o11y/deploy/docker-swarm/docker-compose.yaml at e442dc6bd2c2737ca5688df4e711410ad2edcba8

mirror of https://github.com/hanzoai/o11y.git synced 2026-10-15 12:58:33 +00:00

Files

T

zooqueen e442dc6bd2 fix(deploy): the compose files name what the datastore image ships

Verified against ghcr.io/hanzoai/datastore:26.6.1.1, the image these files run:
config /etc/datastore-server, data /var/lib/datastore, config root <datastore>,
client /usr/bin/datastore-client, and an entrypoint that reads DATASTORE_* and
nothing else. The mounts pointed at /etc/clickhouse-server and
/var/lib/clickhouse, which the image does not have, and passed CLICKHOUSE_* the
entrypoint ignores.

.devenv bound ${PWD}/../../../deploy/common/clickhouse/custom-function.xml; that
directory is deploy/common/datastore.

Service, hostname, volume, anchor and swarm-config names follow, and the cluster
XML replicas match the compose hostnames again.

The eight built-in integrations credited [email protected] and o11y.io, which
does not resolve; ours is o11y.hanzo.ai. The datastore integration is titled
Hanzo Datastore. Its id stays — an installed integration references it.

data-collected.json and the dashboards keep ClickHouseProfileEvents_* and
ClickHouseAsyncMetrics_*: those are the names the server binary emits, checked
in the running pod.

2026-08-14 20:07:33 -07:00

207 lines

5.9 KiB

YAML

Raw Blame History

 version: "3"
 x-common: &common
   networks:
     - o11y-net
   deploy:
     restart_policy:
       condition: on-failure
   logging:
     options:
       max-size: 50m
       max-file: "3"
 x-datastore-defaults: &datastore-defaults
   !!merge <<: *common
   image: ghcr.io/hanzoai/datastore:26.6.1.1
   tty: true
   deploy:
     labels:
       o11y.hanzo.ai/scrape: "true"
       o11y.hanzo.ai/port: "9363"
       o11y.hanzo.ai/path: "/metrics"
   depends_on:
     - init-datastore
     - zookeeper-1
   healthcheck:
     test:
       - CMD
       - wget
       - --spider
       - -q
       - 0.0.0.0:8123/ping
     interval: 30s
     timeout: 5s
     retries: 3
   ulimits:
     nproc: 65535
     nofile:
       soft: 262144
       hard: 262144
   environment:
     - DATASTORE_SKIP_USER_SETUP=1
 x-zookeeper-defaults: &zookeeper-defaults
   !!merge <<: *common
   image: ghcr.io/hanzoai/zookeeper:3.7.1
   user: root
   deploy:
     labels:
       o11y.hanzo.ai/scrape: "true"
       o11y.hanzo.ai/port: "9141"
       o11y.hanzo.ai/path: "/metrics"
   healthcheck:
     test:
       - CMD-SHELL
       - curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null
     interval: 30s
     timeout: 5s
     retries: 3
 x-db-depend: &db-depend
   !!merge <<: *common
   depends_on:
     - datastore
 services:
   init-datastore:
     !!merge <<: *common
     image: ghcr.io/hanzoai/datastore:26.6.1.1
     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/Hanzo O11y/observe/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/datastore/user_scripts/histogramQuantile
     deploy:
       restart_policy:
         condition: on-failure
     volumes:
       - ../common/datastore/user_scripts:/var/lib/datastore/user_scripts/
   zookeeper-1:
     !!merge <<: *zookeeper-defaults
     # ports:
     #   - "2181:2181"
     #   - "2888:2888"
     #   - "3888:3888"
     volumes:
       - zookeeper-1:/bitnami/zookeeper
     environment:
       - ZOO_SERVER_ID=1
       - ALLOW_ANONYMOUS_LOGIN=yes
       - ZOO_AUTOPURGE_INTERVAL=1
       - ZOO_ENABLE_PROMETHEUS_METRICS=yes
       - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
   datastore:
     !!merge <<: *datastore-defaults
     # TODO: needed for datastore TCP connectio
     hostname: datastore
     # ports:
     #   - "9000:9000"
     #   - "8123:8123"
     #   - "9181:9181"
     configs:
       - source: datastore-config
         target: /etc/datastore-server/config.xml
       - source: datastore-users
         target: /etc/datastore-server/users.xml
       - source: datastore-custom-function
         target: /etc/datastore-server/custom-function.xml
       - source: datastore-cluster
         target: /etc/datastore-server/config.d/cluster.xml
     volumes:
       - datastore:/var/lib/datastore/
       - ../common/datastore/user_scripts:/var/lib/datastore/user_scripts/
       # - ../common/datastore/storage.xml:/etc/datastore-server/config.d/storage.xml
   observe:
     !!merge <<: *db-depend
     image: ghcr.io/hanzoai/o11y:v0.115.0
     ports:
       - "8080:8080" # observe port
     volumes:
       - sqlite:/var/lib/observe/
     environment:
       - O11Y_ALERTMANAGER_PROVIDER=observe
       - O11Y_DATASTORE_DSN=tcp://datastore:9000
       - O11Y_SQLSTORE_SQLITE_PATH=/var/lib/ghcr.io/hanzoai/o11y.db
       - O11Y_TOKENIZER_JWT_SECRET=secret
     healthcheck:
       test:
         - CMD
         - wget
         - --spider
         - -q
         - localhost:8080/v1/o11y/v1/health
       interval: 30s
       timeout: 5s
       retries: 3
   otel-collector:
     !!merge <<: *db-depend
     image: ghcr.io/hanzoai/otel-collector:v0.144.2
     entrypoint:
       - /bin/sh
     command:
       - -c
       - |
         /o11y-otel-collector migrate sync check &&
         /o11y-otel-collector --config=/etc/otel-collector-config.yaml --manager-config=/etc/manager-config.yaml --copy-path=/var/tmp/collector-config.yaml
     configs:
       - source: otel-collector-config
         target: /etc/otel-collector-config.yaml
       - source: otel-manager-config
         target: /etc/manager-config.yaml
     environment:
       - OTEL_RESOURCE_ATTRIBUTES=host.name={{.Node.Hostname}},os.type={{.Node.Platform.OS}}
       - LOW_CARDINAL_EXCEPTION_GROUPING=false
       - O11Y_OTEL_COLLECTOR_DATASTORE_DSN=tcp://datastore:9000
       - O11Y_OTEL_COLLECTOR_DATASTORE_CLUSTER=cluster
       - O11Y_OTEL_COLLECTOR_DATASTORE_REPLICATION=true
       - O11Y_OTEL_COLLECTOR_TIMEOUT=10m
     ports:
       # - "1777:1777"     # pprof extension
       - "4317:4317" # OTLP gRPC receiver
       - "4318:4318" # OTLP HTTP receiver
     deploy:
       replicas: 3
   o11y-telemetrystore-migrator:
     !!merge <<: *db-depend
     image: ghcr.io/hanzoai/otel-collector:v0.144.2
     environment:
       - O11Y_OTEL_COLLECTOR_DATASTORE_DSN=tcp://datastore:9000
       - O11Y_OTEL_COLLECTOR_DATASTORE_CLUSTER=cluster
       - O11Y_OTEL_COLLECTOR_DATASTORE_REPLICATION=true
       - O11Y_OTEL_COLLECTOR_TIMEOUT=10m
     entrypoint:
       - /bin/sh
     command:
       - -c
       - |
         /o11y-otel-collector migrate bootstrap &&
         /o11y-otel-collector migrate sync up &&
         /o11y-otel-collector migrate async up
 networks:
   o11y-net:
     name: o11y-net
 volumes:
   datastore:
     name: o11y-datastore
   sqlite:
     name: o11y-sqlite
   zookeeper-1:
     name: o11y-zookeeper-1
 configs:
   datastore-config:
     file: ../common/datastore/config.xml
   datastore-users:
     file: ../common/datastore/users.xml
   datastore-custom-function:
     file: ../common/datastore/custom-function.xml
   datastore-cluster:
     file: ../common/datastore/cluster.xml
   otel-collector-config:
     file: ./otel-collector-config.yaml
   otel-manager-config:
     file: ../common/observe/otel-collector-opamp-config.yaml

207 lines 5.9 KiB YAML Raw Blame History

207 lines

5.9 KiB

YAML

Raw Blame History