diff --git a/OpenTelemetryPlan/09-data-collection-reference.md b/OpenTelemetryPlan/09-data-collection-reference.md index 9bf8aab558..fa5422f115 100644 --- a/OpenTelemetryPlan/09-data-collection-reference.md +++ b/OpenTelemetryPlan/09-data-collection-reference.md @@ -239,36 +239,36 @@ Every span can carry key-value attributes that provide context for filtering and #### Transaction Attributes -| Attribute | Type | Set On | Description | -| ------------------- | ------- | ---------------------------------------------- | --------------------------------------------------------------------- | -| `xrpl.tx.hash` | string | `tx.process`, `tx.receive` | Transaction hash (hex-encoded) | -| `local` | boolean | `tx.process` | `true` if locally submitted, `false` if peer-relayed | -| `path` | string | `tx.process` | Submission path: `"sync"` or `"async"` | -| `suppressed` | boolean | `tx.receive` | `true` if transaction was suppressed (duplicate) | -| `tx_status` | string | `tx.receive` | Transaction status (e.g., `"known_bad"`) | -| `xrpl.peer.id` | int64 | `tx.receive` | Peer identifier (also set on peer spans) | -| `xrpl.peer.version` | string | `tx.receive` | Peer protocol version string | -| `stage` | string | `tx.preflight`, `tx.preclaim`, `tx.transactor` | Apply-pipeline stage: `preflight`, `preclaim`, or `apply` | -| `tx_type` | string | `tx.preflight`, `tx.preclaim`, `tx.transactor` | Transaction type name (e.g., `Payment`) | -| `ter_result` | string | `tx.preflight`, `tx.preclaim`, `tx.transactor` | Engine result token for that stage (e.g., `tesSUCCESS`, `terPRE_SEQ`) | -| `applied` | boolean | `tx.transactor` | `true` if the transaction was applied to the ledger | +| Attribute | Type | Set On | Description | +| -------------- | ------- | ---------------------------------------------- | --------------------------------------------------------------------- | +| `tx_hash` | string | `tx.process`, `tx.receive` | Transaction hash (hex-encoded) | +| `local` | boolean | `tx.process` | `true` if locally submitted, `false` if peer-relayed | +| `path` | string | `tx.process` | Submission path: `"sync"` or `"async"` | +| `suppressed` | boolean | `tx.receive` | `true` if transaction was suppressed (duplicate) | +| `tx_status` | string | `tx.receive` | Transaction status (e.g., `"known_bad"`) | +| `peer_id` | int64 | `tx.receive` | Peer identifier (also set on peer spans) | +| `peer_version` | string | `tx.receive` | Peer protocol version string | +| `stage` | string | `tx.preflight`, `tx.preclaim`, `tx.transactor` | Apply-pipeline stage: `preflight`, `preclaim`, or `apply` | +| `tx_type` | string | `tx.preflight`, `tx.preclaim`, `tx.transactor` | Transaction type name (e.g., `Payment`) | +| `ter_result` | string | `tx.preflight`, `tx.preclaim`, `tx.transactor` | Engine result token for that stage (e.g., `tesSUCCESS`, `terPRE_SEQ`) | +| `applied` | boolean | `tx.transactor` | `true` if the transaction was applied to the ledger | -**Tempo query**: `{span.xrpl.tx.hash=""}` to trace a specific transaction across nodes. +**Tempo query**: `{span.tx_hash=""}` to trace a specific transaction across nodes. **Prometheus label**: `xrpl_tx_local` (used as SpanMetrics dimension). #### PathFind Attributes -| Attribute | Type | Set On | Description | -| ---------------------------- | ------- | --------------------- | ----------------------------------------------- | -| `source_account` | string | `pathfind.request` | Source account address | -| `dest_account` | string | `pathfind.request` | Destination account address | -| `fast` | boolean | `pathfind.compute` | Whether this is a fast (non-full) pathfind | -| `search_level` | int64 | `pathfind.compute` | Search depth level | -| `num_complete_paths` | int64 | `pathfind.compute` | Number of complete paths found | -| `num_paths` | int64 | `pathfind.compute` | Total number of paths explored | -| `num_requests` | int64 | `pathfind.update_all` | Number of active path requests being recomputed | -| `xrpl.pathfind.ledger_index` | int64 | `pathfind.update_all` | Ledger index used for recomputation | +| Attribute | Type | Set On | Description | +| ----------------------- | ------- | --------------------- | ----------------------------------------------- | +| `source_account` | string | `pathfind.request` | Source account address | +| `dest_account` | string | `pathfind.request` | Destination account address | +| `fast` | boolean | `pathfind.compute` | Whether this is a fast (non-full) pathfind | +| `search_level` | int64 | `pathfind.compute` | Search depth level | +| `num_complete_paths` | int64 | `pathfind.compute` | Number of complete paths found | +| `num_paths` | int64 | `pathfind.compute` | Total number of paths explored | +| `num_requests` | int64 | `pathfind.update_all` | Number of active path requests being recomputed | +| `pathfind_ledger_index` | int64 | `pathfind.update_all` | Ledger index used for recomputation | **Tempo query**: `{span.source_account="rHb9..."}` to find pathfind requests from a specific account. @@ -276,13 +276,13 @@ Every span can carry key-value attributes that provide context for filtering and | Attribute | Type | Set On | Description | | -------------------- | ------- | ------------------------------ | ---------------------------------------------------------- | -| `xrpl.tx.hash` | string | `txq.enqueue`, `txq.accept.tx` | Transaction hash in the queue | +| `tx_hash` | string | `txq.enqueue`, `txq.accept.tx` | Transaction hash in the queue | | `txq_status` | string | `txq.enqueue` | Queue result: `"queued"`, `"applied_direct"`, `"rejected"` | | `fee_level_paid` | int64 | `txq.enqueue` | Fee level paid by the transaction | | `required_fee_level` | int64 | `txq.enqueue` | Minimum fee level required for queue admission | | `queue_size` | int64 | `txq.accept` | Queue depth at start of accept | | `ledger_changed` | boolean | `txq.accept` | Whether the open ledger changed since last accept | -| `xrpl.ledger.seq` | int64 | `txq.cleanup` | Ledger sequence for cleanup | +| `ledger_seq` | int64 | `txq.cleanup` | Ledger sequence for cleanup | | `expired_count` | int64 | `txq.cleanup` | Number of expired transactions removed | | `ter_code` | string | `txq.accept.tx` | Transaction engine result code | | `retries_remaining` | int64 | `txq.accept.tx` | Remaining retry attempts for this transaction | @@ -304,10 +304,10 @@ Every span can carry key-value attributes that provide context for filtering and | Attribute | Type | Set On | Description | | --------------------------- | ------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------- | -| `xrpl.consensus.ledger_id` | string | `consensus.round` | Previous ledger hash (used for deterministic trace ID) | -| `xrpl.ledger.seq` | int64 | `consensus.round`, `consensus.ledger_close`, `consensus.accept`, `consensus.validation.send`, `consensus.accept.apply` | Ledger sequence number | -| `xrpl.consensus.mode` | string | `consensus.round`, `consensus.proposal.send`, `consensus.ledger_close` | Node mode via `toDisplayString()`: `"Proposing"`, `"Observing"`, etc. | -| `xrpl.consensus.round` | int64 | `consensus.proposal.send` | Consensus round number | +| `consensus_ledger_id` | string | `consensus.round` | Previous ledger hash (used for deterministic trace ID) | +| `ledger_seq` | int64 | `consensus.round`, `consensus.ledger_close`, `consensus.accept`, `consensus.validation.send`, `consensus.accept.apply` | Ledger sequence number | +| `consensus_mode` | string | `consensus.round`, `consensus.proposal.send`, `consensus.ledger_close` | Node mode via `toDisplayString()`: `"Proposing"`, `"Observing"`, etc. | +| `consensus_round` | int64 | `consensus.proposal.send` | Consensus round number | | `proposers` | int64 | `consensus.proposal.send`, `consensus.accept` | Number of proposers in the round | | `round_time_ms` | int64 | `consensus.accept`, `consensus.accept.apply` | Total consensus round duration in milliseconds | | `proposing` | boolean | `consensus.validation.send` | Whether this node was a proposer | @@ -332,15 +332,15 @@ Every span can carry key-value attributes that provide context for filtering and | `quorum` | int64 | `consensus.check` | Required quorum for validation | | `validation_count` | int64 | `consensus.check` | Number of validations received | | `trace_strategy` | string | `consensus.round` | Trace sampling strategy used for this round | -| `xrpl.consensus.round_id` | string | `consensus.round` | Deterministic round identifier | -| `xrpl.consensus.mode.old` | string | `consensus.mode_change` | Previous consensus mode | -| `xrpl.consensus.mode.new` | string | `consensus.mode_change` | New consensus mode | -| `xrpl.tx.id` | string | `consensus.update_positions` | Disputed transaction ID | +| `consensus_round_id` | string | `consensus.round` | Deterministic round identifier | +| `mode_old` | string | `consensus.mode_change` | Previous consensus mode | +| `mode_new` | string | `consensus.mode_change` | New consensus mode | +| `tx_id` | string | `consensus.update_positions` | Disputed transaction ID | | `dispute_our_vote` | boolean | `consensus.update_positions` | Our vote on the disputed transaction | | `dispute_yays` | int64 | `consensus.update_positions` | Number of proposers voting to include | | `dispute_nays` | int64 | `consensus.update_positions` | Number of proposers voting to exclude | -**Tempo query**: `{span.xrpl.consensus.mode="Proposing"}` to find rounds where node was proposing. +**Tempo query**: `{span.consensus_mode="Proposing"}` to find rounds where node was proposing. **Prometheus label**: `xrpl_consensus_mode` (used as SpanMetrics dimension). @@ -348,7 +348,7 @@ Every span can carry key-value attributes that provide context for filtering and | Attribute | Type | Set On | Description | | --------------------- | ------- | ------------------------------------------------------------- | ------------------------------------------------ | -| `xrpl.ledger.seq` | int64 | `ledger.build`, `ledger.validate`, `ledger.store`, `tx.apply` | Ledger sequence number | +| `ledger_seq` | int64 | `ledger.build`, `ledger.validate`, `ledger.store`, `tx.apply` | Ledger sequence number | | `close_time` | int64 | `ledger.build` | Ledger close time (epoch seconds) | | `close_time_correct` | boolean | `ledger.build` | Whether close time was agreed upon by validators | | `close_resolution_ms` | int64 | `ledger.build` | Close time rounding granularity in milliseconds | @@ -356,15 +356,15 @@ Every span can carry key-value attributes that provide context for filtering and | `tx_failed` | int64 | `ledger.build`, `tx.apply` | Failed transactions in the ledger | | `validations` | int64 | `ledger.validate` | Number of validations received for this ledger | -**Tempo query**: `{span.xrpl.ledger.seq=12345}` to find all spans for a specific ledger. +**Tempo query**: `{span.ledger_seq=12345}` to find all spans for a specific ledger. #### Peer Attributes | Attribute | Type | Set On | Description | | -------------------- | ------- | ---------------------------------------------------------------- | ---------------------------------------------------- | -| `xrpl.peer.id` | int64 | `tx.receive`, `peer.proposal.receive`, `peer.validation.receive` | Peer identifier | +| `peer_id` | int64 | `tx.receive`, `peer.proposal.receive`, `peer.validation.receive` | Peer identifier | | `proposal_trusted` | boolean | `peer.proposal.receive` | Whether the proposal came from a trusted validator | -| `xrpl.ledger.hash` | string | `peer.validation.receive` | Ledger hash the validation refers to | +| `ledger_hash` | string | `peer.validation.receive` | Ledger hash the validation refers to | | `validation_full` | boolean | `peer.validation.receive` | Whether this is a full (not partial) validation | | `validation_trusted` | boolean | `peer.validation.receive` | Whether the validation came from a trusted validator | @@ -389,15 +389,15 @@ The OTel Collector's SpanMetrics connector automatically generates RED (Rate, Er **Additional dimension labels** (configured in `otel-collector-config.yaml`): -| Span Attribute | Prometheus Label | Applies To | -| --------------------- | ------------------------------ | ---------------------------------------------- | -| `command` | `xrpl_rpc_command` | `rpc.command.*` | -| `rpc_status` | `xrpl_rpc_status` | `rpc.command.*` | -| `xrpl.consensus.mode` | `xrpl_consensus_mode` | `consensus.ledger_close` | -| `local` | `xrpl_tx_local` | `tx.process` | -| `proposal_trusted` | `xrpl_peer_proposal_trusted` | `peer.proposal.receive` | -| `validation_trusted` | `xrpl_peer_validation_trusted` | `peer.validation.receive` | -| `stage` | `stage` | `tx.preflight`, `tx.preclaim`, `tx.transactor` | +| Span Attribute | Prometheus Label | Applies To | +| -------------------- | ------------------------------ | ---------------------------------------------- | +| `command` | `xrpl_rpc_command` | `rpc.command.*` | +| `rpc_status` | `xrpl_rpc_status` | `rpc.command.*` | +| `consensus_mode` | `xrpl_consensus_mode` | `consensus.ledger_close` | +| `local` | `xrpl_tx_local` | `tx.process` | +| `proposal_trusted` | `xrpl_peer_proposal_trusted` | `peer.proposal.receive` | +| `validation_trusted` | `xrpl_peer_validation_trusted` | `peer.validation.receive` | +| `stage` | `stage` | `tx.preflight`, `tx.preclaim`, `tx.transactor` | The `stage` dimension (3 values: `preflight`, `preclaim`, `apply`) turns the apply-pipeline spans into per-stage RED metrics with no native instruments — the @@ -614,11 +614,11 @@ Prometheus label. See [telemetry-runbook.md](../docs/telemetry-runbook.md) | Specific RPC command | `{resource.service.name="xrpld" && name="rpc.command.server_info"}` | | Slow RPC calls | `{resource.service.name="xrpld" && name=~"rpc.command.*"} \| duration > 100ms` | | Failed RPC calls | `{span.rpc_status="error"}` | -| Specific transaction | `{span.xrpl.tx.hash=""}` | +| Specific transaction | `{span.tx_hash=""}` | | Local transactions only | `{span.local=true}` | | Consensus rounds | `{resource.service.name="xrpld" && name="consensus.accept"}` | -| Rounds by mode | `{span.xrpl.consensus.mode="proposing"}` | -| Specific ledger | `{span.xrpl.ledger.seq=12345}` | +| Rounds by mode | `{span.consensus_mode="proposing"}` | +| Specific ledger | `{span.ledger_seq=12345}` | | Peer proposals (trusted) | `{span.proposal_trusted=true}` | ### Trace Structure diff --git a/OpenTelemetryPlan/Phase5_IntegrationTest_taskList.md b/OpenTelemetryPlan/Phase5_IntegrationTest_taskList.md index 6f9df2f969..2bf33a390c 100644 --- a/OpenTelemetryPlan/Phase5_IntegrationTest_taskList.md +++ b/OpenTelemetryPlan/Phase5_IntegrationTest_taskList.md @@ -107,13 +107,13 @@ Tempo/Prometheus. - `consensus.validation.send` (Adaptor::validate) - Verify attributes: - `xrpl.consensus.mode` on `consensus.ledger_close` - - `xrpl.consensus.proposers` on `consensus.accept` + - `proposers` on `consensus.accept` - `xrpl.consensus.ledger.seq` on `consensus.validation.send` **Verification**: - [ ] Tempo shows `consensus.ledger_close` traces with `xrpl.consensus.mode` -- [ ] Tempo shows `consensus.accept` traces with `xrpl.consensus.proposers` +- [ ] Tempo shows `consensus.accept` traces with `proposers` - [ ] Tempo shows `consensus.proposal.send` traces - [ ] Tempo shows `consensus.validation.send` traces @@ -147,7 +147,7 @@ Tempo/Prometheus. - Prerequisites section - Single-node standalone test (quick verification) - 6-node consensus test (full verification) - - Expected span catalog (all 12 span names with attributes) + - Expected span catalog (all 11 span names with attributes) - Verification queries (Tempo API, Prometheus API) - Troubleshooting guide @@ -156,7 +156,7 @@ Tempo/Prometheus. **Verification**: - [ ] Document covers both single-node and multi-node testing -- [ ] All 12 span names documented with source file and attributes +- [ ] All 11 span names documented with source file and attributes - [ ] Troubleshooting section covers common failure modes --- diff --git a/docker/telemetry/docker-compose.yml b/docker/telemetry/docker-compose.yml index 30cf81b849..bbfb0c9db9 100644 --- a/docker/telemetry/docker-compose.yml +++ b/docker/telemetry/docker-compose.yml @@ -26,7 +26,10 @@ services: ports: - "4317:4317" # OTLP gRPC - "4318:4318" # OTLP HTTP - - "8125:8125/udp" # StatsD UDP (beast::insight metrics) + # StatsD UDP (beast::insight metrics). Bound to loopback only: the + # receiver has no auth, and xrpld runs on the host, so it reaches the + # collector via 127.0.0.1. Do not expose on 0.0.0.0 in shared setups. + - "127.0.0.1:8125:8125/udp" - "8889:8889" # Prometheus metrics (spanmetrics + statsd) - "13133:13133" # Health check volumes: @@ -53,7 +56,8 @@ services: - xrpld-telemetry prometheus: - image: prom/prometheus:latest + # Pinned to the v2.53 LTS line for reproducible, config-stable runs. + image: prom/prometheus:v2.53.3 ports: - "9090:9090" volumes: diff --git a/docker/telemetry/grafana/dashboards/statsd-ledger-data-sync.json b/docker/telemetry/grafana/dashboards/statsd-ledger-data-sync.json index 0f23bd1013..5a8e86e3aa 100644 --- a/docker/telemetry/grafana/dashboards/statsd-ledger-data-sync.json +++ b/docker/telemetry/grafana/dashboards/statsd-ledger-data-sync.json @@ -463,7 +463,7 @@ "datasource": { "type": "prometheus" }, - "expr": "topk{exported_instance=~\"$node\"}(20, {__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\"})", + "expr": "topk(20, {__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\", exported_instance=~\"$node\"})", "legendFormat": "{{__name__}}" } ], diff --git a/docker/telemetry/grafana/dashboards/statsd-network-traffic.json b/docker/telemetry/grafana/dashboards/statsd-network-traffic.json index db311fb6c0..af68808b79 100644 --- a/docker/telemetry/grafana/dashboards/statsd-network-traffic.json +++ b/docker/telemetry/grafana/dashboards/statsd-network-traffic.json @@ -115,14 +115,14 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_total_Bytes_In[5m])", + "expr": "rate(rippled_total_Bytes_In{exported_instance=~\"$node\"}[5m])", "legendFormat": "Bytes In" }, { "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_total_Bytes_Out[5m])", + "expr": "rate(rippled_total_Bytes_Out{exported_instance=~\"$node\"}[5m])", "legendFormat": "Bytes Out" } ], @@ -161,14 +161,14 @@ "datasource": { "type": "prometheus" }, - "expr": "rippled_total_Messages_In{exported_instance=~\"$node\"}", + "expr": "rate(rippled_total_Messages_In{exported_instance=~\"$node\"}[5m])", "legendFormat": "Messages In" }, { "datasource": { "type": "prometheus" }, - "expr": "rippled_total_Messages_Out{exported_instance=~\"$node\"}", + "expr": "rate(rippled_total_Messages_Out{exported_instance=~\"$node\"}[5m])", "legendFormat": "Messages Out" } ], @@ -380,7 +380,7 @@ "datasource": { "type": "prometheus" }, - "expr": "topk{exported_instance=~\"$node\"}(10, {__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\"})", + "expr": "topk(10, {__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\", exported_instance=~\"$node\"})", "legendFormat": "{{__name__}}" } ], @@ -677,42 +677,42 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_transactions_duplicate_Bytes_In[5m])", + "expr": "rate(rippled_transactions_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])", "legendFormat": "TX Duplicate In" }, { "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_transactions_duplicate_Bytes_Out[5m])", + "expr": "rate(rippled_transactions_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])", "legendFormat": "TX Duplicate Out" }, { "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_proposals_duplicate_Bytes_In[5m])", + "expr": "rate(rippled_proposals_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])", "legendFormat": "Proposals Duplicate In" }, { "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_proposals_duplicate_Bytes_Out[5m])", + "expr": "rate(rippled_proposals_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])", "legendFormat": "Proposals Duplicate Out" }, { "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_validations_duplicate_Bytes_In[5m])", + "expr": "rate(rippled_validations_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])", "legendFormat": "Validations Duplicate In" }, { "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_validations_duplicate_Bytes_Out[5m])", + "expr": "rate(rippled_validations_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])", "legendFormat": "Validations Duplicate Out" } ], @@ -751,7 +751,7 @@ "datasource": { "type": "prometheus" }, - "expr": "topk{exported_instance=~\"$node\"}(15, rate({__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\"}[5m]))", + "expr": "topk(15, rate({__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\", exported_instance=~\"$node\"}[5m]))", "legendFormat": "{{__name__}}" } ], diff --git a/docker/telemetry/grafana/dashboards/statsd-node-health.json b/docker/telemetry/grafana/dashboards/statsd-node-health.json index 9227ed224e..c36d59f60e 100644 --- a/docker/telemetry/grafana/dashboards/statsd-node-health.json +++ b/docker/telemetry/grafana/dashboards/statsd-node-health.json @@ -345,7 +345,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_ledger_fetches_total[5m])", + "expr": "rate(rippled_ledger_fetches_total{exported_instance=~\"$node\"}[5m])", "legendFormat": "Fetches / Sec" } ], @@ -377,7 +377,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_ledger_history_mismatch_total[5m])", + "expr": "rate(rippled_ledger_history_mismatch_total{exported_instance=~\"$node\"}[5m])", "legendFormat": "Mismatches / Sec" } ], @@ -728,7 +728,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rippled_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\"} - rippled_LedgerMaster_Validated_Ledger_Age", + "expr": "rippled_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\"} - rippled_LedgerMaster_Validated_Ledger_Age{exported_instance=~\"$node\"}", "legendFormat": "Publish Gap" } ], @@ -776,14 +776,14 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_State_Accounting_Full_duration[5m]) / 1000000", + "expr": "rate(rippled_State_Accounting_Full_duration{exported_instance=~\"$node\"}[5m]) / 1000000", "legendFormat": "Full Mode Rate" }, { "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_State_Accounting_Tracking_duration[5m]) / 1000000", + "expr": "rate(rippled_State_Accounting_Tracking_duration{exported_instance=~\"$node\"}[5m]) / 1000000", "legendFormat": "Tracking Mode Rate" } ], @@ -822,7 +822,7 @@ "datasource": { "type": "prometheus" }, - "expr": "{__name__{exported_instance=~\"$node\"}=~\"rippled_(makeFetchPack|publishAcqLedger|untrustedValidation|manifest|localTransaction|ledgerReplayRequest|ledgerRequest|untrustedProposal|ledgerReplayTask|ledgerData|clientCommand|clientSubscribe|clientFeeChange|clientConsensus|clientAccountHistory|clientRPC|clientWebsocket|RPC|updatePaths|transaction|batch|advanceLedger|publishNewLedger|fetchTxnData|writeAhead|trustedValidation|writeObjects|acceptLedger|trustedProposal|sweep|clusterReport|heartbeat|administration|handleHaveTransactions|doTransactions)\", quantile=\"$quantile\"}", + "expr": "{__name__=~\"rippled_(makeFetchPack|publishAcqLedger|untrustedValidation|manifest|localTransaction|ledgerReplayRequest|ledgerRequest|untrustedProposal|ledgerReplayTask|ledgerData|clientCommand|clientSubscribe|clientFeeChange|clientConsensus|clientAccountHistory|clientRPC|clientWebsocket|RPC|updatePaths|transaction|batch|advanceLedger|publishNewLedger|fetchTxnData|writeAhead|trustedValidation|writeObjects|acceptLedger|trustedProposal|sweep|clusterReport|heartbeat|administration|handleHaveTransactions|doTransactions)\", exported_instance=~\"$node\", quantile=\"$quantile\"}", "legendFormat": "{{__name__}} [{{quantile}}]" } ], @@ -861,7 +861,7 @@ "datasource": { "type": "prometheus" }, - "expr": "{__name__{exported_instance=~\"$node\"}=~\"rippled_(makeFetchPack_q|publishAcqLedger_q|untrustedValidation_q|manifest_q|localTransaction_q|ledgerReplayRequest_q|ledgerRequest_q|untrustedProposal_q|ledgerReplayTask_q|ledgerData_q|clientCommand_q|clientSubscribe_q|clientFeeChange_q|clientConsensus_q|clientAccountHistory_q|clientRPC_q|clientWebsocket_q|RPC_q|updatePaths_q|transaction_q|batch_q|advanceLedger_q|publishNewLedger_q|fetchTxnData_q|writeAhead_q|trustedValidation_q|writeObjects_q|acceptLedger_q|trustedProposal_q|sweep_q|clusterReport_q|heartbeat_q|administration_q|handleHaveTransactions_q|doTransactions_q)\", quantile=\"$quantile\"}", + "expr": "{__name__=~\"rippled_(makeFetchPack_q|publishAcqLedger_q|untrustedValidation_q|manifest_q|localTransaction_q|ledgerReplayRequest_q|ledgerRequest_q|untrustedProposal_q|ledgerReplayTask_q|ledgerData_q|clientCommand_q|clientSubscribe_q|clientFeeChange_q|clientConsensus_q|clientAccountHistory_q|clientRPC_q|clientWebsocket_q|RPC_q|updatePaths_q|transaction_q|batch_q|advanceLedger_q|publishNewLedger_q|fetchTxnData_q|writeAhead_q|trustedValidation_q|writeObjects_q|acceptLedger_q|trustedProposal_q|sweep_q|clusterReport_q|heartbeat_q|administration_q|handleHaveTransactions_q|doTransactions_q)\", exported_instance=~\"$node\", quantile=\"$quantile\"}", "legendFormat": "{{__name__}} [{{quantile}}]" } ], diff --git a/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json b/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json index a701e4c2f4..a30a3aa82b 100644 --- a/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json +++ b/docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json @@ -30,7 +30,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_rpc_requests_total[5m])", + "expr": "rate(rippled_rpc_requests_total{exported_instance=~\"$node\"}[5m])", "legendFormat": "Requests / Sec" } ], @@ -306,7 +306,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_warn_total[5m])", + "expr": "rate(rippled_warn_total{exported_instance=~\"$node\"}[5m])", "legendFormat": "Warnings / Sec" } ], @@ -354,7 +354,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate{exported_instance=~\"$node\"}(rippled_drop_total[5m])", + "expr": "rate(rippled_drop_total{exported_instance=~\"$node\"}[5m])", "legendFormat": "Drops / Sec" } ], diff --git a/docker/telemetry/xrpld-telemetry.cfg b/docker/telemetry/xrpld-telemetry.cfg index d233ad751a..74b5fecb72 100644 --- a/docker/telemetry/xrpld-telemetry.cfg +++ b/docker/telemetry/xrpld-telemetry.cfg @@ -7,7 +7,7 @@ # ./xrpld --conf docker/telemetry/xrpld-telemetry.cfg -a --start # 3. Send RPC commands to exercise tracing: # curl -s http://localhost:5005 -d '{"method":"server_info"}' -# 4. View traces in Jaeger UI: http://localhost:16686 +# 4. View traces in Grafana Explore: http://localhost:3000/explore [server] port_rpc_admin_local @@ -57,3 +57,11 @@ trace_transactions=1 trace_consensus=1 trace_peer=1 trace_ledger=1 + +# --- StatsD metrics (beast::insight) --- +# Sends UDP metrics to the collector's StatsD receiver so the StatsD +# dashboards have data. The collector binds this port on the host loopback. +[insight] +server=statsd +address=127.0.0.1:8125 +prefix=rippled