From e87432fe3c773f6c0f74b99c82bc3cbf0cb9331a Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 18 Sep 2026 09:24:56 +0100 Subject: [PATCH 1/4] fix(telemetry): drop the suppressed references the span no longer emits tx.receive is created after the duplicate check, so it never carries a suppressed attribute. The Tempo tag filter and the dashboard panel still referenced it, and check_otel_naming rules C and D fail on a reference with no constant behind it. The panel keeps its remaining signal as a plain receive rate. How many relayed copies were dropped is the transactions_duplicate traffic category, which does not depend on a span. The spanmetrics dimension goes too; a dimension for an attribute nothing sets only widens the label set. --- .../grafana/dashboards/transaction-overview.json | 8 ++++---- .../telemetry/grafana/provisioning/datasources/tempo.yaml | 5 ----- docker/telemetry/otel-collector-config.yaml | 1 - 3 files changed, 4 insertions(+), 10 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/transaction-overview.json b/docker/telemetry/grafana/dashboards/transaction-overview.json index 94cc8be828..3fb01f7cd8 100644 --- a/docker/telemetry/grafana/dashboards/transaction-overview.json +++ b/docker/telemetry/grafana/dashboards/transaction-overview.json @@ -140,8 +140,8 @@ } }, { - "title": "Transaction Receive vs Suppressed", - "description": "**What:** Raw transaction messages received from peers, split by whether they were suppressed as duplicates before processing.\n**How it's computed:** Per-second rate split by suppressed flag over a 5-minute window, per node.\n**Reading it:** A healthy relay network produces a steady suppressed share as duplicates are filtered.\n**Healthy range:** Workload-dependent; suppression is expected and normal.\n**Watch for:** A sharp rise in the suppressed line can reflect gossip amplification or a peer replaying transactions.\n**Source:** src/xrpld/overlay/detail/PeerImp.cpp:PeerImp::handleTransaction", + "title": "Transaction Receive Rate", + "description": "**What:** Transactions received from peers that this node went on to process.\n**How it's computed:** Per-second rate of the tx.receive span over a 5-minute window, per node.\n**Reading it:** Tracks the useful inbound transaction load. Copies dropped as duplicates are not counted here, because the span starts after the duplicate check; their volume is the transactions_duplicate traffic category.\n**Healthy range:** Workload-dependent.\n**Watch for:** A fall to zero while peers are connected means inbound relay has stopped.\n**Source:** src/xrpld/overlay/detail/PeerImp.cpp:PeerImp::handleTransaction", "type": "timeseries", "gridPos": { "h": 8, @@ -161,8 +161,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (suppressed, service_instance_id) (rate(traces_span_metrics_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=~\"$service_name\"}[$__rate_interval]))", - "legendFormat": "Suppressed={{suppressed}} [{{service_instance_id}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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=~\"$service_name\"}[$__rate_interval]))", + "legendFormat": "Tx Receive [{{service_instance_id}}]" } ], "fieldConfig": { diff --git a/docker/telemetry/grafana/provisioning/datasources/tempo.yaml b/docker/telemetry/grafana/provisioning/datasources/tempo.yaml index 3497c287ab..dfb0440dd7 100644 --- a/docker/telemetry/grafana/provisioning/datasources/tempo.yaml +++ b/docker/telemetry/grafana/provisioning/datasources/tempo.yaml @@ -186,11 +186,6 @@ datasources: operator: "=" scope: span type: dynamic - - id: tx-suppressed - tag: suppressed - operator: "=" - scope: span - type: dynamic - id: peer-version tag: peer_version operator: "=" diff --git a/docker/telemetry/otel-collector-config.yaml b/docker/telemetry/otel-collector-config.yaml index 806df58449..87892939b6 100644 --- a/docker/telemetry/otel-collector-config.yaml +++ b/docker/telemetry/otel-collector-config.yaml @@ -100,7 +100,6 @@ connectors: - name: consensus_mode - name: close_time_correct - name: local - - name: suppressed - name: proposal_trusted - name: validation_trusted - name: tx_type From 675dffdc718a3f12bb79bfeb2dce26c6e274d42d Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 18 Sep 2026 09:31:23 +0100 Subject: [PATCH 2/4] docs(telemetry): drop suppressed from the tx.receive attribute list The span is created after the duplicate check, so it never carries the attribute, and the row now says which transactions it covers. --- docs/telemetry-runbook.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/telemetry-runbook.md b/docs/telemetry-runbook.md index c1234abc67..e0a3b3e7cf 100644 --- a/docs/telemetry-runbook.md +++ b/docs/telemetry-runbook.md @@ -88,14 +88,14 @@ All spans instrumented in xrpld, grouped by subsystem: ### Transaction Spans -| Span Name | Source File | Attributes | Description | -| --------------- | --------------- | ------------------------------------------------------------------------------------------------------- | ------------------------------------- | -| `tx.process` | NetworkOPs.cpp | `tx_hash`, `local`, `path`, `tx_type`, `fee`, `sequence`, `ter_result`, `applied`, `current_ledger_seq` | Transaction submission and processing | -| `tx.receive` | PeerImp.cpp | `peer_id`, `tx_hash`, `tx_type`, `peer_version`, `suppressed`, `tx_status`, `current_ledger_seq` | Transaction received from peer relay | -| `tx.apply` | BuildLedger.cpp | `ledger_seq`, `tx_count`, `tx_failed` | Transaction set applied per ledger | -| `tx.preflight` | applySteps.cpp | `stage`, `tx_type`, `ter_result` | Stateless checks stage | -| `tx.preclaim` | applySteps.cpp | `stage`, `tx_type`, `ter_result`, `current_ledger_seq`, `current_ledger_hash` | Ledger-aware checks stage | -| `tx.transactor` | Transactor.cpp | `stage`, `tx_type`, `ter_result`, `applied`, `current_ledger_seq`, `current_ledger_hash` | Apply stage (transactor runs) | +| Span Name | Source File | Attributes | Description | +| --------------- | --------------- | ------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ | +| `tx.process` | NetworkOPs.cpp | `tx_hash`, `local`, `path`, `tx_type`, `fee`, `sequence`, `ter_result`, `applied`, `current_ledger_seq` | Transaction submission and processing | +| `tx.receive` | PeerImp.cpp | `peer_id`, `tx_hash`, `tx_type`, `peer_version`, `tx_status`, `current_ledger_seq` | Transaction this node will process, received from peer relay | +| `tx.apply` | BuildLedger.cpp | `ledger_seq`, `tx_count`, `tx_failed` | Transaction set applied per ledger | +| `tx.preflight` | applySteps.cpp | `stage`, `tx_type`, `ter_result` | Stateless checks stage | +| `tx.preclaim` | applySteps.cpp | `stage`, `tx_type`, `ter_result`, `current_ledger_seq`, `current_ledger_hash` | Ledger-aware checks stage | +| `tx.transactor` | Transactor.cpp | `stage`, `tx_type`, `ter_result`, `applied`, `current_ledger_seq`, `current_ledger_hash` | Apply stage (transactor runs) | The three apply-pipeline spans (`tx.preflight`, `tx.preclaim`, `tx.transactor`) share a deterministic `trace_id` from `txID[0:16]`, so they group under one From 3b60a190de9e02cfd8737aebf3b8547224fc18a8 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 18 Sep 2026 09:32:29 +0100 Subject: [PATCH 3/4] fix(telemetry): drop the remaining suppressed dimensions and diagram values Alloy and the Grafana Cloud collector still declared a spanmetrics dimension for an attribute tx.receive no longer sets, which only widens the label set. The runbook's drop-path diagram still listed two tx_status values that no longer exist, because the paths that set them now run before the span starts. --- docker/telemetry/alloy/config.alloy | 1 - docker/telemetry/otel-collector-config.grafanacloud.yaml | 1 - docs/telemetry-runbook.md | 2 +- 3 files changed, 1 insertion(+), 3 deletions(-) diff --git a/docker/telemetry/alloy/config.alloy b/docker/telemetry/alloy/config.alloy index 3135b6149a..e5d5f613de 100644 --- a/docker/telemetry/alloy/config.alloy +++ b/docker/telemetry/alloy/config.alloy @@ -349,7 +349,6 @@ otelcol.connector.spanmetrics "xrpld" { // Overlay / peer dimensions. dimension { name = "local" } - dimension { name = "suppressed" } dimension { name = "proposal_trusted" } dimension { name = "validation_trusted" } diff --git a/docker/telemetry/otel-collector-config.grafanacloud.yaml b/docker/telemetry/otel-collector-config.grafanacloud.yaml index 21ea1804c7..01722e383a 100644 --- a/docker/telemetry/otel-collector-config.grafanacloud.yaml +++ b/docker/telemetry/otel-collector-config.grafanacloud.yaml @@ -223,7 +223,6 @@ connectors: - name: close_time_correct - name: consensus_state - name: local - - name: suppressed - name: proposal_trusted - name: validation_trusted - name: tx_type diff --git a/docs/telemetry-runbook.md b/docs/telemetry-runbook.md index ea56ec3d5f..0f8b527f36 100644 --- a/docs/telemetry-runbook.md +++ b/docs/telemetry-runbook.md @@ -588,7 +588,7 @@ flowchart TB RELAYOUT(["Overlay::relay fan-out to N peers
(no span; if applied / terQUEUED,
shouldRelay, not tfInnerBatchTxn)"]):::plain PREDROP(["Diverged / needNetworkLedger
(no span — dropped before tx.receive)"]):::drop RCV["tx.receive
(peer TMTransaction in)"]:::span - RCVDROP["tx.receive
tx_status = rejected_inner_batch /
suppressed / dropped_no_sync /
dropped_queue_full"]:::drop + RCVDROP["tx.receive
tx_status = dropped_no_sync /
dropped_queue_full"]:::drop CHK(["checkTransaction
(JtTransaction worker, no span)"]):::plain PRELAY_IN(["TMTransaction in (no span)"]):::plain From b54109201695033aeccdbbe8be0928af9e3dc611 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 18 Sep 2026 09:33:04 +0100 Subject: [PATCH 4/4] test(telemetry): drop suppressed from the mirrored dimension list The list mirrors the collector's spanmetrics dimensions, and that dimension is gone. The reduce-relay and squelch counters keep their own names, which are a different thing. --- docker/telemetry/workload/expected_metrics.json | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/docker/telemetry/workload/expected_metrics.json b/docker/telemetry/workload/expected_metrics.json index 34a4b55fad..fe5b32a0b9 100644 --- a/docker/telemetry/workload/expected_metrics.json +++ b/docker/telemetry/workload/expected_metrics.json @@ -26,8 +26,7 @@ "stage", "txq_status", "close_time_correct", - "consensus_state", - "suppressed" + "consensus_state" ], "_dimension_labels_note": "Bare label names as configured in otel-collector-config.yaml spanmetrics dimensions. Informational only (not asserted by the validator)." },