mirror of
https://github.com/XRPLF/rippled.git
synced 2026-08-20 13:50:57 +00:00
Merge branch 'pratik/otel-phase7-native-metrics' into pratik/otel-phase8-log-correlation
This commit is contained in:
Pratik Mankawde
@@ -24,7 +24,7 @@ services:
|
||||
# OpenTelemetry Collector: receives spans from xrpld via OTLP protocol,
|
||||
# batches them for efficiency, and forwards to Tempo for storage.
|
||||
otel-collector:
|
||||
image: otel/opentelemetry-collector-contrib:0.121.0
|
||||
image: otel/opentelemetry-collector-contrib:0.158.0
|
||||
command: ["--config=/etc/otel-collector-config.yaml"]
|
||||
ports:
|
||||
- "4317:4317" # OTLP gRPC
|
||||
@@ -52,7 +52,7 @@ services:
|
||||
# Grafana Tempo: distributed tracing backend that stores and indexes
|
||||
# spans. Queryable via TraceQL in Grafana Explore.
|
||||
tempo:
|
||||
image: grafana/tempo:2.7.2
|
||||
image: grafana/tempo:2.9.4
|
||||
command: ["-config.file=/etc/tempo.yaml"]
|
||||
ports:
|
||||
- "3200:3200" # Tempo HTTP API (health check, query)
|
||||
@@ -79,8 +79,8 @@ services:
|
||||
- xrpld-telemetry
|
||||
|
||||
prometheus:
|
||||
# Pinned to the v2.53 LTS line for reproducible, config-stable runs.
|
||||
image: prom/prometheus:v2.53.3
|
||||
# Pinned to an exact patch release for reproducible, config-stable runs.
|
||||
image: prom/prometheus:v3.13.2
|
||||
ports:
|
||||
- "9090:9090"
|
||||
volumes:
|
||||
@@ -94,7 +94,7 @@ services:
|
||||
# Grafana: visualization UI with Tempo pre-configured as a datasource.
|
||||
# Anonymous admin access enabled for local development convenience.
|
||||
grafana:
|
||||
image: grafana/grafana:11.5.2
|
||||
image: grafana/grafana:13.1.2
|
||||
environment:
|
||||
- GF_AUTH_ANONYMOUS_ENABLED=true # No login required for local dev
|
||||
- GF_AUTH_ANONYMOUS_ORG_ROLE=Admin # Full access without auth
|
||||
|
||||
@@ -1248,7 +1248,7 @@
|
||||
"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\"}[$__rate_interval])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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])), 1), \"series\", \"NuDB us/read\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
@@ -1332,7 +1332,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "${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])) / clamp_min(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])), 1), \"series\", \"NuDB Found Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
|
||||
@@ -530,7 +530,7 @@
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 48
|
||||
},
|
||||
@@ -565,47 +565,6 @@
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Queue Bypass Ratio (Direct Apply vs Enqueue)",
|
||||
"description": "**What:** Fraction of transactions that applied straight to the open ledger versus those that had to be queued.\n**How it's computed:** Ratio of direct applies to direct-plus-queued over a 5-minute window, per node.\n**Reading it:** A high fraction means the network is keeping up without escalation.\n**Healthy range:** Near 1.0 in normal conditions.\n**Watch for:** A falling fraction is the cleanest single signal the network has entered sustained fee escalation.\n**Source:** src/xrpld/app/misc/detail/TxQ.cpp:TxQ::tryDirectApply, TxQ::apply",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 48
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc",
|
||||
"maxHeight": 600
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.apply_direct\"}[$__rate_interval])) / clamp_min(sum by (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=\"txq.apply_direct\"}[$__rate_interval])) + sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.enqueue\"}[$__rate_interval])), 1)",
|
||||
"interval": "15s",
|
||||
"legendFormat": "Direct-Apply Fraction [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percentunit",
|
||||
"custom": {
|
||||
"axisLabel": "Bypass Fraction",
|
||||
"spanNulls": 1800000,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Queue Accept (Drain) Duration per Ledger",
|
||||
"description": "**What:** Time spent draining queued transactions into a newly closed ledger.\n**How it's computed:** 95th and 50th percentile of per-ledger drain durations over a 5-minute window, per node.\n**Reading it:** Rises as the queue holds more transactions to process at close.\n**Healthy range:** A few milliseconds when the queue is light.\n**Watch for:** Rising drain time signals queue pressure at ledger close.\n**Source:** src/xrpld/app/misc/detail/TxQ.cpp:TxQ::accept",
|
||||
|
||||
Reference in New Issue
Block a user