ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-09-27 23:38:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'pratik/otel-sync-diagnostics' into pratik/otel-sync-diagnostics-freshen-fix

Browse Source
This commit is contained in:
Pratik Mankawde
2026-09-22 14:07:19 +01:00
parent 4df3542d17 fb59dfc27a
commit 5f44af7e2c
7 changed files with 37 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
docker/telemetry/docker-compose.workload.yaml
View File

@@ -40,11 +40,17 @@ services:
otel-collector:
image: otel/opentelemetry-collector-contrib:0.158.0
command: ["--config=/etc/otel-collector-config.yaml"]
# Published on the host loopback only. The receivers have no auth and no
# TLS, so only processes on this host may reach them. Note this 127.0.0.1
# is the HOST interface docker listens on; the container-side bind lives in
# the collector config and is a separate choice. Upstream asks for a
# specific interface rather than 0.0.0.0 on either side (CWE-1327):
# https://opentelemetry.io/docs/security/config-best-practices/
ports:
- "4317:4317" # OTLP gRPC
- "4318:4318" # OTLP HTTP (traces + beast::insight metrics)
- "8889:8889" # Prometheus metrics endpoint
- "13133:13133" # Health check
- "127.0.0.1:4317:4317" # OTLP gRPC
- "127.0.0.1:4318:4318" # OTLP HTTP (traces + beast::insight metrics)
- "127.0.0.1:8889:8889" # Prometheus metrics endpoint
- "127.0.0.1:13133:13133" # Health check
volumes:
- ./otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
# Mount the validation workdir so the file_log receiver can tail node
@@ -60,7 +66,7 @@ services:
image: grafana/tempo:2.9.4
command: ["-config.file=/etc/tempo.yaml"]
ports:
- "3200:3200" # Tempo HTTP API
- "127.0.0.1:3200:3200" # Tempo HTTP API
volumes:
- ./tempo.yaml:/etc/tempo.yaml:ro
- tempo-data:/var/tempo
@@ -70,7 +76,7 @@ services:
prometheus:
image: prom/prometheus:v3.13.2
ports:
- "9090:9090"
- "127.0.0.1:9090:9090"
volumes:
- ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
depends_on:
@@ -81,7 +87,7 @@ services:
loki:
image: grafana/loki:3.7.6
ports:
- "3100:3100" # Loki HTTP API
- "127.0.0.1:3100:3100" # Loki HTTP API
command: ["-config.file=/etc/loki/local-config.yaml"]
networks:
- workload-net
@@ -98,7 +104,7 @@ services:
- GF_AUTH_ANONYMOUS_ENABLED=true # No login required for local dev
- GF_AUTH_ANONYMOUS_ORG_ROLE=Admin # Full access without auth
ports:
- "3000:3000" # Grafana web UI
- "127.0.0.1:3000:3000" # Grafana web UI
volumes:
- ./grafana/provisioning:/etc/grafana/provisioning:ro
- ./grafana/dashboards:/var/lib/grafana/dashboards:ro

2
docker/telemetry/docker-compose.yml
View File

@@ -140,7 +140,7 @@ services:
loki:
image: grafana/loki:3.7.6
ports:
- "3100:3100"
- "127.0.0.1:3100:3100"
command: -config.file=/etc/loki/local-config.yaml
volumes:
- loki-data:/loki

14
docker/telemetry/grafana/dashboards/job-queue.json
View File

@@ -621,7 +621,7 @@
"query": "label_values(service_name)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -641,7 +641,7 @@
"query": "label_values(deployment_environment)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -661,7 +661,7 @@
"query": "label_values(xrpl_network_type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -741,7 +741,7 @@
"query": "label_values(target_info, service_instance_id)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -761,7 +761,7 @@
"query": "label_values(job_queued_total, job_type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -781,7 +781,7 @@
"query": "label_values(job_queued_total, handler)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -804,5 +804,5 @@
"title": "Job Queue Analysis",
"uid": "job-queue",
"version": 1,
"refresh": "5s"
"refresh": "30s"
}

11
docker/telemetry/grafana/dashboards/ledger-data-sync.json
View File

@@ -2340,6 +2340,7 @@
"id": 38
}
],
"refresh": "30s",
"schemaVersion": 39,
"tags": ["ledger", "sync"],
"templating": {
@@ -2365,7 +2366,7 @@
"query": "label_values(service_name)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -2385,7 +2386,7 @@
"query": "label_values(deployment_environment)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -2405,7 +2406,7 @@
"query": "label_values(xrpl_network_type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -2485,7 +2486,7 @@
"query": "label_values(target_info, service_instance_id)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -2505,7 +2506,7 @@
"query": "label_values(job_queued_total, handler)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

6
docker/telemetry/grafana/dashboards/log-derived-insights.json
View File

@@ -90,7 +90,7 @@
"query": "label_values(service_name)",
"datasource": {
"type": "loki",
"uid": "loki"
"uid": "${DS_LOKI}"
},
"includeAll": true,
"allValue": ".*",
@@ -110,7 +110,7 @@
"query": "label_values({service_name=\"xrpld\"}, deployment_environment)",
"datasource": {
"type": "loki",
"uid": "loki"
"uid": "${DS_LOKI}"
},
"includeAll": true,
"allValue": ".*",
@@ -130,7 +130,7 @@
"query": "label_values({service_name=\"xrpld\"}, service_instance_id)",
"datasource": {
"type": "loki",
"uid": "loki"
"uid": "${DS_LOKI}"
},
"includeAll": true,
"allValue": ".*",

4
docker/telemetry/grafana/dashboards/overlay-traffic-detail.json
View File

@@ -1135,7 +1135,7 @@
"query": "label_values(getobject_lookups_total, result)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -1155,7 +1155,7 @@
"query": "label_values(getobject_rejected_total, reason)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

7
docker/telemetry/otel-collector-config.grafanacloud.yaml
View File

@@ -90,9 +90,10 @@ processors:
type: probabilistic
probabilistic:
sampling_percentage: 0.5
# A rotation happens every ~2 h and is the trace that proves a
# full->syncing flap. Keep every one; children arrive first, so match
# on the family prefix rather than the root name.
# A nodestore rotation is the trace that proves a full->syncing flap,
# and it is rare, so keep every one rather than leaving it to the
# probabilistic policy. Children arrive before the root, so match on
# the family prefix rather than the root name.
- name: keep-rotation-traces
type: ottl_condition
ottl_condition: