refactor: signoz

src/signoz/docker-compose.yaml

@@ -3,61 +3,199 @@ x-defaults: &defaults
   logging:
     driver: json-file
     options:
-      max-size: 100m
+      max-size: 50m
       max-file: '3'
 
 x-clickhouse-defaults: &clickhouse-defaults
-  restart: on-failure
-  logging:
-    driver: json-file
-    options:
-      max-size: 100m
-      max-file: '3'
+  <<: *defaults
+  image: ${GLOBAL_REGISTRY:-}clickhouse/clickhouse-server:${SIGNOZ_CLICKHOUSE_VERSION:-25.5.6}
+  depends_on:
+    init-clickhouse:
+      condition: service_completed_successfully
+    zookeeper-1:
+      condition: service_healthy
   healthcheck:
-    test: [CMD, wget, --spider, -q, 'localhost:8123/ping']
+    test: [CMD, wget, --spider, -q, '0.0.0.0:8123/ping']
     interval: 30s
     timeout: 5s
     retries: 3
-  deploy:
-    resources:
-      limits:
-        cpus: ${SIGNOZ_CLICKHOUSE_CPU_LIMIT:-2.0}
-        memory: ${SIGNOZ_CLICKHOUSE_MEMORY_LIMIT:-4G}
-      reservations:
-        cpus: ${SIGNOZ_CLICKHOUSE_CPU_RESERVATION:-0.5}
-        memory: ${SIGNOZ_CLICKHOUSE_MEMORY_RESERVATION:-1G}
+  ulimits:
+    nproc: 65535
+    nofile:
+      soft: 262144
+      hard: 262144
+
+x-db-depend: &db-depend
+  <<: *defaults
+  depends_on:
+    clickhouse:
+      condition: service_healthy
 
 services:
+  # One-shot init: downloads histogramQuantile UDF binary into the shared volume
+  init-clickhouse:
+    image: ${GLOBAL_REGISTRY:-}clickhouse/clickhouse-server:${SIGNOZ_CLICKHOUSE_VERSION:-25.5.6}
+    restart: on-failure
+    logging:
+      driver: json-file
+      options:
+        max-size: 10m
+        max-file: '1'
+    command:
+      - bash
+      - -c
+      - |
+        version="v0.0.1"
+        node_os=$$(uname -s | tr '[:upper:]' '[:lower:]')
+        node_arch=$$(uname -m | sed s/aarch64/arm64/ | sed s/x86_64/amd64/)
+        echo "Fetching histogram-binary for $${node_os}/$${node_arch}"
+        cd /tmp
+        wget -O histogram-quantile.tar.gz "https://github.com/SigNoz/signoz/releases/download/histogram-quantile%2F$${version}/histogram-quantile_$${node_os}_$${node_arch}.tar.gz"
+        tar -xvzf histogram-quantile.tar.gz
+        mv histogram-quantile /var/lib/clickhouse/user_scripts/histogramQuantile
+        echo "Done."
+    volumes:
+      - clickhouse_user_scripts:/var/lib/clickhouse/user_scripts/
+    deploy:
+      resources:
+        limits:
+          cpus: '0.5'
+          memory: 256M
+
+  # ZooKeeper for ClickHouse replication metadata
+  zookeeper-1:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}signoz/zookeeper:${SIGNOZ_ZOOKEEPER_VERSION:-3.7.1}
+    user: root
+    environment:
+      - TZ=${TZ:-UTC}
+      - ZOO_SERVER_ID=1
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+    volumes:
+      - zookeeper_data:/bitnami/zookeeper
+    healthcheck:
+      test: [CMD-SHELL, 'curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null']
+      interval: 30s
+      timeout: 5s
+      retries: 3
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          cpus: ${SIGNOZ_ZOOKEEPER_CPU_LIMIT:-0.5}
+          memory: ${SIGNOZ_ZOOKEEPER_MEMORY_LIMIT:-512M}
+        reservations:
+          cpus: ${SIGNOZ_ZOOKEEPER_CPU_RESERVATION:-0.1}
+          memory: ${SIGNOZ_ZOOKEEPER_MEMORY_RESERVATION:-128M}
+
   # ClickHouse for storing traces, metrics and logs
   clickhouse:
     <<: *clickhouse-defaults
-    image: ${GLOBAL_REGISTRY:-}clickhouse/clickhouse-server:${SIGNOZ_CLICKHOUSE_VERSION:-24.11.1-alpine}
-    user: '101:101' # ClickHouse user
-    volumes:
-      - clickhouse_data:/var/lib/clickhouse
-      - ./clickhouse-config.xml:/etc/clickhouse-server/config.d/logging.xml:ro
-      - ./clickhouse-users.xml:/etc/clickhouse-server/users.d/logging.xml:ro
     environment:
       - TZ=${TZ:-UTC}
-      - CLICKHOUSE_DB=${SIGNOZ_CLICKHOUSE_DB:-signoz}
+      - CLICKHOUSE_SKIP_USER_SETUP=1
+    volumes:
+      - clickhouse_data:/var/lib/clickhouse/
+      - clickhouse_user_scripts:/var/lib/clickhouse/user_scripts/
+      - ./clickhouse/config.xml:/etc/clickhouse-server/config.xml:ro
+      - ./clickhouse/users.xml:/etc/clickhouse-server/users.xml:ro
+      - ./clickhouse/custom-function.xml:/etc/clickhouse-server/custom-function.xml:ro
+      - ./clickhouse/cluster.xml:/etc/clickhouse-server/config.d/cluster.xml:ro
+    deploy:
+      resources:
+        limits:
+          cpus: ${SIGNOZ_CLICKHOUSE_CPU_LIMIT:-2.0}
+          memory: ${SIGNOZ_CLICKHOUSE_MEMORY_LIMIT:-4G}
+        reservations:
+          cpus: ${SIGNOZ_CLICKHOUSE_CPU_RESERVATION:-0.5}
+          memory: ${SIGNOZ_CLICKHOUSE_MEMORY_RESERVATION:-1G}
+
+  # One-shot migration: bootstraps and runs schema migrations
+  signoz-telemetrystore-migrator:
+    <<: *db-depend
+    image: ${GLOBAL_REGISTRY:-}signoz/signoz-otel-collector:${SIGNOZ_OTEL_COLLECTOR_VERSION:-v0.144.2}
+    restart: on-failure
+    environment:
+      - TZ=${TZ:-UTC}
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    entrypoint: [/bin/sh]
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate bootstrap &&
+        /signoz-otel-collector migrate sync up &&
+        /signoz-otel-collector migrate async up
+    deploy:
+      resources:
+        limits:
+          cpus: '0.5'
+          memory: 512M
+
+  # SigNoz all-in-one backend + frontend + alertmanager
+  signoz:
+    <<: *db-depend
+    image: ${GLOBAL_REGISTRY:-}signoz/signoz:${SIGNOZ_VERSION:-v0.118.0}
+    ports:
+      - '${SIGNOZ_PORT_OVERRIDE:-8080}:8080'
+    volumes:
+      - signoz_data:/var/lib/signoz/
+    environment:
+      - TZ=${TZ:-UTC}
+      - SIGNOZ_ALERTMANAGER_PROVIDER=signoz
+      - SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_SQLSTORE_SQLITE_PATH=/var/lib/signoz/signoz.db
+      - SIGNOZ_TOKENIZER_JWT_SECRET=${SIGNOZ_JWT_SECRET:-please-change-this-secret}
+    healthcheck:
+      test: [CMD, wget, --spider, -q, 'localhost:8080/api/v1/health']
+      interval: 30s
+      timeout: 5s
+      retries: 3
+      start_period: 60s
+    deploy:
+      resources:
+        limits:
+          cpus: ${SIGNOZ_CPU_LIMIT:-1.0}
+          memory: ${SIGNOZ_MEMORY_LIMIT:-2G}
+        reservations:
+          cpus: ${SIGNOZ_CPU_RESERVATION:-0.25}
+          memory: ${SIGNOZ_MEMORY_RESERVATION:-256M}
 
   # OTel Collector for receiving telemetry data
   otel-collector:
-    <<: *defaults
-    image: ${GLOBAL_REGISTRY:-}signoz/signoz-otel-collector:${SIGNOZ_OTEL_COLLECTOR_VERSION:-0.102.8}
+    <<: *db-depend
+    image: ${GLOBAL_REGISTRY:-}signoz/signoz-otel-collector:${SIGNOZ_OTEL_COLLECTOR_VERSION:-v0.144.2}
+    entrypoint: [/bin/sh]
     command:
-      - --config=/etc/otel-collector-config.yaml
+      - -c
+      - |
+        /signoz-otel-collector migrate sync check &&
+        /signoz-otel-collector --config=/etc/otel-collector-config.yaml --manager-config=/etc/manager-config.yaml --copy-path=/var/tmp/collector-config.yaml
     volumes:
       - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
+      - ./signoz/otel-collector-opamp-config.yaml:/etc/manager-config.yaml:ro
     environment:
       - TZ=${TZ:-UTC}
-      - OTEL_RESOURCE_ATTRIBUTES=${SIGNOZ_OTEL_RESOURCE_ATTRIBUTES:-host.name=signoz-host}
+      - OTEL_RESOURCE_ATTRIBUTES=${SIGNOZ_OTEL_RESOURCE_ATTRIBUTES:-host.name=signoz-host,os.type=linux}
+      - LOW_CARDINAL_EXCEPTION_GROUPING=${SIGNOZ_LOW_CARDINAL_EXCEPTION_GROUPING:-false}
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
     ports:
       - '${SIGNOZ_OTEL_GRPC_PORT_OVERRIDE:-4317}:4317' # OTLP gRPC receiver
       - '${SIGNOZ_OTEL_HTTP_PORT_OVERRIDE:-4318}:4318' # OTLP HTTP receiver
-    depends_on:
-      clickhouse:
-        condition: service_healthy
+    healthcheck:
+      test: [CMD, bash, -c, echo > /dev/tcp/localhost/13133]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
     deploy:
       resources:
         limits:
@@ -66,133 +204,9 @@ services:
         reservations:
           cpus: ${SIGNOZ_OTEL_COLLECTOR_CPU_RESERVATION:-0.25}
           memory: ${SIGNOZ_OTEL_COLLECTOR_MEMORY_RESERVATION:-512M}
-    healthcheck:
-      test:
-        - CMD
-        - wget
-        - --no-verbose
-        - --tries=1
-        - --spider
-        - 'http://localhost:13133/'
-
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 30s
-
-  # Query Service for querying data
-  query-service:
-    <<: *defaults
-    image: ${GLOBAL_REGISTRY:-}signoz/query-service:${SIGNOZ_QUERY_SERVICE_VERSION:-0.55.0}
-    command:
-      - -config=/root/config/prometheus.yml
-    volumes:
-      - ./query-service/prometheus.yml:/root/config/prometheus.yml:ro
-      - signoz_data:/var/lib/signoz
-    environment:
-      - TZ=${TZ:-UTC}
-      - ClickHouseUrl=${SIGNOZ_CLICKHOUSE_URL:-tcp://clickhouse:9000/?database=signoz}
-      - STORAGE=${SIGNOZ_STORAGE:-clickhouse}
-      - GODEBUG=${SIGNOZ_GODEBUG:-netdns=go}
-      - TELEMETRY_ENABLED=${SIGNOZ_TELEMETRY_ENABLED:-true}
-      - DEPLOYMENT_TYPE=${SIGNOZ_DEPLOYMENT_TYPE:-docker-standalone-amd}
-    depends_on:
-      clickhouse:
-        condition: service_healthy
-    deploy:
-      resources:
-        limits:
-          cpus: ${SIGNOZ_QUERY_SERVICE_CPU_LIMIT:-1.0}
-          memory: ${SIGNOZ_QUERY_SERVICE_MEMORY_LIMIT:-1G}
-        reservations:
-          cpus: ${SIGNOZ_QUERY_SERVICE_CPU_RESERVATION:-0.25}
-          memory: ${SIGNOZ_QUERY_SERVICE_MEMORY_RESERVATION:-256M}
-    healthcheck:
-      test:
-        - CMD
-        - wget
-        - --no-verbose
-        - --tries=1
-        - --spider
-        - 'http://localhost:8080/api/v1/health'
-
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 30s
-
-  # Frontend for the UI
-  frontend:
-    <<: *defaults
-    image: ${GLOBAL_REGISTRY:-}signoz/frontend:${SIGNOZ_FRONTEND_VERSION:-0.55.0}
-    ports:
-      - '${SIGNOZ_PORT_OVERRIDE:-3301}:3301'
-    volumes:
-      - ./frontend/nginx-config.conf:/etc/nginx/conf.d/default.conf:ro
-    environment:
-      - TZ=${TZ:-UTC}
-    depends_on:
-      query-service:
-        condition: service_healthy
-    deploy:
-      resources:
-        limits:
-          cpus: ${SIGNOZ_FRONTEND_CPU_LIMIT:-0.5}
-          memory: ${SIGNOZ_FRONTEND_MEMORY_LIMIT:-512M}
-        reservations:
-          cpus: ${SIGNOZ_FRONTEND_CPU_RESERVATION:-0.1}
-          memory: ${SIGNOZ_FRONTEND_MEMORY_RESERVATION:-128M}
-    healthcheck:
-      test:
-        - CMD
-        - wget
-        - --no-verbose
-        - --tries=1
-        - --spider
-        - 'http://localhost:3301/api/v1/health'
-
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 10s
-
-  # Alert Manager for managing alerts
-  alertmanager:
-    <<: *defaults
-    image: ${GLOBAL_REGISTRY:-}signoz/alertmanager:${SIGNOZ_ALERTMANAGER_VERSION:-0.23.5}
-    command:
-      - --queryService.url=http://query-service:8080
-      - --storage.path=/data
-    volumes:
-      - alertmanager_data:/data
-    environment:
-      - TZ=${TZ:-UTC}
-    depends_on:
-      query-service:
-        condition: service_healthy
-    deploy:
-      resources:
-        limits:
-          cpus: ${SIGNOZ_ALERTMANAGER_CPU_LIMIT:-0.5}
-          memory: ${SIGNOZ_ALERTMANAGER_MEMORY_LIMIT:-512M}
-        reservations:
-          cpus: ${SIGNOZ_ALERTMANAGER_CPU_RESERVATION:-0.1}
-          memory: ${SIGNOZ_ALERTMANAGER_MEMORY_RESERVATION:-128M}
-    healthcheck:
-      test:
-        - CMD
-        - wget
-        - --no-verbose
-        - --tries=1
-        - --spider
-        - 'http://localhost:9093/-/healthy'
-
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 10s
 
 volumes:
   clickhouse_data:
+  clickhouse_user_scripts:
   signoz_data:
-  alertmanager_data:
+  zookeeper_data: