woggioni/docker-images
1
0
Fork 0
Code Actions Packages Releases Activity

added otel-lgtm image
CI / Build otel-lgtm docker images (push) Successful in 5m8s
Details

Browse Source
This commit is contained in:
woggioni
2026-06-30 14:19:57 +08:00
parent 85e4600ac1
commit 50ab02aef2
15 changed files with 8856 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitea/workflows/build-otel-lgtm.yaml
+38
View File
@@ -0,0 +1,38 @@
name: CI
on:
push:
branches: [ master ]
paths:
- 'otel-lgtm/**'
- '.gitea/workflows/build-otel-lgtm.yaml'
jobs:
"Build otel-lgtm docker images":
runs-on: hostinger
steps:
-
name: Login to Gitea container registry
uses: docker/login-action@v3
with:
registry: gitea.woggioni.net
username: woggioni
password: ${{ secrets.PUBLISHER_TOKEN }}
-
name: Build and push otel-lgtm vanilla images
uses: docker/build-push-action@v6
with:
builder: multiplatform-builder
context: "{{defaultContext}}:otel-lgtm"
platforms: |
linux/amd64
linux/arm64
push: true
pull: true
ssh: default=/var/lib/gitea-runner/.ssh/id_ed25519
tags: |
"gitea.woggioni.net/woggioni/otel-lgtm:latest"
"gitea.woggioni.net/woggioni/otel-lgtm:0.0.1"
secrets: |
GIT_AUTH_TOKEN.github.com=${{ secrets.GH_ACCESS_TOKEN }}
build-args: |
ALPINE_VERSION=3.24
OTELCOL_VERSION=0.154.0
otel-lgtm/Dockerfile
+84
View File
@@ -0,0 +1,84 @@
# syntax=docker/dockerfile:1
ARG ALPINE_VERSION=3.24
ARG OTELCOL_VERSION=0.154.0
FROM alpine:${ALPINE_VERSION} AS base
FROM base AS downloader
ARG OTELCOL_VERSION
WORKDIR /downloads
RUN --mount=type=cache,target=/var/cache/apk \
apk add curl tar ca-certificates
RUN ARCH=$(uname -m) && \
case "$ARCH" in \
x86_64) TARGETARCH=amd64 ;; \
aarch64) TARGETARCH=arm64 ;; \
*) echo "Unsupported architecture: $ARCH"; exit 1 ;; \
esac && \
curl -fLo otelcol.tar.gz \
"https://github.com/open-telemetry/opentelemetry-collector-releases/releases/download/v${OTELCOL_VERSION}/otelcol-contrib_${OTELCOL_VERSION}_linux_${TARGETARCH}.tar.gz" && \
tar xzf otelcol.tar.gz && \
chmod +x otelcol-contrib
FROM base
# Install Grafana stack and supervisord from Alpine repositories.
RUN --mount=type=cache,target=/var/cache/apk \
apk add \
ca-certificates \
supervisor \
grafana \
mimir \
loki \
tempo
# Copy the OTel Collector binary from the downloader stage.
COPY --from=downloader /downloads/otelcol-contrib /usr/local/bin/otelcol-contrib
# Create data, Grafana, and supervisor directories.
RUN mkdir -p /data/grafana && \
mkdir -p /data/grafana/logs && \
mkdir -p /data/grafana/plugins && \
mkdir -p /data/mimir && \
mkdir -p /data/loki && \
mkdir -p /data/tempo && \
mkdir -p /etc/grafana/provisioning/datasources && \
mkdir -p /etc/grafana/provisioning/dashboards && \
mkdir -p /etc/grafana/provisioning/plugins && \
mkdir -p /etc/grafana/provisioning/alerting && \
mkdir -p /var/log/supervisor && \
mkdir -p /var/run
# Copy configuration files.
COPY config/grafana.ini /etc/grafana.ini
COPY config/grafana-datasources.yaml /etc/grafana/provisioning/datasources/datasources.yaml
COPY config/grafana-dashboards.yaml /etc/grafana/provisioning/dashboards/grafana-dashboards.yaml
COPY config/grafana-dashboard-jvm-metrics.json /usr/share/grafana/grafana-dashboard-jvm-metrics.json
COPY config/grafana-dashboard-red-metrics-classic.json /usr/share/grafana/grafana-dashboard-red-metrics-classic.json
COPY config/grafana-dashboard-red-metrics-native.json /usr/share/grafana/grafana-dashboard-red-metrics-native.json
COPY config/opentelemetry-collector-hostmetrics-node-exporter.json /usr/share/grafana/opentelemetry-collector-hostmetrics-node-exporter.json
RUN mkdir -p /var/lib/grafana/plugins
RUN grafana cli --config /etc/grafana.ini --homepath /usr/share/grafana --pluginsDir /var/lib/grafana/plugins plugins install grafana-exploretraces-app
RUN grafana cli --config /etc/grafana.ini --homepath /usr/share/grafana --pluginsDir /var/lib/grafana/plugins plugins install grafana-lokiexplore-app
RUN grafana cli --config /etc/grafana.ini --homepath /usr/share/grafana --pluginsDir /var/lib/grafana/plugins plugins install grafana-metricsdrilldown-app
RUN grafana cli --config /etc/grafana.ini --homepath /usr/share/grafana --pluginsDir /var/lib/grafana/plugins plugins install grafana-pyroscope-app
COPY config/mimir.yaml /etc/mimir/mimir.yaml
COPY config/loki.yaml /etc/loki/loki.yaml
COPY config/tempo.yaml /etc/tempo/tempo.yaml
COPY config/otelcol.yaml /etc/otelcol/otelcol.yaml
COPY config/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
# Grafana anonymous admin access, provisioning path, and disable plugin pre-install.
VOLUME ["/data"]
EXPOSE 3000 4318
HEALTHCHECK --interval=30s --timeout=5s --retries=3 \
CMD wget -qO- http://127.0.0.1:3000/api/health >/dev/null 2>&1 && \
wget -qO- http://127.0.0.1:13133/ready >/dev/null 2>&1
CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
otel-lgtm/README.md
+108
View File
@@ -0,0 +1,108 @@
# OTel LGTM (Alpine + supervisord)
A single-container observability backend running on Alpine Linux with supervisord.
Components:
- **Grafana** — visualization UI
- **Mimir** — metrics storage
- **Loki** — log storage
- **Tempo** — trace storage
- **OpenTelemetry Collector (contrib)** — OTLP receiver and router
## Ports
| Port | Service | Description |
|------|---------|-------------|
| 3000 | Grafana | Web UI |
| 4318 | OTel Collector | OTLP/HTTP endpoint |
Only these two ports are exposed. All other services communicate internally on `127.0.0.1`.
## Build
```bash
docker build -t otel-lgtm .
```
> The Dockerfile uses BuildKit cache mounts for `apk`. Make sure BuildKit is enabled (default in recent Docker Desktop / `docker buildx`).
### Build args
| Build arg | Default | Description |
|-----------|---------|-------------|
| `ALPINE_VERSION` | `3.24` | Alpine Linux base image version |
| `OTELCOL_VERSION` | `0.154.0` | OpenTelemetry Collector Contrib version |
Grafana, Mimir, Loki, and Tempo versions are determined by the chosen Alpine repository.
Example:
```bash
docker build --build-arg OTELCOL_VERSION=0.155.0 -t otel-lgtm .
```
### Multi-architecture
The Dockerfile detects the build architecture at build time, so it works on both `amd64` and `arm64`. To build a true multi-arch image in one command, use Docker BuildKit / `docker buildx`:
```bash
docker buildx build --platform linux/amd64,linux/arm64 -t otel-lgtm .
```
## Run
```bash
docker run -p 3000:3000 -p 4318:4318 -v lgtm-data:/data otel-lgtm
```
Grafana is available at http://localhost:3000 with anonymous admin access enabled.
Send telemetry to the collector at `http://localhost:4318` (OTLP/HTTP).
## Data persistence
All persistent data is written under `/data`:
| Path | Service |
|------|---------|
| `/data/grafana` | Grafana data, logs, and plugins |
| `/data/mimir` | Mimir metrics storage |
| `/data/loki` | Loki log storage |
| `/data/tempo` | Tempo trace storage |
Mount a volume there to persist data across container restarts.
## Architecture
```
Application ──OTLP/HTTP──> OTel Collector :4318
│
├─ metrics ──OTLP/HTTP──> Mimir :9009
├─ logs ─────OTLP/HTTP──> Loki :3100
└─ traces ───OTLP/HTTP──> Tempo :3200
Grafana :3000 queries Mimir, Loki, and Tempo.
```
## Read-only root filesystem
The image can be run with an immutable root filesystem (`--read-only`). A few runtime-only directories must be mounted as writable `tmpfs`:
```bash
docker run --read-only \
-p 3000:3000 -p 4318:4318 \
-v lgtm-data:/data \
--tmpfs /tmp:rw,noexec,nosuid,size=100m \
--tmpfs /run:rw,noexec,nosuid,size=10m \
--tmpfs /var/log/supervisor:rw,noexec,nosuid,size=50m \
otel-lgtm
```
Persistent data continues to live on the `/data` volume, while temporary/runtime state stays in memory.
## Notes
- This image is intended for development, demo, and testing environments.
- Grafana authentication is disabled (`anonymous` admin).
- Grafana’s default async plugin pre-installation is disabled to avoid relying on internet access at startup.
otel-lgtm/config/grafana-dashboard-jvm-metrics.json
+928
View File
@@ -0,0 +1,928 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"description": "Dashboard for JVM metrics with OpenTelemetry instrumentation",
"editable": true,
"fiscalYearStartMonth": 0,
"gnetId": 18812,
"graphTooltip": 0,
"links": [
{
"asDropdown": false,
"icon": "info",
"includeVars": false,
"keepTime": false,
"tags": [],
"targetBlank": false,
"title": "Semantic Conventions: 1.20.0 - 1.22.0",
"tooltip": "multiple versions of the semantic conventions are supported using 'or' and regex queries",
"type": "link",
"url": "https://github.com/open-telemetry/semantic-conventions/blob/main/schemas/1.20.0"
}
],
"liveNow": false,
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "HTTP server request rate",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 4,
"x": 0,
"y": 0
},
"id": 51,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (instance) (rate({__name__=~\"http_server_request_duration_seconds_count|http_server_request_duration_count|http_server_duration_seconds_count|http_server_duration_count|http_server_duration_milliseconds_count|http_server_requests_milliseconds_count|http_server_requests_count|http_server_requests_seconds_count\", job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))",
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "HTTP server error ratio - ratio of requests that return 5xx",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 5,
"x": 4,
"y": 0
},
"id": 50,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "(sum by (instance)(rate({__name__=~\"http_server_request_duration_seconds_count|http_server_request_duration_count\", job=~\"$job\", instance=~\"$instance\", http_response_status_code=~\"5.*\"}[$__rate_interval]))) / on (instance) (sum by (instance)(rate({__name__=~\"http_server_request_duration_seconds_count|http_server_request_duration_count\", job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))\nor\n(sum by (instance)(rate({__name__=~\"http_server_duration_milliseconds_count|http_server_duration_seconds_count|http_server_duration_count\", job=~\"$job\", instance=~\"$instance\", http_status_code=~\"5.*\"}[$__rate_interval]))) / on (instance) (sum by (instance)(rate({__name__=~\"http_server_duration_milliseconds_count|http_server_duration_seconds_count|http_server_duration_count\", job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))\nor\n(sum by (instance)(rate({__name__=~\"http_server_requests_milliseconds_count|http_server_requests_count|http_server_requests_seconds_count\", job=~\"$job\", instance=~\"$instance\", outcome=\"SERVER_ERROR\"}[$__rate_interval]))) / on (instance) (sum by (instance)(rate({__name__=~\"http_server_requests_milliseconds_count|http_server_requests_count|http_server_requests_seconds_count\", job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))\n",
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Error %",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "95th percentile of HTTP server request duration in seconds",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 5,
"x": 9,
"y": 0
},
"id": 52,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "(histogram_quantile(0.95, sum by(le, instance) (rate({__name__=~\"http_server_request_duration_seconds_bucket|http_server_request_duration_bucket|http_server_duration_seconds_bucket|http_server_duration_bucket|http_server_requests_seconds_bucket\", job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))))\nor\n(histogram_quantile(0.95, sum by(le, instance) (rate({__name__=~\"http_server_duration_milliseconds_bucket|http_server_requests_milliseconds_bucket|http_server_requests_bucket\", job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))) / 1000)\n",
"instant": false,
"legendFormat": "{{instance}}",
"range": true,
"refId": "A"
}
],
"title": "Duration (95%)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "CPU utilization for the whole system",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 7,
"x": 0,
"y": 8
},
"id": 38,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "{__name__=~\"jvm_cpu_recent_utilization|jvm_cpu_recent_utilization_ratio|process_runtime_jvm_system_cpu_utilization|process_runtime_jvm_system_cpu_utilization_ratio|system_cpu_usage\", job=~\"$job\", instance=~\"$instance\"}",
"legendFormat": "{{instance}}",
"range": true,
"refId": "A"
}
],
"title": "CPU utilization",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Used heap memory / heap memory limit ",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 7,
"x": 7,
"y": 8
},
"id": 30,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "(sum by (instance) ({__name__=~\"jvm_memory_used|jvm_memory_used_bytes\",job=~\"$job\",jvm_memory_type=\"heap\", instance=~\"$instance\"}) / on(instance) sum by (instance) ({__name__=~\"jvm_memory_limit|jvm_memory_limit_bytes\",job=~\"$job\",jvm_memory_type=\"heap\", instance=~\"$instance\"}))\nor\n(sum by (instance) ({__name__=~\"process_runtime_jvm_memory_usage|process_runtime_jvm_memory_usage_bytes\",job=~\"$job\",type=\"heap\", instance=~\"$instance\"}) / on(instance) sum by (instance) ({__name__=~\"process_runtime_jvm_memory_limit|process_runtime_jvm_memory_limit_bytes\",job=~\"$job\",type=\"heap\", instance=~\"$instance\"}))\nor\n(sum by (instance) ({__name__=~\"jvm_memory_used|jvm_memory_used_bytes\",job=~\"$job\",area=\"heap\", instance=~\"$instance\"}) / on(instance) sum by (instance) ({__name__=~\"jvm_memory_max|jvm_memory_max_bytes\",job=~\"$job\",area=\"heap\", instance=~\"$instance\"}))",
"legendFormat": "{{instance}}",
"range": true,
"refId": "A"
}
],
"title": "Heap Memory utilization",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Percentage of time spend for garbage collection pauses",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 4,
"x": 0,
"y": 15
},
"id": 46,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "(sum by(instance) (rate({__name__=~\"jvm_gc_duration_sum|jvm_gc_duration_seconds_sum|process_runtime_jvm_gc_duration_sum|process_runtime_jvm_gc_duration_seconds_sum|jvm_gc_pause_sum|jvm_gc_pause_seconds_sum\",job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))\nor\n(sum by(instance) (rate(jvm_gc_pause_milliseconds_sum{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) / 1000)",
"hide": false,
"legendFormat": "__auto",
"range": true,
"refId": "B"
}
],
"title": "Garbage Collection",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Number of currently loaded classes",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 5,
"x": 4,
"y": 15
},
"id": 33,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "{__name__=~\"jvm_class_count|process_runtime_jvm_classes_current_loaded|jvm_classes_loaded\",job=~\"$job\", instance=~\"$instance\"}",
"legendFormat": "{{instance}}",
"range": true,
"refId": "A"
}
],
"title": "Classes",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Number of currently executing (also called \"live\") threads",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 25,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 5,
"x": 9,
"y": 15
},
"id": 42,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum({__name__=~\"jvm_thread_count|process_runtime_jvm_threads_count|jvm_threads_live\",job=~\"$job\", instance=~\"$instance\"}) by (instance)",
"legendFormat": "{{instance}}",
"range": true,
"refId": "A"
}
],
"title": "Threads",
"type": "timeseries"
}
],
"refresh": "",
"schemaVersion": 38,
"tags": ["JVM", "open-telemetry", "Java", "otel", "opentelemetry", "otlp"],
"templating": {
"list": [
{
"current": {
"selected": false,
"text": "Prometheus",
"value": "prometheus"
},
"description": "Choose a Prometheus data source",
"hide": 0,
"includeAll": false,
"label": "Data source",
"multi": false,
"name": "datasource",
"options": [],
"query": "prometheus",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"allValue": ".+",
"current": {
"selected": false,
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values({__name__=~\"jvm_class_count|process_runtime_jvm_classes_current_loaded|jvm_classes_loaded\"},job)",
"hide": 0,
"includeAll": true,
"label": "Job",
"multi": true,
"name": "job",
"options": [],
"query": {
"query": "label_values({__name__=~\"jvm_class_count|process_runtime_jvm_classes_current_loaded|jvm_classes_loaded\"},job)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": ".+",
"current": {
"selected": false,
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values({__name__=~\"(jvm_class_count|process_runtime_jvm_classes_current_loaded|jvm_classes_loaded)\", job=~\"$job\"},instance)",
"description": "The instance of the application, e.g. pod1",
"hide": 0,
"includeAll": true,
"label": "Instance",
"multi": true,
"name": "instance",
"options": [],
"query": {
"query": "label_values({__name__=~\"(jvm_class_count|process_runtime_jvm_classes_current_loaded|jvm_classes_loaded)\", job=~\"$job\"},instance)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": ["5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d"]
},
"timezone": "",
"title": "JVM Overview (OpenTelemetry)",
"uid": "b91844d7-121e-4d0a-93b8-a9c1a05703b3",
"version": 1,
"weekStart": ""
}
otel-lgtm/config/grafana-dashboard-red-metrics-classic.json
+584
View File
@@ -0,0 +1,584 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "request rate, error rate, duration",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 4,
"links": [],
"liveNow": false,
"panels": [
{
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"description": "",
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 0
},
"id": 6,
"options": {
"code": {
"language": "plaintext",
"showLineNumbers": false,
"showMiniMap": false
},
"content": "# RED Metrics: (r)equest rate, (e)rror rate, (d)uration\n\nThis dashboard uses explicit bucket histograms and the stable [OpenTelemetry metrics semantic conventions](https://opentelemetry.io/docs/specs/semconv/general/metrics/).\nTo enable this for the [OpenTelemetry Java instrumentation agent](https://github.com/open-telemetry/opentelemetry-java-instrumentation/), set the following environment variables:\n\n```\nexport OTEL_EXPORTER_OTLP_METRICS_DEFAULT_HISTOGRAM_AGGREGATION=explicit_bucket_histogram\n```",
"mode": "markdown"
},
"pluginVersion": "10.3.3",
"type": "text"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "reqps",
"unitScale": true
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 5
},
"id": 1,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"expr": "sum(rate({__name__=~\"http_server_request_duration_seconds_count|http_server_request_duration_count|http_server_duration_milliseconds_count|http_server_duration_seconds_count|http_server_duration_count\", job=~\"$job\", instance=~\"$instance\"}[5m]))",
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Request Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit",
"unitScale": true
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 13
},
"id": 2,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"expr": "sum(rate({__name__=~\"http_server_request_duration_seconds_count|http_server_request_duration_count|http_server_duration_milliseconds_count|http_server_duration_seconds_count|http_server_duration_count\", job=~\"$job\", instance=~\"$instance\", http_response_status_code=~\"5..\"}[5m])) / sum(rate({__name__=~\"http_server_request_duration_seconds_count|http_server_request_duration_count|http_server_duration_milliseconds_count|http_server_duration_seconds_count|http_server_duration_count\", job=~\"$job\", instance=~\"$instance\"}[5m]))",
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Error Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "reqps",
"unitScale": true
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 21
},
"id": 3,
"options": {
"displayMode": "gradient",
"maxVizHeight": 300,
"minVizHeight": 10,
"minVizWidth": 0,
"namePlacement": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
},
"showUnfilled": true,
"sizing": "auto",
"valueMode": "color"
},
"pluginVersion": "10.3.3",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"exemplar": true,
"expr": "sum by (le) (rate({__name__=~\"http_server_request_duration_seconds_bucket|http_server_request_duration_bucket|http_server_duration_milliseconds_bucket|http_server_duration_seconds_bucket|http_server_duration_bucket\", job=~\"$job\", instance=~\"$instance\"}[5m]))",
"format": "heatmap",
"instant": false,
"legendFormat": "{{le}}",
"range": true,
"refId": "A"
}
],
"title": "Duration histogram (s)",
"type": "bargauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"scaleDistribution": {
"type": "linear"
}
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 29
},
"id": 5,
"options": {
"calculate": false,
"cellGap": 1,
"color": {
"exponent": 0.5,
"fill": "dark-orange",
"mode": "scheme",
"reverse": false,
"scale": "exponential",
"scheme": "Oranges",
"steps": 64
},
"exemplars": {
"color": "rgba(255,0,255,0.7)"
},
"filterValues": {
"le": 1e-9
},
"legend": {
"show": true
},
"rowsFrame": {
"layout": "auto"
},
"tooltip": {
"show": true,
"yHistogram": false
},
"yAxis": {
"axisPlacement": "left",
"reverse": false,
"unit": "s"
}
},
"pluginVersion": "10.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum by (le) (rate({__name__=~\"http_server_request_duration_seconds_bucket|http_server_request_duration_bucket|http_server_duration_milliseconds_bucket|http_server_duration_seconds_bucket|http_server_duration_bucket\", job=~\"$job\", instance=~\"$instance\"}[5m]))",
"format": "heatmap",
"instant": false,
"range": true,
"refId": "A"
}
],
"title": "Duration Heatmap",
"type": "heatmap"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 37
},
"id": 4,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.95, sum by (le) (rate({__name__=~\"http_server_request_duration_seconds_bucket|http_server_request_duration_bucket|http_server_duration_milliseconds_bucket|http_server_duration_seconds_bucket|http_server_duration_bucket\", job=~\"$job\", instance=~\"$instance\"}[5m])))",
"format": "time_series",
"instant": false,
"legendFormat": "95th",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.5, sum by (le) (rate({__name__=~\"http_server_request_duration_seconds_bucket|http_server_request_duration_bucket|http_server_duration_milliseconds_bucket|http_server_duration_seconds_bucket|http_server_duration_bucket\", job=~\"$job\", instance=~\"$instance\"}[5m])))",
"hide": false,
"legendFormat": "50th",
"range": true,
"refId": "B"
}
],
"title": "Duration percentiles",
"type": "timeseries"
}
],
"refresh": "",
"schemaVersion": 39,
"tags": [],
"templating": {
"list": [
{
"allValue": ".+",
"current": {
"selected": true,
"text": ["All"],
"value": ["$__all"]
},
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"definition": "label_values(job)",
"hide": 0,
"includeAll": true,
"label": "",
"multi": true,
"name": "job",
"options": [],
"query": {
"query": "label_values(job)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
},
{
"allValue": ".+",
"current": {
"selected": true,
"text": ["All"],
"value": ["$__all"]
},
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"definition": "label_values({job=~\"$job\"},instance)",
"hide": 0,
"includeAll": true,
"label": "instance",
"multi": true,
"name": "instance",
"options": [],
"query": {
"query": "label_values({job=~\"$job\"},instance)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
}
]
},
"time": {
"from": "now-30m",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "RED Metrics (classic histogram)",
"uid": "f543a537-cb96-470d-a349-660ad1513136",
"version": 1,
"weekStart": ""
}
otel-lgtm/config/grafana-dashboard-red-metrics-native.json
+514
View File
@@ -0,0 +1,514 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "request rate, error rate, duration",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"links": [],
"liveNow": false,
"panels": [
{
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"description": "",
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 0
},
"id": 6,
"options": {
"code": {
"language": "plaintext",
"showLineNumbers": false,
"showMiniMap": false
},
"content": "# RED Metrics: (r)equest rate, (e)rror rate, (d)uration\n\nThis dashboard uses exponential histograms and the stable [OpenTelemetry metrics semantic conventions](https://opentelemetry.io/docs/specs/semconv/general/metrics/).\nTo enable this for the [OpenTelemetry Java instrumentation agent](https://github.com/open-telemetry/opentelemetry-java-instrumentation/), set the following environment variables:\n\n```\nexport OTEL_EXPORTER_OTLP_METRICS_DEFAULT_HISTOGRAM_AGGREGATION=base2_exponential_bucket_histogram\n```",
"mode": "markdown"
},
"pluginVersion": "10.3.3",
"type": "text"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "reqps",
"unitScale": true
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 5
},
"id": 1,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"expr": "sum(histogram_count(rate({__name__=~\"http_server_request_duration_seconds|http_server_request_duration|http_server_duration_milliseconds|http_server_duration_seconds|http_server_duration\", job=~\"$job\", instance=~\"$instance\"}[5m])))",
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Request Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit",
"unitScale": true
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 13
},
"id": 2,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"expr": "sum(histogram_count(rate({__name__=~\"http_server_request_duration_seconds|http_server_request_duration|http_server_duration_milliseconds|http_server_duration_seconds|http_server_duration\", job=~\"$job\", instance=~\"$instance\", http_response_status_code=~\"5..\"}[5m]))) / sum(histogram_count(rate({__name__=~\"http_server_request_duration_seconds|http_server_request_duration|http_server_duration_milliseconds|http_server_duration_seconds|http_server_duration\", job=~\"$job\", instance=~\"$instance\"}[5m])))\n\n",
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Error Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"scaleDistribution": {
"type": "linear"
}
},
"unitScale": true
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 21
},
"id": 5,
"options": {
"calculate": false,
"cellGap": 1,
"color": {
"exponent": 0.5,
"fill": "dark-orange",
"mode": "scheme",
"reverse": false,
"scale": "exponential",
"scheme": "Oranges",
"steps": 64
},
"exemplars": {
"color": "rgba(255,0,255,0.7)"
},
"filterValues": {
"le": 1e-9
},
"legend": {
"show": true
},
"rowsFrame": {
"layout": "auto"
},
"tooltip": {
"mode": "single",
"showColorScale": false,
"yHistogram": false
},
"yAxis": {
"axisPlacement": "left",
"reverse": false,
"unit": "s"
}
},
"pluginVersion": "10.3.3",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate({__name__=~\"http_server_request_duration_seconds|http_server_request_duration|http_server_duration_milliseconds|http_server_duration_seconds|http_server_duration\",job=~\"$job\", instance=~\"$instance\"}[5m]))",
"format": "time_series",
"instant": false,
"range": true,
"refId": "A"
}
],
"title": "Duration Heatmap",
"type": "heatmap"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s",
"unitScale": true
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 29
},
"id": 4,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.95, sum(rate({__name__=~\"http_server_request_duration_seconds|http_server_request_duration|http_server_duration_milliseconds|http_server_duration_seconds|http_server_duration\",job=~\"$job\", instance=~\"$instance\"}[5m])))",
"format": "time_series",
"instant": false,
"legendFormat": "95th",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.5, sum(rate({__name__=~\"http_server_request_duration_seconds|http_server_request_duration|http_server_duration_milliseconds|http_server_duration_seconds|http_server_duration\",job=~\"$job\", instance=~\"$instance\"}[5m])))",
"hide": false,
"legendFormat": "50th",
"range": true,
"refId": "B"
}
],
"title": "Duration percentiles",
"type": "timeseries"
}
],
"refresh": "",
"schemaVersion": 39,
"tags": [],
"templating": {
"list": [
{
"allValue": ".+",
"current": {
"selected": true,
"text": ["All"],
"value": ["$__all"]
},
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"definition": "label_values(job)",
"hide": 0,
"includeAll": true,
"label": "",
"multi": true,
"name": "job",
"options": [],
"query": {
"query": "label_values(job)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
},
{
"allValue": ".+",
"current": {
"selected": true,
"text": ["All"],
"value": ["$__all"]
},
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"definition": "label_values({job=~\"$job\"},instance)",
"hide": 0,
"includeAll": true,
"label": "instance",
"multi": true,
"name": "instance",
"options": [],
"query": {
"query": "label_values({job=~\"$job\"},instance)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
}
]
},
"time": {
"from": "now-30m",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "RED Metrics (native histogram)",
"uid": "f543a537-cb96-470d-a349-660ad1513135",
"version": 1,
"weekStart": ""
}
otel-lgtm/config/grafana-dashboards.yaml
+23
View File
@@ -0,0 +1,23 @@
apiVersion: 1
providers:
- name: "RED Metrics (classic histogram)"
type: file
options:
path: /usr/share/grafana/grafana-dashboard-red-metrics-classic.json
foldersFromFilesStructure: false
- name: "RED Metrics (exponential/native histogram)"
type: file
options:
path: /usr/share/grafana/grafana-dashboard-red-metrics-native.json
foldersFromFilesStructure: false
- name: "JVM Metrics"
type: file
options:
path: /usr/share/grafana/grafana-dashboard-jvm-metrics.json
foldersFromFilesStructure: false
- name: "OpenTelemetry Collector HostMetrics (Node Exporter)"
type: file
options:
path: /usr/share/grafana/opentelemetry-collector-hostmetrics-node-exporter.json
foldersFromFilesStructure: false
otel-lgtm/config/grafana-datasources.yaml
+52
View File
@@ -0,0 +1,52 @@
apiVersion: 1
datasources:
- name: Mimir
type: prometheus
uid: mimir
url: http://127.0.0.1:9009/prometheus
access: proxy
isDefault: true
editable: true
jsonData:
timeInterval: 60s
exemplarTraceIdDestinations:
- name: trace_id
datasourceUid: tempo
urlDisplayLabel: "Trace: $${__value.raw}"
- name: Tempo
type: tempo
uid: tempo
url: http://127.0.0.1:3200
editable: true
jsonData:
tracesToLogsV2:
customQuery: true
datasourceUid: "loki"
query: '{$${__tags}} | trace_id = "$${__trace.traceId}"'
tags:
- key: "service.name"
value: "service_name"
serviceMap:
datasourceUid: "mimir"
search:
hide: false
nodeGraph:
enabled: true
lokiSearch:
datasourceUid: "loki"
- name: Loki
type: loki
uid: loki
url: http://127.0.0.1:3100
editable: true
jsonData:
derivedFields:
- name: "trace_id"
matcherType: "label"
matcherRegex: "trace_id"
url: "$${__value.raw}"
datasourceUid: "tempo"
urlDisplayLabel: "Trace: $${__value.raw}"
otel-lgtm/config/grafana.ini
+2160
View File
File diff suppressed because it is too large Load Diff
otel-lgtm/config/loki.yaml
+45
View File
@@ -0,0 +1,45 @@
auth_enabled: false
server:
http_listen_port: 3100
grpc_listen_port: 9097
common:
instance_addr: 127.0.0.1
path_prefix: /data/loki
storage:
filesystem:
chunks_directory: /data/loki/chunks
rules_directory: /data/loki/rules
replication_factor: 1
ring:
kvstore:
store: inmemory
schema_config:
configs:
- from: 2020-10-24
store: tsdb
object_store: filesystem
schema: v13
index:
prefix: index_
period: 24h
ruler:
alertmanager_url: http://127.0.0.1:9093
pattern_ingester:
lifecycler:
min_ready_duration: 1s
ingester:
lifecycler:
min_ready_duration: 1s
frontend:
scheduler_dns_lookup_period: 1s
address: 127.0.0.1:9097
query_scheduler:
use_scheduler_ring: false
otel-lgtm/config/mimir.yaml
+52
View File
@@ -0,0 +1,52 @@
# Mimir monolithic mode configuration for local development.
# Do not use this configuration in production.
activity_tracker:
filepath: /data/mimir/metrics-activity.log
multitenancy_enabled: false
server:
http_listen_port: 9009
log_level: warn
blocks_storage:
backend: filesystem
bucket_store:
sync_dir: /data/mimir/tsdb-sync
filesystem:
dir: /data/mimir/data/tsdb
tsdb:
dir: /data/mimir/tsdb
compactor:
data_dir: /data/mimir/compactor
sharding_ring:
kvstore:
store: memberlist
distributor:
ring:
instance_addr: 127.0.0.1
kvstore:
store: memberlist
ingester:
ring:
instance_addr: 127.0.0.1
kvstore:
store: memberlist
replication_factor: 1
ruler:
rule_path: /data/mimir/ruler
alertmanager_url: http://127.0.0.1:9093
ruler_storage:
backend: filesystem
filesystem:
dir: /data/mimir/rules
store_gateway:
sharding_ring:
replication_factor: 1
otel-lgtm/config/opentelemetry-collector-hostmetrics-node-exporter.json
+4116
View File
File diff suppressed because it is too large Load Diff
otel-lgtm/config/otelcol.yaml
+43
View File
@@ -0,0 +1,43 @@
receivers:
otlp:
protocols:
http:
endpoint: 0.0.0.0:4318
extensions:
health_check:
endpoint: 127.0.0.1:13133
path: "/ready"
processors:
batch:
exporters:
otlphttp/metrics:
endpoint: http://127.0.0.1:9009/otlp
tls:
insecure: true
otlphttp/traces:
endpoint: http://127.0.0.1:4418
tls:
insecure: true
otlphttp/logs:
endpoint: http://127.0.0.1:3100/otlp
tls:
insecure: true
service:
extensions: [health_check]
pipelines:
traces:
receivers: [otlp]
processors: [batch]
exporters: [otlphttp/traces]
metrics:
receivers: [otlp]
processors: [batch]
exporters: [otlphttp/metrics]
logs:
receivers: [otlp]
processors: [batch]
exporters: [otlphttp/logs]
otel-lgtm/config/supervisord.conf
+58
View File
@@ -0,0 +1,58 @@
[supervisord]
nodaemon=true
user=root
logfile=/var/log/supervisor/supervisord.log
pidfile=/var/run/supervisord.pid
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface
[unix_http_server]
file = /run/supervisord.sock
chmod = 0700
[program:mimir]
command=/usr/bin/mimir -config.file=/etc/mimir/mimir.yaml
autostart=true
autorestart=true
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:loki]
command=/usr/bin/loki -config.file=/etc/loki/loki.yaml
autostart=true
autorestart=true
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:tempo]
command=/usr/bin/tempo -config.file=/etc/tempo/tempo.yaml
autostart=true
autorestart=true
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:otelcol]
command=/usr/local/bin/otelcol-contrib --config=/etc/otelcol/otelcol.yaml
autostart=true
autorestart=true
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:grafana]
directory=/usr/share/grafana
command=/usr/bin/grafana server --homepath=/usr/share/grafana --config=/etc/grafana.ini --homepath=/usr/share/grafana --packaging=docker
autostart=true
autorestart=true
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
otel-lgtm/config/tempo.yaml
+51
View File
@@ -0,0 +1,51 @@
server:
http_listen_port: 3200
grpc_listen_port: 9096
live_store:
shutdown_marker_dir: /data/tempo/live-store/shutdown-marker
wal:
path: /data/tempo/live-store/traces
distributor:
receivers:
otlp:
protocols:
grpc:
endpoint: "127.0.0.1:4417"
http:
endpoint: "127.0.0.1:4418"
memberlist:
bind_addr: [127.0.0.1]
bind_port: 7947
querier:
frontend_worker:
frontend_address: 127.0.0.1:9096
storage:
trace:
backend: local
wal:
path: /data/tempo/wal
local:
path: /data/tempo/blocks
metrics_generator:
processor:
span_metrics:
dimensions:
- service_name
- operation
- status_code
storage:
path: /data/tempo/generator/wal
remote_write:
- url: http://127.0.0.1:9009/api/v1/write
send_exemplars: true
overrides:
defaults:
metrics_generator:
processors: [service-graphs, span-metrics]