diff --git a/docker/telemetry/grafana/dashboards/node-health.json b/docker/telemetry/grafana/dashboards/node-health.json index cf86b02c3f..8818e6d8c2 100644 --- a/docker/telemetry/grafana/dashboards/node-health.json +++ b/docker/telemetry/grafana/dashboards/node-health.json @@ -810,7 +810,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "description": "###### What this is:\n*Cumulative count of transitions into each operating mode.*\n\n###### How it's computed:\n*Current value of each per-mode transition counter, plotted as lines.*\n\n###### Reading it:\n*Flat lines are healthy; steps up mean the node changed mode.*\n\n###### Healthy range:\n*Few transitions once the node is stable in Full mode.*\n\n###### Watch for:\n*Frequent transitions out of Full, or into Disconnected or Syncing, indicate instability.*\n\n###### Keywords:\n- **Operating mode / server state** *(per node)* \u2014 the node's sync level: Disconnected, Connected, Syncing, Tracking, Full (and Validating/Proposing).\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`\n\n###### References:\n[Operating mode / server state](https://xrpl.org/docs/references/http-websocket-apis/api-conventions/xrpld-server-states) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#operating-mode-server-state)", + "description": "###### What this is:\n*Transitions into each operating mode, per interval.*\n\n###### How it's computed:\n*increase() over each per-mode transition counter, so each point is the number of transitions in that bucket and the series stays correct across an xrpld restart (the counters reset to 0).*\n\n###### Reading it:\n*Zero is healthy; each point is a mode change within that bucket. Brief flaps show up here even when they are too short to appear on Operating Mode (State Timeline), which can only sample state once per scrape.*\n\n###### Healthy range:\n*Few transitions once the node is stable in Full mode.*\n\n###### Watch for:\n*Frequent transitions out of Full, or into Disconnected or Syncing, indicate instability.*\n\n###### Keywords:\n- **Operating mode / server state** *(per node)* \u2014 the node's sync level: Disconnected, Connected, Syncing, Tracking, Full (and Validating/Proposing).\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`\n\n###### References:\n[Operating mode / server state](https://xrpl.org/docs/references/http-websocket-apis/api-conventions/xrpld-server-states) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#operating-mode-server-state)", "fieldConfig": { "defaults": { "color": { @@ -901,7 +901,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(state_accounting_full_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Full\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(increase(state_accounting_full_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$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\", \"Full\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "A" }, { @@ -909,7 +909,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(state_accounting_tracking_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Tracking\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(increase(state_accounting_tracking_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$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\", \"Tracking\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "B" }, { @@ -917,7 +917,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(state_accounting_syncing_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Syncing\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(increase(state_accounting_syncing_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$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\", \"Syncing\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "C" }, { @@ -925,7 +925,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(state_accounting_connected_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Connected\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(increase(state_accounting_connected_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$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\", \"Connected\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "D" }, { @@ -933,7 +933,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(state_accounting_disconnected_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Disconnected\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "expr": "label_replace(label_join(label_replace(increase(state_accounting_disconnected_transitions{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$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\", \"Disconnected\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "E" } ], diff --git a/docs/telemetry-runbook.md b/docs/telemetry-runbook.md index 4f41cbf97f..f0868b2abf 100644 --- a/docs/telemetry-runbook.md +++ b/docs/telemetry-runbook.md @@ -2133,7 +2133,7 @@ Requires `trace_peer=1` in the `[telemetry]` config section. | Validated Ledger Age | stat | `ledgermaster_validated_ledger_age` | — | | Published Ledger Age | stat | `ledgermaster_published_ledger_age` | — | | Operating Mode (Time Share) | timeseries | `rate(state_accounting_X_duration) / sum(rate(all modes))` | — | -| Operating Mode Transitions | timeseries | `state_accounting_*_transitions` | — | +| Operating Mode Transitions | timeseries | `increase(state_accounting_*_transitions[$__rate_interval])` | — | | I/O Latency | timeseries | `histogram_quantile(0.95, ios_latency_milliseconds_bucket)` | — | | Job Queue Depth | timeseries | `jobq_job_count` | — | | Ledger Fetch Rate | stat | `rate(ledger_fetches[5m])` | — |