7 @@ "h": 10, "w": 12, "x": 0, - "y": 122 + "y": 142 }, "options": { "tooltip": { @@ -794,7 +895,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[5m]))), \"series\", \"tx.apply\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[5m]))), \"series\", \"tx.apply\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -823,7 +924,7 @@ "h": 1, "w": 24, "x": 0, - "y": 132 + "y": 152 }, "collapsed": false, "panels": [], @@ -837,7 +938,7 @@ "h": 10, "w": 12, "x": 0, - "y": 133 + "y": 153 }, "options": { "tooltip": { @@ -852,7 +953,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (tx_type, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.enqueue\"}[$__rate_interval])), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (tx_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.enqueue\"}[$__rate_interval])), \"series\", \"$1\", \"tx_type\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -882,7 +983,7 @@ "h": 10, "w": 12, "x": 12, - "y": 133 + "y": 153 }, "options": { "tooltip": { @@ -897,7 +998,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.accept\"}[5m]))), \"series\", \"Drain\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.accept\"}[5m]))), \"series\", \"Drain\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -927,7 +1028,7 @@ "h": 10, "w": 12, "x": 0, - "y": 143 + "y": 163 }, "options": { "tooltip": { @@ -942,7 +1043,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.cleanup\"}[$__rate_interval])), \"series\", \"Cleanups / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"txq.cleanup\"}[$__rate_interval])), \"series\", \"Cleanups / Sec\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/dashboards/validator-health.json b/docker/telemetry/grafana/dashboards/validator-health.json index df76ace0b3..15254cb9ca 100644 --- a/docker/telemetry/grafana/dashboards/validator-health.json +++ b/docker/telemetry/grafana/dashboards/validator-health.json @@ -801,7 +801,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(3600 * sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(state_changes_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Changes/hr\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(3600 * sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(state_changes_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])), \"series\", \"Changes/hr\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { From 173e76556e39bad55e2565728d23d24df4379a85 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:57:54 +0100 Subject: [PATCH 16/23] fix(telemetry): stop the mainnet node colliding with devnet and drop signing The mainnet and devnet telemetry configs are host processes sharing one network namespace and working directory, and they agreed on every port and both database paths. Running them together left the second unable to bind, and running them in sequence pointed a mainnet node at a store holding the other network's ledgers, silently and with no error. Offset the mainnet ports by ten and name both database paths after the network, matching what debug_logfile already did. Also narrow the attack surface this config carried. [port_ws_public] has no admin key, so every caller on it is a guest, and it was bound to all interfaces on a node following Mainnet; it is now loopback, and nothing in the repo connects to that port. [signing_support] is removed: it only affects non-admin callers, the admin ports already grant signing to local callers, and upstream deprecates the commands it exposes. Verified against a running node: signing still succeeds on the admin port and is refused as notSupported on the public one. --- docker/telemetry/xrpld-telemetry-mainnet.cfg | 40 ++++++++++++++------ 1 file changed, 29 insertions(+), 11 deletions(-) diff --git a/docker/telemetry/xrpld-telemetry-mainnet.cfg b/docker/telemetry/xrpld-telemetry-mainnet.cfg index 28ebce9567..720c9a1b6b 100644 --- a/docker/telemetry/xrpld-telemetry-mainnet.cfg +++ b/docker/telemetry/xrpld-telemetry-mainnet.cfg @@ -11,11 +11,15 @@ # 2. Run xrpld: # ./xrpld --conf docker/telemetry/xrpld-telemetry-mainnet.cfg # 3. Wait for sync (server_state=full), then exercise workflows: -# curl -s http://localhost:5005 -d '{"method":"server_info"}' +# curl -s http://localhost:5015 -d '{"method":"server_info"}' # 4. View traces in Grafana Explore -> Tempo: http://localhost:3000 # --- Server ports ----------------------------------------------------------- +# Ports are offset by +10 from the devnet config (xrpld-telemetry.cfg) so both +# nodes can run at the same time. They are host processes sharing one network +# namespace, so identical ports would leave the second node unable to bind. + [server] port_rpc_admin_local port_ws_admin_local @@ -23,24 +27,30 @@ port_ws_public port_peer [port_rpc_admin_local] -port = 5005 +port = 5015 ip = 127.0.0.1 admin = 127.0.0.1 protocol = http [port_ws_admin_local] -port = 6006 +port = 6016 ip = 127.0.0.1 admin = 127.0.0.1 protocol = ws +# Bound to loopback: this port has no `admin` key, so every caller resolves to +# Role::GUEST. Every workflow documented for this config is driven over the two +# admin ports above, which also serve WebSocket, and this node follows Mainnet, so +# there is no reason to accept off-host clients. [port_ws_public] -port = 6005 -ip = 0.0.0.0 +port = 6015 +ip = 127.0.0.1 protocol = ws +# Stays on all interfaces: this is the peer-protocol listener, and binding it to +# loopback would stop inbound overlay connections. [port_peer] -port = 51235 +port = 51245 ip = 0.0.0.0 protocol = peer @@ -73,21 +83,29 @@ validators-mainnet.txt [path_search_max] 10 -# --- Signing (allows sign/sign_for RPC for test tx submission) -------------- +# --- Signing ---------------------------------------------------------------- -[signing_support] -true +# [signing_support] is deliberately omitted (it defaults to false). It is only +# consulted for non-admin callers, and every signing path in this repo already +# runs as admin over the loopback admin ports above, so enabling it would add +# nothing except exposing sign/sign_for/channel_authorize to guests on a node +# that follows Mainnet. Upstream also deprecates these commands. # --- Database --------------------------------------------------------------- +# Paths carry the network name so this node never shares a store with the devnet +# config. Both are relative to the working directory (the repo root, per the +# usage note above), so an unqualified `data/` would have the two nodes opening +# the same NuDB and the same SQLite ledger databases — including the case where +# they run one after the other rather than concurrently. [node_db] type=NuDB -path=docker/telemetry/data/nudb +path=docker/telemetry/data/mainnet/nudb online_delete=2000 advisory_delete=0 [database_path] -docker/telemetry/data +docker/telemetry/data/mainnet [ledger_history] 1000 From b82ee49cca66760014a837109f96a9a8487b38fb Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 21:57:57 +0100 Subject: [PATCH 17/23] docs(telemetry): correct the ledger.acquire outcome guidance The runbook told operators to read a missing outcome as "never went to the network", which stopped being true once the abort path started setting it, and the glossary still described outcome as a two-value split. Document all three values, where each is written, and why peer_count is absent on the abort path. Several claims were wrong and are corrected: - Give-up is reached at about 18s, not 21s. There is no setTimer call, so the first timer runs immediately and the old derivation counted a wait that does not happen. - A live aborted rate does not imply stalled acquisitions. A clean shutdown clears every in-flight acquire, the admin fetch_info clear does the same, and a full job lane stops timeouts advancing so give-up cannot fire. The runbook already said the last of these elsewhere. - A missing outcome does not mean exactly one thing. tryDB can set failed_ and return before done() runs, exporting a span with no outcome at all. - failed covers unusable ledger data as well as exhausting the retry limit, so a failed span can carry timeouts=0. - The aborted lower bound of one minute holds only on the sweep path. - The sweep measures time since anything last asked for the ledger, not since data last arrived. Also fixes the mainnet verification command, which still used the old RPC port, and drops an inaccurate claim from the config comment about which ports the workload scripts use. --- .../09-data-collection-reference.md | 72 ++++++++++--------- docs/telemetry-glossary.md | 2 +- docs/telemetry-runbook.md | 63 ++++++++++++++-- 3 files changed, 99 insertions(+), 38 deletions(-) diff --git a/OpenTelemetryPlan/09-data-collection-reference.md b/OpenTelemetryPlan/09-data-collection-reference.md index b03b7e4ceb..3b0f2b16a2 100644 --- a/OpenTelemetryPlan/09-data-collection-reference.md +++ b/OpenTelemetryPlan/09-data-collection-reference.md @@ -447,8 +447,8 @@ Join a transaction's work to its ledger with `{span.current_ledger_seq=}`. > **`consensus.check` carries nine attributes, all set before the early > returns.** `Consensus::haveConsensus()` sets them at -> `include/xrpl/consensus/Consensus.h:1899-1912` and `consensus_result` at -> `:1925`, deliberately ahead of the `No` / `Expired` branches, so the span is +> `include/xrpl/consensus/Consensus.h:1899-1911` and `consensus_result` at +> `:1926`, deliberately ahead of the `No` / `Expired` branches, so the span is > fully populated even on rounds that never reach consensus. In set order: > `agree_count`, `disagree_count`, `converge_percent`, > `have_close_time_consensus`, `threshold_percent`, `proposers_finished`, @@ -477,15 +477,24 @@ Join a transaction's work to its ledger with `{span.current_ledger_seq=}`. | `tx_count` | int64 | `tx.apply` | Transactions applied to the ledger | | `tx_failed` | int64 | `tx.apply` | Failed transactions in the apply set | | `validations` | int64 | `ledger.validate` | Number of validations received for this ledger | -| `acquire_reason` | string | `ledger.acquire` | Why the ledger fetch was triggered | +| `acquire_reason` | string | `ledger.acquire` | Fetch trigger (`history`/`consensus`/`generic`) | | `timeouts` | int64 | `ledger.acquire` | Number of fetch timeouts | | `peer_count` | int64 | `ledger.acquire` | Peers queried during the fetch | -| `outcome` | string | `ledger.acquire` | Fetch outcome | +| `outcome` | string | `ledger.acquire` | Fetch outcome (`complete`/`failed`/`aborted`) | The apply-step span `tx.apply` (child of `ledger.build`) carries `tx_count`/`tx_failed`; the parent `ledger.build` carries `ledger_seq` and the close-time attributes. `ledger.acquire` (InboundLedger) also sets `ledger_seq`. +`outcome` takes one of **three** values, not two. `complete` and `failed` are both set in +`done()` (`InboundLedger.cpp:530-532`), where `failed` covers both giving up after the +retry limit and hitting unusable ledger data, so a `failed` span can carry `timeouts=0`. `aborted` is set in `~InboundLedger()` when the object is destroyed while +`!isDone()` (`InboundLedger.cpp:242-246`) — the acquisition was **abandoned** before it +finished, rather than having run to its retry limit. The abort path records `timeouts` but +deliberately **not** `peer_count`, because reading the peer count goes through `Overlay`, which +a destructor must not depend on still existing. A query that only groups by +`complete`/`failed` therefore silently loses every abandoned fetch. + **Tempo query**: `{span.ledger_seq=12345}` to find all spans for a specific ledger. #### Peer Attributes @@ -626,7 +635,7 @@ prefix=xrpld > (`src/xrpld/app/misc/NetworkOPs.cpp:4884-4897`). Divide by `1e6` for seconds. > The `node-health` "State Duration Rate (All States)" panel already does > (`/ 1000000` on each `rate(...)`), and -> `docker/telemetry/grafana/dashboards/validate_dashboards.py:43` lints the +> `docker/telemetry/grafana/dashboards/validate_dashboards.py:44-45` lints the > family as "cumulative µs". Reading the raw value as seconds overstates time > in state by a factor of one million. @@ -755,7 +764,7 @@ types where this bites are the ones with a low concurrency limit > **Sampling caveat.** These are sampled, not integrated. The values are read > when the SDK's periodic reader invokes the observable callbacks, which run the > collector hooks; the export interval is 1000 ms -> (`export_interval_millis` in `src/libxrpl/telemetry/Telemetry.cpp:441`) and +> (`export_interval_millis` in `src/libxrpl/telemetry/Telemetry.cpp:476`) and > hook invocation is debounced to at most once per 500 ms. A spike shorter than > the interval can be missed entirely, so read these as pressure indicators > rather than as exact peak depths. @@ -1030,8 +1039,8 @@ async callbacks for new categories. > **Label values are case-sensitive and three cache values are not lowercase.** > The `metric` label carries the string literal passed to `Observe()`, verbatim: > `SLE_hit_rate`, `AL_hit_rate` and `AL_size` are upper-case -> (`src/xrpld/telemetry/MetricsRegistry.cpp:649`, `:665`, `:691`), while -> `ledger_hit_rate` genuinely is lowercase (`:658`). A selector written as +> (`src/xrpld/telemetry/MetricsRegistry.cpp:666`, `:682`, `:708`), while +> `ledger_hit_rate` genuinely is lowercase (`:675`). A selector written as > `cache_metrics{metric="sle_hit_rate"}` matches nothing. #### Server Info (via OTel MetricsRegistry) @@ -1131,7 +1140,7 @@ Phase-7 parity set, see | Dashboard | UID | Data Source | Key Panels | | ------------------ | ------------ | ----------- | ----------------------------------------------------------------- | | Fee Market & TxQ | `fee-market` | Prometheus | TxQ depth/capacity, fee levels, load factor breakdown, escalation | -| Job Queue Analysis | `job-queue` | Prometheus | Per-job rates, queue wait times, execution times, queue depth | +| Job Queue Analysis | `job-queue` | Prometheus | Per-job rates, queue wait times, execution times, overflow rate | --- @@ -1179,7 +1188,7 @@ Phase 10 builds a 5-node validator docker-compose harness with RPC load generato > (`nodestore_state`, `cache_metrics`, …) once. > > Note that `ledgers_closed_total` appears in **both** instrument rows: it is -> created as a `MetricsRegistry` member (`MetricsRegistry.cpp:369-370`, whose +> created as a `MetricsRegistry` member (`MetricsRegistry.cpp:386-387`, whose > `incrementLedgersClosed()` has no callers) and separately incremented at its > call site via `XRPL_METRIC_COUNTER_INC` (`RCLConsensus.cpp:749`). The distinct > name count across the two rows is therefore 41, not 42. @@ -1294,7 +1303,7 @@ via OTLP/HTTP to the OTel Collector and scraped by Prometheus. > **On NuDB, `write_load` and `nudb_writers_in_flight` are the same number.** > Both read the same atomic. `NuDBBackend::getWriteLoad()` returns > `concurrentWriters.load()` -> (`src/libxrpl/nodestore/backend/NuDBFactory.cpp:355-361`), and +> (`src/libxrpl/nodestore/backend/NuDBFactory.cpp:375-381`), and > `WriteStats::concurrentWriters` is that same counter. So the two series track > each other exactly, sampled microseconds apart in one callback. Do not read > their agreement as two signals confirming each other — it is one signal twice. @@ -1311,7 +1320,7 @@ Further label values on the same instrument, added to separate the two bottlenecks that both present as the `ledgerData` job lane pinned at its concurrency cap. Observed in `MetricsRegistry::observeNodeStoreTotals()`, `observeWritePathDetail()`, and `observeAcquireStats()` -(`src/xrpld/telemetry/MetricsRegistry.cpp:854-925`). +(`src/xrpld/telemetry/MetricsRegistry.cpp:871-942`). | Prometheus Metric | Type | Labels | Description | | ---------------------------------------------------- | ----- | -------- | ------------------------------------------------------- | @@ -1403,7 +1412,7 @@ data as uninformative unless the build is known to include the fix. #### TxQ Admission and Ledger Mismatch (Synchronous Counters) Three monotonic counters created alongside the Phase 7+ parity counters -(`src/xrpld/telemetry/MetricsRegistry.cpp:377-382`). The gauges above answer +(`src/xrpld/telemetry/MetricsRegistry.cpp:394-399`). The gauges above answer "how deep is the queue"; these answer "what did the queue refuse, and did the ledger we built match the one the network validated". @@ -1449,7 +1458,7 @@ Rejections (Dropped)", "Queue Abandonment Rate (Expired)"; _Consensus Health_ #### Reduce-Relay Efficiency (Observable Gauge — `reduce_relay_metrics`) Transaction reduce-relay effectiveness, read from `Overlay::txMetrics()` each -collection cycle (`src/xrpld/telemetry/MetricsRegistry.cpp:1353-1385`). A high +collection cycle (`src/xrpld/telemetry/MetricsRegistry.cpp:1370-1402`). A high `suppressed_peers` : `selected_peers` ratio proves the feature is saving bandwidth; a high `not_enabled_peers` means stale peers are forcing full relay. @@ -1610,7 +1619,7 @@ not a lowercase word and not a friendly alias. The value is `beast::typeName()` (`include/xrpl/basics/CountedObject.h:115`), which demangles `typeid(T).name()` with `abi::__cxa_demangle` (`include/xrpl/beast/type_name.h:16-45`) and applies no stripping; the observer -copies it through verbatim (`src/xrpld/telemetry/MetricsRegistry.cpp:764-770`). +copies it through verbatim (`src/xrpld/telemetry/MetricsRegistry.cpp:781-787`). Values therefore keep their `xrpl::` namespace, nested `::`, and template arguments. @@ -1745,7 +1754,7 @@ These metrics fill gaps identified by comparing xrpld's internal observability w Data source: `ValidationTracker` class with 8s grace period and 5m late repair window. > **Every value on this instrument is a double.** The family is one -> `CreateDoubleObservableGauge` (`src/xrpld/telemetry/MetricsRegistry.cpp:1576`), +> `CreateDoubleObservableGauge` (`src/xrpld/telemetry/MetricsRegistry.cpp:1593`), > so the integral counts are cast to `double` before `Observe()` — there is no > Int64 sub-series to filter on. The same holds for `validator_health`, > `peer_quality` and `state_tracking` below; an earlier revision of these four @@ -1754,7 +1763,7 @@ Data source: `ValidationTracker` class with 8s grace period and 5m late repair w > > The 7-day window is `ValidationTracker::kWindow7d` = 168 hours > (`src/xrpld/telemetry/ValidationTracker.h:311`) and is observed alongside the 1h -> and 24h windows at `MetricsRegistry.cpp:1606-1609`. Panels exist on _Validator +> and 24h windows at `MetricsRegistry.cpp:1623-1626`. Panels exist on _Validator > Health_ (`validator-health`): "Agreement % (7d)" and "Agreements vs Missed > (7d)". @@ -1767,7 +1776,7 @@ Data source: `ValidationTracker` class with 8s grace period and 5m late repair w | `validator_health{metric="unl_expiry_days"}` | Double | `metric` | Days until UNL list expires | | `validator_health{metric="validation_quorum"}` | Double | `metric` | Validation quorum threshold | -Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1200`. +Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1217`. #### Peer Quality (Observable Gauge — `peer_quality`) @@ -1778,7 +1787,7 @@ Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1200`. | `peer_quality{metric="peers_higher_version_pct"}` | Double | `metric` | % of peers on newer xrpld version | | `peer_quality{metric="upgrade_recommended"}` | Double | `metric` | 1 if >60% of peers are newer version | -Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1249`. +Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1266`. #### Ledger Economy (Observable Gauge — `ledger_economy`) @@ -1797,9 +1806,9 @@ Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1249`. | `state_tracking{metric="state_value"}` | Double | `metric` | Numeric state 0-6 (see encoding below) | | `state_tracking{metric="time_in_current_state_seconds"}` | Double | `metric` | Duration in current state | -Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1466`. +Single `CreateDoubleObservableGauge` at `MetricsRegistry.cpp:1483`. -State value encoding: 0=disconnected, 1=connected, 2=syncing, 3=tracking, 4=full, 5=validating (FULL + validating), 6=proposing (FULL + proposing). Values 0-4 are `OperatingMode` cast to double (`include/xrpl/server/NetworkOPs.h:60-66`); 5 and 6 are the FULL-only refinements at `MetricsRegistry.cpp:1483-1498`. **The range is 0-6, not 0-7** — there is no seventh state. +State value encoding: 0=disconnected, 1=connected, 2=syncing, 3=tracking, 4=full, 5=validating (FULL + validating), 6=proposing (FULL + proposing). Values 0-4 are `OperatingMode` cast to double (`include/xrpl/server/NetworkOPs.h:60-66`); 5 and 6 are the FULL-only refinements at `MetricsRegistry.cpp:1500-1515`. **The range is 0-6, not 0-7** — there is no seventh state. #### Storage Detail (Observable Gauge — `storage_detail`) @@ -1808,11 +1817,11 @@ State value encoding: 0=disconnected, 1=connected, 2=syncing, 3=tracking, 4=full | `storage_detail{metric="stored_object_bytes"}` | Int64 | `metric` | Cumulative object-payload bytes written (not on-disk size) | > **`stored_object_bytes` is not a file size.** It observes `getStoreSize()` -> (`src/xrpld/telemetry/MetricsRegistry.cpp:1557`), which sums the object payloads +> (`src/xrpld/telemetry/MetricsRegistry.cpp:1574`), which sums the object payloads > this process has written. It therefore excludes NuDB's keys, bucket padding and > log, and it resets when the process restarts while the files on disk do not. > `node_written_bytes` on the `nodestore_state` gauge calls the same accessor -> (`MetricsRegistry.cpp:860`), so the two series are equal by construction and any +> (`MetricsRegistry.cpp:877`), so the two series are equal by construction and any > write-amplification ratio built from the pair is a constant 1.0. To size the store > on disk, stat the backend's files; no metric reports it today. > @@ -1833,9 +1842,9 @@ State value encoding: 0=disconnected, 1=connected, 2=syncing, 3=tracking, 4=full > **Known issue — `ledgers_closed_total` has a dead second producer.** The > instrument is created twice. `MetricsRegistry::registerCounters()` eagerly > creates it as the member `ledgersClosedCounter_` -> (`src/xrpld/telemetry/MetricsRegistry.cpp:369-370`), and its only mutator, +> (`src/xrpld/telemetry/MetricsRegistry.cpp:386-387`), and its only mutator, > `MetricsRegistry::incrementLedgersClosed()` -> (declared `MetricsRegistry.h:591`, defined `MetricsRegistry.cpp:1686`), has +> (declared `MetricsRegistry.h:591`, defined `MetricsRegistry.cpp:1703`), has > **zero callers** — the header says so itself at `MetricsRegistry.h:584-588`. > The value operators actually see comes from the single live increment, > the `XRPL_METRIC_COUNTER_INC` call site in @@ -1889,8 +1898,8 @@ What the code emits today, and where it is documented: | `xrpl.validation.ledger_hash`, `xrpl.peer.validation.ledger_hash` | one bare `ledger_hash` on both `consensus.validation.send` and `peer.validation.receive` | | `xrpl.validation.full`, `xrpl.peer.validation.full` | one bare `full_validation` on both of those spans | | `xrpl.consensus.validation_quorum` | `quorum`, on `consensus.accept` only | -| `xrpl.node.amendment_blocked` | **not a span attribute at all** — only the metric `validator_health{metric="amendment_blocked"}` (`MetricsRegistry.cpp:1216`) | -| `xrpl.node.server_state` | **not a span attribute at all** — only the metric `server_info{metric="server_state"}` (`MetricsRegistry.cpp:1014`) | +| `xrpl.node.amendment_blocked` | **not a span attribute at all** — only the metric `validator_health{metric="amendment_blocked"}` (`MetricsRegistry.cpp:1233`) | +| `xrpl.node.server_state` | **not a span attribute at all** — only the metric `server_info{metric="server_state"}` (`MetricsRegistry.cpp:1031`) | | `xrpl.consensus.proposers_validated` | **never implemented** in any form | The identical nine-row list was deleted from @@ -1910,10 +1919,9 @@ query, an alert — matches nothing and should be pointed at the live keys above ### Updated Grafana Dashboards (Phase 9) -| Dashboard | UID | New Panels Added | -| -------------------- | -------------------------- | -------------------------------------------------------------------- | -| Node Health (StatsD) | `xrpld-statsd-node-health` | NodeStore I/O, cache hit rates, object instance counts | -| System Node Health | `node-health` | Ledger economy row: base fee, reserves, ledger age, transaction rate | +| Dashboard | UID | New Panels Added | +| ----------- | ------------- | -------------------------------------------------------------------------------------------------------------------------------- | +| Node Health | `node-health` | NodeStore I/O row, cache hit rates, object instance counts; Ledger Economy row: base fee, reserves, ledger age, transaction rate | ### New Grafana Dashboards (Phase 11) @@ -2079,7 +2087,7 @@ discovery cache has any instrument at all. | Reading | Source | Why it matters | | --------------------------------------------------- | ---------------------- | ---------------------------------------------------------------------------------------------------------------------- | -| `attempts()`, `attemptsNeeded()` | `Counts.h:68,79` | Outbound connection churn; distinguishes "not trying" from "trying and failing" | +| `attemptsNeeded()`, `attempts()` | `Counts.h:68,79` | Outbound connection churn; distinguishes "not trying" from "trying and failing" | | `outMax()`, `outActive()`, `outboundSlotsFree()` | `Counts.h:88,98,205` | Outbound slot saturation | | `inMax()`, `inboundActive()`, `inboundSlotsFree()` | `Counts.h:165,174,193` | Inbound slot saturation — the two exported gauges give the actives but not the caps, so utilization cannot be computed | | `acceptCount()`, `connectCount()`, `closingCount()` | `Counts.h:138,147,156` | Handshake pipeline depth; `closingCount()` rising is teardown backpressure | diff --git a/docs/telemetry-glossary.md b/docs/telemetry-glossary.md index 10261f0cd1..c949ab274a 100644 --- a/docs/telemetry-glossary.md +++ b/docs/telemetry-glossary.md @@ -553,7 +553,7 @@ The rate at which the node fetches older ledgers to extend or repair its stored ### Ledger acquire (inbound fetch) -Acquiring a ledger means requesting it and its contents from peers when the node lacks it. Acquire outcomes split into complete and failed; a rising failed rate means the node cannot fetch needed ledgers from its peers. +Acquiring a ledger means requesting it and its contents from peers when the node lacks it. Acquire outcomes split three ways: complete, failed (the acquisition ended on its own without the ledger, having run out of retries or hit unusable data), and aborted (it was abandoned before finishing, either swept away as stale or discarded wholesale at shutdown). A rising failed rate means the node cannot fetch needed ledgers from its peers. **Scope:** per node — measured on and specific to this individual server. diff --git a/docs/telemetry-runbook.md b/docs/telemetry-runbook.md index 0a29771db0..0a8f23bd69 100644 --- a/docs/telemetry-runbook.md +++ b/docs/telemetry-runbook.md @@ -114,7 +114,7 @@ Metrics begin flowing as soon as the node connects to peers (`server_state` (`server_state` = `full`). Check progress with: ```bash -curl -s http://localhost:5005 -d '{"method":"server_info"}' | +curl -s http://localhost:5015 -d '{"method":"server_info"}' | jq '.result.info | {server_state, peers, complete_ledgers}' ``` @@ -393,10 +393,35 @@ Span attributes are filtered with `span.` inside `{}`. Combine conditions | `ledger.acquire` | InboundLedger.cpp | `ledger_seq`, `acquire_reason`, `timeouts`, `peer_count`, `outcome` | Fetch a missing ledger from peers (parent varies — see [known issues](#where-telemetry-parenting-differs-from-protocol-flow)) | `ledger.acquire` sets only `ledger_seq` and `acquire_reason` when the span opens -in `init()`; `outcome`, `timeouts` and `peer_count` are written on the `done()` -path. All three are therefore **absent** when `init()` satisfies the ledger -straight from the local store and the acquire never runs — treat a missing -`outcome` as "never went to the network", not as a lost span. +in `init()`. `outcome` has three values, written on two different paths: + +| `outcome` | Written where | Meaning | +| ---------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `complete` | `done()` | The ledger was fetched. | +| `failed` | `done()` | The acquisition ended on its own without the ledger. Usually it gave up after `timeouts_ > kLedgerTimeoutRetriesMax` (= 6), but `trigger()` also fails immediately on an unusable state or transaction map, so a `failed` span can carry `timeouts=0`. Carries span status `Error`. | +| `aborted` | destructor | The acquisition was abandoned before finishing — the sweep evicted it a minute after anything last asked for it, or `ledgers_` was cleared wholesale by shutdown or by `clearFailures()`. Status is left `Unset`, because the shutdown case is benign. | + +`peer_count` is written only on the `done()` path, so it is absent on `aborted` +spans: reading it would go through `Overlay`, which a destructor running at +teardown cannot depend on still existing. `timeouts` is written on both paths. + +A missing `outcome` has two causes, and neither is a lost span. The common one is +that `init()` satisfied the ledger straight from the local store, so the acquire +never went to the network. The other is a hard failure inside `tryDB()`: a stored +header that cannot be this ledger, or a zero account hash, sets `failed_` and +`init()` returns without ever calling `done()`, so no outcome is written. The +destructor does not fill the gap either — its `if (!isDone())` guard is already +false once `failed_` is set, because `isDone()` is `complete_ || failed_`. Such a +span carries `ledger_seq` and `acquire_reason` only. Since `aborted` exists, a +missing `outcome` is no longer how an abandoned acquisition presents. + +When reading acquire **duration**, exclude or split out `outcome="aborted"`. +Those spans stay open from `init()` until the object is destroyed, so they measure +how long the acquisition stayed outstanding rather than fetch latency, and will +skew a percentile that mixes them with `complete`. Only on the sweep path is that +duration bounded below by the one-minute threshold. The shutdown and +`clearFailures()` paths abort at whatever age the acquisition happened to have, so +an `aborted` span can also be arbitrarily short. `ledger.build` does **not** carry `tx_count` / `tx_failed`. Those two live on its child `tx.apply` span, which is where the set is actually applied @@ -1032,6 +1057,34 @@ Side-flow evidence: - **Acquire outcome fork**: `timeouts_ > kLedgerTimeoutRetriesMax` (= 6) sets `failed_` → terminal `logFailure`, no store/checkAccept ([InboundLedger.cpp:402](../src/xrpld/app/ledger/detail/InboundLedger.cpp#L402)). + A third path never reaches `done()` at all: the destructor marks any acquisition + that is still neither `complete_` nor `failed_` as `outcome=aborted` + ([InboundLedgers.cpp:393](../src/xrpld/app/ledger/detail/InboundLedgers.cpp#L393) + sweep eviction; [InboundLedger.cpp:224](../src/xrpld/app/ledger/detail/InboundLedger.cpp#L224) + abort branch). Give-up fires at roughly **18s**, not 21s: `init()` enters the + retry loop through `queueJob()` with no preceding `setTimer()`, so the first + `invokeOnTimer()` runs immediately with `progress_` still `false` and takes + `timeouts_` to 1 at t≈0. The test needs `timeouts_ > 6` — the seventh invocation + — and only six 3s intervals separate the seventh from the first, so 6 x 3s = 18s. + A live `aborted` rate does **not** by itself mean acquisitions are stalling. + Three unrelated paths produce it: + - **Sweep eviction** — the only cause that implies staleness, and it fires a + minute after anything last _asked for_ this ledger, not a minute after the + last byte arrived. + - **Shutdown** — `InboundLedgers::stop()` clears `ledgers_` wholesale, so every + clean stop aborts every acquisition still in flight. + - **`clearFailures()`** — also clears `ledgers_`, and is reachable at runtime + from the `fetch_info` admin RPC (`clear: true` → + `NetworkOPsImp::clearLedgerFetch()`), so an operator can produce aborts on a + perfectly healthy node. + + The 18s-vs-60s gap does not settle it either: while the acquisition lane sits at + its job limit the timer body never runs, so `timeouts_` cannot advance and the + give-up path is disarmed exactly when aborts are likeliest — see + [The deferral/timeout pair](#the-deferraltimeout-pair). Rule out shutdown and + `clearFailures()` first, then read a sustained `aborted` rate against + `acquire_sweep_evictions`. + - **done() reason branch (store side only)**: `HISTORY` → `onLedgerFetched`, **no** `storeLedger`; else → `storeLedger`. But `checkAccept` + `tryAdvance` run for **any** `complete_ && !failed_` acquire regardless of reason From 90900192871dad700218f12f6517f168a012f21f Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 22:19:03 +0100 Subject: [PATCH 18/23] chore: stop this branch touching the root gitignore Two unrelated edits had crept in. The added `.claude/` line duplicates `/.claude`, which the same file has already carried since well before this branch, so it never changed behaviour. Removing the root `.env.*` rule did change behaviour: contributors lost repo-level cover for any env file outside docker/telemetry, and the local ignore that masks this on one machine is not part of the repo. Restore the rule and drop the duplicate, which leaves the root gitignore byte-identical to the parent branch. The scoped rules added under docker/telemetry stay: they keep the three tracked .env.*.example files visible and stop the generated Grafana Cloud dashboards being committed, which is telemetry work this branch owns. --- .gitignore | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/.gitignore b/.gitignore index 92b4e56d07..0b4e68af74 100644 --- a/.gitignore +++ b/.gitignore @@ -89,4 +89,6 @@ target/ # clangd cache /.cache -.claude/ + +# Env. file carrying environmental setup data for local or cloud runs. +.env.* From 7273b06d35c02d430f7f062b7860d6ad87a65191 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 22:19:24 +0100 Subject: [PATCH 19/23] docs(telemetry): describe metrics instead of citing plan task numbers These comments were indexed by task, use-case and limitation numbers that are defined only in planning documents outside the shipped tree. Nothing in the repository defined them, so the cross-references resolved nowhere. Each comment now states what the code does. --- src/tests/libxrpl/telemetry/MetricMacros.cpp | 16 ++++---- src/xrpld/app/consensus/RCLConsensus.cpp | 2 +- src/xrpld/perflog/detail/PerfLogImp.cpp | 33 ++++++++-------- src/xrpld/telemetry/MetricMacros.h | 35 +++++++++-------- src/xrpld/telemetry/MetricsRegistry.cpp | 40 ++++++++++---------- src/xrpld/telemetry/MetricsRegistry.h | 40 ++++++++++---------- 6 files changed, 82 insertions(+), 84 deletions(-) diff --git a/src/tests/libxrpl/telemetry/MetricMacros.cpp b/src/tests/libxrpl/telemetry/MetricMacros.cpp index ddcd2af33c..988cf1f1ba 100644 --- a/src/tests/libxrpl/telemetry/MetricMacros.cpp +++ b/src/tests/libxrpl/telemetry/MetricMacros.cpp @@ -277,9 +277,9 @@ TEST(MetricMacros, observable_gauge_register_reports_current_value) FakeApp app; wire(app, /*enabled=*/true); - // Own the state exactly as a real caller would (Use Case 5 in the - // design doc) -- the macro's callback reads through this atomic on - // every collection tick, it does not own the value itself. + // Own the state exactly as a real caller would -- the macro's callback + // reads through this atomic on every collection tick, it does not own + // the value itself. std::atomic queueDepth{0}; XRPL_METRIC_OBSERVABLE_GAUGE_REGISTER( app, @@ -287,11 +287,11 @@ TEST(MetricMacros, observable_gauge_register_reports_current_value) "Test observable gauge for macro unit test", [&queueDepth] { return queueDepth.load(); }); - // There is no application-level read-back API (Use Case 4) -- this - // test can only prove registration doesn't crash and that meter() was - // consulted to create the observable instrument. It does NOT assert the - // observed value reaches Prometheus; that is Task 3b's docker-harness - // job, not this hermetic unit test. + // There is no application-level read-back API -- this test can only + // prove registration doesn't crash and that meter() was consulted to + // create the observable instrument. It does NOT assert the observed + // value reaches Prometheus; that is the docker-harness integration + // test's job, not this hermetic unit test. queueDepth.store(42); EXPECT_EQ(app.registry().meterCalls(), 1); } diff --git a/src/xrpld/app/consensus/RCLConsensus.cpp b/src/xrpld/app/consensus/RCLConsensus.cpp index 5af4412ce8..8157a55c09 100644 --- a/src/xrpld/app/consensus/RCLConsensus.cpp +++ b/src/xrpld/app/consensus/RCLConsensus.cpp @@ -745,7 +745,7 @@ RCLConsensus::Adaptor::doAccept( // Record ledger close for OTel dashboard parity counter. Uses the // call-site macro (see MetricMacros.h) rather than a MetricsRegistry - // member -- proof-of-concept for tasks/metric-macro-plan.md. + // member. XRPL_METRIC_COUNTER_INC(app_, "ledgers_closed_total", "Total ledgers closed by consensus"); //------------------------------------------------------------------------- diff --git a/src/xrpld/perflog/detail/PerfLogImp.cpp b/src/xrpld/perflog/detail/PerfLogImp.cpp index 106c36f157..b3cd723872 100644 --- a/src/xrpld/perflog/detail/PerfLogImp.cpp +++ b/src/xrpld/perflog/detail/PerfLogImp.cpp @@ -336,17 +336,16 @@ PerfLogImp::rpcStart(std::string const& method, std::uint64_t const requestId) counters_.methods[requestId] = {counter->first.c_str(), steady_clock::now()}; } - // Task 9.4: Record RPC start in OTel metrics pipeline. Recorded after the - // locks above are released: the OTel call path allocates and takes locks + // Record RPC start in OTel metrics pipeline. Recorded after the locks + // above are released: the OTel call path allocates and takes locks // inside the SDK, so holding methodsMutex across it would widen a // process-wide critical section for no reason. Mirrors rpcEnd(). if (auto* mr = app_.getMetricsRegistry()) mr->recordRpcStarted(method); - // Proof-of-concept for tasks/metric-macro-plan.md Use Case 2: a value - // that must be able to decrease (UpDownCounter), added at its call - // site with no MetricsRegistry member/init-line/method. Paired with the - // matching -1 in rpcEnd(). Runs on the same path as recordRpcStarted + // A value that must be able to decrease (UpDownCounter), added at its + // call site with no MetricsRegistry member/init-line/method. Paired with + // the matching -1 in rpcEnd(). Runs on the same path as recordRpcStarted // above, i.e. only after a methods-map entry exists for this request. XRPL_METRIC_UPDOWN_ADD(app_, "rpc_in_flight_requests", "RPC requests currently executing", 1); } @@ -397,9 +396,9 @@ PerfLogImp::rpcEnd(std::string const& method, std::uint64_t const requestId, boo counter->second.value.duration += durationUs; } - // Task 9.4: Record RPC completion in OTel metrics pipeline. - // Mirrors the rpcStart() instrumentation so the finished/errored - // counters and duration histogram advance with every call. + // Record RPC completion in OTel metrics pipeline. Mirrors the + // rpcStart() instrumentation so the finished/errored counters and + // duration histogram advance with every call. if (auto* mr = app_.getMetricsRegistry()) { if (finish) @@ -434,8 +433,8 @@ PerfLogImp::jobQueue(JobType const type, std::string const& name) ++counter->second.value.queued; } - // Task 9.5: Record job enqueue in OTel metrics pipeline, after the lock - // above is released so the SDK's work stays outside the critical section. + // Record job enqueue in OTel metrics pipeline, after the lock above is + // released so the SDK's work stays outside the critical section. if (auto* mr = app_.getMetricsRegistry()) mr->recordJobQueued(JobTypes::name(type), name); } @@ -468,10 +467,10 @@ PerfLogImp::jobStart( counters_.jobs[instance] = {type, startTime}; } - // Task 9.5: Record job start in OTel metrics pipeline, after the locks - // above are released. jobsMutex is process-wide and taken by every worker - // thread on every job, so the SDK's allocation and internal locking must - // not run inside it. + // Record job start in OTel metrics pipeline, after the locks above are + // released. jobsMutex is process-wide and taken by every worker thread + // on every job, so the SDK's allocation and internal locking must not + // run inside it. if (auto* mr = app_.getMetricsRegistry()) mr->recordJobStarted(JobTypes::name(type), name, dur.count()); } @@ -499,8 +498,8 @@ PerfLogImp::jobFinish(JobType const type, std::string const& name, microseconds counters_.jobs[instance] = {JtInvalid, steady_time_point()}; } - // Task 9.5: Record job finish in OTel metrics pipeline, after the locks - // above are released, for the same reason as jobStart(). + // Record job finish in OTel metrics pipeline, after the locks above + // are released, for the same reason as jobStart(). if (auto* mr = app_.getMetricsRegistry()) mr->recordJobFinished(JobTypes::name(type), name, dur.count()); } diff --git a/src/xrpld/telemetry/MetricMacros.h b/src/xrpld/telemetry/MetricMacros.h index 6bea92d8e3..a870df3319 100644 --- a/src/xrpld/telemetry/MetricMacros.h +++ b/src/xrpld/telemetry/MetricMacros.h @@ -87,27 +87,26 @@ * @note A histogram whose values can exceed ~10,000 units (e.g. a * microsecond duration beyond 10ms) needs an explicit-bucket View, which * OTel can only register at MeterProvider construction time -- this - * cannot be done from a call site. See Limitation 2. Register such a - * view in MetricsRegistry::initExporterAndProvider() as today; the + * cannot be done from a call site. Register such a view in + * MetricsRegistry::initExporterAndProvider() as today; the * histogram-record call itself can still use the macro. * * @note Only call the SYNCHRONOUS macros (Counter/UpDownCounter/ * Histogram/Gauge) from code that runs AFTER MetricsRegistry::start() has * completed (RPC handlers, job callbacks, consensus rounds, tx apply, peer - * message handlers). See Limitation 1. + * message handlers). * * @note The OBSERVABLE registration macros are the opposite: call them * EAGERLY, exactly once, from constructor/init code -- never from a hot * path. Repeated calls at the same call site register a NEW callback * each time (no create-once caching, unlike the synchronous macros), - * which leaks callbacks. See Limitation 3. + * which leaks callbacks. * * @note There is no way to read back a synchronous instrument's current * accumulated value from application code -- the OTel API is * write-only/push-based by design. If your logic needs both to record a * metric AND read its running value, keep your own state (std::atomic or - * similar) and separately feed OTel via these macros. See "Use Case 4" in - * tasks/metric-macro-plan.md. + * similar) and separately feed OTel via these macros. */ // On Windows, OTel's spin_lock_mutex.h (transitively included from @@ -208,11 +207,11 @@ } while (false) // UpDownCounter: like COUNTER_ADD, but the underlying instrument permits a -// negative amount (Use Case 2 -- e.g. in-flight request count, +1 on start -// / -1 on finish from two different points in the same or different call -// sites). A plain Counter's Add() must never see a negative value per the -// OTel API contract; use this macro, not COUNTER_ADD, whenever the value -// can decrease. +// negative amount (e.g. in-flight request count, +1 on start / -1 on +// finish from two different points in the same or different call sites). +// A plain Counter's Add() must never see a negative value per the OTel +// API contract; use this macro, not COUNTER_ADD, whenever the value can +// decrease. #define XRPL_METRIC_UPDOWN_ADD(app, name, description, amount) \ do \ { \ @@ -354,15 +353,15 @@ #endif // OPENTELEMETRY_ABI_VERSION_NO >= 2 // ----------------------------------------------------------------- -// Observable/async instrument registration (Use Case 5). Unlike the -// synchronous macros above, these do NOT lazily create-on-first-call -- -// they register a callback with the SDK immediately, at the call site, -// the moment the macro executes. Callers MUST invoke this during +// Observable/async instrument registration. Unlike the synchronous +// macros above, these do NOT lazily create-on-first-call -- they +// register a callback with the SDK immediately, at the call site, the +// moment the macro executes. Callers MUST invoke this during // construction/init, before the server is fully live (same timing rule // MetricsRegistry::registerAsyncGauges() already follows for its own -// gauges -- see Limitation 3). Calling it from a hot-path function -// instead of an init path re-registers a new callback on every call, -// which leaks callbacks and is NOT what this macro is for. +// gauges). Calling it from a hot-path function instead of an init path +// re-registers a new callback on every call, which leaks callbacks and +// is NOT what this macro is for. // // The callable is captured in a heap-allocated std::function, and its // address is passed as the `void* state` to AddCallback (whose signature, diff --git a/src/xrpld/telemetry/MetricsRegistry.cpp b/src/xrpld/telemetry/MetricsRegistry.cpp index 40e434416d..c07817e41e 100644 --- a/src/xrpld/telemetry/MetricsRegistry.cpp +++ b/src/xrpld/telemetry/MetricsRegistry.cpp @@ -382,7 +382,7 @@ MetricsRegistry::initSyncInstruments() jobRunningDurationHistogram_ = meter_->CreateDoubleHistogram(kJobRunningDurationUs, "Job execution time in microseconds"); - // --- External dashboard parity counters (Task 7.14) --- + // --- External dashboard parity counters --- ledgersClosedCounter_ = meter_->CreateUInt64Counter("ledgers_closed_total", "Total ledgers closed by consensus"); validationsSentCounter_ = meter_->CreateUInt64Counter( @@ -441,7 +441,7 @@ MetricsRegistry::stop() } // ----------------------------------------------------------------- -// Synchronous instrument recording — RPC metrics (Task 9.4) +// Synchronous instrument recording — RPC metrics // ----------------------------------------------------------------- void @@ -500,7 +500,7 @@ MetricsRegistry::recordRpcErrored(std::string_view method, std::int64_t duration } // ----------------------------------------------------------------- -// Synchronous instrument recording — Job Queue metrics (Task 9.5) +// Synchronous instrument recording — Job Queue metrics // ----------------------------------------------------------------- void @@ -579,7 +579,7 @@ MetricsRegistry::recordJobFinished( } // ----------------------------------------------------------------- -// Observable gauge callbacks (Tasks 9.1, 9.2, 9.3, 9.6, 9.7) +// Observable gauge callbacks // ----------------------------------------------------------------- #ifdef XRPL_ENABLE_TELEMETRY @@ -647,7 +647,7 @@ MetricsRegistry::registerJqTransOverflowCounter() void MetricsRegistry::registerCacheHitRateGauge() { - // --- Task 9.2: Cache hit rate and size gauges --- + // --- Cache hit rate and size gauges --- cacheHitRateGauge_ = meter_->CreateDoubleObservableGauge("cache_metrics", "Cache hit rates and sizes"); cacheHitRateGauge_->AddCallback( @@ -718,7 +718,7 @@ MetricsRegistry::registerCacheHitRateGauge() void MetricsRegistry::registerTxqGauge() { - // --- Task 9.3: TxQ metrics gauges --- + // --- TxQ metrics gauges --- txqGauge_ = meter_->CreateDoubleObservableGauge("txq_metrics", "Transaction queue metrics"); txqGauge_->AddCallback( [](opentelemetry::metrics::ObserverResult result, void* state) { @@ -765,7 +765,7 @@ MetricsRegistry::registerTxqGauge() void MetricsRegistry::registerObjectCountGauge() { - // --- Task 9.6: Counted object instance gauges --- + // --- Counted object instance gauges --- objectCountGauge_ = meter_->CreateInt64ObservableGauge( "object_count", "Live instance counts for key internal object types"); objectCountGauge_->AddCallback( @@ -797,7 +797,7 @@ MetricsRegistry::registerObjectCountGauge() void MetricsRegistry::registerLoadFactorGauge() { - // --- Task 9.7: Load factor breakdown gauges --- + // --- Load factor breakdown gauges --- loadFactorGauge_ = meter_->CreateDoubleObservableGauge("load_factor_metrics", "Fee load factor breakdown"); loadFactorGauge_->AddCallback( @@ -961,7 +961,7 @@ MetricsRegistry::observeReadQueue(node_store::Database& db, ObserveFn const& obs void MetricsRegistry::registerNodeStoreGauge() { - // --- Task 9.1: NodeStore I/O gauges --- + // --- NodeStore I/O gauges --- // The cumulative counters (reads, writes, bytes) are also exposed here // as observable gauges. This avoids adding an xrpld dependency into the // libxrpl nodestore code — the MetricsRegistry reads the existing atomic @@ -1009,7 +1009,7 @@ MetricsRegistry::registerNodeStoreGauge() void MetricsRegistry::registerServerInfoGauge() { - // --- Task 9.7a: Server info gauges --- + // --- Server info gauges --- serverInfoGauge_ = meter_->CreateInt64ObservableGauge("server_info", "Server-level health metrics"); serverInfoGauge_->AddCallback( @@ -1094,7 +1094,7 @@ MetricsRegistry::registerServerInfoGauge() void MetricsRegistry::registerBuildInfoGauge() { - // --- Task 9.7b: Build info gauge --- + // --- Build info gauge --- buildInfoGauge_ = meter_->CreateInt64ObservableGauge("build_info", "Build version information"); buildInfoGauge_->AddCallback( [](opentelemetry::metrics::ObserverResult result, void* /* state */) { @@ -1114,7 +1114,7 @@ MetricsRegistry::registerBuildInfoGauge() void MetricsRegistry::registerCompleteLedgersGauge() { - // --- Task 9.7c: Complete ledgers range gauge --- + // --- Complete ledgers range gauge --- completeLedgersGauge_ = meter_->CreateInt64ObservableGauge( "complete_ledgers", "Complete ledger range start/end pairs"); completeLedgersGauge_->AddCallback( @@ -1173,7 +1173,7 @@ MetricsRegistry::registerCompleteLedgersGauge() void MetricsRegistry::registerDbMetricsGauge() { - // --- Task 9.7d: Database size and fetch rate gauges --- + // --- Database size and fetch rate gauges --- dbMetricsGauge_ = meter_->CreateInt64ObservableGauge("db_metrics", "Database storage sizes and fetch rates"); dbMetricsGauge_->AddCallback( @@ -1212,7 +1212,7 @@ MetricsRegistry::registerDbMetricsGauge() void MetricsRegistry::registerValidatorHealthGauge() { - // --- Task 7.9: Validator health gauges --- + // --- Validator health gauges --- validatorHealthGauge_ = meter_->CreateDoubleObservableGauge("validator_health", "Validator health indicators"); validatorHealthGauge_->AddCallback( @@ -1259,7 +1259,7 @@ MetricsRegistry::registerValidatorHealthGauge() void MetricsRegistry::registerPeerQualityGauge() { - // --- Task 7.10: Peer quality gauges --- + // --- Peer quality gauges --- // Uses Peer::json() to read latency and version since those accessors // are not on the abstract Peer interface (they live on PeerImp). peerQualityGauge_ = @@ -1413,7 +1413,7 @@ MetricsRegistry::registerReduceRelayGauge() void MetricsRegistry::registerLedgerEconomyGauge() { - // --- Task 7.11: Ledger economy gauges --- + // --- Ledger economy gauges --- ledgerEconomyGauge_ = meter_->CreateDoubleObservableGauge("ledger_economy", "Ledger fee and economy metrics"); ledgerEconomyGauge_->AddCallback( @@ -1478,7 +1478,7 @@ MetricsRegistry::registerLedgerEconomyGauge() void MetricsRegistry::registerStateTrackingGauge() { - // --- Task 7.12: State tracking gauges --- + // --- State tracking gauges --- stateTrackingGauge_ = meter_->CreateDoubleObservableGauge("state_tracking", "Node state and mode tracking"); stateTrackingGauge_->AddCallback( @@ -1532,7 +1532,7 @@ MetricsRegistry::registerStateTrackingGauge() void MetricsRegistry::registerStorageDetailGauge() { - // --- Task 7.13: Storage detail gauges --- + // --- Storage detail gauges --- // Reports the cumulative payload bytes handed to the NodeStore. See the // note at the observe() call below: this is logical bytes stored, not // on-disk file size, because no accessor for the latter exists. The label @@ -1584,7 +1584,7 @@ MetricsRegistry::registerStorageDetailGauge() void MetricsRegistry::registerValidationAgreementGauge() { - // --- Task 7.15: Validation agreement gauges --- + // --- Validation agreement gauges --- // Reports rolling-window agreement percentages and counts from // ValidationTracker. reconcile() is called at the start of the // callback so that pending ledger events are resolved before the @@ -1696,7 +1696,7 @@ MetricsRegistry::registerValidationTotalsCounters() #endif // XRPL_ENABLE_TELEMETRY // ----------------------------------------------------------------- -// External dashboard parity counter increments (Task 7.14) +// External dashboard parity counter increments // ----------------------------------------------------------------- void diff --git a/src/xrpld/telemetry/MetricsRegistry.h b/src/xrpld/telemetry/MetricsRegistry.h index 017e2c7bae..3662f1960b 100644 --- a/src/xrpld/telemetry/MetricsRegistry.h +++ b/src/xrpld/telemetry/MetricsRegistry.h @@ -231,8 +231,8 @@ namespace telemetry { * edit needed. Fall back to a dedicated member + init line + record * method (the pattern below) only when the metric needs to be read * back by other code (e.g. ValidationTracker-style accumulation) or - * needs a custom histogram bucket View (see MetricMacros.h Limitation - * 2 in tasks/metric-macro-plan.md). + * needs a custom histogram bucket View (see the histogram note in + * MetricMacros.h). * - Adding a new OBSERVABLE gauge still requires eager central * registration -- pull-model instruments cannot be lazily created. */ @@ -575,7 +575,7 @@ public: std::int64_t runningDurUs); // ----------------------------------------------------------------- - // External dashboard parity counters (Tasks 7.9-7.14) + // External dashboard parity counters // ----------------------------------------------------------------- /** @@ -862,7 +862,7 @@ private: */ opentelemetry::nostd::shared_ptr dbMetricsGauge_; - // --- External dashboard parity gauges (Tasks 7.9-7.13) --- + // --- External dashboard parity gauges --- /** * Observable gauge for validator health indicators (amendment blocked, * UNL blocked, quorum, UNL expiry). @@ -905,7 +905,7 @@ private: opentelemetry::nostd::shared_ptr validationAgreementGauge_; - // --- External dashboard parity counters (Task 7.14) --- + // --- External dashboard parity counters --- /** * Counter: ledgers_closed_total — incremented each consensus round. */ @@ -1003,15 +1003,15 @@ private: void registerJqTransOverflowCounter(); // gap-fill: overlay overflow total void - registerCacheHitRateGauge(); // Task 9.2 + registerCacheHitRateGauge(); void - registerTxqGauge(); // Task 9.3 + registerTxqGauge(); void - registerObjectCountGauge(); // Task 9.6 + registerObjectCountGauge(); void - registerLoadFactorGauge(); // Task 9.7 + registerLoadFactorGauge(); void - registerNodeStoreGauge(); // Task 9.1 + registerNodeStoreGauge(); // The four nodestore_state helpers and their ObserveFn sink are public // (above), so a test can drive each one with a recording sink and assert @@ -1019,27 +1019,27 @@ private: // arguments, so exposing them widens no state. void - registerServerInfoGauge(); // Task 9.7a + registerServerInfoGauge(); void - registerBuildInfoGauge(); // Task 9.7b + registerBuildInfoGauge(); void - registerCompleteLedgersGauge(); // Task 9.7c + registerCompleteLedgersGauge(); void - registerDbMetricsGauge(); // Task 9.7d + registerDbMetricsGauge(); void - registerValidatorHealthGauge(); // Task 7.9 + registerValidatorHealthGauge(); void - registerPeerQualityGauge(); // Task 7.10 + registerPeerQualityGauge(); void registerReduceRelayGauge(); // Reduce-relay efficiency void - registerLedgerEconomyGauge(); // Task 7.11 + registerLedgerEconomyGauge(); void - registerStateTrackingGauge(); // Task 7.12 + registerStateTrackingGauge(); void - registerStorageDetailGauge(); // Task 7.13 + registerStorageDetailGauge(); void - registerValidationAgreementGauge(); // Task 7.15 + registerValidationAgreementGauge(); void registerValidationTotalsCounters(); // gap-fill: lifetime agree/miss _total #endif // XRPL_ENABLE_TELEMETRY From ca19c456fd0f123b4564d44c20bf9520e6bdefeb Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 22:26:26 +0100 Subject: [PATCH 20/23] test(telemetry): name the metrics under test instead of plan task numbers The integration-test sections, alert provisioning headers and a naming-check test comment were indexed by rollout phase and task numbers defined only in planning documents outside the shipped tree. Each now names what it covers. --- .../otel-naming/test_check_otel_naming.py | 2 +- .../provisioning/alerting/contactpoints.yaml | 2 +- .../provisioning/alerting/policies.yaml | 2 +- .../grafana/provisioning/alerting/rules.yaml | 2 +- docker/telemetry/integration-test.sh | 20 +++++++++---------- 5 files changed, 14 insertions(+), 14 deletions(-) diff --git a/.github/scripts/otel-naming/test_check_otel_naming.py b/.github/scripts/otel-naming/test_check_otel_naming.py index 055e43b28e..c5de49f073 100644 --- a/.github/scripts/otel-naming/test_check_otel_naming.py +++ b/.github/scripts/otel-naming/test_check_otel_naming.py @@ -509,7 +509,7 @@ class RuleEAllowDottedMarkerEnforcement(unittest.TestCase): ) def test_all_named_keys_exempt_on_a_table_row(self): - # The real shape in the plan docs: a "was -> is now" row naming two old + # The real-world shape: a "was -> is now" row naming two old # dotted keys, with both listed in the marker. tokens, _ = _run_rule_e_docs( { diff --git a/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml b/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml index 03fa2344b4..0d36642776 100644 --- a/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml +++ b/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml @@ -1,6 +1,6 @@ # Grafana contact-point provisioning for rippled OTel alerts. # -# Phase 9: Internal metric gap fill — alerting on health-critical metrics. +# Alerting on health-critical internal metrics. # # A contact point is where a firing alert is delivered. Two are defined: # xrpld-default — Slack only; receives warning-severity alerts. diff --git a/docker/telemetry/grafana/provisioning/alerting/policies.yaml b/docker/telemetry/grafana/provisioning/alerting/policies.yaml index b1c4c92c70..3b65bb4ae6 100644 --- a/docker/telemetry/grafana/provisioning/alerting/policies.yaml +++ b/docker/telemetry/grafana/provisioning/alerting/policies.yaml @@ -1,6 +1,6 @@ # Grafana notification-policy provisioning for rippled OTel alerts. # -# Phase 9: Internal metric gap fill — alerting on health-critical metrics. +# Alerting on health-critical internal metrics. # # The notification policy tree decides which contact point receives a firing # alert and how alerts are batched. Routing is split by severity: diff --git a/docker/telemetry/grafana/provisioning/alerting/rules.yaml b/docker/telemetry/grafana/provisioning/alerting/rules.yaml index 0a8b294fda..9746559b28 100644 --- a/docker/telemetry/grafana/provisioning/alerting/rules.yaml +++ b/docker/telemetry/grafana/provisioning/alerting/rules.yaml @@ -1,6 +1,6 @@ # Grafana alert-rule provisioning for rippled OTel metrics. # -# Phase 9: Internal metric gap fill — alerting on health-critical metrics. +# Alerting on health-critical internal metrics. # # Thirteen rules across five subsystems: consensus/ledger health, validator # health, the job queue, node operating state, and the overlay (manifests). diff --git a/docker/telemetry/integration-test.sh b/docker/telemetry/integration-test.sh index b4401d5906..0a6fb98645 100755 --- a/docker/telemetry/integration-test.sh +++ b/docker/telemetry/integration-test.sh @@ -660,10 +660,10 @@ else fi # --------------------------------------------------------------------------- -# Step 10c: Verify Phase 9 OTel SDK Metrics +# Step 10c: Verify OTel SDK Metrics # --------------------------------------------------------------------------- log "" -log "--- Phase 9: OTel SDK Metrics (MetricsRegistry) ---" +log "--- OTel SDK Metrics (MetricsRegistry) ---" log "Waiting 15s for OTel metric export + Prometheus scrape..." sleep 15 @@ -679,34 +679,34 @@ check_otel_metric() { fi } -# Task 9.1: NodeStore I/O +# NodeStore I/O check_otel_metric 'nodestore_state{metric="node_reads_total"}' check_otel_metric 'nodestore_state{metric="write_load"}' -# Task 9.2: Cache hit rates +# Cache hit rates check_otel_metric 'cache_metrics{metric="SLE_hit_rate"}' check_otel_metric 'cache_metrics{metric="treenode_cache_size"}' -# Task 9.3: TxQ metrics +# TxQ metrics check_otel_metric 'txq_metrics{metric="txq_count"}' check_otel_metric 'txq_metrics{metric="txq_reference_fee_level"}' -# Task 9.4: Per-RPC metrics +# Per-RPC metrics check_otel_metric "rpc_method_started_total" check_otel_metric "rpc_method_finished_total" -# Task 9.5: Per-job metrics +# Per-job metrics check_otel_metric "job_queued_total" check_otel_metric "job_finished_total" -# Task 9.6: Counted object instances +# Counted object instances check_otel_metric "object_count" -# Task 9.7: Load factor breakdown +# Load factor breakdown check_otel_metric 'load_factor_metrics{metric="load_factor"}' check_otel_metric 'load_factor_metrics{metric="load_factor_server"}' -# Task 7.15 / Phase 9: ValidationTracker rolling-window agreement gauge. +# ValidationTracker rolling-window agreement gauge. # MetricsRegistry::registerValidationAgreementGauge() publishes # validation_agreement with a `metric` label for each window # (1h / 24h / 7d) plus the matching agreement/miss counts. The 7-day From 372de0cdc8ed7276401fc547194564378a8569dd Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 22:32:53 +0100 Subject: [PATCH 21/23] docs(telemetry): keep the runbook to files that ship The runbook pointed at a planning document and a helper script that are outside the shipped tree, and at a dashboard script that no longer exists, so an operator following it hit three dead ends. The Cloud alert workflow is now described by what it does to the tracked rules.yaml. --- docs/telemetry-glossary.md | 12 +++++----- docs/telemetry-runbook.md | 47 +++++++++++++++++++++----------------- 2 files changed, 32 insertions(+), 27 deletions(-) diff --git a/docs/telemetry-glossary.md b/docs/telemetry-glossary.md index c949ab274a..23b8686ac4 100644 --- a/docs/telemetry-glossary.md +++ b/docs/telemetry-glossary.md @@ -9,12 +9,12 @@ documentation. > **Related docs**: > [docs/telemetry-runbook.md](./telemetry-runbook.md) (operator runbook). - + ## Contents diff --git a/docs/telemetry-runbook.md b/docs/telemetry-runbook.md index 0a8f23bd69..16ead134ce 100644 --- a/docs/telemetry-runbook.md +++ b/docs/telemetry-runbook.md @@ -226,9 +226,8 @@ to a datasource of the matching type — auto-selecting it when only one exists (the usual case: one Mimir, one Tempo). This is what makes the same files work unchanged on both the local stack and Cloud. -> Dashboards are parameterized by `grafana/parameterize-datasources.py`. If you -> add a dashboard exported with hardcoded UIDs, re-run that script (idempotent) -> before committing so it stays portable. +> If you add a dashboard exported with hardcoded datasource UIDs, replace them +> with `${DS_PROMETHEUS}` / `${DS_TEMPO}` before committing. To import: @@ -1946,9 +1945,7 @@ line added to `addMicrosecondHistogramView()` in `MetricsRegistry.cpp` -- the only case that still touches a central file. There is no way to read a metric's current value back from application code -- OTel's API is write-only by design; keep your own state if your logic needs to both record and read a running value -(see the Doxygen header in `MetricMacros.h` and "Use Case 4" in -`tasks/metric-macro-plan.md` for the full explanation and the `prometheus-cpp` -contrast rationale). +(see the Doxygen header in `MetricMacros.h` for the full explanation). ## Deployment Tiers @@ -2562,25 +2559,33 @@ docker compose -f docker/telemetry/docker-compose.yml exec renderer \ #### Deploying alerts to Grafana Cloud Grafana Cloud has **no provisioning filesystem**, so these `apiVersion: 1` files -cannot be loaded there. Cloud deployment goes through the REST API via -`docker/telemetry/upload_alerts_to_grafana.py`, which reads the same tracked -`rules.yaml` as the single source of truth (so local and Cloud cannot drift) and -applies the Cloud-specific transforms: the local `prometheus` datasource uid is -swapped for the Cloud one, the `folder:` _name_ becomes an existing `folderUID`, -and `interval` becomes integer seconds. +cannot be loaded there. Cloud deployment goes through the Grafana alerting **REST +API**, driven from the same tracked `rules.yaml` — it stays the single source of +truth, so local and Cloud cannot drift. -```bash -cd docker/telemetry -python3 upload_alerts_to_grafana.py --dry-run # always dry-run first -python3 upload_alerts_to_grafana.py # create rules, paused -python3 upload_alerts_to_grafana.py --verify # read back what is deployed -``` +Each rule needs three Cloud-specific transforms on the way out: + +| Field in `rules.yaml` | Cloud form | +| --------------------------------- | ------------------------ | +| local `prometheus` datasource uid | the Cloud datasource uid | +| `folder:` _name_ | an existing `folderUID` | +| `interval` (duration string) | integer seconds | + +Then, in order: + +1. **Dry-run first** — render what would be sent and review it before writing + anything to the Cloud stack. +2. **Create the rules paused**, so nothing can fire on a threshold that has not + been reviewed against this fleet. +3. **Read back** the deployed rules and verify they are what was sent. + +Land the rules with delivery disabled while no recipient has been chosen, and +activate them only once the thresholds have been checked against the target +fleet's baseline. Credentials come from `.env.grafanaserviceapi` (gitignored, a service-account token with `alert.rules:write`); the recipient address comes from `ALERT_EMAIL_TO` -in `.env.alerting`. Neither is ever written to a tracked file. Use -`--no-delivery` to land the rules before a recipient is chosen, and `--activate` -only once the thresholds have been checked against the target fleet's baseline. +in `.env.alerting`. Neither is ever written to a tracked file. > **The Cloud notification policy tree must not be pushed.** There is exactly one > policy tree per org and the PUT endpoint **replaces it wholesale**. On a shared From 84536ef25f76cf29191f3192ac49efeed12448fa Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 22:37:33 +0100 Subject: [PATCH 22/23] docs(telemetry): name the workload stack instead of its phase number The health-check note identified the stack by a rollout phase number defined only in a planning folder outside the shipped tree. --- docker/telemetry/TESTING.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/telemetry/TESTING.md b/docker/telemetry/TESTING.md index 780af0a4af..048e6b8526 100644 --- a/docker/telemetry/TESTING.md +++ b/docker/telemetry/TESTING.md @@ -63,7 +63,7 @@ curl -sf http://localhost:3200/ready >/dev/null && echo "tempo ready" > The collector's `health_check` extension listens on **13133**, but > `docker-compose.yml` publishes only 4317, 4318 and 8889 — so 13133 is not > reachable from the host with the base stack. It is published only by the -> Phase-10 workload stack (`docker-compose.workload.yaml`). +> workload validation stack (`docker-compose.workload.yaml`). ### Step 2: Start xrpld in standalone mode From 2e1ebf90bbceb1862d52cfb54f1cba94890430d5 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 14 Aug 2026 22:40:53 +0100 Subject: [PATCH 23/23] docs(telemetry): describe the Cloud alert path without the helper script The alerting example env file, the contact-point provisioning header and one runbook line still pointed at a gitignored helper script and at a rollout phase number, neither of which ships. The contact-point header now states the policy-tree warning inline rather than deferring to a file the reader cannot open. --- docker/telemetry/.env.alerting.example | 6 +++--- .../grafana/provisioning/alerting/contactpoints.yaml | 9 +++++---- docs/telemetry-runbook.md | 2 +- 3 files changed, 9 insertions(+), 8 deletions(-) diff --git a/docker/telemetry/.env.alerting.example b/docker/telemetry/.env.alerting.example index 594c55c064..aa0bdf9891 100644 --- a/docker/telemetry/.env.alerting.example +++ b/docker/telemetry/.env.alerting.example @@ -14,8 +14,8 @@ # GF_SMTP_* consumed by the Grafana container (compose `env_file`) to # turn on mail delivery. Without these, an email contact point # provisions fine and then silently sends nothing. -# ALERT_EMAIL_TO read by upload_alerts_to_grafana.py to build the Grafana -# CLOUD email contact point over the REST API (Cloud has no +# ALERT_EMAIL_TO the recipient for the Grafana CLOUD email contact point, +# which is created over the REST API (Cloud has no # provisioning filesystem). Not used by the local stack. # --- Slack (local stack: paste the webhook into contactpoints.yaml instead) --- @@ -25,7 +25,7 @@ SLACK_WEBHOOK_URL= # --- Email --- # Recipient for Grafana Cloud alerts (comma- or semicolon-separated). -# Consumed by upload_alerts_to_grafana.py. +# Used when creating the Cloud email contact point over the REST API. ALERT_EMAIL_TO= # SMTP relay Grafana sends through. Email only delivers when SMTP is enabled diff --git a/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml b/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml index 0d36642776..06407f904e 100644 --- a/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml +++ b/docker/telemetry/grafana/provisioning/alerting/contactpoints.yaml @@ -41,10 +41,11 @@ # GF_SMTP_ENABLED=true and the relay settings point somewhere real. # # Grafana Cloud does NOT use this file — Cloud has no provisioning filesystem. -# Cloud delivery is created over the REST API by upload_alerts_to_grafana.py, -# which builds a single email-only contact point and attaches it to each rule -# via per-rule notification_settings. See that script's header for why the -# notification policy tree must not be touched on a shared Cloud instance. +# Cloud delivery is created over the REST API instead: a single email-only +# contact point, attached to each rule via per-rule notification_settings. +# The notification policy tree must never be pushed to a shared Cloud +# instance -- there is exactly one tree per org and the PUT endpoint +# replaces it wholesale. apiVersion: 1 diff --git a/docs/telemetry-runbook.md b/docs/telemetry-runbook.md index 16ead134ce..d09ce1c3e8 100644 --- a/docs/telemetry-runbook.md +++ b/docs/telemetry-runbook.md @@ -3309,7 +3309,7 @@ Two more pairs from the same family: cumulative object-payload bytes this process has written — the same value as `node_written_bytes`, from the same accessor — so it excludes keys, padding and the log, and it resets with the process. A ratio of the two is a constant 1.0 and - measures nothing. This label value was called `nudb_bytes` before Phase 9; it + measures nothing. This label value was previously called `nudb_bytes`; it comes from `node_store::Database` rather than the NuDB backend, so it is not part of the `nudb_*` family above and reads the same on RocksDB. - These gauges are sampled on the `MetricsRegistry` reader's 10 s cadence, while