Files
rustfs/.docker/observability/docker-compose.yml
T
majinghe a2ec13ab04 fix(otel): fix container unhealty issue caused by healthy check (#4145)
* fix: fix container unhealty issue caused by healthy check

* update readme file

---------

Co-authored-by: houseme <housemecn@gmail.com>
2026-07-01 21:56:26 +08:00

212 lines
5.3 KiB
YAML

# Copyright 2024 RustFS Team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
services:
# --- Tracing ---
tempo:
image: grafana/tempo:2.10.5
container_name: tempo
command: [ "-config.file=/etc/tempo.yaml" ]
volumes:
- ./tempo.yaml:/etc/tempo.yaml:ro
- tempo-data:/var/tempo
ports:
- "3200:3200" # tempo
- "4317" # otlp grpc
- "4318" # otlp http
- "7946" # memberlist
networks:
- otel-network
restart: unless-stopped
healthcheck:
test: [ "CMD", "/tempo", "-version" ]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
vulture:
image: grafana/tempo-vulture:latest
restart: always
command:
[
"-prometheus-listen-address=:8080",
"-tempo-query-url=http://tempo:3200",
"-tempo-push-url=http://tempo:4317",
]
depends_on:
- tempo
jaeger:
image: jaegertracing/jaeger:latest
container_name: jaeger
environment:
- SPAN_STORAGE_TYPE=badger
- BADGER_EPHEMERAL=false
- BADGER_DIRECTORY_VALUE=/badger/data
- BADGER_DIRECTORY_KEY=/badger/key
- COLLECTOR_OTLP_ENABLED=true
volumes:
- ./jaeger.yaml:/etc/jaeger/config.yml
- jaeger-data:/badger
ports:
- "16686:16686" # Web UI
- "18888:8888" # Metrics
- "4317" # otlp grpc
- "4318" # otlp http
command: [ "--config", "/etc/jaeger/config.yml" ]
networks:
- otel-network
restart: unless-stopped
healthcheck:
test: [ "CMD", "wget", "--spider", "-q", "http://localhost:8888/metrics" ]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
# --- Metrics ---
prometheus:
image: prom/prometheus:latest
container_name: prometheus
volumes:
- ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
- ./prometheus-rules:/etc/prometheus/rules:ro
- prometheus-data:/prometheus
ports:
- "9090:9090"
command:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--web.enable-otlp-receiver" # Enable OTLP
- "--web.enable-remote-write-receiver" # Enable remote write
- "--enable-feature=promql-experimental-functions" # Enable info()
- "--storage.tsdb.retention.time=30d"
restart: unless-stopped
networks:
- otel-network
healthcheck:
test: [ "CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy" ]
interval: 10s
timeout: 5s
retries: 3
# --- Logging ---
loki:
image: grafana/loki:latest
container_name: loki
volumes:
- ./loki.yaml:/etc/loki/loki.yaml:ro
- loki-data:/loki
ports:
- "3100:3100"
command: -config.file=/etc/loki/loki.yaml
networks:
- otel-network
restart: unless-stopped
healthcheck:
test: [ "CMD", "/usr/bin/loki", "--version" ]
interval: 15s
timeout: 10s
retries: 5
start_period: 60s
# --- Collection ---
otel-collector:
image: otel/opentelemetry-collector-contrib:latest
volumes:
- ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml:ro
ports:
- "1888:1888" # pprof
- "8888:8888" # Prometheus metrics for Collector
- "8889:8889" # Prometheus metrics for application indicators
- "13133:13133" # health check
- "4317:4317" # OTLP gRPC
- "4318:4318" # OTLP HTTP
- "55679:55679" # zpages
networks:
- otel-network
restart: unless-stopped
depends_on:
- tempo
- jaeger
- prometheus
- loki
healthcheck:
test: [ "CMD", "/otelcol-contrib", "--version" ]
interval: 10s
timeout: 5s
retries: 3
# --- Profiles ---
pyroscope:
image: grafana/pyroscope:latest
container_name: pyroscope
ports:
- "4040:4040"
command:
- -self-profiling.disable-push=true
networks:
- otel-network
restart: unless-stopped
# --- Visualization ---
grafana:
image: grafana/grafana:latest
container_name: grafana
ports:
- "3000:3000"
environment:
- GF_SECURITY_ADMIN_PASSWORD=admin
- GF_SECURITY_ADMIN_USER=admin
volumes:
- ./grafana/provisioning:/etc/grafana/provisioning:ro
- ./grafana/dashboards:/etc/grafana/dashboards:ro
- grafana-data:/var/lib/grafana
networks:
- otel-network
restart: unless-stopped
depends_on:
- prometheus
- tempo
- loki
healthcheck:
test:
[ "CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health" ]
interval: 10s
timeout: 5s
retries: 3
volumes:
tempo-data:
jaeger-data:
prometheus-data:
loki-data:
grafana-data:
networks:
otel-network:
driver: bridge
name: "network_otel"
ipam:
config:
- subnet: 172.28.0.0/16
driver_opts:
com.docker.network.enable_ipv6: "true"