diff --git a/.env.template b/.env.template new file mode 100644 index 0000000..ba84338 --- /dev/null +++ b/.env.template @@ -0,0 +1,17 @@ +# Base +RUSTFS_API_PORT=14602 +RUSTFS_CONSOLE_PORT=14601 + +# Observability +GRAFANA_PORT=14603 +PGADMIN_PORT=14604 +VICTORIAMETRICS_PORT=14605 +OTEL_GRPC_PORT=14607 +OTEL_HTTP_PORT=14608 +GRAFANA_PYROSCOPE_PORT=14611 + +# Backend +BACKEND_PORT=14609 + +# Proxy +CADDY_PORT=80 diff --git a/compose.prod.yaml b/compose.prod.yaml new file mode 100644 index 0000000..15e6464 --- /dev/null +++ b/compose.prod.yaml @@ -0,0 +1,16 @@ +name: movienight + +x-defaults: &defaults + project_directory: ./ + env_file: + - ./.env.template + +include: + - path: ./deploy/compose/compose.yaml + <<: *defaults + - path: ./deploy/compose/compose.proxy.yaml + <<: *defaults + - path: ./deploy/compose/compose.backend.yaml + <<: *defaults + - path: ./deploy/compose/compose.observability.yaml + <<: *defaults diff --git a/compose.yaml b/compose.yaml new file mode 100644 index 0000000..42f8fa6 --- /dev/null +++ b/compose.yaml @@ -0,0 +1,14 @@ +name: movienight + +x-defaults: &defaults + project_directory: ./ + env_file: + - ./.env.template + +include: + - path: ./deploy/compose/compose.yaml + <<: *defaults + - path: ./deploy/compose/compose.proxy.yaml + <<: *defaults + - path: ./deploy/compose/compose.backend.yaml + <<: *defaults diff --git a/deploy/compose/compose.backend.yaml b/deploy/compose/compose.backend.yaml new file mode 100644 index 0000000..4322d9a --- /dev/null +++ b/deploy/compose/compose.backend.yaml @@ -0,0 +1,41 @@ +services: + backend: + build: + context: . + dockerfile: Containerfile + depends_on: + valkey: + restart: false + condition: service_healthy + required: true + postgresql: + restart: false + condition: service_healthy + required: true + s3: + restart: false + condition: service_healthy + required: true + env_file: + - path: ./infrastructure/configs/backend/.env.template + required: true + - path: ./infrastructure/configs/backend/.env + required: false + healthcheck: + test: [ "CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8080/actuator/health" ] + interval: 10s + timeout: 5s + start_period: 5s + start_interval: 2s + retries: 5 + ports: + - name: http + target: 8080 + published: ${BACKEND_PORT} + host_ip: 127.0.0.1 + protocol: tcp + app_protocol: http + networks: + - default + restart: unless-stopped + shm_size: 4mb diff --git a/deploy/compose/compose.observability.yaml b/deploy/compose/compose.observability.yaml new file mode 100644 index 0000000..0ae722e --- /dev/null +++ b/deploy/compose/compose.observability.yaml @@ -0,0 +1,297 @@ +services: + grafana: + image: docker.io/grafana/grafana-oss:12.3.2 + entrypoint: + - /etc/grafana/scripts/entrypoint.sh + env_file: + - path: ./infrastructure/configs/grafana/.env.template + required: true + - path: ./infrastructure/configs/grafana/.env + required: false + healthcheck: + test: ["CMD", "wget", "-O", "-", "http://localhost:3000/api/health"] + interval: 30s + timeout: 5s + start_period: 5s + start_interval: 2s + retries: 5 + ports: + - name: web + target: 3000 + published: ${GRAFANA_PORT} + host_ip: 127.0.0.1 + protocol: tcp + app_protocol: http + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + volumes: + - type: bind + source: ./infrastructure/configs/grafana/provisioning + target: /etc/grafana/provisioning + read_only: true + - type: bind + source: ./infrastructure/configs/grafana/scripts + target: /etc/grafana/scripts + read_only: true + + otel-collector: + image: docker.io/otel/opentelemetry-collector-contrib:latest + command: + - --config=/etc/otelcol-contrib/config.yaml + configs: + - source: otel_collector_config + target: /etc/otelcol-contrib/config.yaml + ports: + - name: otlp-grpc + target: 4317 + published: ${OTEL_GRPC_PORT} + host_ip: 127.0.0.1 + protocol: tcp + - name: otlp-http + target: 4318 + published: ${OTEL_HTTP_PORT} + host_ip: 127.0.0.1 + protocol: tcp + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + + grafana-loki: + image: docker.io/grafana/loki:3.6.5 + command: + - --config.file=/etc/loki/local-config.yaml + - --config.expand-env=true + depends_on: + s3: + restart: false + condition: service_healthy + required: true + configs: + - source: grafana_loki_config + target: /etc/loki/local-config.yaml + env_file: + - path: ./infrastructure/configs/s3/.env.template + required: true + - path: ./infrastructure/configs/s3/.env + required: false + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + + grafana-tempo: + image: docker.io/grafana/tempo:2.10.0 + command: + - --config.file=/etc/tempo/tempo-config.yaml + - --config.expand-env=true + depends_on: + s3: + restart: false + condition: service_healthy + required: true + configs: + - source: grafana_tempo_config + target: /etc/tempo/tempo-config.yaml + env_file: + - path: ./infrastructure/configs/s3/.env.template + required: true + - path: ./infrastructure/configs/s3/.env + required: false + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + + grafana-pyroscope: + image: docker.io/grafana/pyroscope:1.18.0 + command: + - -config.file=/etc/pyroscope/config.yaml + - -config.expand-env=true + depends_on: + s3: + restart: false + condition: service_healthy + required: true + configs: + - source: grafana_pyroscope_config + target: /etc/pyroscope/config.yaml + env_file: + - path: ./infrastructure/configs/s3/.env.template + required: true + - path: ./infrastructure/configs/s3/.env + required: false + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + + vmagent: + image: docker.io/victoriametrics/vmagent:v1.135.0 + command: + - -promscrape.config=/etc/vmagent/scrape.yaml + - -remoteWrite.url=http://victoriametrics:8428/api/v1/write + configs: + - source: vmagent_config + target: /etc/vmagent/scrape.yaml + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + + victoriametrics: + image: docker.io/victoriametrics/victoria-metrics:v1.134.0 + command: + - -storageDataPath=/var/lib/victoriametrics + - -retentionPeriod=30d + - -httpListenAddr=:8428 + healthcheck: + test: ["CMD", "wget", "-qO-", "http://127.0.0.1:8428/-/healthy"] + interval: 30s + timeout: 5s + start_period: 5s + start_interval: 2s + retries: 5 + ports: + - name: web + target: 8428 + published: ${VICTORIAMETRICS_PORT} + host_ip: 127.0.0.1 + protocol: tcp + app_protocol: http + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + volumes: + - type: volume + source: victoriametrics_data + target: /var/lib/victoriametrics + read_only: false + + redis-exporter: + image: docker.io/oliver006/redis_exporter:v1.80.2-alpine + depends_on: + valkey: + restart: false + condition: service_healthy + required: true + env_file: + - path: ./infrastructure/configs/redis-exporter/.env.template + required: true + - path: ./infrastructure/configs/redis-exporter/.env + required: false + healthcheck: + test: ["CMD", "wget", "-O", "-", "http://localhost:9121/metrics"] + interval: 30s + timeout: 5s + start_period: 5s + start_interval: 2s + retries: 5 + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + + postgres-exporter: + image: quay.io/prometheuscommunity/postgres-exporter:latest + depends_on: + postgresql: + restart: false + condition: service_healthy + required: true + env_file: + - path: ./infrastructure/configs/postgres-exporter/.env.template + required: true + - path: ./infrastructure/configs/postgres-exporter/.env + required: false + healthcheck: + test: ["CMD", "wget", "-O", "-", "http://localhost:9187/metrics"] + interval: 30s + timeout: 5s + start_period: 5s + start_interval: 2s + retries: 5 + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + + pgadmin: + image: docker.io/dpage/pgadmin4:9 + configs: + - source: pgadmin_servers_config + target: /pgadmin4/servers.json + depends_on: + postgresql: + restart: false + condition: service_healthy + required: true + env_file: + - path: ./infrastructure/configs/pgadmin/.env.template + required: true + - path: ./infrastructure/configs/pgadmin/.env + required: false + healthcheck: + test: ["CMD", "wget", "-O", "-", "http://localhost:80/misc/ping"] + interval: 30s + timeout: 5s + start_period: 5s + start_interval: 2s + retries: 5 + ports: + - name: web + target: 80 + published: ${PGADMIN_PORT} + host_ip: 127.0.0.1 + protocol: tcp + app_protocol: http + networks: + - default + profiles: + - observability + restart: unless-stopped + shm_size: 4mb + volumes: + - type: volume + source: pgadmin_data + target: /var/lib/pgadmin + read_only: false + +volumes: + victoriametrics_data: + pgadmin_data: + +configs: + otel_collector_config: + file: ./infrastructure/configs/otel-collector/config.yaml + grafana_loki_config: + file: ./infrastructure/configs/grafana-loki/loki.yaml + grafana_tempo_config: + file: ./infrastructure/configs/grafana-tempo/tempo.yaml + grafana_pyroscope_config: + file: ./infrastructure/configs/grafana-pyroscope/config.yaml + vmagent_config: + file: ./infrastructure/configs/victoriametrics/vmagent.yaml + pgadmin_servers_config: + file: ./infrastructure/configs/pgadmin/servers.json diff --git a/deploy/compose/compose.proxy.yaml b/deploy/compose/compose.proxy.yaml new file mode 100644 index 0000000..ff23fde --- /dev/null +++ b/deploy/compose/compose.proxy.yaml @@ -0,0 +1,21 @@ +services: + caddy: + image: docker.io/caddy:2-alpine + configs: + - source: caddy_config + target: /etc/caddy/Caddyfile + ports: + - name: http + target: 80 + published: 80 + host_ip: 0.0.0.0 + protocol: tcp + app_protocol: http + networks: + - default + restart: unless-stopped + shm_size: 4mb + +configs: + caddy_config: + file: ./infrastructure/configs/caddy/Caddyfile diff --git a/deploy/compose/compose.yaml b/deploy/compose/compose.yaml new file mode 100644 index 0000000..492c504 --- /dev/null +++ b/deploy/compose/compose.yaml @@ -0,0 +1,149 @@ +services: + postgresql: + image: docker.io/postgres:18-alpine + command: + - -c + - config_file=/etc/postgresql/postgresql.conf + configs: + - source: postgresql_config + target: /etc/postgresql/postgresql.conf + - source: postgresql_hba_config + target: /etc/postgresql/pg_hba.conf + env_file: + - path: ./infrastructure/configs/postgresql/.env.template + required: true + - path: ./infrastructure/configs/postgresql/.env + required: false + healthcheck: + test: ["CMD", "sh", "-c", "pg_isready -U postgres -d postgres"] + interval: 30s + timeout: 5s + start_period: 5s + start_interval: 2s + retries: 5 + networks: + - default + oom_kill_disable: true + restart: unless-stopped + shm_size: 128mb + volumes: + - type: volume + source: postgresql_data + target: /var/lib/postgresql/data + + valkey: + image: docker.io/valkey/valkey:9-alpine + command: valkey-server /usr/local/etc/valkey/valkey.conf + configs: + - source: valkey_config + target: /usr/local/etc/valkey/valkey.conf + env_file: + - path: ./infrastructure/configs/valkey/.env.template + required: true + - path: ./infrastructure/configs/valkey/.env + required: false + healthcheck: + test: + ["CMD", "sh", "-c", "valkey-cli -p 6379 --pass valkey ping | grep PONG"] + interval: 10s + timeout: 2s + start_period: 5s + start_interval: 2s + retries: 3 + networks: + - default + restart: unless-stopped + shm_size: 4mb + volumes: + - type: volume + source: valkey_data + target: /data + read_only: false + + s3: + image: docker.io/rustfs/rustfs:1.0.0-alpha.82 + env_file: + - path: ./infrastructure/configs/rustfs/.env.template + required: true + - path: ./infrastructure/configs/rustfs/.env + required: false + healthcheck: + test: + [ + "CMD", + "sh", + "-c", + "curl -f http://localhost:9000/health && curl -f http://localhost:9001/rustfs/console/health", + ] + interval: 30s + timeout: 5s + start_period: 5s + start_interval: 5s + retries: 3 + ports: + - name: api + target: 9000 + published: ${RUSTFS_API_PORT} + host_ip: 127.0.0.1 + protocol: tcp + app_protocol: http + - name: console + target: 9001 + published: ${RUSTFS_CONSOLE_PORT} + host_ip: 127.0.0.1 + protocol: tcp + app_protocol: http + networks: + - default + restart: unless-stopped + shm_size: 4mb + volumes: + - type: volume + source: rustfs_data + target: /data + + s3-init: + image: docker.io/minio/mc:latest + entrypoint: > + sh -c "until mc alias set default $$S3_URL $$S3_ACCESS_KEY $$S3_SECRET_KEY; do sleep 1; done && + mc mb default/loki; + mc mb default/tempo; + mc mb default/pyroscope; + mc mb default/backend; + mc policy set public default/loki; true" + depends_on: + s3: + restart: false + condition: service_healthy + required: true + env_file: + - path: ./infrastructure/configs/s3/.env.template + required: true + - path: ./infrastructure/configs/s3/.env + required: false + networks: + - default + restart: no + shm_size: 4mb + +networks: + default: + driver: bridge + name: $COMPOSE_PROJECT_NAME + attachable: false + enable_ipv4: true + enable_ipv6: true + internal: false + +volumes: + postgresql_data: + valkey_data: + rustfs_data: + +configs: + postgresql_config: + file: ./infrastructure/configs/postgresql/postgresql.conf + postgresql_hba_config: + file: ./infrastructure/configs/postgresql/pg_hba.conf + valkey_config: + file: ./infrastructure/configs/valkey/valkey.conf diff --git a/infrastructure/.gitignore b/infrastructure/.gitignore new file mode 100644 index 0000000..8e9f998 --- /dev/null +++ b/infrastructure/.gitignore @@ -0,0 +1,2 @@ +# Custom environment files +.env diff --git a/infrastructure/configs/backend/.env.template b/infrastructure/configs/backend/.env.template new file mode 100644 index 0000000..17829f0 --- /dev/null +++ b/infrastructure/configs/backend/.env.template @@ -0,0 +1,19 @@ +SERVER_PORT=8080 + +SPRING_DATASOURCE_URL=jdbc:postgresql://postgresql:5432/postgres +SPRING_DATASOURCE_USERNAME=postgres +SPRING_DATASOURCE_PASSWORD=postgres +SPRING_DATASOURCE_DRIVER_CLASS_NAME=org.postgresql.Driver + +SPRING_DATASOURCE_HIKARI_MAXIMUM_POOL_SIZE=20 +SPRING_DATASOURCE_HIKARI_MINIMUM_IDLE=5 +SPRING_DATASOURCE_HIKARI_CONNECTION_TIMEOUT=30000 +SPRING_DATASOURCE_HIKARI_IDLE_TIMEOUT=600000 +SPRING_DATASOURCE_HIKARI_MAX_LIFETIME=1800000 + +SPRING_FLYWAY_ENABLED=true +SPRING_FLYWAY_URL=jdbc:postgresql://postgresql:5432/postgres +SPRING_FLYWAY_USER=postgres +SPRING_FLYWAY_PASSWORD=postgres +SPRING_FLYWAY_LOCATIONS=classpath:db/migration +SPRING_FLYWAY_BASELINE_ON_MIGRATE=true diff --git a/infrastructure/configs/caddy/Caddyfile b/infrastructure/configs/caddy/Caddyfile new file mode 100644 index 0000000..99bd6a5 --- /dev/null +++ b/infrastructure/configs/caddy/Caddyfile @@ -0,0 +1,51 @@ +{ + log { + output stdout + format json + level INFO + } +} + +:80 { + encode gzip zstd + + handle_path /static/* { + uri strip_prefix /static + reverse_proxy backend-staticfiles:80 { + fail_duration 30s + max_fails 10 + } + } + + handle /grafana/* { + reverse_proxy grafana:3000 { + fail_duration 30s + max_fails 10 + health_uri /api/health + health_interval 10s + health_timeout 2s + } + } + + handle { + request_body { + max_size 5976883 + } + + reverse_proxy backend:8080 { + fail_duration 30s + max_fails 10 + + health_uri /ready + health_interval 10s + health_timeout 2s + } + } +} + +:8404 { + metrics /metrics + log { + output discard + } +} diff --git a/infrastructure/configs/celery-exporter/.env.template b/infrastructure/configs/celery-exporter/.env.template new file mode 100644 index 0000000..9bd5b82 --- /dev/null +++ b/infrastructure/configs/celery-exporter/.env.template @@ -0,0 +1 @@ +CE_BROKER_URL=redis://default:valkey@valkey:6379 diff --git a/infrastructure/configs/grafana-loki/loki.yaml b/infrastructure/configs/grafana-loki/loki.yaml new file mode 100644 index 0000000..ee1ae1b --- /dev/null +++ b/infrastructure/configs/grafana-loki/loki.yaml @@ -0,0 +1,44 @@ +auth_enabled: false +pattern_ingester: + enabled: true + +server: + http_listen_port: 3100 + +common: + ring: + instance_addr: 127.0.0.1 + kvstore: + store: inmemory + replication_factor: 1 + path_prefix: /loki + storage: + s3: + endpoint: ${S3_ENDPOINT} + bucketnames: loki + access_key_id: ${S3_ACCESS_KEY} + secret_access_key: ${S3_SECRET_KEY} + insecure: true + s3forcepathstyle: true + +schema_config: + configs: + - from: 2020-05-15 + store: tsdb + object_store: s3 + schema: v13 + index: + prefix: index_ + period: 24h + +storage_config: + tsdb_shipper: + active_index_directory: /loki/index + cache_location: /loki/index_cache + +compactor: + working_directory: /loki/compactor + compaction_interval: 10m + +limits_config: + allow_structured_metadata: true diff --git a/infrastructure/configs/grafana-pyroscope/config.yaml b/infrastructure/configs/grafana-pyroscope/config.yaml new file mode 100644 index 0000000..9689fa9 --- /dev/null +++ b/infrastructure/configs/grafana-pyroscope/config.yaml @@ -0,0 +1,14 @@ +server: + http_listen_port: 4040 + +storage: + backend: s3 + s3: + bucket_name: pyroscope + endpoint: ${S3_ENDPOINT} + access_key_id: ${S3_ACCESS_KEY} + secret_access_key: ${S3_SECRET_KEY} + insecure: true + +analytics: + reporting_enabled: false diff --git a/infrastructure/configs/grafana-tempo/tempo.yaml b/infrastructure/configs/grafana-tempo/tempo.yaml new file mode 100644 index 0000000..2e6ac9a --- /dev/null +++ b/infrastructure/configs/grafana-tempo/tempo.yaml @@ -0,0 +1,64 @@ +stream_over_http_enabled: true +server: + http_listen_port: 3200 + log_level: info + +query_frontend: + search: + duration_slo: 5s + throughput_bytes_slo: 1.073741824e+09 + metadata_slo: + duration_slo: 5s + throughput_bytes_slo: 1.073741824e+09 + trace_by_id: + duration_slo: 5s + metrics: + max_duration: 120h + query_backend_after: 5m + duration_slo: 5s + throughput_bytes_slo: 1.073741824e+09 + +distributor: + receivers: + otlp: + protocols: + grpc: + endpoint: 0.0.0.0:4317 + http: + endpoint: 0.0.0.0:4318 + +ingester: + max_block_duration: 5m + +metrics_generator: + registry: + external_labels: + source: tempo + storage: + path: /var/tempo/generator/wal + traces_storage: + path: /var/tempo/generator/traces + processor: + local_blocks: + filter_server_spans: false + flush_to_storage: true + +storage: + trace: + backend: s3 + s3: + bucket: tempo + endpoint: ${S3_ENDPOINT} + access_key: ${S3_ACCESS_KEY} + secret_key: ${S3_SECRET_KEY} + insecure: true + wal: + path: /var/tempo/wal + local: + path: /var/tempo/blocks + +overrides: + defaults: + metrics_generator: + processors: [service-graphs, span-metrics, local-blocks] + generate_native_histograms: both diff --git a/infrastructure/configs/grafana/.env.template b/infrastructure/configs/grafana/.env.template new file mode 100644 index 0000000..6d940ee --- /dev/null +++ b/infrastructure/configs/grafana/.env.template @@ -0,0 +1,3 @@ +GF_SECURITY_ADMIN_PASSWORD=prooooood +GF_SERVER_ROOT_URL=http://localhost:80/grafana/ +GF_SERVER_SERVE_FROM_SUB_PATH=true diff --git a/infrastructure/configs/grafana/provisioning/alerting/contact_points.yaml b/infrastructure/configs/grafana/provisioning/alerting/contact_points.yaml new file mode 100644 index 0000000..262547a --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/alerting/contact_points.yaml @@ -0,0 +1,17 @@ +apiVersion: 1 + +contactPoints: + - orgId: 1 + name: Telegram + receivers: + - uid: aet1srtyc40lca + type: telegram + settings: + bottoken: 7797967907:AAGZuUzzuS4LLb525rDNY52Awc2tvpsLjd4 + chatid: "-1002555823797" + disable_notification: false + disable_web_page_preview: false + message: '{{ template "telegram.default.message" . }}' + parse_mode: Markdown + protect_content: false + disableResolveMessage: false diff --git a/infrastructure/configs/grafana/provisioning/alerting/rules.yaml b/infrastructure/configs/grafana/provisioning/alerting/rules.yaml new file mode 100644 index 0000000..8376d62 --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/alerting/rules.yaml @@ -0,0 +1,141 @@ +apiVersion: 1 + +groups: + - orgId: 1 + name: Default + folder: Backend + interval: 10s + rules: + - uid: aet1xbx1yaupsb + title: Backend p99 > 500 ms + condition: C + data: + - refId: A + relativeTimeRange: + from: 600 + to: 0 + datasourceUid: prometheus + model: + editorMode: code + expr: | + histogram_quantile( + 0.99, + sum( + rate( + caddy_http_request_duration_seconds_bucket{instance="proxy:2019",handler="reverse_proxy",host="proxy:8080",job="caddy"}[$__rate_interval] + ) + ) by (le) + ) + instant: true + intervalMs: 1000 + legendFormat: __auto + maxDataPoints: 43200 + range: false + refId: A + - refId: C + datasourceUid: __expr__ + model: + conditions: + - evaluator: + params: + - 0.5 + type: gte + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query + datasource: + type: __expr__ + uid: __expr__ + expression: A + intervalMs: 1000 + maxDataPoints: 43200 + refId: C + type: threshold + dashboardUid: e3a78c36-2f34-4ad6-81d5-284002896829 + panelId: 32 + noDataState: OK + execErrState: Error + for: 10s + keepFiringFor: 10s + annotations: + __dashboardUid__: e3a78c36-2f34-4ad6-81d5-284002896829 + __panelId__: "32" + runbook_url: https://admin.adnova.itqdev.xyz + summary: p99 > 500 ms + isPaused: false + notification_settings: + receiver: Telegram + - orgId: 1 + name: Default + folder: Postgres + interval: 10s + rules: + - uid: fet1txr4slywwe + title: "> 100 QPS on Postgresql" + condition: C + data: + - refId: A + relativeTimeRange: + from: 600 + to: 0 + datasourceUid: prometheus + model: + editorMode: code + expr: | + sum( + irate(pg_stat_database_xact_commit{datname="postgres",instance="postgres-exporter:9187",job="postgres"}[5m]) + ) + + sum( + irate(pg_stat_database_xact_rollback{datname="postgres",instance="postgres-exporter:9187",job="postgres"}[5m]) + ) + instant: true + intervalMs: 1000 + legendFormat: __auto + maxDataPoints: 43200 + range: false + refId: A + - refId: C + datasourceUid: __expr__ + model: + conditions: + - evaluator: + params: + - 100 + type: gte + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query + datasource: + type: __expr__ + uid: __expr__ + expression: A + intervalMs: 1000 + maxDataPoints: 43200 + refId: C + type: threshold + dashboardUid: postgres-overview + panelId: 14 + noDataState: NoData + execErrState: Error + for: 10s + keepFiringFor: 1m + annotations: + __dashboardUid__: postgres-overview + __panelId__: "14" + runbook_url: https://admin.adnova.itqdev.xyz + summary: Postgresql QPS exceeded 100 + isPaused: false + notification_settings: + receiver: Telegram diff --git a/infrastructure/configs/grafana/provisioning/alerting/templates.yaml b/infrastructure/configs/grafana/provisioning/alerting/templates.yaml new file mode 100644 index 0000000..b1ade37 --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/alerting/templates.yaml @@ -0,0 +1,54 @@ +apiVersion: 1 + +templates: + - orgId: 1 + name: Telegram + template: | + {{ define "telegram.default.message" }} {{ if gt (len .Alerts.Firing) 0 }} + 🔥🚨 *FIRE IN THE HOLE!* 🚨🔥 + We've got *{{ len .Alerts.Firing }} firing alert(s)* that need your immediate attention! + {{ range .Alerts.Firing }} + --- + *Alert:* `{{ .Labels.alertname }}` + {{ if .Labels.instance }}*Instance:* `{{ .Labels.instance }}`{{ end }} + *Status:* 🔴 *FIRING* since {{ .StartsAt.Format "2006-01-02 15:04:05 MST" }} + + {{ if .Annotations.summary }}*Summary:* {{ .Annotations.summary }}{{ end }} + {{ if .Annotations.description }}*Description:* {{ .Annotations.description }}{{ end }} + *Labels:* + {{ range .Labels.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}` + {{ end }} + {{ if gt (len .Annotations) 0 }}*Annotations:* + {{ range .Annotations.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}` + {{ end }}{{ end }} + + {{ if .DashboardURL }}📊 [View Dashboard]({{ .DashboardURL }}) + {{ end }}{{ if .PanelURL }}📈 [View Panel]({{ .PanelURL }}) + {{ end }}{{ if .GeneratorURL }}🔗 [Alert Source]({{ .GeneratorURL }}) + {{ end }}{{ if .SilenceURL }}🤫 [Silence Alert]({{ .SilenceURL }}) + {{ end }}--- {{ end }} {{ end }} + {{ if gt (len .Alerts.Resolved) 0 }} + ✅🟢 *ALL CLEAR!* 🟢✅ + Great news! *{{ len .Alerts.Resolved }} alert(s)* have been resolved. + {{ range .Alerts.Resolved }} + --- + *Alert:* `{{ .Labels.alertname }}` + {{ if .Labels.instance }}*Instance:* `{{ .Labels.instance }}`{{ end }} + *Status:* ✅ *RESOLVED* at {{ .EndsAt.Format "2006-01-02 15:04:05 MST" }} (was active since {{ .StartsAt.Format "2006-01-02 15:04:05 MST" }}) + + {{ if .Annotations.summary }}*Summary:* {{ .Annotations.summary }}{{ end }} + {{ if .Annotations.description }}*Description:* {{ .Annotations.description }}{{ end }} + *Labels:* + {{ range .Labels.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}` + {{ end }} + {{ if gt (len .Annotations) 0 }}*Annotations:* + {{ range .Annotations.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}` + {{ end }}{{ end }} + + {{ if .DashboardURL }}📊 [View Dashboard]({{ .DashboardURL }}) + {{ end }}{{ if .PanelURL }}📈 [View Panel]({{ .PanelURL }}) + {{ end }}{{ if .GeneratorURL }}🔗 [Alert Source]({{ .GeneratorURL }}) {{ end }} {{ end }} {{ end }} + {{ if or (gt (len .Alerts.Firing) 0) (gt (len .Alerts.Resolved) 0) }} + 🔔 *Grafana Alertmanager:* [View All Alerts]({{ template "__alertmanagerURL" . }}) 🔔 + {{ end }} + {{ end }} diff --git a/infrastructure/configs/grafana/provisioning/dashboards/Celery/by-task.json b/infrastructure/configs/grafana/provisioning/dashboards/Celery/by-task.json new file mode 100644 index 0000000..485755b --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/dashboards/Celery/by-task.json @@ -0,0 +1,768 @@ +{ + "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": "A dashboard that monitors Celery.", + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 0, + "id": 2, + "links": [ + { + "tags": ["celery"], + "targetBlank": true, + "title": "Celery Dashboards", + "type": "dashboards" + } + ], + "liveNow": true, + "panels": [ + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 1, + "panels": [], + "title": "Tasks", + "type": "row" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Success Rate" + }, + "properties": [ + { + "id": "unit", + "value": "percentunit" + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 16, + "x": 0, + "y": 1 + }, + "id": 2, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "enablePagination": true, + "fields": "", + "reducer": ["sum"], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "Succeeded" + } + ] + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name)\n/(sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name)\n+sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name)\n) > -1\n", + "format": "table", + "instant": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "C" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_sent_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "D" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_received_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "E" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_rejected_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "F" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_retried_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "G" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_revoked_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "H" + } + ], + "title": "Task Stats", + "transformations": [ + { + "id": "merge" + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "Value #A": 1, + "Value #B": 2, + "Value #C": 3, + "Value #D": 4, + "Value #E": 5, + "Value #F": 6, + "Value #G": 7, + "Value #H": 8, + "name": 0 + }, + "renameByName": { + "Value #A": "Success Rate", + "Value #B": "Succeeded", + "Value #C": "Failed", + "Value #D": "Sent", + "Value #E": "Received", + "Value #F": "Rejected", + "Value #G": "Retried", + "Value #H": "Revoked", + "name": "Name" + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 16, + "y": 1 + }, + "id": 3, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "enablePagination": true, + "fields": "", + "reducer": ["sum"], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "Value" + } + ] + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "round(\n sum (\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n ) by (name, exception) > 0\n)\n", + "format": "table", + "instant": true, + "refId": "A" + } + ], + "title": "Task Exceptions", + "transformations": [ + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true, + "job": true + }, + "indexByName": { + "Value": 2, + "exception": 1, + "name": 0 + }, + "renameByName": { + "exception": "Exception", + "name": "Task" + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 9 + }, + "id": 4, + "options": { + "legend": { + "calcs": ["mean", "max"], + "displayMode": "table", + "placement": "right", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n", + "legendFormat": "Succeeded - {{ name }}", + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n", + "legendFormat": "Failed - {{ name }}", + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_sent_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n", + "legendFormat": "Sent - {{ name }}", + "refId": "C" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_received_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n", + "legendFormat": "Received - {{ name }}", + "refId": "D" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_retried_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n", + "legendFormat": "Retried - {{ name }}", + "refId": "E" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_revoked_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n", + "legendFormat": "Revoked - {{ name }}", + "refId": "F" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_rejected_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n", + "legendFormat": "Rejected - {{ name }}", + "refId": "G" + } + ], + "title": "Tasks Completed", + "type": "timeseries" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "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": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 17 + }, + "id": 5, + "options": { + "legend": { + "calcs": ["mean", "max"], + "displayMode": "table", + "placement": "right", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name, exception) > 0\n", + "legendFormat": "{{ name }}/{{ exception }}", + "refId": "A" + } + ], + "title": "Task Exceptions", + "type": "timeseries" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "spanNulls": false + }, + "unit": "s" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "P50" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "green", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "P95" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "yellow", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "P99" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "red", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 25 + }, + "id": 6, + "options": { + "legend": { + "calcs": ["mean", "max"], + "displayMode": "table", + "placement": "right", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "v11.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "histogram_quantile(0.50,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (name, job, le)\n)\n", + "legendFormat": "P50 - {{ name }}", + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "histogram_quantile(0.95,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (name, job, le)\n)\n", + "legendFormat": "P95 - {{ name }}", + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "histogram_quantile(0.99,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (name, job, le)\n)\n", + "legendFormat": "P99 - {{ name }}", + "refId": "C" + } + ], + "title": "Tasks Runtime", + "type": "timeseries" + } + ], + "preload": false, + "refresh": "10s", + "schemaVersion": 41, + "tags": ["celery"], + "templating": { + "list": [ + { + "label": "Data source", + "name": "datasource", + "query": "prometheus", + "refresh": 1, + "type": "datasource" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${datasource}" + }, + "includeAll": false, + "label": "Namespace", + "name": "namespace", + "query": "label_values(celery_worker_up{}, namespace)", + "refresh": 2, + "sort": 1, + "type": "query" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${datasource}" + }, + "includeAll": false, + "label": "Job", + "name": "job", + "query": "label_values(celery_worker_up{namespace=\"$namespace\"}, job)", + "refresh": 2, + "sort": 1, + "type": "query" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${datasource}" + }, + "includeAll": false, + "label": "Queue Name", + "name": "queue_name", + "query": "label_values(celery_task_received_total{namespace=\"$namespace\", job=\"$job\", name!~\"None\"}, queue_name)", + "refresh": 2, + "sort": 1, + "type": "query" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${datasource}" + }, + "includeAll": false, + "label": "Task", + "multi": true, + "name": "task", + "query": "label_values(celery_task_received_total{namespace=\"$namespace\", job=\"$job\", queue_name=~\"$queue_name\", name!~\"None\"}, name)", + "refresh": 2, + "sort": 1, + "type": "query" + } + ] + }, + "time": { + "from": "now-24h", + "to": "now" + }, + "timepicker": {}, + "timezone": "browser", + "title": "By Task", + "uid": "celery-tasks-by-task", + "version": 1, + "weekStart": "monday" +} diff --git a/infrastructure/configs/grafana/provisioning/dashboards/Celery/overview.json b/infrastructure/configs/grafana/provisioning/dashboards/Celery/overview.json new file mode 100644 index 0000000..b582169 --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/dashboards/Celery/overview.json @@ -0,0 +1,1224 @@ +{ + "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": "A dashboard that monitors Celery.", + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 0, + "id": 3, + "links": [ + { + "tags": ["celery"], + "targetBlank": true, + "title": "Celery Dashboards", + "type": "dashboards" + } + ], + "liveNow": true, + "panels": [ + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 1, + "panels": [], + "title": "Summary", + "type": "row" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 0.1 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 0, + "y": 1 + }, + "id": 2, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "count(\n celery_worker_up{\n job=\"$job\",\n } == 1\n)\n", + "refId": "A" + } + ], + "title": "Workers", + "type": "stat" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 0.1 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 5, + "y": 1 + }, + "id": 3, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum(\n celery_worker_tasks_active{\n job=\"$job\",\n }\n)\n", + "refId": "A" + } + ], + "title": "Tasks Active", + "type": "stat" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 0.1 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 10, + "y": 1 + }, + "id": 4, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum(\n round(\n increase(\n celery_task_received_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n )\n)\n", + "refId": "A" + } + ], + "title": "Tasks received by workers [1w]", + "type": "stat" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "yellow", + "value": 0.95 + }, + { + "color": "green", + "value": 0.99 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 15, + "y": 1 + }, + "id": 5, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum(\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n )\n)\n/(sum(\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n )\n)\n+sum(\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n )\n)\n)\n", + "refId": "A" + } + ], + "title": "Tasks Success Rate [1w]", + "type": "stat" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 0.1 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 20, + "y": 1 + }, + "id": 6, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum(\n rate(\n celery_task_runtime_sum{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n)\n/\nsum(\n rate(\n celery_task_runtime_count{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n) > 0\n", + "refId": "A" + } + ], + "title": "Average Runtime for Tasks [1w]", + "type": "stat" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Task" + }, + "properties": [ + { + "id": "links", + "value": [ + { + "targetBlank": true, + "title": "Go To View", + "type": "dashboard", + "url": "/d/celery-tasks-by-task/by-task?var-task=${__data.fields.Task}" + } + ] + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 0, + "y": 5 + }, + "id": 7, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "enablePagination": true, + "fields": "", + "reducer": ["sum"], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "Value" + } + ] + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "round(\n sum (\n increase(\n celery_task_failed_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n ) > 0\n ) by (job, name)\n)\n", + "format": "table", + "instant": true, + "refId": "A" + } + ], + "title": "Top Failed Tasks [1w]", + "transformations": [ + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true, + "job": true + }, + "indexByName": { + "Value": 1, + "name": 0 + }, + "renameByName": { + "name": "Task" + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 8, + "y": 5 + }, + "id": 8, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "enablePagination": true, + "fields": "", + "reducer": ["sum"], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "Value" + } + ] + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "round(\n sum (\n increase(\n celery_task_failed_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n ) by (job, exception) > 0\n)\n", + "format": "table", + "instant": true, + "refId": "A" + } + ], + "title": "Top Task Exceptions [1w]", + "transformations": [ + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true, + "job": true + }, + "indexByName": { + "Value": 1, + "exception": 0 + }, + "renameByName": { + "exception": "Exception" + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Task" + }, + "properties": [ + { + "id": "links", + "value": [ + { + "targetBlank": true, + "title": "Go To Task", + "type": "dashboard", + "url": "/d/celery-tasks-by-task/by-task?var-task=${__data.fields.Task}" + } + ] + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 16, + "y": 5 + }, + "id": 9, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "enablePagination": true, + "fields": "", + "reducer": ["sum"], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "Runtime" + } + ] + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n rate(\n celery_task_runtime_sum{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n) by(name)\n/\nsum (\n rate(\n celery_task_runtime_count{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[1w]\n )\n) by (name) > 0\n", + "format": "table", + "instant": true, + "refId": "A" + } + ], + "title": "Top Average Task Runtime [1w]", + "transformations": [ + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "Value": 1, + "name": 0 + }, + "renameByName": { + "Value": "Runtime", + "name": "Task" + } + } + } + ], + "type": "table" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 13 + }, + "id": 10, + "panels": [], + "title": "Queues", + "type": "row" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "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": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 6, + "w": 24, + "x": 0, + "y": 14 + }, + "id": 11, + "options": { + "legend": { + "calcs": ["mean", "max"], + "displayMode": "table", + "placement": "right", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n celery_queue_length{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }\n) by (job, queue_name)\n", + "legendFormat": "{{ job }}/{{ queue_name }}", + "refId": "A" + } + ], + "title": "Queue Length", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 20 + }, + "id": 12, + "panels": [], + "title": "Tasks", + "type": "row" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "noValue": 0, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Success Rate" + }, + "properties": [ + { + "id": "unit", + "value": "percentunit" + } + ] + } + ] + }, + "gridPos": { + "h": 4, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 13, + "options": { + "sortBy": [ + { + "desc": true, + "displayName": "Succeeded" + } + ] + }, + "pluginVersion": "v11.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job)\n/(sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job)\n+sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job)\n) > -1\n", + "format": "table", + "instant": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job) > 0\n", + "format": "table", + "instant": true, + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job) > 0\n", + "format": "table", + "instant": true, + "refId": "C" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_sent_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job) > 0\n", + "format": "table", + "instant": true, + "refId": "D" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_received_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job) > 0\n", + "format": "table", + "instant": true, + "refId": "E" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_rejected_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job) > 0\n", + "format": "table", + "instant": true, + "refId": "F" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_retried_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job) > 0\n", + "format": "table", + "instant": true, + "refId": "G" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_revoked_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (job) > 0\n", + "format": "table", + "instant": true, + "refId": "H" + } + ], + "title": "Task Stats", + "transformations": [ + { + "id": "merge" + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "Value #A": 1, + "Value #B": 2, + "Value #C": 3, + "Value #D": 4, + "Value #E": 5, + "Value #F": 6, + "Value #G": 7, + "Value #H": 8, + "job": 0 + }, + "renameByName": { + "Value #A": "Success Rate", + "Value #B": "Succeeded", + "Value #C": "Failed", + "Value #D": "Sent", + "Value #E": "Received", + "Value #F": "Rejected", + "Value #G": "Retried", + "Value #H": "Revoked", + "job": "Job" + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "spanNulls": false + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 10, + "w": 24, + "x": 0, + "y": 25 + }, + "id": 14, + "options": { + "legend": { + "calcs": ["mean", "max"], + "displayMode": "table", + "placement": "right", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "v11.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n)\n", + "legendFormat": "Succeeded", + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n)\n", + "legendFormat": "Failed", + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_sent_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n)\n", + "legendFormat": "Sent", + "refId": "C" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_received_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n)\n", + "legendFormat": "Received", + "refId": "D" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_retried_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n)\n", + "legendFormat": "Retried", + "refId": "E" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_revoked_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n)\n", + "legendFormat": "Revoked", + "refId": "F" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "sum (\n round(\n increase(\n celery_task_rejected_total{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n)\n", + "legendFormat": "Rejected", + "refId": "G" + } + ], + "title": "Tasks Completed", + "type": "timeseries" + }, + { + "datasource": { + "type": "datasource", + "uid": "-- Mixed --" + }, + "fieldConfig": { + "defaults": { + "custom": { + "spanNulls": false + }, + "unit": "s" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "P50" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "green", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "P95" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "yellow", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "P99" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "red", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 10, + "w": 24, + "x": 0, + "y": 35 + }, + "id": 15, + "options": { + "legend": { + "calcs": ["mean", "max"], + "displayMode": "table", + "placement": "right", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "v11.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "histogram_quantile(0.50,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (job, le)\n)\n", + "legendFormat": "P50", + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "histogram_quantile(0.95,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (job, le)\n)\n", + "legendFormat": "P95", + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "expr": "histogram_quantile(0.99,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (job, le)\n)\n", + "legendFormat": "P99", + "refId": "C" + } + ], + "title": "Tasks Runtime", + "type": "timeseries" + } + ], + "preload": false, + "refresh": "10s", + "schemaVersion": 41, + "tags": ["celery"], + "templating": { + "list": [ + { + "label": "Data source", + "name": "datasource", + "query": "prometheus", + "refresh": 1, + "type": "datasource" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${datasource}" + }, + "includeAll": false, + "label": "Namespace", + "name": "namespace", + "query": "label_values(celery_worker_up{}, namespace)", + "refresh": 2, + "sort": 1, + "type": "query" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${datasource}" + }, + "includeAll": false, + "label": "Job", + "name": "job", + "query": "label_values(celery_worker_up{namespace=\"$namespace\"}, job)", + "refresh": 2, + "sort": 1, + "type": "query" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${datasource}" + }, + "includeAll": false, + "label": "Queue Name", + "name": "queue_name", + "query": "label_values(celery_task_received_total{namespace=\"$namespace\", job=\"$job\", name!~\"None\"}, queue_name)", + "refresh": 2, + "sort": 1, + "type": "query" + } + ] + }, + "time": { + "from": "now-24h", + "to": "now" + }, + "timepicker": {}, + "timezone": "browser", + "title": "Overview", + "uid": "celery-tasks-overview", + "version": 1, + "weekStart": "monday" +} diff --git a/infrastructure/configs/grafana/provisioning/dashboards/Postgres/overview.json b/infrastructure/configs/grafana/provisioning/dashboards/Postgres/overview.json new file mode 100644 index 0000000..d49a287 --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/dashboards/Postgres/overview.json @@ -0,0 +1,1416 @@ +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "datasource", + "uid": "grafana" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "A PostgreSQL dashboard.", + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 0, + "id": 4, + "links": [], + "liveNow": true, + "panels": [ + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 20, + "x": 0, + "y": 0 + }, + "id": 1, + "options": { + "alertThreshold": true, + "legend": { + "calcs": ["mean", "max", "min"], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "alias": "fetched", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_fetched{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "fetched", + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["tup_fetched"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": ["10s"], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "fetched", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_returned{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "returned", + "measurement": "postgresql", + "policy": "default", + "refId": "B", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["tup_fetched"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": ["10s"], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "fetched", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_inserted{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "inserted", + "measurement": "postgresql", + "policy": "default", + "refId": "C", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["tup_fetched"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": ["10s"], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "fetched", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_updated{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "updated", + "measurement": "postgresql", + "policy": "default", + "refId": "D", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["tup_fetched"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": ["10s"], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "fetched", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_deleted{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "deleted", + "measurement": "postgresql", + "policy": "default", + "refId": "E", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["tup_fetched"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": ["10s"], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + } + ], + "title": "Rows", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "fixedColor": "rgb(31, 120, 193)", + "mode": "fixed" + }, + "decimals": 0, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 20, + "y": 0 + }, + "id": 11, + "maxDataPoints": 100, + "options": { + "colorMode": "none", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["mean"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_xact_commit{datname=~\"$db\",instance=~\"$instance\"}[5m])) + sum(irate(pg_stat_database_xact_rollback{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["xact_commit"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": ["10s"], + "type": "non_negative_derivative" + } + ] + ], + "step": 1800, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + } + ], + "title": "QPS", + "transparent": true, + "type": "stat" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "fixedColor": "rgb(31, 120, 193)", + "mode": "fixed" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "smooth", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 7 + }, + "id": 14, + "maxDataPoints": 100, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": false + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_xact_commit{datname=~\"$db\",instance=~\"$instance\"}[5m])) + sum(irate(pg_stat_database_xact_rollback{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["xact_commit"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": ["10s"], + "type": "non_negative_derivative" + } + ] + ], + "step": 1800, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + } + ], + "title": "QPS", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byValue", + "options": { + "op": "gte", + "reducer": "allIsZero", + "value": 0 + } + }, + "properties": [ + { + "id": "custom.hideFrom", + "value": { + "legend": true, + "tooltip": true, + "viz": false + } + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 16 + }, + "id": 2, + "options": { + "alertThreshold": true, + "legend": { + "calcs": ["mean", "max", "min"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "alias": "Buffers Allocated", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_alloc{instance=~'$instance'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_alloc", + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["buffers_alloc"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_backend_fsync{instance=~'$instance'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_backend_fsync", + "measurement": "postgresql", + "policy": "default", + "refId": "B", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["buffers_alloc"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_backend{instance=~'$instance'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_backend", + "measurement": "postgresql", + "policy": "default", + "refId": "C", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["buffers_alloc"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_clean{instance=~'$instance'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_clean", + "measurement": "postgresql", + "policy": "default", + "refId": "D", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["buffers_alloc"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_checkpoint{instance=~'$instance'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_checkpoint", + "measurement": "postgresql", + "policy": "default", + "refId": "E", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["buffers_alloc"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + } + ], + "title": "Buffers", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 16 + }, + "id": 3, + "options": { + "alertThreshold": true, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "alias": "conflicts", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(rate(pg_stat_database_deadlocks{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "deadlocks", + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["conflicts"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + }, + { + "alias": "deadlocks", + "datasource": { + "uid": "$datasource" + }, + "dsType": "prometheus", + "expr": "sum(rate(pg_stat_database_conflicts{datname=~\"$db\",instance=~\"$instance\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": ["$interval"], + "type": "time" + }, + { + "params": ["null"], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "conflicts", + "measurement": "postgresql", + "policy": "default", + "refId": "B", + "resultFormat": "time_series", + "select": [ + [ + { + "params": ["deadlocks"], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "instance", + "operator": "=~", + "value": "/^$instance$/" + } + ] + } + ], + "title": "Conflicts/Deadlocks", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 23 + }, + "id": 12, + "options": { + "alertThreshold": true, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$instance\"}) / (sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$instance\"}) + sum(pg_stat_database_blks_read{datname=~\"$db\",instance=~\"$instance\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "cache hit rate", + "refId": "A", + "step": 240 + } + ], + "title": "Cache hit ratio", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 23 + }, + "id": 13, + "options": { + "alertThreshold": true, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "pg_stat_database_numbackends{datname=~\"$db\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "A", + "step": 240 + } + ], + "title": "Number of active connections", + "type": "timeseries" + } + ], + "preload": false, + "refresh": "5s", + "schemaVersion": 41, + "tags": ["postgres"], + "templating": { + "list": [ + { + "includeAll": false, + "label": "Data Source", + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "datasource": "$datasource", + "definition": "", + "includeAll": true, + "label": "Instance", + "name": "instance", + "options": [], + "query": "label_values(up{job=~\"postgres.*\"},instance)", + "refresh": 1, + "regex": "", + "type": "query" + }, + { + "allValue": ".*", + "datasource": "$datasource", + "definition": "label_values(pg_stat_database_tup_fetched{instance=~\"$instance\",datname!~\"template.*|postgres\"},datname)", + "includeAll": true, + "label": "Database", + "name": "db", + "options": [], + "query": "label_values(pg_stat_database_tup_fetched{instance=~\"$instance\",datname!~\"template.*|postgres\"},datname)", + "refresh": 1, + "regex": "", + "type": "query" + }, + { + "datasource": "$datasource", + "definition": "label_values(pg_up, job)", + "includeAll": false, + "label": "Job", + "name": "job", + "options": [], + "query": "label_values(pg_up, job)", + "refresh": 1, + "regex": "", + "type": "query" + } + ] + }, + "time": { + "from": "now-30m", + "to": "now" + }, + "timepicker": {}, + "timezone": "browser", + "title": "Overview", + "uid": "postgres-overview", + "version": 2, + "weekStart": "monday" +} diff --git a/infrastructure/configs/grafana/provisioning/dashboards/Valkey/overview.json b/infrastructure/configs/grafana/provisioning/dashboards/Valkey/overview.json new file mode 100644 index 0000000..23ad194 --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/dashboards/Valkey/overview.json @@ -0,0 +1,1551 @@ +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "datasource", + "uid": "grafana" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "A Redis overview dashboard.", + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 1, + "id": 3, + "links": [], + "liveNow": true, + "panels": [ + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 24, + "panels": [], + "title": "Performance", + "type": "row" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Average taken across instances", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 1 + }, + "id": 18, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "avg(irate(redis_commands_total{instance=~\"$instance\"} [1m])) by (cmd)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{cmd}}", + "metric": "redis_command_calls_total", + "refId": "A", + "step": 240 + } + ], + "title": "Commands per second", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Average taken across instances", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [ + { + "matcher": { + "id": "byValue", + "options": { + "op": "gte", + "reducer": "allIsZero", + "value": 0 + } + }, + "properties": [ + { + "id": "custom.hideFrom", + "value": { + "legend": true, + "tooltip": true, + "viz": false + } + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 1 + }, + "id": 20, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "avg(irate(redis_commands_duration_seconds_total{instance=~\"$instance\"}[1m])) by (cmd)\n /\navg(irate(redis_commands_total{instance=~\"$instance\"}[1m])) by (cmd)\n", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{ cmd }}", + "metric": "redis_command_calls_total", + "refId": "A", + "step": 240 + } + ], + "title": "Command latency per second", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Hit rate shows the percentage of key space lookups that hit a key.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Hit ratio" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "blue", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/Target/" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#56A64B", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineWidth", + "value": 1 + }, + { + "id": "custom.lineStyle", + "value": { + "dash": [10, 10], + "fill": "dash" + } + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 1 + }, + "id": 1, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "avg(irate(redis_keyspace_hits_total{instance=~\"$instance\"}[1m]) / (irate(redis_keyspace_misses_total{instance=~\"$instance\"}[1m]) + irate(redis_keyspace_hits_total{instance=~\"$instance\"}[1m]))) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "metric": "", + "refId": "A", + "step": 240, + "target": "" + }, + { + "datasource": { + "uid": "$datasource" + }, + "expr": "1", + "interval": "", + "legendFormat": "Target hit ratio for cache", + "refId": "B" + } + ], + "title": "Hit ratio per instance", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 8 + }, + "id": 22, + "panels": [], + "title": "Memory", + "type": "row" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Total taken across instances", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "max" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#BF1B00", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/max/" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineWidth", + "value": 1 + }, + { + "id": "custom.lineStyle", + "value": { + "dash": [10, 10], + "fill": "dash" + } + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 9 + }, + "id": 7, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(redis_memory_used_bytes{instance=~\"$instance\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Used Memory", + "metric": "", + "refId": "A", + "step": 240, + "target": "" + }, + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(redis_memory_max_bytes{instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Configured max memory", + "refId": "B", + "step": 240 + }, + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(redis_memory_used_rss_bytes{instance=~\"$instance\"})", + "interval": "", + "legendFormat": "Used RSS memory", + "refId": "C" + } + ], + "title": "Total Memory Usage", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Recommend restart redis" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "red", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/restart/" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineWidth", + "value": 1 + }, + { + "id": "custom.lineStyle", + "value": { + "dash": [10, 10], + "fill": "dash" + } + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 9 + }, + "id": 10, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "redis_memory_fragmentation_ratio{instance=~\"$instance\"}", + "hide": false, + "interval": "", + "legendFormat": "{{instance}}", + "refId": "C" + } + ], + "title": "Memory fragmentation ratio per instance", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Evictions" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "red", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "evicts" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#890F02", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "memcached_items_evicted_total{instance=\"172.17.0.1:9150\",job=\"prometheus\"}" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#890F02", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "reclaims" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#3F6833", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "{container=\"redis-exporter\", instance=\"redis-86cb5d76d7-fcdln:redis-exporter:redis-metrics\", job=\"default/redis\", namespace=\"default\", pod=\"redis-86cb5d76d7-fcdln\"}" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "red", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "{instance=\"redis-86cb5d76d7-fcdln:redis-exporter:redis-metrics\"}" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "red", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "reclaims" + }, + "properties": [ + { + "id": "custom.axisPlacement", + "value": "right" + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 9 + }, + "id": 8, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "irate(redis_evicted_keys_total{instance=~\"$instance\"}[1m])", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "B", + "step": 240 + } + ], + "title": "Key evictions per second per instance", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 16 + }, + "id": 26, + "panels": [], + "title": "Basic activity", + "type": "row" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Sum taken across instances", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 17 + }, + "id": 16, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(redis_connected_clients{instance=~\"$instance\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "Connected", + "refId": "A" + }, + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(redis_blocked_clients{instance=~\"$instance\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "Blocked", + "refId": "B" + } + ], + "title": "Connected/Blocked Clients", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Sum taken across instances", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "db1" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "yellow", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byValue", + "options": { + "op": "gte", + "reducer": "allIsZero", + "value": 0 + } + }, + "properties": [ + { + "id": "custom.hideFrom", + "value": { + "legend": true, + "tooltip": true, + "viz": false + } + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 17 + }, + "id": 5, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "asc" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum (redis_db_keys{instance=~\"$instance\"}) by (db)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{ db }}", + "refId": "A", + "step": 240, + "target": "" + } + ], + "title": "Total Items per DB", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Sum taken across instances", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 17 + }, + "id": 13, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum (redis_db_keys{instance=~\"$instance\"}) - sum (redis_db_keys_expiring{instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "Not expiring", + "refId": "A", + "step": 240, + "target": "" + }, + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(redis_db_keys_expiring{instance=~\"$instance\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Expiring", + "metric": "", + "refId": "B", + "step": 240 + } + ], + "title": "Expiring vs Not-Expiring Keys", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "This metric will only be non-zero if the instance is a master", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 24 + }, + "id": 28, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(redis_connected_slaves{instance=~\"$instance\"}) by (instance)", + "interval": "", + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Connected slaves by instance", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "This metric is only exported if the instance is a slave.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 24 + }, + "id": 30, + "options": { + "dataLinks": [], + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.2", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "expr": "redis_master_last_io_seconds_ago{instance=~\"$instance\"}", + "interval": "", + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Time since last master connection", + "type": "timeseries" + } + ], + "preload": false, + "refresh": "5s", + "schemaVersion": 41, + "tags": ["redis"], + "templating": { + "list": [ + { + "includeAll": false, + "label": "Data Source", + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "datasource": "${datasource}", + "definition": "label_values(redis_up, instance)", + "includeAll": false, + "label": "Instance", + "multi": true, + "name": "instance", + "options": [], + "query": "label_values(redis_up, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "type": "query" + } + ] + }, + "time": { + "from": "now-30m", + "to": "now" + }, + "timepicker": {}, + "timezone": "browser", + "title": "Overview", + "uid": "redis-overview", + "version": 4, + "weekStart": "monday" +} diff --git a/infrastructure/configs/grafana/provisioning/dashboards/providers.yaml b/infrastructure/configs/grafana/provisioning/dashboards/providers.yaml new file mode 100644 index 0000000..958af91 --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/dashboards/providers.yaml @@ -0,0 +1,13 @@ +apiVersion: 1 + +providers: + - name: default + orgId: 1 + folder: "" + type: file + disableDeletion: false + updateIntervalSeconds: 10 + allowUiUpdates: false + options: + path: /etc/grafana/provisioning/dashboards + foldersFromFilesStructure: true diff --git a/infrastructure/configs/grafana/provisioning/datasources/loki.yaml b/infrastructure/configs/grafana/provisioning/datasources/loki.yaml new file mode 100755 index 0000000..a173541 --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/datasources/loki.yaml @@ -0,0 +1,13 @@ +apiVersion: 1 +prune: true + +datasources: +- name: Grafana Loki + type: loki + access: proxy + orgId: 1 + uid: loki + url: http://grafana-loki:3100 + isDefault: false + version: 1 + editable: false diff --git a/infrastructure/configs/grafana/provisioning/datasources/pyroscope.yaml b/infrastructure/configs/grafana/provisioning/datasources/pyroscope.yaml new file mode 100644 index 0000000..676288e --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/datasources/pyroscope.yaml @@ -0,0 +1,15 @@ +apiVersion: 1 +prune: true + +datasources: +- name: Pyroscope + type: grafana-pyroscope-datasource + access: proxy + orgId: 1 + uid: pyroscope + url: http://grafana-pyroscope:4040 + isDefault: false + version: 1 + editable: false + jsonData: + minStep: 15s diff --git a/infrastructure/configs/grafana/provisioning/datasources/tempo.yaml b/infrastructure/configs/grafana/provisioning/datasources/tempo.yaml new file mode 100755 index 0000000..64a988c --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/datasources/tempo.yaml @@ -0,0 +1,13 @@ +apiVersion: 1 +prune: true + +datasources: +- name: Grafana Tempo + type: tempo + access: proxy + orgId: 1 + uid: tempo + url: http://grafana-tempo:3200 + isDefault: false + version: 1 + editable: false diff --git a/infrastructure/configs/grafana/provisioning/datasources/victoriametrics.yaml b/infrastructure/configs/grafana/provisioning/datasources/victoriametrics.yaml new file mode 100755 index 0000000..5bb557a --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/datasources/victoriametrics.yaml @@ -0,0 +1,19 @@ +apiVersion: 1 +prune: true + +datasources: +- name: VictoriaMetrics + type: prometheus + access: proxy + orgId: 1 + uid: victoriametrics + url: http://victoriametrics:8428 + basicAuth: false + basicAuthUser: "" + withCredentials: false + isDefault: true + editable: false + jsonData: + httpMethod: POST + queryTimeout: 10s + timeInterval": 10s diff --git a/infrastructure/configs/grafana/provisioning/plugins/plugins.yaml b/infrastructure/configs/grafana/provisioning/plugins/plugins.yaml new file mode 100644 index 0000000..2e4bd2f --- /dev/null +++ b/infrastructure/configs/grafana/provisioning/plugins/plugins.yaml @@ -0,0 +1,5 @@ +apiVersion: 1 + +apps: + - type: yesoreyeram-infinity-datasource + orgId: 1 diff --git a/infrastructure/configs/grafana/scripts/entrypoint.sh b/infrastructure/configs/grafana/scripts/entrypoint.sh new file mode 100755 index 0000000..b0e9383 --- /dev/null +++ b/infrastructure/configs/grafana/scripts/entrypoint.sh @@ -0,0 +1,9 @@ +#!/usr/bin/env sh + +set -e + +echo "Installing Grafana plugins..." +grafana cli plugins install yesoreyeram-infinity-datasource + +echo "Starting Grafana..." +exec /run.sh diff --git a/infrastructure/configs/otel-collector/config.yaml b/infrastructure/configs/otel-collector/config.yaml new file mode 100644 index 0000000..d34460b --- /dev/null +++ b/infrastructure/configs/otel-collector/config.yaml @@ -0,0 +1,65 @@ +receivers: + otlp: + protocols: + grpc: + endpoint: 0.0.0.0:4317 + http: + endpoint: 0.0.0.0:4318 + +processors: + batch: + timeout: 1s + send_batch_size: 1024 + +exporters: + otlphttp/loki: + endpoint: http://grafana-loki:3100/otlp + tls: + insecure: true + otlphttp/tempo: + endpoint: http://grafana-tempo:4318 + tls: + insecure: true + prometheusremotewrite: + endpoint: http://victoriametrics:8428/api/v1/write + tls: + insecure: true + +extensions: + health_check: + endpoint: 0.0.0.0:13133 + path: /health + response_body: + healthy: '{"status": "healthy"}' + unhealthy: '{"status": "unhealthy"}' + pprof: + endpoint: 0.0.0.0:1777 + zpages: + endpoint: 0.0.0.0:55679 + +service: + extensions: [health_check, pprof, zpages] + + pipelines: + traces: + receivers: [otlp] + processors: [batch] + exporters: [otlphttp/tempo] + logs: + receivers: [otlp] + processors: [batch] + exporters: [otlphttp/loki] + metrics: + receivers: [otlp] + processors: [batch] + exporters: [prometheusremotewrite] + + telemetry: + metrics: + level: detailed + readers: + - pull: + exporter: + prometheus: + host: 0.0.0.0 + port: 8888 diff --git a/infrastructure/configs/pgadmin/.env.template b/infrastructure/configs/pgadmin/.env.template new file mode 100644 index 0000000..292edfa --- /dev/null +++ b/infrastructure/configs/pgadmin/.env.template @@ -0,0 +1,4 @@ +PGADMIN_DEFAULT_EMAIL=admin@mail.com +PGADMIN_DEFAULT_PASSWORD=password +PGADMIN_DISABLE_POSTFIX=True +PGADMIN_REPLACE_SERVERS_ON_STARTUP=True diff --git a/infrastructure/configs/pgadmin/servers.json b/infrastructure/configs/pgadmin/servers.json new file mode 100644 index 0000000..f735178 --- /dev/null +++ b/infrastructure/configs/pgadmin/servers.json @@ -0,0 +1,18 @@ +{ + "Servers": { + "1": { + "Name": "default", + "Group": "Servers", + "Host": "postgresql", + "Port": 5432, + "MaintenanceDB": "postgres", + "Username": "postgres", + "KerberosAuthentication": false, + "ConnectionParameters": { + "sslmode": "prefer", + "connect_timeout": 10 + }, + "Tags": [] + } + } +} diff --git a/infrastructure/configs/postgres-exporter/.env.template b/infrastructure/configs/postgres-exporter/.env.template new file mode 100644 index 0000000..ee4e931 --- /dev/null +++ b/infrastructure/configs/postgres-exporter/.env.template @@ -0,0 +1,3 @@ +DATA_SOURCE_URI=postgresql:5432/postgres?sslmode=disable +DATA_SOURCE_USER=postgres +DATA_SOURCE_PASS=postgres diff --git a/infrastructure/configs/postgresql/.env.template b/infrastructure/configs/postgresql/.env.template new file mode 100644 index 0000000..8acbdb3 --- /dev/null +++ b/infrastructure/configs/postgresql/.env.template @@ -0,0 +1,3 @@ +POSTGRES_DB=postgres +POSTGRES_USER=postgres +POSTGRES_PASSWORD=postgres diff --git a/infrastructure/configs/postgresql/pg_hba.conf b/infrastructure/configs/postgresql/pg_hba.conf new file mode 100644 index 0000000..008eb9a --- /dev/null +++ b/infrastructure/configs/postgresql/pg_hba.conf @@ -0,0 +1,2 @@ +host all all 0.0.0.0/0 scram-sha-256 +host all all ::/0 scram-sha-256 diff --git a/infrastructure/configs/postgresql/postgresql.conf b/infrastructure/configs/postgresql/postgresql.conf new file mode 100644 index 0000000..49442be --- /dev/null +++ b/infrastructure/configs/postgresql/postgresql.conf @@ -0,0 +1,890 @@ +# ----------------------------- +# PostgreSQL configuration file +# ----------------------------- +# +# This file consists of lines of the form: +# +# name = value +# +# (The "=" is optional.) Whitespace may be used. Comments are introduced with +# "#" anywhere on a line. The complete list of parameter names and allowed +# values can be found in the PostgreSQL documentation. +# +# The commented-out settings shown in this file represent the default values. +# Re-commenting a setting is NOT sufficient to revert it to the default value; +# you need to reload the server. +# +# This file is read on server startup and when the server receives a SIGHUP +# signal. If you edit the file on a running system, you have to SIGHUP the +# server for the changes to take effect, run "pg_ctl reload", or execute +# "SELECT pg_reload_conf()". Some parameters, which are marked below, +# require a server shutdown and restart to take effect. +# +# Any parameter can also be given as a command-line option to the server, e.g., +# "postgres -c log_connections=all". Some parameters can be changed at run time +# with the "SET" SQL command. +# +# Memory units: B = bytes Time units: us = microseconds +# kB = kilobytes ms = milliseconds +# MB = megabytes s = seconds +# GB = gigabytes min = minutes +# TB = terabytes h = hours +# d = days + + +#------------------------------------------------------------------------------ +# FILE LOCATIONS +#------------------------------------------------------------------------------ + +# The default values of these variables are driven from the -D command-line +# option or PGDATA environment variable, represented here as ConfigDir. + +#data_directory = 'ConfigDir' # use data in another directory + # (change requires restart) +hba_file = '/etc/postgresql/pg_hba.conf' # host-based authentication file + # (change requires restart) +#ident_file = 'ConfigDir/pg_ident.conf' # ident configuration file + # (change requires restart) + +# If external_pid_file is not explicitly set, no extra PID file is written. +#external_pid_file = '' # write an extra PID file + # (change requires restart) + + +#------------------------------------------------------------------------------ +# CONNECTIONS AND AUTHENTICATION +#------------------------------------------------------------------------------ + +# - Connection Settings - + +listen_addresses = '*' # what IP address(es) to listen on; + # comma-separated list of addresses; + # defaults to 'localhost'; use '*' for all + # (change requires restart) +#port = 5432 # (change requires restart) +max_connections = 500 # (change requires restart) +#reserved_connections = 0 # (change requires restart) +#superuser_reserved_connections = 3 # (change requires restart) +#unix_socket_directories = '/tmp' # comma-separated list of directories + # (change requires restart) +#unix_socket_group = '' # (change requires restart) +#unix_socket_permissions = 0777 # begin with 0 to use octal notation + # (change requires restart) +#bonjour = off # advertise server via Bonjour + # (change requires restart) +#bonjour_name = '' # defaults to the computer name + # (change requires restart) + +# - TCP settings - +# see "man tcp" for details + +#tcp_keepalives_idle = 0 # TCP_KEEPIDLE, in seconds; + # 0 selects the system default +#tcp_keepalives_interval = 0 # TCP_KEEPINTVL, in seconds; + # 0 selects the system default +#tcp_keepalives_count = 0 # TCP_KEEPCNT; + # 0 selects the system default +#tcp_user_timeout = 0 # TCP_USER_TIMEOUT, in milliseconds; + # 0 selects the system default + +#client_connection_check_interval = 0 # time between checks for client + # disconnection while running queries; + # 0 for never + +# - Authentication - + +#authentication_timeout = 1min # 1s-600s +#password_encryption = scram-sha-256 # scram-sha-256 or (deprecated) md5 +#scram_iterations = 4096 +#md5_password_warnings = on # display md5 deprecation warnings? +#oauth_validator_libraries = '' # comma-separated list of trusted validator modules + +# GSSAPI using Kerberos +#krb_server_keyfile = 'FILE:${sysconfdir}/krb5.keytab' +#krb_caseins_users = off +#gss_accept_delegation = off + +# - SSL - + +#ssl = off +#ssl_ca_file = '' +#ssl_cert_file = 'server.crt' +#ssl_crl_file = '' +#ssl_crl_dir = '' +#ssl_key_file = 'server.key' +#ssl_ciphers = 'HIGH:MEDIUM:+3DES:!aNULL' # allowed TLSv1.2 ciphers +#ssl_tls13_ciphers = '' # allowed TLSv1.3 cipher suites, blank for default +#ssl_prefer_server_ciphers = on +#ssl_groups = 'X25519:prime256v1' +#ssl_min_protocol_version = 'TLSv1.2' +#ssl_max_protocol_version = '' +#ssl_dh_params_file = '' +#ssl_passphrase_command = '' +#ssl_passphrase_command_supports_reload = off + + +#------------------------------------------------------------------------------ +# RESOURCE USAGE (except WAL) +#------------------------------------------------------------------------------ + +# - Memory - + +#shared_buffers = 128MB # min 128kB + # (change requires restart) +#huge_pages = try # on, off, or try + # (change requires restart) +#huge_page_size = 0 # zero for system default + # (change requires restart) +#temp_buffers = 8MB # min 800kB +#max_prepared_transactions = 0 # zero disables the feature + # (change requires restart) +# Caution: it is not advisable to set max_prepared_transactions nonzero unless +# you actively intend to use prepared transactions. +#work_mem = 4MB # min 64kB +#hash_mem_multiplier = 2.0 # 1-1000.0 multiplier on hash table work_mem +#maintenance_work_mem = 64MB # min 64kB +#autovacuum_work_mem = -1 # min 64kB, or -1 to use maintenance_work_mem +#logical_decoding_work_mem = 64MB # min 64kB +#max_stack_depth = 2MB # min 100kB +#shared_memory_type = mmap # the default is the first option + # supported by the operating system: + # mmap + # sysv + # windows + # (change requires restart) +#dynamic_shared_memory_type = posix # the default is usually the first option + # supported by the operating system: + # posix + # sysv + # windows + # mmap + # (change requires restart) +#min_dynamic_shared_memory = 0MB # (change requires restart) +#vacuum_buffer_usage_limit = 2MB # size of vacuum and analyze buffer access strategy ring; + # 0 to disable vacuum buffer access strategy; + # range 128kB to 16GB + +# SLRU buffers (change requires restart) +#commit_timestamp_buffers = 0 # memory for pg_commit_ts (0 = auto) +#multixact_offset_buffers = 16 # memory for pg_multixact/offsets +#multixact_member_buffers = 32 # memory for pg_multixact/members +#notify_buffers = 16 # memory for pg_notify +#serializable_buffers = 32 # memory for pg_serial +#subtransaction_buffers = 0 # memory for pg_subtrans (0 = auto) +#transaction_buffers = 0 # memory for pg_xact (0 = auto) + +# - Disk - + +#temp_file_limit = -1 # limits per-process temp file space + # in kilobytes, or -1 for no limit + +#file_copy_method = copy # copy, clone (if supported by OS) + +#max_notify_queue_pages = 1048576 # limits the number of SLRU pages allocated + # for NOTIFY / LISTEN queue + +# - Kernel Resources - + +#max_files_per_process = 1000 # min 64 + # (change requires restart) + +# - Background Writer - + +#bgwriter_delay = 200ms # 10-10000ms between rounds +#bgwriter_lru_maxpages = 100 # max buffers written/round, 0 disables +#bgwriter_lru_multiplier = 2.0 # 0-10.0 multiplier on buffers scanned/round +#bgwriter_flush_after = 0 # measured in pages, 0 disables + +# - I/O - + +#backend_flush_after = 0 # measured in pages, 0 disables +#effective_io_concurrency = 16 # 1-1000; 0 disables issuing multiple simultaneous IO requests +#maintenance_io_concurrency = 16 # 1-1000; same as effective_io_concurrency +#io_max_combine_limit = 128kB # usually 1-128 blocks (depends on OS) + # (change requires restart) +#io_combine_limit = 128kB # usually 1-128 blocks (depends on OS) + +#io_method = worker # worker, io_uring, sync + # (change requires restart) +#io_max_concurrency = -1 # Max number of IOs that one process + # can execute simultaneously + # -1 sets based on shared_buffers + # (change requires restart) +#io_workers = 3 # 1-32; + +# - Worker Processes - + +#max_worker_processes = 8 # (change requires restart) +#max_parallel_workers_per_gather = 2 # limited by max_parallel_workers +#max_parallel_maintenance_workers = 2 # limited by max_parallel_workers +#max_parallel_workers = 8 # number of max_worker_processes that + # can be used in parallel operations +#parallel_leader_participation = on + + +#------------------------------------------------------------------------------ +# WRITE-AHEAD LOG +#------------------------------------------------------------------------------ + +# - Settings - + +#wal_level = replica # minimal, replica, or logical + # (change requires restart) +#fsync = on # flush data to disk for crash safety + # (turning this off can cause + # unrecoverable data corruption) +#synchronous_commit = on # synchronization level; + # off, local, remote_write, remote_apply, or on +#wal_sync_method = fsync # the default is the first option + # supported by the operating system: + # open_datasync + # fdatasync (default on Linux and FreeBSD) + # fsync + # fsync_writethrough + # open_sync +#full_page_writes = on # recover from partial page writes +#wal_log_hints = off # also do full page writes of non-critical updates + # (change requires restart) +#wal_compression = off # enables compression of full-page writes; + # off, pglz, lz4, zstd, or on +#wal_init_zero = on # zero-fill new WAL files +#wal_recycle = on # recycle WAL files +#wal_buffers = -1 # min 32kB, -1 sets based on shared_buffers + # (change requires restart) +#wal_writer_delay = 200ms # 1-10000 milliseconds +#wal_writer_flush_after = 1MB # measured in pages, 0 disables +#wal_skip_threshold = 2MB + +#commit_delay = 0 # range 0-100000, in microseconds +#commit_siblings = 5 # range 0-1000 + +# - Checkpoints - + +#checkpoint_timeout = 5min # range 30s-1d +#checkpoint_completion_target = 0.9 # checkpoint target duration, 0.0 - 1.0 +#checkpoint_flush_after = 0 # measured in pages, 0 disables +#checkpoint_warning = 30s # 0 disables +#max_wal_size = 1GB +#min_wal_size = 80MB + +# - Prefetching during recovery - + +#recovery_prefetch = try # prefetch pages referenced in the WAL? +#wal_decode_buffer_size = 512kB # lookahead window used for prefetching + # (change requires restart) + +# - Archiving - + +#archive_mode = off # enables archiving; off, on, or always + # (change requires restart) +#archive_library = '' # library to use to archive a WAL file + # (empty string indicates archive_command should + # be used) +#archive_command = '' # command to use to archive a WAL file + # placeholders: %p = path of file to archive + # %f = file name only + # e.g. 'test ! -f "/mnt/server/archivedir/%f" && cp "%p" "/mnt/server/archivedir/%f"' +#archive_timeout = 0 # force a WAL file switch after this + # number of seconds; 0 disables + +# - Archive Recovery - + +# These are only used in recovery mode. + +#restore_command = '' # command to use to restore an archived WAL file + # placeholders: %p = path of file to restore + # %f = file name only + # e.g. 'cp "/mnt/server/archivedir/%f" "%p"' +#archive_cleanup_command = '' # command to execute at every restartpoint +#recovery_end_command = '' # command to execute at completion of recovery + +# - Recovery Target - + +# Set these only when performing a targeted recovery. + +#recovery_target = '' # 'immediate' to end recovery as soon as a + # consistent state is reached + # (change requires restart) +#recovery_target_name = '' # the named restore point to which recovery will proceed + # (change requires restart) +#recovery_target_time = '' # the time stamp up to which recovery will proceed + # (change requires restart) +#recovery_target_xid = '' # the transaction ID up to which recovery will proceed + # (change requires restart) +#recovery_target_lsn = '' # the WAL LSN up to which recovery will proceed + # (change requires restart) +#recovery_target_inclusive = on # Specifies whether to stop: + # just after the specified recovery target (on) + # just before the recovery target (off) + # (change requires restart) +#recovery_target_timeline = 'latest' # 'current', 'latest', or timeline ID + # (change requires restart) +#recovery_target_action = 'pause' # 'pause', 'promote', 'shutdown' + # (change requires restart) + +# - WAL Summarization - + +#summarize_wal = off # run WAL summarizer process? +#wal_summary_keep_time = '10d' # when to remove old summary files, 0 = never + + +#------------------------------------------------------------------------------ +# REPLICATION +#------------------------------------------------------------------------------ + +# - Sending Servers - + +# Set these on the primary and on any standby that will send replication data. + +#max_wal_senders = 10 # max number of walsender processes + # (change requires restart) +#max_replication_slots = 10 # max number of replication slots + # (change requires restart) +#wal_keep_size = 0 # in megabytes; 0 disables +#max_slot_wal_keep_size = -1 # in megabytes; -1 disables +#idle_replication_slot_timeout = 0 # in seconds; 0 disables +#wal_sender_timeout = 60s # in milliseconds; 0 disables +#track_commit_timestamp = off # collect timestamp of transaction commit + # (change requires restart) + +# - Primary Server - + +# These settings are ignored on a standby server. + +#synchronous_standby_names = '' # standby servers that provide sync rep + # method to choose sync standbys, number of sync standbys, + # and comma-separated list of application_name + # from standby(s); '*' = all +#synchronized_standby_slots = '' # streaming replication standby server slot + # names that logical walsender processes will wait for + +# - Standby Servers - + +# These settings are ignored on a primary server. + +#primary_conninfo = '' # connection string to sending server +#primary_slot_name = '' # replication slot on sending server +#hot_standby = on # "off" disallows queries during recovery + # (change requires restart) +#max_standby_archive_delay = 30s # max delay before canceling queries + # when reading WAL from archive; + # -1 allows indefinite delay +#max_standby_streaming_delay = 30s # max delay before canceling queries + # when reading streaming WAL; + # -1 allows indefinite delay +#wal_receiver_create_temp_slot = off # create temp slot if primary_slot_name + # is not set +#wal_receiver_status_interval = 10s # send replies at least this often + # 0 disables +#hot_standby_feedback = off # send info from standby to prevent + # query conflicts +#wal_receiver_timeout = 60s # time that receiver waits for + # communication from primary + # in milliseconds; 0 disables +#wal_retrieve_retry_interval = 5s # time to wait before retrying to + # retrieve WAL after a failed attempt +#recovery_min_apply_delay = 0 # minimum delay for applying changes during recovery +#sync_replication_slots = off # enables slot synchronization on the physical standby from the primary + +# - Subscribers - + +# These settings are ignored on a publisher. + +#max_active_replication_origins = 10 # max number of active replication origins + # (change requires restart) +#max_logical_replication_workers = 4 # taken from max_worker_processes + # (change requires restart) +#max_sync_workers_per_subscription = 2 # taken from max_logical_replication_workers +#max_parallel_apply_workers_per_subscription = 2 # taken from max_logical_replication_workers + + +#------------------------------------------------------------------------------ +# QUERY TUNING +#------------------------------------------------------------------------------ + +# - Planner Method Configuration - + +#enable_async_append = on +#enable_bitmapscan = on +#enable_gathermerge = on +#enable_hashagg = on +#enable_hashjoin = on +#enable_incremental_sort = on +#enable_indexscan = on +#enable_indexonlyscan = on +#enable_material = on +#enable_memoize = on +#enable_mergejoin = on +#enable_nestloop = on +#enable_parallel_append = on +#enable_parallel_hash = on +#enable_partition_pruning = on +#enable_partitionwise_join = off +#enable_partitionwise_aggregate = off +#enable_presorted_aggregate = on +#enable_seqscan = on +#enable_sort = on +#enable_tidscan = on +#enable_group_by_reordering = on +#enable_distinct_reordering = on +#enable_self_join_elimination = on +#enable_eager_aggregate = on + +# - Planner Cost Constants - + +#seq_page_cost = 1.0 # measured on an arbitrary scale +#random_page_cost = 4.0 # same scale as above +#cpu_tuple_cost = 0.01 # same scale as above +#cpu_index_tuple_cost = 0.005 # same scale as above +#cpu_operator_cost = 0.0025 # same scale as above +#parallel_setup_cost = 1000.0 # same scale as above +#parallel_tuple_cost = 0.1 # same scale as above +#min_parallel_table_scan_size = 8MB +#min_parallel_index_scan_size = 512kB +#effective_cache_size = 4GB +#min_eager_agg_group_size = 8.0 + +#jit_above_cost = 100000 # perform JIT compilation if available + # and query more expensive than this; + # -1 disables +#jit_inline_above_cost = 500000 # inline small functions if query is + # more expensive than this; -1 disables +#jit_optimize_above_cost = 500000 # use expensive JIT optimizations if + # query is more expensive than this; + # -1 disables + +# - Genetic Query Optimizer - + +#geqo = on +#geqo_threshold = 12 +#geqo_effort = 5 # range 1-10 +#geqo_pool_size = 0 # selects default based on effort +#geqo_generations = 0 # selects default based on effort +#geqo_selection_bias = 2.0 # range 1.5-2.0 +#geqo_seed = 0.0 # range 0.0-1.0 + +# - Other Planner Options - + +#default_statistics_target = 100 # range 1-10000 +#constraint_exclusion = partition # on, off, or partition +#cursor_tuple_fraction = 0.1 # range 0.0-1.0 +#from_collapse_limit = 8 +#jit = on # allow JIT compilation +#join_collapse_limit = 8 # 1 disables collapsing of explicit + # JOIN clauses +#plan_cache_mode = auto # auto, force_generic_plan or + # force_custom_plan +#recursive_worktable_factor = 10.0 # range 0.001-1000000 + + +#------------------------------------------------------------------------------ +# REPORTING AND LOGGING +#------------------------------------------------------------------------------ + +# - Where to Log - + +#log_destination = 'stderr' # Valid values are combinations of + # stderr, csvlog, jsonlog, syslog, and + # eventlog, depending on platform. + # csvlog and jsonlog require + # logging_collector to be on. + +# This is used when logging to stderr: +#logging_collector = off # Enable capturing of stderr, jsonlog, + # and csvlog into log files. Required + # to be on for csvlogs and jsonlogs. + # (change requires restart) + +# These are only used if logging_collector is on: +#log_directory = 'log' # directory where log files are written, + # can be absolute or relative to PGDATA +#log_filename = 'postgresql-%Y-%m-%d_%H%M%S.log' # log file name pattern, + # can include strftime() escapes +#log_file_mode = 0600 # creation mode for log files, + # begin with 0 to use octal notation +#log_rotation_age = 1d # Automatic rotation of logfiles will + # happen after that time. 0 disables. +#log_rotation_size = 10MB # Automatic rotation of logfiles will + # happen after that much log output. + # 0 disables. +#log_truncate_on_rotation = off # If on, an existing log file with the + # same name as the new log file will be + # truncated rather than appended to. + # But such truncation only occurs on + # time-driven rotation, not on restarts + # or size-driven rotation. Default is + # off, meaning append to existing files + # in all cases. + +# These are relevant when logging to syslog: +#syslog_facility = 'LOCAL0' +#syslog_ident = 'postgres' +#syslog_sequence_numbers = on +#syslog_split_messages = on + +# This is only relevant when logging to eventlog (Windows): +# (change requires restart) +#event_source = 'PostgreSQL' + +# - When to Log - + +#log_min_messages = warning # values in order of decreasing detail: + # debug5 + # debug4 + # debug3 + # debug2 + # debug1 + # info + # notice + # warning + # error + # log + # fatal + # panic + +#log_min_error_statement = error # values in order of decreasing detail: + # debug5 + # debug4 + # debug3 + # debug2 + # debug1 + # info + # notice + # warning + # error + # log + # fatal + # panic (effectively off) + +#log_min_duration_statement = -1 # -1 is disabled, 0 logs all statements + # and their durations, > 0 logs only + # statements running at least this number + # of milliseconds + +#log_min_duration_sample = -1 # -1 is disabled, 0 logs a sample of statements + # and their durations, > 0 logs only a sample of + # statements running at least this number + # of milliseconds; + # sample fraction is determined by log_statement_sample_rate + +#log_statement_sample_rate = 1.0 # fraction of logged statements exceeding + # log_min_duration_sample to be logged; + # 1.0 logs all such statements, 0.0 never logs + + +#log_transaction_sample_rate = 0.0 # fraction of transactions whose statements + # are logged regardless of their duration; 1.0 logs all + # statements from all transactions, 0.0 never logs + +#log_startup_progress_interval = 10s # Time between progress updates for + # long-running startup operations. + # 0 disables the feature, > 0 indicates + # the interval in milliseconds. + +# - What to Log - + +#debug_print_raw_parse = off +#debug_print_parse = off +#debug_print_rewritten = off +#debug_print_plan = off +#debug_pretty_print = on +#log_autovacuum_min_duration = 10min # log vacuum activity by autovacuum; + # -1 disables, 0 logs all actions and + # their durations, > 0 logs only + # actions running at least this number + # of milliseconds. +#log_autoanalyze_min_duration = 10min # log analyze activity by autovacuum; + # -1 disables, 0 logs all actions and + # their durations, > 0 logs only + # actions running at least this number + # of milliseconds. +#log_checkpoints = on +#log_connections = '' # log aspects of connection setup + # options include receipt, authentication, authorization, + # setup_durations, and all to log all of these aspects +#log_disconnections = off +#log_duration = off # log statement duration +#log_error_verbosity = default # terse, default, or verbose messages +#log_hostname = off +#log_line_prefix = '%m [%p] ' # special values: + # %a = application name + # %u = user name + # %d = database name + # %r = remote host and port + # %h = remote host + # %L = local address + # %b = backend type + # %p = process ID + # %P = process ID of parallel group leader + # %t = timestamp without milliseconds + # %m = timestamp with milliseconds + # %n = timestamp with milliseconds (as a Unix epoch) + # %Q = query ID (0 if none or not computed) + # %i = command tag + # %e = SQL state + # %c = session ID + # %l = session line number + # %s = session start timestamp + # %v = virtual transaction ID + # %x = transaction ID (0 if none) + # %q = stop here in non-session + # processes + # %% = '%' + # e.g. '<%u%%%d> ' +#log_lock_waits = on # log lock waits >= deadlock_timeout +#log_lock_failures = off # log lock failures +#log_recovery_conflict_waits = off # log standby recovery conflict waits + # >= deadlock_timeout +#log_parameter_max_length = -1 # when logging statements, limit logged + # bind-parameter values to N bytes; + # -1 means print in full, 0 disables +#log_parameter_max_length_on_error = 0 # when logging an error, limit logged + # bind-parameter values to N bytes; + # -1 means print in full, 0 disables +#log_statement = 'none' # none, ddl, mod, all +#log_replication_commands = off +#log_temp_files = -1 # log temporary files equal or larger + # than the specified size in kilobytes; + # -1 disables, 0 logs all temp files +#log_timezone = 'GMT' + +# - Process Title - + +#cluster_name = '' # added to process titles if nonempty + # (change requires restart) +#update_process_title = on + + +#------------------------------------------------------------------------------ +# STATISTICS +#------------------------------------------------------------------------------ + +# - Cumulative Query and Index Statistics - + +#track_activities = on +#track_activity_query_size = 1024 # (change requires restart) +#track_counts = on +#track_cost_delay_timing = off +#track_io_timing = off +#track_wal_io_timing = off +#track_functions = none # none, pl, all +#stats_fetch_consistency = cache # cache, none, snapshot + + +# - Monitoring - + +#compute_query_id = auto +#log_statement_stats = off +#log_parser_stats = off +#log_planner_stats = off +#log_executor_stats = off + + +#------------------------------------------------------------------------------ +# VACUUMING +#------------------------------------------------------------------------------ + +# - Automatic Vacuuming - + +#autovacuum = on # Enable autovacuum subprocess? 'on' + # requires track_counts to also be on. +#autovacuum_worker_slots = 16 # autovacuum worker slots to allocate + # (change requires restart) +#autovacuum_max_workers = 3 # max number of autovacuum subprocesses +#autovacuum_naptime = 1min # time between autovacuum runs +#autovacuum_vacuum_threshold = 50 # min number of row updates before + # vacuum +#autovacuum_vacuum_insert_threshold = 1000 # min number of row inserts + # before vacuum; -1 disables insert + # vacuums +#autovacuum_analyze_threshold = 50 # min number of row updates before + # analyze +#autovacuum_vacuum_scale_factor = 0.2 # fraction of table size before vacuum +#autovacuum_vacuum_insert_scale_factor = 0.2 # fraction of unfrozen pages + # before insert vacuum +#autovacuum_analyze_scale_factor = 0.1 # fraction of table size before analyze +#autovacuum_vacuum_max_threshold = 100000000 # max number of row updates + # before vacuum; -1 disables max + # threshold +#autovacuum_freeze_max_age = 200000000 # maximum XID age before forced vacuum + # (change requires restart) +#autovacuum_multixact_freeze_max_age = 400000000 # maximum multixact age + # before forced vacuum + # (change requires restart) +#autovacuum_vacuum_cost_delay = 2ms # default vacuum cost delay for + # autovacuum, in milliseconds; + # -1 means use vacuum_cost_delay +#autovacuum_vacuum_cost_limit = -1 # default vacuum cost limit for + # autovacuum, -1 means use + # vacuum_cost_limit + +# - Cost-Based Vacuum Delay - + +#vacuum_cost_delay = 0 # 0-100 milliseconds (0 disables) +#vacuum_cost_page_hit = 1 # 0-10000 credits +#vacuum_cost_page_miss = 2 # 0-10000 credits +#vacuum_cost_page_dirty = 20 # 0-10000 credits +#vacuum_cost_limit = 200 # 1-10000 credits + +# - Default Behavior - + +#vacuum_truncate = on # enable truncation after vacuum + +# - Freezing - + +#vacuum_freeze_table_age = 150000000 +#vacuum_freeze_min_age = 50000000 +#vacuum_failsafe_age = 1600000000 +#vacuum_multixact_freeze_table_age = 150000000 +#vacuum_multixact_freeze_min_age = 5000000 +#vacuum_multixact_failsafe_age = 1600000000 +#vacuum_max_eager_freeze_failure_rate = 0.03 # 0 disables eager scanning + +#------------------------------------------------------------------------------ +# CLIENT CONNECTION DEFAULTS +#------------------------------------------------------------------------------ + +# - Statement Behavior - + +#client_min_messages = notice # values in order of decreasing detail: + # debug5 + # debug4 + # debug3 + # debug2 + # debug1 + # log + # notice + # warning + # error +#search_path = '"$user", public' # schema names +#row_security = on +#default_table_access_method = 'heap' +#default_tablespace = '' # a tablespace name, '' uses the default +#default_toast_compression = 'pglz' # 'pglz' or 'lz4' +#temp_tablespaces = '' # a list of tablespace names, '' uses + # only default tablespace +#check_function_bodies = on +#default_transaction_isolation = 'read committed' +#default_transaction_read_only = off +#default_transaction_deferrable = off +#session_replication_role = 'origin' +#statement_timeout = 0 # in milliseconds, 0 is disabled +#transaction_timeout = 0 # in milliseconds, 0 is disabled +#lock_timeout = 0 # in milliseconds, 0 is disabled +#idle_in_transaction_session_timeout = 0 # in milliseconds, 0 is disabled +#idle_session_timeout = 0 # in milliseconds, 0 is disabled +#bytea_output = 'hex' # hex, escape +#xmlbinary = 'base64' +#xmloption = 'content' +#gin_pending_list_limit = 4MB +#createrole_self_grant = '' # set and/or inherit +#event_triggers = on + +# - Locale and Formatting - + +#datestyle = 'iso, mdy' +#intervalstyle = 'postgres' +#timezone = 'GMT' +#timezone_abbreviations = 'Default' # Select the set of available time zone + # abbreviations. Currently, there are + # Default + # Australia (historical usage) + # India + # You can create your own file in + # share/timezonesets/. +#extra_float_digits = 1 # min -15, max 3; any value >0 actually + # selects precise output mode +#client_encoding = sql_ascii # actually, defaults to database + # encoding + +# These settings are initialized by initdb, but they can be changed. +#lc_messages = '' # locale for system error message + # strings +#lc_monetary = 'C' # locale for monetary formatting +#lc_numeric = 'C' # locale for number formatting +#lc_time = 'C' # locale for time formatting + +#icu_validation_level = warning # report ICU locale validation + # errors at the given level + +# default configuration for text search +#default_text_search_config = 'pg_catalog.simple' + +# - Shared Library Preloading - + +#local_preload_libraries = '' +#session_preload_libraries = '' +#shared_preload_libraries = '' # (change requires restart) +#jit_provider = 'llvmjit' # JIT library to use + +# - Other Defaults - + +#dynamic_library_path = '$libdir' +#extension_control_path = '$system' +#gin_fuzzy_search_limit = 0 + + +#------------------------------------------------------------------------------ +# LOCK MANAGEMENT +#------------------------------------------------------------------------------ + +#deadlock_timeout = 1s +#max_locks_per_transaction = 64 # min 10 + # (change requires restart) +#max_pred_locks_per_transaction = 64 # min 10 + # (change requires restart) +#max_pred_locks_per_relation = -2 # negative values mean + # (max_pred_locks_per_transaction + # / -max_pred_locks_per_relation) - 1 +#max_pred_locks_per_page = 2 # min 0 + + +#------------------------------------------------------------------------------ +# VERSION AND PLATFORM COMPATIBILITY +#------------------------------------------------------------------------------ + +# - Previous PostgreSQL Versions - + +#array_nulls = on +#backslash_quote = safe_encoding # on, off, or safe_encoding +#lo_compat_privileges = off +#quote_all_identifiers = off +#synchronize_seqscans = on + +# - Other Platforms and Clients - + +#transform_null_equals = off +#allow_alter_system = on + + +#------------------------------------------------------------------------------ +# ERROR HANDLING +#------------------------------------------------------------------------------ + +#exit_on_error = off # terminate session on any error? +#restart_after_crash = on # reinitialize after backend crash? +#data_sync_retry = off # retry or panic on failure to fsync + # data? + # (change requires restart) +#recovery_init_sync_method = fsync # fsync, syncfs (Linux 5.8+) + + +#------------------------------------------------------------------------------ +# CONFIG FILE INCLUDES +#------------------------------------------------------------------------------ + +# These options allow settings to be loaded from files other than the +# default postgresql.conf. Note that these are directives, not variable +# assignments, so they can usefully be given more than once. + +#include_dir = '...' # include files ending in '.conf' from + # a directory, e.g., 'conf.d' +#include_if_exists = '...' # include file only if it exists +#include = '...' # include file + + +#------------------------------------------------------------------------------ +# CUSTOMIZED OPTIONS +#------------------------------------------------------------------------------ + +# Add settings for extensions here diff --git a/infrastructure/configs/redis-exporter/.env.template b/infrastructure/configs/redis-exporter/.env.template new file mode 100644 index 0000000..dc76dbf --- /dev/null +++ b/infrastructure/configs/redis-exporter/.env.template @@ -0,0 +1,4 @@ +REDIS_ADDR=redis://valkey:6379 +REDIS_USER=default +REDIS_PASSWORD=valkey +REDIS_EXPORTER_PING_ON_CONNECT=true diff --git a/infrastructure/configs/rustfs/.env.template b/infrastructure/configs/rustfs/.env.template new file mode 100644 index 0000000..a25ab5b --- /dev/null +++ b/infrastructure/configs/rustfs/.env.template @@ -0,0 +1,24 @@ +RUSTFS_VOLUMES=/data + +RUSTFS_ADDRESS=0.0.0.0:9000 + +RUSTFS_ACCESS_KEY=access +RUSTFS_SECRET_KEY=storage-secret + +RUSTFS_CONSOLE_ENABLE=true +RUSTFS_CONSOLE_ADDRESS=0.0.0.0:9001 + +RUSTFS_OBS_ENDPOINT=http://otel-collector:4318 +RUSTFS_OBS_LOGGER_LEVEL=info + +RUSTFS_REGION=local + +#RUSTFS_KMS_ENABLE=true +#RUSTFS_KMS_BACKEND=vault +#RUSTFS_KMS_KEY_DIR= +#RUSTFS_KMS_VAULT_ADDRESS= +#RUSTFS_KMS_VAULT_TOKEN= +#RUSTFS_KMS_DEFAULT_KEY_ID= + +# Options: GeneralPurpose, AiTraining, DataAnalytics, WebWorkload, IndustrialIoT, SecureStorage +RUSTFS_BUFFER_PROFILE=WebWorkload diff --git a/infrastructure/configs/s3/.env.template b/infrastructure/configs/s3/.env.template new file mode 100644 index 0000000..aa22505 --- /dev/null +++ b/infrastructure/configs/s3/.env.template @@ -0,0 +1,4 @@ +S3_ENDPOINT=s3:9000 +S3_URL=http://s3:9000 +S3_ACCESS_KEY=access +S3_SECRET_KEY=storage-secret diff --git a/infrastructure/configs/valkey/.env.template b/infrastructure/configs/valkey/.env.template new file mode 100644 index 0000000..943ffa6 --- /dev/null +++ b/infrastructure/configs/valkey/.env.template @@ -0,0 +1 @@ +VALKEY_PASSWORD=valkey diff --git a/infrastructure/configs/valkey/valkey.conf b/infrastructure/configs/valkey/valkey.conf new file mode 100644 index 0000000..b54a81b --- /dev/null +++ b/infrastructure/configs/valkey/valkey.conf @@ -0,0 +1,2664 @@ +# Valkey configuration file example. +# +# Note that in order to read the configuration file, the server must be +# started with the file path as first argument: +# +# ./valkey-server /path/to/valkey.conf + +# Note on units: when memory size is needed, it is possible to specify +# it in the usual form of 1k 5GB 4M and so forth: +# +# 1k => 1000 bytes +# 1kb => 1024 bytes +# 1m => 1000000 bytes +# 1mb => 1024*1024 bytes +# 1g => 1000000000 bytes +# 1gb => 1024*1024*1024 bytes +# +# units are case insensitive so 1GB 1Gb 1gB are all the same. + +################################## INCLUDES ################################### + +# Include one or more other config files here. This is useful if you +# have a standard template that goes to all servers but also need +# to customize a few per-server settings. Include files can include +# other files, so use this wisely. +# +# Note that option "include" won't be rewritten by command "CONFIG REWRITE" +# from admin or Sentinel. Since the server always uses the last processed +# line as value of a configuration directive, you'd better put includes +# at the beginning of this file to avoid overwriting config change at runtime. +# +# If instead you are interested in using includes to override configuration +# options, it is better to use include as the last line. +# +# Included paths may contain wildcards. All files matching the wildcards will +# be included in alphabetical order. +# Note that if an include path contains a wildcards but no files match it when +# the server is started, the include statement will be ignored and no error will +# be emitted. It is safe, therefore, to include wildcard files from empty +# directories. +# +# include /path/to/local.conf +# include /path/to/other.conf +# include /path/to/fragments/*.conf +# + +################################## MODULES ##################################### + +# Load modules at startup. If the server is not able to load modules +# it will abort. It is possible to use multiple loadmodule directives. +# +# loadmodule /path/to/my_module.so +# loadmodule /path/to/other_module.so +# loadmodule /path/to/args_module.so [arg [arg ...]] + +################################## NETWORK ##################################### + +# By default, if no "bind" configuration directive is specified, the server listens +# for connections from all available network interfaces on the host machine. +# It is possible to listen to just one or multiple selected interfaces using +# the "bind" configuration directive, followed by one or more IP addresses. +# Each address can be prefixed by "-", which means that the server will not fail to +# start if the address is not available. Being not available only refers to +# addresses that does not correspond to any network interface. Addresses that +# are already in use will always fail, and unsupported protocols will always be +# silently skipped. +# +# Examples: +# +# bind 192.168.1.100 10.0.0.1 # listens on two specific IPv4 addresses +# bind 127.0.0.1 ::1 # listens on loopback IPv4 and IPv6 +# bind * -::* # like the default, all available interfaces +# +# ~~~ WARNING ~~~ If the computer running the server is directly exposed to the +# internet, binding to all the interfaces is dangerous and will expose the +# instance to everybody on the internet. So by default we uncomment the +# following bind directive, that will force the server to listen only on the +# IPv4 and IPv6 (if available) loopback interface addresses (this means the server +# will only be able to accept client connections from the same host that it is +# running on). +# +# IF YOU ARE SURE YOU WANT YOUR INSTANCE TO LISTEN TO ALL THE INTERFACES +# COMMENT OUT THE FOLLOWING LINE. +# +# You will also need to set a password unless you explicitly disable protected +# mode. +# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +# bind 127.0.0.1 -::1 + +# By default, outgoing connections (from replica to primary, from Sentinel to +# instances, cluster bus, etc.) are not bound to a specific local address. In +# most cases, this means the operating system will handle that based on routing +# and the interface through which the connection goes out. +# +# Using bind-source-addr it is possible to configure a specific address to bind +# to, which may also affect how the connection gets routed. +# +# Example: +# +# bind-source-addr 10.0.0.1 + +# Protected mode is a layer of security protection, in order to avoid that +# the server instances left open on the internet are accessed and exploited. +# +# When protected mode is on and the default user has no password, the server +# only accepts local connections from the IPv4 address (127.0.0.1), IPv6 address +# (::1) or Unix domain sockets. +# +# By default protected mode is enabled. You should disable it only if +# you are sure you want clients from other hosts to connect to the server +# even if no authentication is configured. +protected-mode yes + +# The server uses default hardened security configuration directives to reduce the +# attack surface on innocent users. Therefore, several sensitive configuration +# directives are immutable, and some potentially-dangerous commands are blocked. +# +# Configuration directives that control files that the server writes to (e.g., 'dir' +# and 'dbfilename') and that aren't usually modified during runtime +# are protected by making them immutable. +# +# Commands that can increase the attack surface of the server and that aren't usually +# called by users are blocked by default. +# +# These can be exposed to either all connections or just local ones by setting +# each of the configs listed below to either of these values: +# +# no - Block for any connection (remain immutable) +# yes - Allow for any connection (no protection) +# local - Allow only for local connections. Ones originating from the +# IPv4 address (127.0.0.1), IPv6 address (::1) or Unix domain sockets. +# +# enable-protected-configs no +# enable-debug-command no +# enable-module-command no + +# Accept connections on the specified port, default is 6379 (IANA #815344). +# If port 0 is specified the server will not listen on a TCP socket. +port 6379 + +# TCP listen() backlog. +# +# In high requests-per-second environments you need a high backlog in order +# to avoid slow clients connection issues. Note that the Linux kernel +# will silently truncate it to the value of /proc/sys/net/core/somaxconn so +# make sure to raise both the value of somaxconn and tcp_max_syn_backlog +# in order to get the desired effect. +tcp-backlog 511 + +# Multipath TCP (MPTCP) +# +# MPTCP splits a single TCP connection into subflows over multiple interfaces or paths. +# It enables bandwidth aggregation, failover, and improved reliability. +# When set to 'yes', clients will be able to use MPTCP if requested. When not +# requested, regular TCP can be used like before. +# Note: MPTCP is supported in the mainline Linux kernel starting from version 5.6. +# +# mptcp yes + +# Unix socket. +# +# Specify the path for the Unix socket that will be used to listen for +# incoming connections. There is no default, so the server will not listen +# on a unix socket when not specified. +# +# unixsocket /run/valkey.sock +# unixsocketgroup wheel +# unixsocketperm 700 + +# Close the connection after a client is idle for N seconds (0 to disable) +timeout 0 + +# TCP keepalive. +# +# If non-zero, use SO_KEEPALIVE to send TCP ACKs to clients in absence +# of communication. This is useful for two reasons: +# +# 1) Detect dead peers. +# 2) Force network equipment in the middle to consider the connection to be +# alive. +# +# On Linux, the specified value (in seconds) is the period used to send ACKs. +# Note that to close the connection the double of the time is needed. +# On other kernels the period depends on the kernel configuration. +tcp-keepalive 300 + +# Apply OS-specific mechanism to mark the listening socket with the specified +# ID, to support advanced routing and filtering capabilities. +# +# On Linux, the ID represents a connection mark. +# On FreeBSD, the ID represents a socket cookie ID. +# On OpenBSD, the ID represents a route table ID. +# +# The default value is 0, which implies no marking is required. +# socket-mark-id 0 + +################################# TLS/SSL ##################################### + +# By default, TLS/SSL is disabled. To enable it, the "tls-port" configuration +# directive can be used to define TLS-listening ports. To enable TLS on the +# default port, use: +# +# port 0 +# tls-port 6379 + +# Configure a X.509 certificate and private key to use for authenticating the +# server to connected clients, primaries or cluster peers. These files should be +# PEM formatted. +# +# tls-cert-file valkey.crt +# tls-key-file valkey.key +# +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-key-file-pass secret + +# Normally the server uses the same certificate for both server functions (accepting +# connections) and client functions (replicating from a primary, establishing +# cluster bus connections, etc.). +# +# Sometimes certificates are issued with attributes that designate them as +# client-only or server-only certificates. In that case it may be desired to use +# different certificates for incoming (server) and outgoing (client) +# connections. To do that, use the following directives: +# +# tls-client-cert-file client.crt +# tls-client-key-file client.key +# +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-client-key-file-pass secret + +# Configure a DH parameters file to enable Diffie-Hellman (DH) key exchange, +# required by older versions of OpenSSL (<3.0). Newer versions do not require +# this configuration and recommend against it. +# +# tls-dh-params-file valkey.dh + +# Configure a CA certificate(s) bundle or directory to authenticate TLS/SSL +# clients and peers. The server requires an explicit configuration of at least one +# of these, and will not implicitly use the system wide configuration. +# +# tls-ca-cert-file ca.crt +# tls-ca-cert-dir /etc/ssl/certs + +# By default, clients (including replica servers) on a TLS port are required +# to authenticate using valid client side certificates. +# +# If "no" is specified, client certificates are not required and not accepted. +# If "optional" is specified, client certificates are accepted and must be +# valid if provided, but are not required. +# +# tls-auth-clients no +# tls-auth-clients optional + +# Automatically authenticate TLS clients as Valkey users based on their +# certificates. +# +# If set to a field like "CN", the server will extract the corresponding field +# from the client's TLS certificate and attempt to find a Valkey user with the +# same name. If a matching user is found, the client is automatically +# authenticated as that user during the TLS handshake. If no matching user is +# found, the client is connected as the unauthenticated default user. Set to +# "off" to disable automatic user authentication via certificate fields. +# +# Supported values: CN, off. Default: off. +# +# tls-auth-clients-user CN + +# By default, a replica does not attempt to establish a TLS connection +# with its primary. +# +# Use the following directive to enable TLS on replication links. +# +# tls-replication yes + +# By default, the cluster bus uses a plain TCP connection. To enable +# TLS for the bus protocol, use the following directive: +# +# tls-cluster yes + +# By default, only TLSv1.2 and TLSv1.3 are enabled and it is highly recommended +# that older formally deprecated versions are kept disabled to reduce the attack surface. +# You can explicitly specify TLS versions to support. +# Allowed values are case insensitive and include "TLSv1", "TLSv1.1", "TLSv1.2", +# "TLSv1.3" (OpenSSL >= 1.1.1) or any combination. +# To enable only TLSv1.2 and TLSv1.3, use: +# +# tls-protocols "TLSv1.2 TLSv1.3" + +# Configure allowed ciphers. See the ciphers(1ssl) manpage for more information +# about the syntax of this string. +# +# Note: this configuration applies only to <= TLSv1.2. +# +# tls-ciphers DEFAULT:!MEDIUM + +# Configure allowed TLSv1.3 ciphersuites. See the ciphers(1ssl) manpage for more +# information about the syntax of this string, and specifically for TLSv1.3 +# ciphersuites. +# +# tls-ciphersuites TLS_CHACHA20_POLY1305_SHA256 + +# When choosing a cipher, use the server's preference instead of the client +# preference. By default, the server follows the client's preference. +# +# tls-prefer-server-ciphers yes + +# By default, TLS session caching is enabled to allow faster and less expensive +# reconnections by clients that support it. Use the following directive to disable +# caching. +# +# tls-session-caching no + +# Change the default number of TLS sessions cached. A zero value sets the cache +# to unlimited size. The default size is 20480. +# +# tls-session-cache-size 5000 + +# Change the default timeout of cached TLS sessions. The default timeout is 300 +# seconds. +# +# tls-session-cache-timeout 60 + +# Interval of TLS material reloading in seconds. +# The default value is 0 (disabled, no automatic reload). +# When set to a value greater than 0, the server will periodically check the +# certificate and key files and, if modified, reload the TLS materials. The +# reload work is performed in a background thread, so it does not block the main +# thread. +# +# For example, to reload TLS materials daily: +# tls-auto-reload-interval 86400 + +################################### RDMA ###################################### + +# Valkey Over RDMA is experimental, it may be changed or be removed in any minor or major version. +# By default, RDMA is disabled. To enable it, the "rdma-port" configuration +# directive can be used to define RDMA-listening ports. +# +# rdma-port 6379 +# rdma-bind 192.168.1.100 + +# The RDMA receive transfer buffer is 1M by default. It can be set between 64K and 16M. +# Note that page size aligned size is preferred. +# +# rdma-rx-size 1048576 + +# The RDMA completion queue will use the completion vector to signal completion events +# via hardware interrupts. A large number of hardware interrupts can affect CPU performance. +# It is possible to tune the performance using rdma-completion-vector. +# +# Example 1. a) Pin hardware interrupt vectors [0, 3] to CPU [0, 3]. +# b) Set CPU affinity for valkey to CPU [4, X]. +# c) Any valkey server uses a random RDMA completion vector [-1]. +# All valkey servers will not affect each other and will be isolated from kernel interrupts. +# +# SYS SYS SYS SYS VALKEY VALKEY VALKEY +# | | | | | | | +# CPU0 CPU1 CPU2 CPU3 CPU4 CPU5 ... CPUX +# | | | | +# INTR0 INTR1 INTR2 INTR3 +# +# Example 2. a) 1:1 pin hardware interrupt vectors [0, X] to CPU [0, X]. +# b) Set CPU affinity for valkey [M] to CPU [M]. +# c) Valkey server [M] uses RDMA completion vector [M]. +# A single CPU [M] handles hardware interrupts, the RDMA completion vector [M], +# and the valkey server [M] within its context only. +# This avoids overhead and function calls across multiple CPUs, fully isolating +# each valkey server from one another. +# +# VALKEY VALKEY VALKEY VALKEY VALKEY VALKEY VALKEY +# | | | | | | | +# CPU0 CPU1 CPU2 CPU3 CPU4 CPU5 ... CPUX +# | | | | | | | +# INTR0 INTR1 INTR2 INTR3 INTR4 INTR5 INTRX +# +# Use 0 and positive numbers to specify the RDMA completion vector, or specify -1 to allow +# the server to use a random vector for a new connection. The default vector is -1. +# +# rdma-completion-vector 0 + +################################# GENERAL ##################################### + +# By default the server does not run as a daemon. Use 'yes' if you need it. +# Note that the server will write a pid file in /var/run/valkey.pid when daemonized. +# When the server is supervised by upstart or systemd, this parameter has no impact. +daemonize no + +# If you run the server from upstart or systemd, the server can interact with your +# supervision tree. Options: +# supervised no - no supervision interaction +# supervised upstart - signal upstart by putting the server into SIGSTOP mode +# requires "expect stop" in your upstart job config +# supervised systemd - signal systemd by writing READY=1 to $NOTIFY_SOCKET +# on startup, and updating the server status on a regular +# basis. +# supervised auto - detect upstart or systemd method based on +# UPSTART_JOB or NOTIFY_SOCKET environment variables +# Note: these supervision methods only signal "process is ready." +# They do not enable continuous pings back to your supervisor. +# +# The default is "no". To run under upstart/systemd, you can simply uncomment +# the line below: +# +# supervised auto + +# If a pid file is specified, the server writes it where specified at startup +# and removes it at exit. +# +# When the server runs non daemonized, no pid file is created if none is +# specified in the configuration. When the server is daemonized, the pid file +# is used even if not specified, defaulting to "/var/run/valkey.pid". +# +# Creating a pid file is best effort: if the server is not able to create it +# nothing bad happens, the server will start and run normally. +# +# Note that on modern Linux systems "/run/valkey.pid" is more conforming +# and should be used instead. +pidfile /var/run/valkey_6379.pid + +# Specify the server verbosity level. +# This can be one of: +# debug (a lot of information, useful for development/testing) +# verbose (many rarely useful info, but not a mess like the debug level) +# notice (moderately verbose, what you want in production probably) +# warning (only very important / critical messages are logged) +# nothing (nothing is logged) +loglevel notice + +# Specify the logging format. +# This can be one of: +# +# - legacy: the default, traditional log format +# - logfmt: a structured log format; see https://www.brandur.org/logfmt +# - json: a structured log format +# +# log-format legacy + +# Specify the timestamp format used in logs using 'log-timestamp-format'. +# +# - legacy: default format +# - iso8601: ISO 8601 extended date and time with time zone, on the form +# yyyy-mm-ddThh:mm:ss.sss±hh:mm +# - milliseconds: milliseconds since the epoch +# +# log-timestamp-format legacy + +# Specify the log file name. Also the empty string can be used to force +# the server to log on the standard output. Note that if you use standard +# output for logging but daemonize, logs will be sent to /dev/null +logfile "" + +# To enable logging to the system logger, just set 'syslog-enabled' to yes, +# and optionally update the other syslog parameters to suit your needs. +# syslog-enabled no + +# Specify the syslog identity. +# syslog-ident valkey + +# Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7. +# syslog-facility local0 + +# To disable the built in crash log, which will possibly produce cleaner core +# dumps when they are needed, uncomment the following: +# +# crash-log-enabled no + +# To disable the fast memory check that's run as part of the crash log, which +# will possibly let the server terminate sooner, uncomment the following: +# +# crash-memcheck-enabled no + +# Set the number of databases. The default database is DB 0, you can select +# a different one on a per-connection basis using SELECT where +# dbid is a number between 0 and 'databases'-1 +# Note: This setting is ignored in cluster mode. Use `cluster-databases` instead. +databases 16 + +# By default the server shows an ASCII art logo only when started to log to the +# standard output and if the standard output is a TTY and syslog logging is +# disabled. Basically this means that normally a logo is displayed only in +# interactive sessions. +# +# However it is possible to force the pre-4.0 behavior and always show a +# ASCII art logo in startup logs by setting the following option to yes. +always-show-logo no + +# User data, including keys, values, client names, and ACL usernames, can be +# logged as part of assertions and other error cases. To prevent sensitive user +# information, such as PII, from being recorded in the server log file, this +# user data is hidden from the log by default. If you need to log user data for +# debugging or troubleshooting purposes, you can disable this feature by +# changing the config value to no. +hide-user-data-from-log yes + +# By default, the server modifies the process title (as seen in 'top' and 'ps') to +# provide some runtime information. It is possible to disable this and leave +# the process name as executed by setting the following to no. +set-proc-title yes + +# When changing the process title, the server uses the following template to construct +# the modified title. +# +# Template variables are specified in curly brackets. The following variables are +# supported: +# +# {title} Name of process as executed if parent, or type of child process. +# {listen-addr} Bind address or '*' followed by TCP or TLS port listening on, or +# Unix socket if only that's available. +# {server-mode} Special mode, i.e. "[sentinel]" or "[cluster]". +# {port} TCP port listening on, or 0. +# {tls-port} TLS port listening on, or 0. +# {unixsocket} Unix domain socket listening on, or "". +# {config-file} Name of configuration file used. +# +proc-title-template "{title} {listen-addr} {server-mode}" + +# Set the local environment which is used for string comparison operations, and +# also affect the performance of Lua scripts. Empty String indicates the locale +# is derived from the environment variables. +locale-collate "" + +# Valkey is largely compatible with Redis OSS, apart from a few cases where +# Valkey identifies itself as "Valkey" rather than "Redis". Extended +# Redis OSS compatibility mode makes Valkey pretend to be Redis. Enable this +# only if you have problems with tools or clients. This is a temporary +# configuration added in Valkey 8.0 and is scheduled to have no effect and +# will be removed in a future version. +# +# extended-redis-compatibility no + +# Inform Valkey of the availability zone if running in a cloud environment. Currently +# this is exposed in the INFO and HELLO commands for clients to use. Default is +# the empty string. +# +# availability-zone "zone-name" + +# Use a fixed hash seed for hashtable instead of a random one. +# Setting this option makes commands like SCAN return keys in a consistent +# order across restarts and failovers. The seed can be any string up to 256 characters. +# The value is immutable and must be provided only at server startup. +# +# hash-seed example-seed-val + +################################ SNAPSHOTTING ################################ + +# Save the DB to disk. +# +# save [ ...] +# +# The server will save the DB if the given number of seconds elapsed and it +# surpassed the given number of write operations against the DB. +# +# Snapshotting can be completely disabled with a single empty string argument +# as in following example: +# +# save "" +# +# Unless specified otherwise, by default the server will save the DB: +# * After 3600 seconds (an hour) if at least 1 change was performed +# * After 300 seconds (5 minutes) if at least 100 changes were performed +# * After 60 seconds if at least 10000 changes were performed +# +# You can set these explicitly by uncommenting the following line. +# +# save 3600 1 300 100 60 10000 + +# By default the server will stop accepting writes if RDB snapshots are enabled +# (at least one save point) and the latest background save failed. +# This will make the user aware (in a hard way) that data is not persisting +# on disk properly, otherwise chances are that no one will notice and some +# disaster will happen. +# +# If the background saving process will start working again, the server will +# automatically allow writes again. +# +# However if you have setup your proper monitoring of the server +# and persistence, you may want to disable this feature so that the server will +# continue to work as usual even if there are problems with disk, +# permissions, and so forth. +stop-writes-on-bgsave-error yes + +# Compress string objects using LZF when dump .rdb databases? +# By default compression is enabled as it's almost always a win. +# If you want to save some CPU in the saving child set it to 'no' but +# the dataset will likely be bigger if you have compressible values or keys. +rdbcompression yes + +# Since version 5 of RDB a CRC64 checksum is placed at the end of the file. +# This makes the format more resistant to corruption but there is a performance +# hit to pay (around 10%) when saving and loading RDB files, so you can disable it +# for maximum performances. +# +# RDB files created with checksum disabled have a checksum of zero that will +# tell the loading code to skip the check. +rdbchecksum yes + +# Valkey can try to load an RDB dump produced by a future version of Valkey. +# This can only work on a best-effort basis, because future RDB versions may +# contain information that's not known to the current version. If no new features +# are used, it may be possible to import the data produced by a later version, +# but loading is aborted if unknown information is encountered. Possible values +# are 'strict' and 'relaxed'. This also applies to replication and the RESTORE +# command. +rdb-version-check strict + +# Enables or disables full sanitization checks for ziplist and listpack etc when +# loading an RDB or RESTORE payload. This reduces the chances of a assertion or +# crash later on while processing commands. +# Options: +# no - Never perform full sanitization +# yes - Always perform full sanitization +# clients - Perform full sanitization only for user connections. +# Excludes: RDB files, RESTORE commands received from the primary +# connection, and client connections which have the +# skip-sanitize-payload ACL flag. +# The default should be 'clients' but since it currently affects cluster +# resharding via MIGRATE, it is temporarily set to 'no' by default. +# +# sanitize-dump-payload no + +# The filename where to dump the DB +dbfilename dump.rdb + +# Remove RDB files used by replication in instances without persistence +# enabled. By default this option is disabled, however there are environments +# where for regulations or other security concerns, RDB files persisted on +# disk by primaries in order to feed replicas, or stored on disk by replicas +# in order to load them for the initial synchronization, should be deleted +# ASAP. Note that this option ONLY WORKS in instances that have both AOF +# and RDB persistence disabled, otherwise is completely ignored. +# +# An alternative (and sometimes better) way to obtain the same effect is +# to use diskless replication on both primary and replicas instances. However +# in the case of replicas, diskless is not always an option. +rdb-del-sync-files no + +# The working directory. +# +# The server log is written relative this directory, if the 'logfile' +# configuration directive is a relative path. +# +# The DB will be written inside this directory, with the filename specified +# above using the 'dbfilename' configuration directive. +# +# The Append Only File will also be created inside this directory. +# +# The Cluster config file is written relative this directory, if the +# 'cluster-config-file' configuration directive is a relative path. +# +# Note that you must specify a directory here, not a file name. +# Note that modifying 'dir' during runtime may have unexpected behavior, +# for example when a child process is running, related file operations may +# have unexpected effects. +dir ./ + +################################# REPLICATION ################################# + +# Master-Replica replication. Use replicaof to make a server a copy of +# another server. A few things to understand ASAP about replication. +# +# +------------------+ +---------------+ +# | Master | ---> | Replica | +# | (receive writes) | | (exact copy) | +# +------------------+ +---------------+ +# +# 1) Replication is asynchronous, but you can configure a primary to +# stop accepting writes if it appears to be not connected with at least +# a given number of replicas. +# 2) Replicas are able to perform a partial resynchronization with the +# primary if the replication link is lost for a relatively small amount of +# time. You may want to configure the replication backlog size (see the next +# sections of this file) with a sensible value depending on your needs. +# 3) Replication is automatic and does not need user intervention. After a +# network partition replicas automatically try to reconnect to primaries +# and resynchronize with them. +# +# replicaof + +# If the primary is password protected (using the "requirepass" configuration +# directive below) it is possible to tell the replica to authenticate before +# starting the replication synchronization process, otherwise the primary will +# refuse the replica request. +# +# primaryauth +# +# However this is not enough if you are using ACLs +# and the default user is not capable of running the PSYNC +# command and/or other commands needed for replication. In this case it's +# better to configure a special user to use with replication, and specify the +# primaryuser configuration as such: +# +# primaryuser +# +# When primaryuser is specified, the replica will authenticate against its +# primary using the new AUTH form: AUTH . + +# When a replica loses its connection with the primary, or when the replication +# is still in progress, the replica can act in two different ways: +# +# 1) if replica-serve-stale-data is set to 'yes' (the default) the replica will +# still reply to client requests, possibly with out of date data, or the +# data set may just be empty if this is the first synchronization. +# +# 2) If replica-serve-stale-data is set to 'no' the replica will reply with error +# "MASTERDOWN Link with MASTER is down and replica-serve-stale-data is set to 'no'" +# to all data access commands, excluding commands such as: +# INFO, REPLICAOF, AUTH, SHUTDOWN, REPLCONF, ROLE, CONFIG, SUBSCRIBE, +# UNSUBSCRIBE, PSUBSCRIBE, PUNSUBSCRIBE, PUBLISH, PUBSUB, COMMAND, POST, +# HOST and LATENCY. +# +replica-serve-stale-data yes + +# You can configure a replica instance to accept writes or not. Writing against +# a replica instance may be useful to store some ephemeral data (because data +# written on a replica will be easily deleted after resync with the primary) but +# may also cause problems if clients are writing to it because of a +# misconfiguration. +# +# By default, replicas are read-only. +# +# Note: read only replicas are not designed to be exposed to untrusted clients +# on the internet. It's just a protection layer against misuse of the instance. +# Still a read only replica exports by default all the administrative commands +# such as CONFIG, DEBUG, and so forth. To a limited extent you can improve +# security of read only replicas using 'rename-command' to shadow all the +# administrative / dangerous commands. +replica-read-only yes + +# Replication SYNC strategy: disk or socket. +# +# New replicas and reconnecting replicas that are not able to continue the +# replication process just receiving differences, need to do what is called a +# "full synchronization". An RDB file is transmitted from the primary to the +# replicas. +# +# The transmission can happen in two different ways: +# +# 1) Disk-backed: The primary creates a new process that writes the RDB +# file on disk. Later the file is transferred by the parent +# process to the replicas incrementally. +# 2) Diskless: The primary creates a new process that directly writes the +# RDB file to replica sockets, without touching the disk at all. +# +# With disk-backed replication, while the RDB file is generated, more replicas +# can be queued and served with the RDB file as soon as the current child +# producing the RDB file finishes its work. With diskless replication instead +# once the transfer starts, new replicas arriving will be queued and a new +# transfer will start when the current one terminates. +# +# When diskless replication is used, the primary waits a configurable amount of +# time (in seconds) before starting the transfer in the hope that multiple +# replicas will arrive and the transfer can be parallelized. +# +# With slow disks and fast (large bandwidth) networks, diskless replication +# works better. +repl-diskless-sync yes + +# When diskless replication is enabled, it is possible to configure the delay +# the server waits in order to spawn the child that transfers the RDB via socket +# to the replicas. +# +# This is important since once the transfer starts, it is not possible to serve +# new replicas arriving, that will be queued for the next RDB transfer, so the +# server waits a delay in order to let more replicas arrive. +# +# The delay is specified in seconds, and by default is 5 seconds. To disable +# it entirely just set it to 0 seconds and the transfer will start ASAP. +repl-diskless-sync-delay 5 + +# When diskless replication is enabled with a delay, it is possible to let +# the replication start before the maximum delay is reached if the maximum +# number of replicas expected have connected. Default of 0 means that the +# maximum is not defined and the server will wait the full delay. +repl-diskless-sync-max-replicas 0 + +# ----------------------------------------------------------------------------- +# WARNING: Since in this setup the replica does not immediately store an RDB on +# disk, it may cause data loss during failovers. RDB diskless load + server +# modules not handling I/O reads may cause the server to abort in case of I/O errors +# during the initial synchronization stage with the primary. +# ----------------------------------------------------------------------------- +# +# Replica can load the RDB it reads from the replication link directly from the +# socket, or store the RDB to a file and read that file after it was completely +# received from the primary. +# +# In many cases the disk is slower than the network, and storing and loading +# the RDB file may increase replication time (and even increase the primary's +# Copy on Write memory and replica buffers). +# However, when parsing the RDB file directly from the socket, in order to avoid +# data loss it's only safe to flush the current dataset when the new dataset is +# fully loaded in memory, resulting in higher memory usage. +# For this reason we have the following options: +# +# "disabled" - Don't use diskless load (store the rdb file to the disk first) +# "swapdb" - Keep current db contents in RAM while parsing the data directly +# from the socket. Replicas in this mode can keep serving current +# dataset while replication is in progress, except for cases where +# they can't recognize primary as having a data set from same +# replication history. +# Note that this requires sufficient memory, if you don't have it, +# you risk an OOM kill. +# "on-empty-db" - Use diskless load only when current dataset is empty. This is +# safer and avoid having old and new dataset loaded side by side +# during replication. +# "flush-before-load" - [dangerous] Flush all data before parsing. Note that if +# there's a problem before the replication succeeded you may +# lose all your data. +repl-diskless-load disabled + +# This dual channel replication sync feature optimizes the full synchronization process +# between a primary and its replicas. When enabled, it reduces both memory and CPU load +# on the primary server. +# +# How it works: +# 1. During full sync, instead of accumulating replication data on the primary server, +# the data is sent directly to the syncing replica. +# 2. The primary's background save (bgsave) process streams the RDB snapshot directly +# to the replica over a separate connection. +# +# Tradeoff: +# While this approach reduces load on the primary, it shifts the burden of storing +# the replication buffer to the replica. This means the replica must have sufficient +# memory to accommodate the buffer during synchronization. However, this tradeoff is +# generally beneficial as it prevents potential performance degradation on the primary +# server, which is typically handling more critical operations. +# +# During the dual channel full sync, the maximum size of the local replication buffer +# on the replica is limited by the hard limit of the replica client output buffer on +# the replica side. When the replica reaches the limit, it will stop accumulating the +# further data. At this point, any additional data accumulation will occur on primary +# side, which is depending on the replica client output buffer on the primary side. +# +# When toggling this configuration on or off during an ongoing synchronization process, +# it does not change the already running sync method. The new configuration will take +# effect only for subsequent synchronization processes. +# +# To enable dual channel replication, both the primary and its replicas should have +# dual-channel-replication-enabled set to yes. Additionally, the primary is required +# to have repl-diskless-sync enabled, as this allows the RDB snapshot to be streamed +# directly over the connection for the dual channel mechanism to function properly. +# +dual-channel-replication-enabled no + +# Master send PINGs to its replicas in a predefined interval. It's possible to +# change this interval with the repl_ping_replica_period option. The default +# value is 10 seconds. +# +# repl-ping-replica-period 10 + +# The following option sets the replication timeout for: +# +# 1) Bulk transfer I/O during SYNC, from the point of view of replica. +# 2) Master timeout from the point of view of replicas (data, pings). +# 3) Replica timeout from the point of view of primaries (REPLCONF ACK pings). +# +# It is important to make sure that this value is greater than the value +# specified for repl-ping-replica-period otherwise a timeout will be detected +# every time there is low traffic between the primary and the replica. The default +# value is 60 seconds. +# +# repl-timeout 60 + +# Disable TCP_NODELAY on the replica socket after SYNC? +# +# If you select "yes", the server will use a smaller number of TCP packets and +# less bandwidth to send data to replicas. But this can add a delay for +# the data to appear on the replica side, up to 40 milliseconds with +# Linux kernels using a default configuration. +# +# If you select "no" the delay for data to appear on the replica side will +# be reduced but more bandwidth will be used for replication. +# +# By default we optimize for low latency, but in very high traffic conditions +# or when the primary and replicas are many hops away, turning this to "yes" may +# be a good idea. +repl-disable-tcp-nodelay no + +# Enables MPTCP for the replica's connection to the primary. +# +# An MPTCP connection is established between the primary and the replica if +# the replica has set 'repl-mptcp yes' and the primary has set 'mptcp yes'. +# Otherwise, it will automatically and implicitly fall back to a regular TCP +# connection. +# +# repl-mptcp no + +# Set the replication backlog size. The backlog is a buffer that accumulates +# replica data when replicas are disconnected for some time, so that when a +# replica wants to reconnect again, often a full resync is not needed, but a +# partial resync is enough, just passing the portion of data the replica +# missed while disconnected. +# +# The bigger the replication backlog, the longer the replica can endure the +# disconnect and later be able to perform a partial resynchronization. +# +# The backlog is only allocated if there is at least one replica connected. +# +# repl-backlog-size 10mb + +# After a primary has no connected replicas for some time, the backlog will be +# freed. The following option configures the amount of seconds that need to +# elapse, starting from the time the last replica disconnected, for the backlog +# buffer to be freed. +# +# Note that replicas never free the backlog for timeout, since they may be +# promoted to primaries later, and should be able to correctly "partially +# resynchronize" with other replicas: hence they should always accumulate backlog. +# +# A value of 0 means to never release the backlog. +# +# repl-backlog-ttl 3600 + +# The replica priority is an integer number published by the server in the INFO +# output. It is used by Sentinel in order to select a replica to promote +# into a primary if the primary is no longer working correctly. +# +# A replica with a low priority number is considered better for promotion, so +# for instance if there are three replicas with priority 10, 100, 25 Sentinel +# will pick the one with priority 10, that is the lowest. +# +# However a special priority of 0 marks the replica as not able to perform the +# role of primary, so a replica with priority of 0 will never be selected by +# Sentinel for promotion. +# +# By default the priority is 100. +replica-priority 100 + +# The propagation error behavior controls how the server will behave when it is +# unable to handle a command being processed in the replication stream from a primary +# or processed while reading from an AOF file. Errors that occur during propagation +# are unexpected, and can cause data inconsistency. +# +# If an application wants to ensure there is no data divergence, this configuration +# should be set to 'panic' instead. The value can also be set to 'panic-on-replicas' +# to only panic when a replica encounters an error on the replication stream. One of +# these two panic values will become the default value in the future once there are +# sufficient safety mechanisms in place to prevent false positive crashes. +# +# propagation-error-behavior ignore + +# Replica ignore disk write errors controls the behavior of a replica when it is +# unable to persist a write command received from its primary to disk. By default, +# this configuration is set to 'no' and will crash the replica in this condition. +# It is not recommended to change this default. +# +# replica-ignore-disk-write-errors no + +# Make the primary forbid expiration and eviction. +# This is useful for sync tools, because expiration and eviction may cause the data corruption. +# Sync tools can mark their connections as importing source by CLIENT IMPORT-SOURCE. +# NOTICE: Clients should avoid writing the same key on the source server and the destination server. +# +# import-mode no + +# ----------------------------------------------------------------------------- +# By default, Sentinel includes all replicas in its reports. A replica +# can be excluded from Sentinel's announcements. An unannounced replica +# will be ignored by the 'sentinel replicas ' command and won't be +# exposed to Sentinel's clients. +# +# This option does not change the behavior of replica-priority. Even with +# replica-announced set to 'no', the replica can be promoted to primary. To +# prevent this behavior, set replica-priority to 0. +# +# replica-announced yes + +# It is possible for a primary to stop accepting writes if there are less than +# N replicas connected, having a lag less or equal than M seconds. +# +# The N replicas need to be in "online" state. +# +# The lag in seconds, that must be <= the specified value, is calculated from +# the last ping received from the replica, that is usually sent every second. +# +# This option does not GUARANTEE that N replicas will accept the write, but +# will limit the window of exposure for lost writes in case not enough replicas +# are available, to the specified number of seconds. +# +# For example to require at least 3 replicas with a lag <= 10 seconds use: +# +# min-replicas-to-write 3 +# min-replicas-max-lag 10 +# +# Setting one or the other to 0 disables the feature. +# +# By default min-replicas-to-write is set to 0 (feature disabled) and +# min-replicas-max-lag is set to 10. + +# A primary is able to list the address and port of the attached +# replicas in different ways. For example the "INFO replication" section +# offers this information, which is used, among other tools, by +# Sentinel in order to discover replica instances. +# Another place where this info is available is in the output of the +# "ROLE" command of a primary. +# +# The listed IP address and port normally reported by a replica is +# obtained in the following way: +# +# IP: The address is auto detected by checking the peer address +# of the socket used by the replica to connect with the primary. +# +# Port: The port is communicated by the replica during the replication +# handshake, and is normally the port that the replica is using to +# listen for connections. +# +# However when port forwarding or Network Address Translation (NAT) is +# used, the replica may actually be reachable via different IP and port +# pairs. The following two options can be used by a replica in order to +# report to its primary a specific set of IP and port, so that both INFO +# and ROLE will report those values. +# +# There is no need to use both the options if you need to override just +# the port or the IP address. +# +# replica-announce-ip 5.5.5.5 +# replica-announce-port 1234 + +############################### KEYS TRACKING ################################# + +# The client side caching of values is assisted via server-side support. +# This is implemented using an invalidation table that remembers, using +# a radix key indexed by key name, what clients have which keys. In turn +# this is used in order to send invalidation messages to clients. Please +# check this page to understand more about the feature: +# +# https://valkey.io/topics/client-side-caching +# +# When tracking is enabled for a client, all the read only queries are assumed +# to be cached: this will force the server to store information in the invalidation +# table. When keys are modified, such information is flushed away, and +# invalidation messages are sent to the clients. However if the workload is +# heavily dominated by reads, the server could use more and more memory in order +# to track the keys fetched by many clients. +# +# For this reason it is possible to configure a maximum fill value for the +# invalidation table. By default it is set to 1M of keys, and once this limit +# is reached, the server will start to evict keys in the invalidation table +# even if they were not modified, just to reclaim memory: this will in turn +# force the clients to invalidate the cached values. Basically the table +# maximum size is a trade off between the memory you want to spend server +# side to track information about who cached what, and the ability of clients +# to retain cached objects in memory. +# +# If you set the value to 0, it means there are no limits, and the server will +# retain as many keys as needed in the invalidation table. +# In the "stats" INFO section, you can find information about the number of +# keys in the invalidation table at every given moment. +# +# Note: when key tracking is used in broadcasting mode, no memory is used +# in the server side so this setting is useless. +# +# tracking-table-max-keys 1000000 + +################################## SECURITY ################################### + +# Warning: since the server is pretty fast, an outside user can try up to +# 1 million passwords per second against a modern box. This means that you +# should use very strong passwords, otherwise they will be very easy to break. +# Note that because the password is really a shared secret between the client +# and the server, and should not be memorized by any human, the password +# can be easily a long string from /dev/urandom or whatever, so by using a +# long and unguessable password no brute force attack will be possible. + +# ACL users are defined in the following format: +# +# user ... acl rules ... +# +# For example: +# +# user worker +@list +@connection ~jobs:* on >ffa9203c493aa99 +# +# The special username "default" is used for new connections. If this user +# has the "nopass" rule, then new connections will be immediately authenticated +# as the "default" user without the need of any password provided via the +# AUTH command. Otherwise if the "default" user is not flagged with "nopass" +# the connections will start in not authenticated state, and will require +# AUTH (or the HELLO command AUTH option) in order to be authenticated and +# start to work. +# +# The ACL rules that describe what a user can do are the following: +# +# on Enable the user: it is possible to authenticate as this user. +# off Disable the user: it's no longer possible to authenticate +# with this user, however the already authenticated connections +# will still work. +# skip-sanitize-payload RESTORE dump-payload sanitization is skipped. +# sanitize-payload RESTORE dump-payload is sanitized (default). +# + Allow the execution of that command. +# May be used with `|` for allowing subcommands (e.g "+config|get") +# - Disallow the execution of that command. +# May be used with `|` for blocking subcommands (e.g "-config|set") +# +@ Allow the execution of all the commands in such category +# with valid categories are like @admin, @set, @sortedset, ... +# and so forth, see the full list in the server.c file where +# the server command table is described and defined. +# The special category @all means all the commands, but currently +# present in the server, and that will be loaded in the future +# via modules. +# +|first-arg Allow a specific first argument of an otherwise +# disabled command. It is only supported on commands with +# no sub-commands, and is not allowed as negative form +# like -SELECT|1, only additive starting with "+". This +# feature is deprecated and may be removed in the future. +# allcommands Alias for +@all. Note that it implies the ability to execute +# all the future commands loaded via the modules system. +# nocommands Alias for -@all. +# ~ Add a pattern of keys that can be mentioned as part of +# commands. For instance ~* allows all the keys. The pattern +# is a glob-style pattern like the one of KEYS. +# It is possible to specify multiple patterns. +# %R~ Add key read pattern that specifies which keys can be read +# from. +# %W~ Add key write pattern that specifies which keys can be +# written to. +# allkeys Alias for ~* +# resetkeys Flush the list of allowed keys patterns. +# & Add a glob-style pattern of Pub/Sub channels that can be +# accessed by the user. It is possible to specify multiple channel +# patterns. +# allchannels Alias for &* +# resetchannels Flush the list of allowed channel patterns. +# > Add this password to the list of valid password for the user. +# For example >mypass will add "mypass" to the list. +# This directive clears the "nopass" flag (see later). +# < Remove this password from the list of valid passwords. +# nopass All the set passwords of the user are removed, and the user +# is flagged as requiring no password: it means that every +# password will work against this user. If this directive is +# used for the default user, every new connection will be +# immediately authenticated with the default user without +# any explicit AUTH command required. Note that the "resetpass" +# directive will clear this condition. +# resetpass Flush the list of allowed passwords. Moreover removes the +# "nopass" status. After "resetpass" the user has no associated +# passwords and there is no way to authenticate without adding +# some password (or setting it as "nopass" later). +# reset Performs the following actions: resetpass, resetkeys, resetchannels, +# allchannels (if acl-pubsub-default is set), off, clearselectors, -@all. +# The user returns to the same state it has immediately after its creation. +# () Create a new selector with the options specified within the +# parentheses and attach it to the user. Each option should be +# space separated. The first character must be ( and the last +# character must be ). +# clearselectors Remove all of the currently attached selectors. +# Note this does not change the "root" user permissions, +# which are the permissions directly applied onto the +# user (outside the parentheses). +# +# ACL rules can be specified in any order: for instance you can start with +# passwords, then flags, or key patterns. However note that the additive +# and subtractive rules will CHANGE MEANING depending on the ordering. +# For instance see the following example: +# +# user alice on +@all -DEBUG ~* >somepassword +# +# This will allow "alice" to use all the commands with the exception of the +# DEBUG command, since +@all added all the commands to the set of the commands +# alice can use, and later DEBUG was removed. However if we invert the order +# of two ACL rules the result will be different: +# +# user alice on -DEBUG +@all ~* >somepassword +# +# Now DEBUG was removed when alice had yet no commands in the set of allowed +# commands, later all the commands are added, so the user will be able to +# execute everything. +# +# Basically ACL rules are processed left-to-right. +# +# The following is a list of command categories and their meanings: +# * keyspace - Writing or reading from keys, databases, or their metadata +# in a type agnostic way. Includes DEL, RESTORE, DUMP, RENAME, EXISTS, DBSIZE, +# KEYS, EXPIRE, TTL, FLUSHALL, etc. Commands that may modify the keyspace, +# key or metadata will also have `write` category. Commands that only read +# the keyspace, key or metadata will have the `read` category. +# * read - Reading from keys (values or metadata). Note that commands that don't +# interact with keys, will not have either `read` or `write`. +# * write - Writing to keys (values or metadata) +# * admin - Administrative commands. Normal applications will never need to use +# these. Includes REPLICAOF, CONFIG, DEBUG, SAVE, MONITOR, ACL, SHUTDOWN, etc. +# * dangerous - Potentially dangerous (each should be considered with care for +# various reasons). This includes FLUSHALL, MIGRATE, RESTORE, SORT, KEYS, +# CLIENT, DEBUG, INFO, CONFIG, SAVE, REPLICAOF, etc. +# * connection - Commands affecting the connection or other connections. +# This includes AUTH, SELECT, COMMAND, CLIENT, ECHO, PING, etc. +# * blocking - Potentially blocking the connection until released by another +# command. +# * fast - Fast O(1) commands. May loop on the number of arguments, but not the +# number of elements in the key. +# * slow - All commands that are not Fast. +# * pubsub - PUBLISH / SUBSCRIBE related +# * transaction - WATCH / MULTI / EXEC related commands. +# * scripting - Scripting related. +# * set - Data type: sets related. +# * sortedset - Data type: zsets related. +# * list - Data type: lists related. +# * hash - Data type: hashes related. +# * string - Data type: strings related. +# * bitmap - Data type: bitmaps related. +# * hyperloglog - Data type: hyperloglog related. +# * geo - Data type: geo related. +# * stream - Data type: streams related. +# +# For more information about ACL configuration please refer to +# the Valkey web site at https://valkey.io/topics/acl + +# ACL LOG +# +# The ACL Log tracks failed commands and authentication events associated +# with ACLs. The ACL Log is useful to troubleshoot failed commands blocked +# by ACLs. The ACL Log is stored in memory. You can reclaim memory with +# ACL LOG RESET. Define the maximum entry length of the ACL Log below. +acllog-max-len 128 + +# Using an external ACL file +# +# Instead of configuring users here in this file, it is possible to use +# a stand-alone file just listing users. The two methods cannot be mixed: +# if you configure users here and at the same time you activate the external +# ACL file, the server will refuse to start. +# +# The format of the external ACL user file is exactly the same as the +# format that is used inside valkey.conf to describe users. +# +# aclfile /etc/valkey/users.acl + +# IMPORTANT NOTE: "requirepass" is just a compatibility +# layer on top of the new ACL system. The option effect will be just setting +# the password for the default user. Clients will still authenticate using +# AUTH as usually, or more explicitly with AUTH default +# if they follow the new protocol: both will work. +# +# The requirepass is not compatible with aclfile option and the ACL LOAD +# command, these will cause requirepass to be ignored. +# +requirepass valkey + +# The default Pub/Sub channels permission for new users is controlled by the +# acl-pubsub-default configuration directive, which accepts one of these values: +# +# allchannels: grants access to all Pub/Sub channels +# resetchannels: revokes access to all Pub/Sub channels +# +# acl-pubsub-default defaults to 'resetchannels' permission. +# +# acl-pubsub-default resetchannels + +# Command renaming (DEPRECATED). +# +# ------------------------------------------------------------------------ +# WARNING: avoid using this option if possible. Instead use ACLs to remove +# commands from the default user, and put them only in some admin user you +# create for administrative purposes. +# ------------------------------------------------------------------------ +# +# It is possible to change the name of dangerous commands in a shared +# environment. For instance the CONFIG command may be renamed into something +# hard to guess so that it will still be available for internal-use tools +# but not available for general clients. +# +# Example: +# +# rename-command CONFIG b840fc02d524045429941cc15f59e41cb7be6c52 +# +# It is also possible to completely kill a command by renaming it into +# an empty string: +# +# rename-command CONFIG "" +# +# Please note that changing the name of commands that are logged into the +# AOF file or transmitted to replicas may cause problems. + +################################### CLIENTS #################################### + +# Set the max number of connected clients at the same time. By default +# this limit is set to 10000 clients, however if the server is not +# able to configure the process file limit to allow for the specified limit +# the max number of allowed clients is set to the current file limit +# minus 32 (as the server reserves a few file descriptors for internal uses). +# +# Once the limit is reached the server will close all the new connections sending +# an error 'max number of clients reached'. +# +# IMPORTANT: With a cluster-enabled setup, the max number of connections is also +# shared with the cluster bus: every node in the cluster will use two +# connections, one incoming and another outgoing. It is important to size the +# limit accordingly in case of very large clusters. +# +# maxclients 10000 + +############################## MEMORY MANAGEMENT ################################ + +# Set a memory usage limit to the specified amount of bytes. +# When the memory limit is reached the server will try to remove keys +# according to the eviction policy selected (see maxmemory-policy). +# +# If the server can't remove keys according to the policy, or if the policy is +# set to 'noeviction', the server will start to reply with errors to commands +# that would use more memory, like SET, LPUSH, and so on, and will continue +# to reply to read-only commands like GET. +# +# This option is usually useful when using the server as an LRU or LFU cache, or to +# set a hard memory limit for an instance (using the 'noeviction' policy). +# +# WARNING: If you have replicas attached to an instance with maxmemory on, +# the size of the output buffers needed to feed the replicas are subtracted +# from the used memory count, so that network problems / resyncs will +# not trigger a loop where keys are evicted, and in turn the output +# buffer of replicas is full with DELs of keys evicted triggering the deletion +# of more keys, and so forth until the database is completely emptied. +# +# In short... if you have replicas attached it is suggested that you set a lower +# limit for maxmemory so that there is some free RAM on the system for replica +# output buffers (but this is not needed if the policy is 'noeviction'). +# +# maxmemory + +# MAXMEMORY POLICY: how the server will select what to remove when maxmemory +# is reached. You can select one from the following behaviors: +# +# volatile-lru -> Evict using approximated LRU, only keys with an expire set. +# allkeys-lru -> Evict any key using approximated LRU. +# volatile-lfu -> Evict using approximated LFU, only keys with an expire set. +# allkeys-lfu -> Evict any key using approximated LFU. +# volatile-random -> Remove a random key having an expire set. +# allkeys-random -> Remove a random key, any key. +# volatile-ttl -> Remove the key with the nearest expire time (minor TTL) +# noeviction -> Don't evict anything, just return an error on write operations. +# +# LRU means Least Recently Used +# LFU means Least Frequently Used +# +# Both LRU, LFU and volatile-ttl are implemented using approximated +# randomized algorithms. +# +# Note: with any of the above policies, when there are no suitable keys for +# eviction, the server will return an error on write operations that require +# more memory. These are usually commands that create new keys, add data or +# modify existing keys. A few examples are: SET, INCR, HSET, LPUSH, SUNIONSTORE, +# SORT (due to the STORE argument), and EXEC (if the transaction includes any +# command that requires memory). +# +# The default is: +# +# maxmemory-policy noeviction + +# LRU, LFU and minimal TTL algorithms are not precise algorithms but approximated +# algorithms (in order to save memory), so you can tune it for speed or +# accuracy. By default the server will check five keys and pick the one that was +# used least recently, you can change the sample size using the following +# configuration directive. +# +# The default of 5 produces good enough results. 10 Approximates very closely +# true LRU but costs more CPU. 3 is faster but not very accurate. The maximum +# value that can be set is 64. +# +# maxmemory-samples 5 + +# Eviction processing is designed to function well with the default setting. +# If there is an unusually large amount of write traffic, this value may need to +# be increased. Decreasing this value may reduce latency at the risk of +# eviction processing effectiveness +# 0 = minimum latency, 10 = default, 100 = process without regard to latency +# +# maxmemory-eviction-tenacity 10 + +# By default a replica will ignore its maxmemory setting +# (unless it is promoted to primary after a failover or manually). It means +# that the eviction of keys will be just handled by the primary, sending the +# DEL commands to the replica as keys evict in the primary side. +# +# This behavior ensures that primaries and replicas stay consistent, and is usually +# what you want, however if your replica is writable, or you want the replica +# to have a different memory setting, and you are sure all the writes performed +# to the replica are idempotent, then you may change this default (but be sure +# to understand what you are doing). +# +# Note that since the replica by default does not evict, it may end using more +# memory than the one set via maxmemory (there are certain buffers that may +# be larger on the replica, or data structures may sometimes take more memory +# and so forth). So make sure you monitor your replicas and make sure they +# have enough memory to never hit a real out-of-memory condition before the +# primary hits the configured maxmemory setting. +# +# replica-ignore-maxmemory yes + +# The server reclaims expired keys in two ways: upon access when those keys are +# found to be expired, and also in the background, in what is called the +# "active expire key". The key space is slowly and incrementally scanned +# looking for expired keys to reclaim, so that it is possible to free memory +# of keys that are expired and will never be accessed again in a short time. +# +# The default effort of the expire cycle will try to avoid having more than +# ten percent of expired keys still in memory, and will try to avoid consuming +# more than 25% of total memory and to add latency to the system. However +# it is possible to increase the expire "effort" that is normally set to +# "1", to a greater value, up to the value "10". At its maximum value the +# system will use more CPU, longer cycles (and technically may introduce +# more latency), and will tolerate less already expired keys still present +# in the system. It's a tradeoff between memory, CPU and latency. +# +# active-expire-effort 1 + +############################# LAZY FREEING #################################### + +# When keys are deleted, the served has historically freed their memory using +# blocking operations. It means that the server stopped processing new commands +# in order to reclaim all the memory associated with an object in a synchronous +# way. If the key deleted is associated with a small object, the time needed +# in order to execute the DEL command is very small and comparable to most other +# O(1) or O(log_N) commands in the server. However if the key is associated with an +# aggregated value containing millions of elements, the server can block for +# a long time (even seconds) in order to complete the operation. +# +# For the above reasons, lazy freeing (or asynchronous freeing), has been +# introduced. With lazy freeing, keys are deleted in constant time. Another +# thread will incrementally free the object in the background as fast as +# possible. +# +# Starting from Valkey 8.0, lazy freeing is enabled by default. It is possible +# to retain the synchronous freeing behaviour by setting the lazyfree related +# configuration directives to 'no'. + +# Commands like DEL, FLUSHALL and FLUSHDB delete keys, but the server can also +# delete keys or flush the whole database as a side effect of other operations. +# Specifically the server deletes objects independently of a user call in the +# following scenarios: +# +# 1) On eviction, because of the maxmemory and maxmemory policy configurations, +# in order to make room for new data, without going over the specified +# memory limit. +# 2) Because of expire: when a key with an associated time to live (see the +# EXPIRE command) must be deleted from memory. +# 3) Because of a side effect of a command that stores data on a key that may +# already exist. For example the RENAME command may delete the old key +# content when it is replaced with another one. Similarly SUNIONSTORE +# or SORT with STORE option may delete existing keys. The SET command +# itself removes any old content of the specified key in order to replace +# it with the specified string. +# 4) During replication, when a replica performs a full resynchronization with +# its primary, the content of the whole database is removed in order to +# load the RDB file just transferred. +# +# In all the above cases, the default is to release memory in a non-blocking +# way. + +lazyfree-lazy-eviction yes +lazyfree-lazy-expire yes +lazyfree-lazy-server-del yes +replica-lazy-flush yes + +# For keys deleted using the DEL command, lazy freeing is controlled by the +# configuration directive 'lazyfree-lazy-user-del'. The default is 'yes'. The +# UNLINK command is identical to the DEL command, except that UNLINK always +# frees the memory lazily, regardless of this configuration directive: + +lazyfree-lazy-user-del yes + +# FLUSHDB, FLUSHALL, SCRIPT FLUSH and FUNCTION FLUSH support both asynchronous and synchronous +# deletion, which can be controlled by passing the [SYNC|ASYNC] flags into the +# commands. When neither flag is passed, this directive will be used to determine +# if the data should be deleted asynchronously. +# +# When a replica performs a node reset via CLUSTER RESET, the entire +# database content is removed to allow the node to become an empty primary. +# This directive also determines whether the data should be deleted asynchronously. +# +# There are many problems with running flush synchronously. Even in single CPU +# environments, the thread managers should balance between the freeing and +# serving incoming requests. The default value is yes. + +lazyfree-lazy-user-flush yes + +################################ THREADED I/O ################################# + +# The server is mostly single threaded, however there are certain threaded +# operations such as UNLINK, slow I/O accesses and other things that are +# performed on side threads. +# +# Now it is also possible to handle the server clients socket reads and writes +# in different I/O threads. Since especially writing is so slow, normally +# users use pipelining in order to speed up the server performances per +# core, and spawn multiple instances in order to scale more. Using I/O +# threads it is possible to easily speedup two times the server without resorting +# to pipelining nor sharding of the instance. +# +# By default threading is disabled, we suggest enabling it only in machines +# that have at least 3 or more cores, leaving at least one spare core. +# We also recommend using threaded I/O only if you actually have performance problems, with +# instances being able to use a quite big percentage of CPU time, otherwise +# there is no point in using this feature. +# +# So for instance if you have a four cores boxes, try to use 2 or 3 I/O +# threads, if you have a 8 cores, try to use 6 threads. In order to +# enable I/O threads use the following configuration directive: +# +# io-threads 4 +# +# Setting io-threads to 1 will just use the main thread as usual. +# When I/O threads are enabled, we use threads for reads and writes, that is +# to thread the write and read syscall and transfer the client buffers to the +# socket and to enable threading of reads and protocol parsing. +# +# +# NOTE: +# 1. The 'io-threads-do-reads' config is deprecated and has no effect. Please +# avoid using this config if possible. +# +# 2. If you want to test the server speedup using valkey-benchmark, make +# sure you also run the benchmark itself in threaded mode, using the +# --threads option to match the number of server threads, otherwise you'll not +# be able to notice the improvements. + +############################ KERNEL OOM CONTROL ############################## + +# On Linux, it is possible to hint the kernel OOM killer on what processes +# should be killed first when out of memory. +# +# Enabling this feature makes the server actively control the oom_score_adj value +# for all its processes, depending on their role. The default scores will +# attempt to have background child processes killed before all others, and +# replicas killed before primaries. +# +# The server supports these options: +# +# no: Don't make changes to oom-score-adj (default). +# yes: Alias to "relative" see below. +# absolute: Values in oom-score-adj-values are written as is to the kernel. +# relative: Values are used relative to the initial value of oom_score_adj when +# the server starts and are then clamped to a range of -1000 to 1000. +# Because typically the initial value is 0, they will often match the +# absolute values. +oom-score-adj no + +# When oom-score-adj is used, this directive controls the specific values used +# for primary, replica and background child processes. Values range -2000 to +# 2000 (higher means more likely to be killed). +# +# Unprivileged processes (not root, and without CAP_SYS_RESOURCE capabilities) +# can freely increase their value, but not decrease it below its initial +# settings. This means that setting oom-score-adj to "relative" and setting the +# oom-score-adj-values to positive values will always succeed. +oom-score-adj-values 0 200 800 + + +#################### KERNEL transparent hugepage CONTROL ###################### + +# Usually the kernel Transparent Huge Pages control is set to "madvise" or +# "never" by default (/sys/kernel/mm/transparent_hugepage/enabled), in which +# case this config has no effect. On systems in which it is set to "always", +# the server will attempt to disable it specifically for the server process in order +# to avoid latency problems specifically with fork(2) and CoW. +# If for some reason you prefer to keep it enabled, you can set this config to +# "no" and the kernel global to "always". + +disable-thp yes + +############################## APPEND ONLY MODE ############################### + +# By default the server asynchronously dumps the dataset on disk. This mode is +# good enough in many applications, but an issue with the server process or +# a power outage may result into a few minutes of writes lost (depending on +# the configured save points). +# +# The Append Only File is an alternative persistence mode that provides +# much better durability. For instance using the default data fsync policy +# (see later in the config file) the server can lose just one second of writes in a +# dramatic event like a server power outage, or a single write if something +# wrong with the process itself happens, but the operating system is +# still running correctly. +# +# AOF and RDB persistence can be enabled at the same time without problems. +# If the AOF is enabled on startup the server will load the AOF, that is the file +# with the better durability guarantees. +# +# Note that changing this value in a config file of an existing database and +# restarting the server can lead to data loss. A conversion needs to be done +# by setting it via CONFIG command on a live server first. +# +# Please check https://valkey.io/topics/persistence for more information. + +appendonly no + +# The base name of the append only file. +# +# The server uses a set of append-only files to persist the dataset +# and changes applied to it. There are two basic types of files in use: +# +# - Base files, which are a snapshot representing the complete state of the +# dataset at the time the file was created. Base files can be either in +# the form of RDB (binary serialized) or AOF (textual commands). +# - Incremental files, which contain additional commands that were applied +# to the dataset following the previous file. +# +# In addition, manifest files are used to track the files and the order in +# which they were created and should be applied. +# +# Append-only file names are created by the server following a specific pattern. +# The file name's prefix is based on the 'appendfilename' configuration +# parameter, followed by additional information about the sequence and type. +# +# For example, if appendfilename is set to appendonly.aof, the following file +# names could be derived: +# +# - appendonly.aof.1.base.rdb as a base file. +# - appendonly.aof.1.incr.aof, appendonly.aof.2.incr.aof as incremental files. +# - appendonly.aof.manifest as a manifest file. + +appendfilename "appendonly.aof" + +# For convenience, the server stores all persistent append-only files in a dedicated +# directory. The name of the directory is determined by the appenddirname +# configuration parameter. + +appenddirname "appendonlydir" + +# The fsync() call tells the Operating System to actually write data on disk +# instead of waiting for more data in the output buffer. Some OS will really flush +# data on disk, some other OS will just try to do it ASAP. +# +# The server supports three different modes: +# +# no: don't fsync, just let the OS flush the data when it wants. Faster. +# always: fsync after every write to the append only log. Slow, Safest. +# everysec: fsync only one time every second. Compromise. +# +# The default is "everysec", as that's usually the right compromise between +# speed and data safety. It's up to you to understand if you can relax this to +# "no" that will let the operating system flush the output buffer when +# it wants, for better performances (but if you can live with the idea of +# some data loss consider the default persistence mode that's snapshotting), +# or on the contrary, use "always" that's very slow but a bit safer than +# everysec. +# +# More details please check the following article: +# http://antirez.com/post/redis-persistence-demystified.html +# +# If unsure, use "everysec". + +# appendfsync always +appendfsync everysec +# appendfsync no + +# When the AOF fsync policy is set to always or everysec, and a background +# saving process (a background save or AOF log background rewriting) is +# performing a lot of I/O against the disk, in some Linux configurations +# the server may block too long on the fsync() call. Note that there is no fix for +# this currently, as even performing fsync in a different thread will block +# our synchronous write(2) call. +# +# In order to mitigate this problem it's possible to use the following option +# that will prevent fsync() from being called in the main process while a +# BGSAVE or BGREWRITEAOF is in progress. +# +# This means that while another child is saving, the durability of the server is +# the same as "appendfsync no". In practical terms, this means that it is +# possible to lose up to 30 seconds of log in the worst scenario (with the +# default Linux settings). +# +# If you have latency problems turn this to "yes". Otherwise leave it as +# "no" that is the safest pick from the point of view of durability. + +no-appendfsync-on-rewrite no + +# Automatic rewrite of the append only file. +# The server is able to automatically rewrite the log file implicitly calling +# BGREWRITEAOF when the AOF log size grows by the specified percentage. +# +# This is how it works: The server remembers the size of the AOF file after the +# latest rewrite (if no rewrite has happened since the restart, the size of +# the AOF at startup is used). +# +# This base size is compared to the current size. If the current size is +# bigger than the specified percentage, the rewrite is triggered. Also +# you need to specify a minimal size for the AOF file to be rewritten, this +# is useful to avoid rewriting the AOF file even if the percentage increase +# is reached but it is still pretty small. +# +# Specify a percentage of zero in order to disable the automatic AOF +# rewrite feature. + +auto-aof-rewrite-percentage 100 +auto-aof-rewrite-min-size 64mb + +# An AOF file may be found to be truncated at the end during the server +# startup process, when the AOF data gets loaded back into memory. +# This may happen when the system where the server is running +# crashes, especially when an ext4 filesystem is mounted without the +# data=ordered option (however this can't happen when the server itself +# crashes or aborts but the operating system still works correctly). +# +# The server can either exit with an error when this happens, or load as much +# data as possible (the default now) and start if the AOF file is found +# to be truncated at the end. The following option controls this behavior. +# +# If aof-load-truncated is set to yes, a truncated AOF file is loaded and +# the server starts emitting a log to inform the user of the event. +# Otherwise if the option is set to no, the server aborts with an error +# and refuses to start. When the option is set to no, the user requires +# to fix the AOF file using the "valkey-check-aof" utility before to restart +# the server. +# +# Note that if the AOF file will be found to be corrupted in the middle +# the server will still exit with an error. This option only applies when +# the server will try to read more data from the AOF file but not enough bytes +# will be found. +aof-load-truncated yes + +# The server can create append-only base files in either RDB or AOF formats. Using +# the RDB format is always faster and more efficient, and disabling it is only +# supported for backward compatibility purposes. +aof-use-rdb-preamble yes + +# The server supports recording timestamp annotations in the AOF to support restoring +# the data from a specific point-in-time. However, using this capability changes +# the AOF format in a way that may not be compatible with existing AOF parsers. +aof-timestamp-enabled no + +################################ SHUTDOWN ##################################### + +# Maximum time to wait for replicas when shutting down, in seconds. +# +# During shut down, a grace period allows any lagging replicas to catch up with +# the latest replication offset before the primary exits. This period can +# prevent data loss, especially for deployments without configured disk backups. +# +# The 'shutdown-timeout' value is the grace period's duration in seconds. It is +# only applicable when the instance has replicas. To disable the feature, set +# the value to 0. +# +# shutdown-timeout 10 + +# When the server receives a SIGINT or SIGTERM, shutdown is initiated and by default +# an RDB snapshot is written to disk in a blocking operation if save points are configured. +# The options used on signaled shutdown can include the following values: +# +# default: Saves RDB snapshot only if save points are configured. +# Waits for lagging replicas to catch up. +# save: Forces a DB saving operation even if no save points are configured. +# nosave: Prevents DB saving operation even if one or more save points are configured. +# now: Skips waiting for lagging replicas. +# force: Ignores any errors that would normally prevent the server from exiting. +# safe: Shut down only when safe. Note that safe cannot prevent force, in the case of +# force, safe will print the relevant logs. The definition of safe may be different +# in different modes. Here are the definitions: +# * In cluster mode, it is unsafe to shut down a primary with slots, and may cause +# the cluster to go down. +# failover: In cluster mode, when shutting down a primary, it can proactively +# initiate a manual failover. This promotes one of its replicas to +# primary before shutdown, resulting in a quicker and safer transition +# than relying on an automatic failover. For a replica to be eligible +# for this promotion, it must be fully synchronized with the primary +# node at the time of the shutdown signal after waiting up to the +# configured shutdown-timeout. If no such replica is found, this +# proactive failover will not occur. +# +# Any combination of values is allowed as long as "save" and "nosave" are not set simultaneously. +# Example: "nosave force now" +# +# shutdown-on-sigint default +# shutdown-on-sigterm default + +################ NON-DETERMINISTIC LONG BLOCKING COMMANDS ##################### + +# Maximum time in milliseconds for EVAL scripts, functions and in some cases +# modules' commands before the server can start processing or rejecting other clients. +# +# If the maximum execution time is reached the server will start to reply to most +# commands with a BUSY error. +# +# In this state the server will only allow a handful of commands to be executed. +# For instance, SCRIPT KILL, FUNCTION KILL, SHUTDOWN NOSAVE and possibly some +# module specific 'allow-busy' commands. +# +# SCRIPT KILL and FUNCTION KILL will only be able to stop a script that did not +# yet call any write commands, so SHUTDOWN NOSAVE may be the only way to stop +# the server in the case a write command was already issued by the script when +# the user doesn't want to wait for the natural termination of the script. +# +# The default is 5 seconds. It is possible to set it to 0 or a negative value +# to disable this mechanism (uninterrupted execution). Note that in the past +# this config had a different name, which is now an alias, so both of these do +# the same: +# lua-time-limit 5000 +# busy-reply-threshold 5000 + +################################ VALKEY CLUSTER ############################### + +# Normal server instances can't be part of a cluster; only nodes that are +# started as cluster nodes can. In order to start a server instance as a +# cluster node enable the cluster support uncommenting the following: +# +# cluster-enabled yes + +# Every cluster node has a cluster configuration file. This file is not +# intended to be edited by hand. It is created and updated by each node. +# Every cluster node requires a different cluster configuration file. +# Make sure that instances running in the same system do not have +# overlapping cluster configuration file names. +# +# cluster-config-file nodes-6379.conf + +# Cluster node timeout is the amount of milliseconds a node must be unreachable +# for it to be considered in failure state. +# Most other internal time limits are a multiple of the node timeout. +# +# cluster-node-timeout 15000 + +# The cluster port is the port that the cluster bus will listen for inbound connections on. When set +# to the default value, 0, it will be bound to the command port + 10000. Setting this value requires +# you to specify the cluster bus port when executing cluster meet. +# cluster-port 0 + +# A replica of a failing primary will avoid to start a failover if its data +# looks too old. +# +# There is no simple way for a replica to actually have an exact measure of +# its "data age", so the following two checks are performed: +# +# 1) If there are multiple replicas able to failover, they exchange messages +# in order to try to give an advantage to the replica with the best +# replication offset (more data from the primary processed). +# Replicas will try to get their rank by offset, and apply to the start +# of the failover a delay proportional to their rank. +# +# 2) Every single replica computes the time of the last interaction with +# its primary. This can be the last ping or command received (if the primary +# is still in the "connected" state), or the time that elapsed since the +# disconnection with the primary (if the replication link is currently down). +# If the last interaction is too old, the replica will not try to failover +# at all. +# +# The point "2" can be tuned by user. Specifically a replica will not perform +# the failover if, since the last interaction with the primary, the time +# elapsed is greater than: +# +# (node-timeout * cluster-replica-validity-factor) + repl-ping-replica-period +# +# So for example if node-timeout is 30 seconds, and the cluster-replica-validity-factor +# is 10, and assuming a default repl-ping-replica-period of 10 seconds, the +# replica will not try to failover if it was not able to talk with the primary +# for longer than 310 seconds. +# +# A large cluster-replica-validity-factor may allow replicas with too old data to failover +# a primary, while a too small value may prevent the cluster from being able to +# elect a replica at all. +# +# For maximum availability, it is possible to set the cluster-replica-validity-factor +# to a value of 0, which means, that replicas will always try to failover the +# primary regardless of the last time they interacted with the primary. +# (However they'll always try to apply a delay proportional to their +# offset rank). +# +# Zero is the only value able to guarantee that when all the partitions heal +# the cluster will always be able to continue. +# +# cluster-replica-validity-factor 10 + +# Cluster replicas are able to migrate to orphaned primaries, that are primaries +# that are left without working replicas. This improves the cluster ability +# to resist to failures as otherwise an orphaned primary can't be failed over +# in case of failure if it has no working replicas. +# +# Replicas migrate to orphaned primaries only if there are still at least a +# given number of other working replicas for their old primary. This number +# is the "migration barrier". A migration barrier of 1 means that a replica +# will migrate only if there is at least 1 other working replica for its primary +# and so forth. It usually reflects the number of replicas you want for every +# primary in your cluster. +# +# Default is 1 (replicas migrate only if their primaries remain with at least +# one replica). To disable migration just set it to a very large value or +# set cluster-allow-replica-migration to 'no'. +# A value of 0 can be set but is useful only for debugging and dangerous +# in production. +# +# cluster-migration-barrier 1 + +# Turning off this option allows to use less automatic cluster configuration. +# It disables migration of replicas to orphaned primaries. Masters that become +# empty due to losing their last slots to another primary will not automatically +# replicate from the primary that took over their last slots. Instead, they will +# remain as empty primaries without any slots. +# +# Default is 'yes' (allow automatic migrations). +# +# cluster-allow-replica-migration yes + +# By default cluster nodes stop accepting queries if they detect there +# is at least a hash slot uncovered (no available node is serving it). +# This way if the cluster is partially down (for example a range of hash slots +# are no longer covered) all the cluster becomes, eventually, unavailable. +# It automatically returns available as soon as all the slots are covered again. +# +# However sometimes you want the subset of the cluster which is working, +# to continue to accept queries for the part of the key space that is still +# covered. In order to do so, just set the cluster-require-full-coverage +# option to no. +# +# cluster-require-full-coverage yes + +# This option, when set to yes, prevents replicas from trying to failover its +# primary during primary failures. However the replica can still perform a +# manual failover, if forced to do so. +# +# This is useful in different scenarios, especially in the case of multiple +# data center operations, where we want one side to never be promoted if not +# in the case of a total DC failure. +# +# cluster-replica-no-failover no + +# The timeout in milliseconds for cluster manual failover. If a manual failover +# does not complete within the specified time, both the replica and the primary +# will abort it. Note that this timeout is also used for the finalization of +# migrations initiated with the CLUSTER MIGRATESLOTS command. +# +# A manual failover is a special kind of failover that is usually executed when +# there are no actual failures, and we wish to swap the current primary with one +# of its replicas in a safe way, without any window for data loss. +# +# To avoid data loss, the primary and the replica need to wait for each other for +# a period of time, the primary need to pause the clients writes to stop processing +# traffic. The default failover timeout is 5000ms, it is possible to configure the +# timeout and decide how long the primary will pause in the worst case scenario, +# i.e. the manual failover timed out due to the insufficient votes. +# +# Check https://valkey.io/commands/cluster-failover/ for more information. +# +# cluster-manual-failover-timeout 5000 + +# This option, when set to yes, allows nodes to serve read traffic while the +# cluster is in a down state, as long as it believes it owns the slots. +# +# This is useful for two cases. The first case is for when an application +# doesn't require consistency of data during node failures or network partitions. +# One example of this is a cache, where as long as the node has the data it +# should be able to serve it. +# +# The second use case is for configurations that don't meet the recommended +# three shards but want to enable cluster mode and scale later. A +# primary outage in a 1 or 2 shard configuration causes a read/write outage to the +# entire cluster without this option set, with it set there is only a write outage. +# Without a quorum of primaries, slot ownership will not change automatically. +# +# cluster-allow-reads-when-down no + +# This option, when set to yes, allows nodes to serve pubsub shard traffic while +# the cluster is in a down state, as long as it believes it owns the slots. +# +# This is useful if the application would like to use the pubsub feature even when +# the cluster global stable state is not OK. If the application wants to make sure only +# one shard is serving a given channel, this feature should be kept as yes. +# +# cluster-allow-pubsubshard-when-down yes + +# Cluster link send buffer limit is the limit on the memory usage of an individual +# cluster bus link's send buffer in bytes. Cluster links would be freed if they exceed +# this limit. This is to primarily prevent send buffers from growing unbounded on links +# toward slow peers (E.g. PubSub messages being piled up). +# This limit is disabled by default. Enable this limit when 'mem_cluster_links' INFO field +# and/or 'send-buffer-allocated' entries in the 'CLUSTER LINKS` command output continuously increase. +# Minimum limit of 1gb is recommended so that cluster link buffer can fit in at least a single +# PubSub message by default. (client-query-buffer-limit default value is 1gb) +# +# cluster-link-sendbuf-limit 0 + +# Clusters can configure their announced hostname using this config. This is a common use case for +# applications that need to use TLS Server Name Indication (SNI) or dealing with DNS based +# routing. By default this value is only shown as additional metadata in the CLUSTER SLOTS +# command, but can be changed using 'cluster-preferred-endpoint-type' config. This value is +# communicated along the clusterbus to all nodes, setting it to an empty string will remove +# the hostname and also propagate the removal. +# +# cluster-announce-hostname "" + +# Clusters can configure an optional nodename to be used in addition to the node ID for +# debugging and admin information. This name is broadcasted between nodes, so will be used +# in addition to the node ID when reporting cross node events such as node failures. +# cluster-announce-human-nodename "" + +# Clusters can advertise how clients should connect to them using either their IP address, +# a user defined hostname, or by declaring they have no endpoint. Which endpoint is +# shown as the preferred endpoint is set by using the cluster-preferred-endpoint-type +# config with values 'ip', 'hostname', or 'unknown-endpoint'. This value controls how +# the endpoint returned for MOVED/ASKING requests as well as the first field of CLUSTER SLOTS. +# If the preferred endpoint type is set to hostname, but no announced hostname is set, a '?' +# will be returned instead. +# +# When a cluster advertises itself as having an unknown endpoint, it's indicating that +# the server doesn't know how clients can reach the cluster. This can happen in certain +# networking situations where there are multiple possible routes to the node, and the +# server doesn't know which one the client took. In this case, the server is expecting +# the client to reach out on the same endpoint it used for making the last request, but use +# the port provided in the response. +# +# cluster-preferred-endpoint-type ip + +# The cluster blacklist is used when removing a node from the cluster completely. +# When CLUSTER FORGET is called for a node, that node is put into the blacklist for +# some time so that when gossip messages are received from other nodes that still +# remember it, it is not re-added. This gives time for CLUSTER FORGET to be sent to +# every node in the cluster. The blacklist TTL is 60 seconds by default, which should +# be sufficient for most clusters, but you may considering increasing this if you see +# nodes getting re-added while using CLUSTER FORGET. +# +# cluster-blacklist-ttl 60 + +# Clusters can be configured to track per-slot resource statistics, +# which are accessible by the CLUSTER SLOT-STATS command. +# +# By default, the 'cluster-slot-stats-enabled' is disabled, and only 'key-count' is captured. +# By enabling the 'cluster-slot-stats-enabled' config, the cluster will begin to capture advanced statistics. +# These statistics can be leveraged to assess general slot usage trends, identify hot / cold slots, +# migrate slots for a balanced cluster workload, and / or re-write application logic to better utilize slots. +# +# cluster-slot-stats-enabled no + +# Slot migrations using the CLUSTER MIGRATESLOTS command will generate an in-memory migration log on both +# the source and target nodes of the migration. These can be observed with CLUSTER GETSLOTMIGRATIONS. +# 'cluster-slot-migration-log-max-len' allows the maximum length of this log to be specified. Only +# migrations that are completed will be considered for removal. +# +# cluster-slot-migration-log-max-len 1000 + +# During the CLUSTER MIGRATESLOTS command execution, the source node needs to pause itself and allow all +# writes to be fully processed by the target node. The amount of data remaining in the buffer on the +# source node when this pause happens will affect how long this pause takes. +# 'slot-migration-max-failover-repl-bytes' allows the pause to wait until there are at most this +# many bytes in the output buffer. Setting this to -1 will disable this limit, and 0 will require +# no data be in the source output buffer (although this is not a guaranatee the data is fully +# received by the target). +# +# slot-migration-max-failover-repl-bytes 0 + +# In order to setup your cluster make sure to read the documentation +# available at https://valkey.io web site. + +########################## CLUSTER DOCKER/NAT support ######################## + +# In certain deployments, cluster node's address discovery fails, because +# addresses are NAT-ted or because ports are forwarded (the typical case is +# Docker and other containers). +# +# In order to make a cluster work in such environments, a static +# configuration where each node knows its public address is needed. The +# following options are used for this scope, and are: +# +# * cluster-announce-ip +# * cluster-announce-client-ipv4 +# * cluster-announce-client-ipv6 +# * cluster-announce-port +# * cluster-announce-tls-port +# * cluster-announce-bus-port +# * cluster-announce-client-port +# * cluster-announce-client-tls-port +# +# Each instructs the node about its address, possibly other addresses to expose +# to clients, client ports (for connections without and with TLS) and cluster +# message bus port. The information is then published in the bus packets so that +# other nodes will be able to correctly map the address of the node publishing +# the information. +# +# If tls-cluster is set to yes and cluster-announce-tls-port is omitted or set +# to zero, then cluster-announce-port refers to the TLS port. Note also that +# cluster-announce-tls-port has no effect if tls-cluster is set to no. +# +# If cluster-announce-client-ipv4 and cluster-announce-client-ipv6 are omitted, +# then cluster-announce-ip is exposed to clients. +# +# If the port that clients will use to connect to Valkey is different than +# the one other valkey nodes in the cluster will connect to it on, either +# through special networking rules or because Valkey is behind a load balancer, +# you can configure the port that clients will see by setting +# cluster-announce-client-port or cluster-announce-client-tls-port. +# +# If the above options are not used, the normal cluster auto-detection +# will be used instead. +# +# Note that when remapped, the bus port may not be at the fixed offset of +# clients port + 10000, so you can specify any port and bus-port depending +# on how they get remapped. If the bus-port is not set, a fixed offset of +# 10000 will be used as usual. +# +# Example: +# +# cluster-announce-ip 10.1.1.5 +# cluster-announce-client-ipv4 123.123.123.5 +# cluster-announce-client-ipv6 2001:db8::8a2e:370:7334 +# cluster-announce-tls-port 6379 +# cluster-announce-port 0 +# cluster-announce-bus-port 6380 +# cluster-announce-client-tls-port 6479 +# cluster-announce-client-port 0 + +# Set the number of databases in cluster mode. The default database is DB 0, +# you can select a different one on a per-connection basis using SELECT where +# dbid is a number between 0 and 'cluster-databases'-1. +# cluster-databases 1 + +################################## COMMAND LOG ################################### + +# The Command Log system is used to record commands that consume significant resources +# during server operation, including CPU, memory, and network bandwidth. +# These commands and the data they access may lead to abnormal instance operations, +# the commandlog can help users quickly and intuitively locate issues. +# +# Currently, three types of command logs are supported: +# +# SLOW: Logs commands that exceed a specified execution time. This excludes time spent +# on I/O operations like client communication and focuses solely on the command's +# processing time, where the main thread is blocked. +# +# LARGE-REQUEST: Logs commands with requests exceeding a defined size. This helps +# identify potentially problematic commands that send excessive data to the server. +# +# LARGE-REPLY: Logs commands that generate replies exceeding a defined size. This +# helps identify commands that return unusually large amounts of data, which may +# impact network performance or client processing. +# +# Each log type has two key parameters: +# 1. A threshold value that determines when a command is logged. This threshold is specific +# to the type of log (e.g., execution time, request size, or reply size). A negative value disables +# logging. A value of 0 logs all commands. +# 2. A maximum length that specifies the number of entries to retain in the log. Increasing +# the length allows more entries to be stored but consumes additional memory. To clear all +# entries for a specific log type and reclaim memory, use the `COMMANDLOG RESET` +# subcommand followed by the log type. +# +# SLOW Command Logs +# The SLOW log records commands that exceed a specified execution time. The execution time +# does not include I/O operations, such as client communication or sending responses. +# It only measures the time spent executing the command, during which the thread is blocked +# and cannot handle other requests. +# +# The threshold is measured in microseconds. +# +# Backward Compatibility: The parameters `slowlog-log-slower-than` and `slowlog-max-len` +# are still supported but deprecated in favor of these commandlog parameters. +# +# The following time is expressed in microseconds, so 1000000 is equivalent to 1 second. +# Note that -1 disables the slow log, while 0 forces logging of every command. +commandlog-execution-slower-than 10000 +# Record the number of commands. +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the slow log with SLOWLOG RESET or COMMANDLOG RESET SLOW. +commandlog-slow-execution-max-len 128 +# +# LARGE_REQUEST Command Logs +# The LARGE_REQUEST log tracks commands with requests exceeding a specified size. The request size +# includes the command itself and all its arguments. For example, in `SET KEY VALUE`, the size is +# determined by the combined size of the key and value. Commands that consume excessive network +# bandwidth or query buffer space are recorded here. +# +# The threshold is measured in bytes. +# Note that -1 disables the large request log, while 0 forces logging of every command. +commandlog-request-larger-than 1048576 +# Record the number of commands. +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the large request log with COMMANDLOG RESET LARGE-REQUEST. +commandlog-large-request-max-len 128 +# +# LARGE_REPLY Command Logs +# The LARGE_REPLY log records commands that produce replies exceeding a specified size. These replies +# may consume significant network bandwidth or client output buffer space. Examples include commands +# like `KEYS` or `HGETALL` that return large datasets. Even a `GET` command may qualify if the value +# is substantial. +# +# The threshold is measured in bytes. +# Note that -1 disables the large reply log, while 0 forces logging of every command. +commandlog-reply-larger-than 1048576 +# Record the number of commands. +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the large reply log with COMMANDLOG RESET LARGE-REPLY. +commandlog-large-reply-max-len 128 + +################################ LATENCY MONITOR ############################## + +# The server latency monitoring subsystem samples different operations +# at runtime in order to collect data related to possible sources of +# latency of a server instance. +# +# Via the LATENCY command this information is available to the user that can +# print graphs and obtain reports. +# +# The system only logs operations that were performed in a time equal or +# greater than the amount of milliseconds specified via the +# latency-monitor-threshold configuration directive. When its value is set +# to zero, the latency monitor is turned off. +# +# By default latency monitoring is disabled since it is mostly not needed +# if you don't have latency issues, and collecting data has a performance +# impact, that while very small, can be measured under big load. Latency +# monitoring can easily be enabled at runtime using the command +# "CONFIG SET latency-monitor-threshold " if needed. +latency-monitor-threshold 0 + +################################ LATENCY TRACKING ############################## + +# The server's extended latency monitoring tracks the per command latencies and enables +# exporting the percentile distribution via the INFO latencystats command, +# and cumulative latency distributions (histograms) via the LATENCY command. +# +# By default, the extended latency monitoring is enabled since the overhead +# of keeping track of the command latency is very small. +# latency-tracking yes + +# By default the exported latency percentiles via the INFO latencystats command +# are the p50, p99, and p999. +# latency-tracking-info-percentiles 50 99 99.9 + +############################# EVENT NOTIFICATION ############################## + +# The server can notify Pub/Sub clients about events happening in the key space. +# This feature is documented at https://valkey.io/topics/notifications +# +# For instance if keyspace events notification is enabled, and a client +# performs a DEL operation on key "foo" stored in the Database 0, two +# messages will be published via Pub/Sub: +# +# PUBLISH __keyspace@0__:foo del +# PUBLISH __keyevent@0__:del foo +# +# It is possible to select the events that the server will notify among a set +# of classes. Every class is identified by a single character: +# +# K Keyspace events, published with __keyspace@__ prefix. +# E Keyevent events, published with __keyevent@__ prefix. +# g Generic commands (non-type specific) like DEL, EXPIRE, RENAME, ... +# $ String commands +# l List commands +# s Set commands +# h Hash commands +# z Sorted set commands +# x Expired events (events generated every time a key expires) +# e Evicted events (events generated when a key is evicted for maxmemory) +# n New key events (Note: not included in the 'A' class) +# t Stream commands +# d Module key type events +# m Key-miss events (Note: It is not included in the 'A' class) +# A Alias for g$lshzxetd, so that the "AKE" string means all the events +# (Except key-miss events which are excluded from 'A' due to their +# unique nature). +# +# The "notify-keyspace-events" takes as argument a string that is composed +# of zero or multiple characters. The empty string means that notifications +# are disabled. +# +# Example: to enable list and generic events, from the point of view of the +# event name, use: +# +# notify-keyspace-events Elg +# +# Example 2: to get the stream of the expired keys subscribing to channel +# name __keyevent@0__:expired use: +# +# notify-keyspace-events Ex +# +# By default all notifications are disabled because most users don't need +# this feature and the feature has some overhead. Note that if you don't +# specify at least one of K or E, no events will be delivered. +notify-keyspace-events "" + +############################### ADVANCED CONFIG ############################### + +# Hashes are encoded using a memory efficient data structure when they have a +# small number of entries, and the biggest entry does not exceed a given +# threshold. These thresholds can be configured using the following directives. +hash-max-listpack-entries 512 +hash-max-listpack-value 64 + +# Lists are also encoded in a special way to save a lot of space. +# The number of entries allowed per internal list node can be specified +# as a fixed maximum size or a maximum number of elements. +# For a fixed maximum size, use -5 through -1, meaning: +# -5: max size: 64 Kb <-- not recommended for normal workloads +# -4: max size: 32 Kb <-- not recommended +# -3: max size: 16 Kb <-- probably not recommended +# -2: max size: 8 Kb <-- good +# -1: max size: 4 Kb <-- good +# Positive numbers mean store up to _exactly_ that number of elements +# per list node. +# The highest performing option is usually -2 (8 Kb size) or -1 (4 Kb size), +# but if your use case is unique, adjust the settings as necessary. +list-max-listpack-size -2 + +# Lists may also be compressed. +# Compress depth is the number of quicklist ziplist nodes from *each* side of +# the list to *exclude* from compression. The head and tail of the list +# are always uncompressed for fast push/pop operations. Settings are: +# 0: disable all list compression +# 1: depth 1 means "don't start compressing until after 1 node into the list, +# going from either the head or tail" +# So: [head]->node->node->...->node->[tail] +# [head], [tail] will always be uncompressed; inner nodes will compress. +# 2: [head]->[next]->node->node->...->node->[prev]->[tail] +# 2 here means: don't compress head or head->next or tail->prev or tail, +# but compress all nodes between them. +# 3: [head]->[next]->[next]->node->node->...->node->[prev]->[prev]->[tail] +# etc. +list-compress-depth 0 + +# Sets have a special encoding when a set is composed +# of just strings that happen to be integers in radix 10 in the range +# of 64 bit signed integers. +# The following configuration setting sets the limit in the size of the +# set in order to use this special memory saving encoding. +set-max-intset-entries 512 + +# Sets containing non-integer values are also encoded using a memory efficient +# data structure when they have a small number of entries, and the biggest entry +# does not exceed a given threshold. These thresholds can be configured using +# the following directives. +set-max-listpack-entries 128 +set-max-listpack-value 64 + +# Similarly to hashes and lists, sorted sets are also specially encoded in +# order to save a lot of space. This encoding is only used when the length and +# elements of a sorted set are below the following limits: +zset-max-listpack-entries 128 +zset-max-listpack-value 64 + +# HyperLogLog sparse representation bytes limit. The limit includes the +# 16 bytes header. When a HyperLogLog using the sparse representation crosses +# this limit, it is converted into the dense representation. +# +# A value greater than 16000 is totally useless, since at that point the +# dense representation is more memory efficient. +# +# The suggested value is ~ 3000 in order to have the benefits of +# the space efficient encoding without slowing down too much PFADD, +# which is O(N) with the sparse encoding. The value can be raised to +# ~ 10000 when CPU is not a concern, but space is, and the data set is +# composed of many HyperLogLogs with cardinality in the 0 - 15000 range. +hll-sparse-max-bytes 3000 + +# Streams macro node max size / items. The stream data structure is a radix +# tree of big nodes that encode multiple items inside. Using this configuration +# it is possible to configure how big a single node can be in bytes, and the +# maximum number of items it may contain before switching to a new node when +# appending new stream entries. If any of the following settings are set to +# zero, the limit is ignored, so for instance it is possible to set just a +# max entries limit by setting max-bytes to 0 and max-entries to the desired +# value. +stream-node-max-bytes 4096 +stream-node-max-entries 100 + +# Active rehashing uses 1% of the CPU time to help perform incremental rehashing +# of the main server hash tables, the ones mapping top-level keys to values. +# +# If active rehashing is disabled and rehashing is needed, a hash table is +# rehashed one "step" on every operation performed on the hash table (add, find, +# etc.), so if the server is idle, the rehashing may never complete and some +# more memory is used by the hash tables. Active rehashing helps prevent this. +# +# Active rehashing runs as a background task. Depending on the value of 'hz', +# the frequency at which the server performs background tasks, active rehashing +# can cause the server to freeze for a short time. For example, if 'hz' is set +# to 10, active rehashing runs for up to one millisecond every 100 milliseconds. +# If a freeze of one millisecond is not acceptable, you can increase 'hz' to let +# active rehashing run more often. If instead 'hz' is set to 100, active +# rehashing runs up to only 100 microseconds every 10 milliseconds. The total is +# still 1% of the time. +activerehashing yes + +# The client output buffer limits can be used to force disconnection of clients +# that are not reading data from the server fast enough for some reason (a +# common reason is that a Pub/Sub client can't consume messages as fast as the +# publisher can produce them). +# +# The limit can be set differently for the three different classes of clients: +# +# normal -> normal clients including MONITOR clients +# replica -> replica clients +# pubsub -> clients subscribed to at least one pubsub channel or pattern +# +# The syntax of every client-output-buffer-limit directive is the following: +# +# client-output-buffer-limit +# +# A client is immediately disconnected once the hard limit is reached, or if +# the soft limit is reached and remains reached for the specified number of +# seconds (continuously). +# So for instance if the hard limit is 32 megabytes and the soft limit is +# 16 megabytes / 10 seconds, the client will get disconnected immediately +# if the size of the output buffers reach 32 megabytes, but will also get +# disconnected if the client reaches 16 megabytes and continuously overcomes +# the limit for 10 seconds. +# +# By default normal clients are not limited because they don't receive data +# without asking (in a push way), but just after a request, so only +# asynchronous clients may create a scenario where data is requested faster +# than it can read. +# +# Instead there is a default limit for pubsub and replica clients, since +# subscribers and replicas receive data in a push fashion. +# +# Note that it doesn't make sense to set the replica clients output buffer +# limit lower than the repl-backlog-size config (partial sync will succeed +# and then replica will get disconnected). +# Such a configuration is ignored (the size of repl-backlog-size will be used). +# This doesn't have memory consumption implications since the replica client +# will share the backlog buffers memory. +# +# Both the hard or the soft limit can be disabled by setting them to zero. +client-output-buffer-limit normal 0 0 0 +client-output-buffer-limit replica 256mb 64mb 60 +client-output-buffer-limit pubsub 32mb 8mb 60 + +# Client query buffers accumulate new commands. They are limited to a fixed +# amount by default in order to avoid that a protocol desynchronization (for +# instance due to a bug in the client) will lead to unbound memory usage in +# the query buffer. However you can configure it here if you have very special +# needs, such as a command with huge argument, or huge multi/exec requests or alike. +# +# client-query-buffer-limit 1gb + +# In some scenarios client connections can hog up memory leading to OOM +# errors or data eviction. To avoid this we can cap the accumulated memory +# used by all client connections (all pubsub and normal clients). Once we +# reach that limit connections will be dropped by the server freeing up +# memory. The server will attempt to drop the connections using the most +# memory first. We call this mechanism "client eviction". +# +# Client eviction is configured using the maxmemory-clients setting as follows: +# 0 - client eviction is disabled (default) +# +# A memory value can be used for the client eviction threshold, +# for example: +# maxmemory-clients 1g +# +# A percentage value (between 1% and 100%) means the client eviction threshold +# is based on a percentage of the maxmemory setting. For example to set client +# eviction at 5% of maxmemory: +# maxmemory-clients 5% + +# In the server protocol, bulk requests, that are, elements representing single +# strings, are normally limited to 512 mb. However you can change this limit +# here, but must be 1mb or greater +# +# proto-max-bulk-len 512mb + +# The server calls an internal function to perform many background tasks, like +# closing connections of clients in timeout, purging expired keys that are +# never requested, and so forth. +# +# Not all tasks are performed with the same frequency, but the server checks for +# tasks to perform according to the specified "hz" value. +# +# By default "hz" is set to 10. Raising the value will use more CPU when +# the server is idle, but at the same time will make the server more responsive when +# there are many keys expiring at the same time, and timeouts may be +# handled with more precision. +# +# The range is between 1 and 500, however a value over 100 is usually not +# a good idea. Most users should use the default of 10 and raise this up to +# 100 only in environments where very low latency is required. +hz 10 + +# When a child rewrites the AOF file, if the following option is enabled +# the file will be fsync-ed every 4 MB of data generated. This is useful +# in order to commit the file to the disk more incrementally and avoid +# big latency spikes. +aof-rewrite-incremental-fsync yes + +# When the server saves RDB file, if the following option is enabled +# the file will be fsync-ed every 4 MB of data generated. This is useful +# in order to commit the file to the disk more incrementally and avoid +# big latency spikes. +rdb-save-incremental-fsync yes + +# The server's LFU eviction (see maxmemory setting) can be tuned. However it is a good +# idea to start with the default settings and only change them after investigating +# how to improve the performances and how the keys LFU change over time, which +# is possible to inspect via the OBJECT FREQ command. +# +# There are two tunable parameters in the server LFU implementation: the +# counter logarithm factor and the counter decay time. It is important to +# understand what the two parameters mean before changing them. +# +# The LFU counter is just 8 bits per key, it's maximum value is 255, so the server +# uses a probabilistic increment with logarithmic behavior. Given the value +# of the old counter, when a key is accessed, the counter is incremented in +# this way: +# +# 1. A random number R between 0 and 1 is extracted. +# 2. A probability P is calculated as 1/(old_value*lfu_log_factor+1). +# 3. The counter is incremented only if R < P. +# +# The default lfu-log-factor is 10. This is a table of how the frequency +# counter changes with a different number of accesses with different +# logarithmic factors: +# +# +--------+------------+------------+------------+------------+------------+ +# | factor | 100 hits | 1000 hits | 100K hits | 1M hits | 10M hits | +# +--------+------------+------------+------------+------------+------------+ +# | 0 | 104 | 255 | 255 | 255 | 255 | +# +--------+------------+------------+------------+------------+------------+ +# | 1 | 18 | 49 | 255 | 255 | 255 | +# +--------+------------+------------+------------+------------+------------+ +# | 10 | 10 | 18 | 142 | 255 | 255 | +# +--------+------------+------------+------------+------------+------------+ +# | 100 | 8 | 11 | 49 | 143 | 255 | +# +--------+------------+------------+------------+------------+------------+ +# +# NOTE: The above table was obtained by running the following commands: +# +# valkey-benchmark -n 1000000 incr foo +# valkey-cli object freq foo +# +# NOTE 2: The counter initial value is 5 in order to give new objects a chance +# to accumulate hits. +# +# The counter decay time is the time, in minutes, that must elapse in order +# for the key counter to be decremented. +# +# The default value for the lfu-decay-time is 1. A special value of 0 means we +# will never decay the counter. +# +# lfu-log-factor 10 +# lfu-decay-time 1 + + +# The maximum number of new client connections accepted per event-loop cycle. This configuration +# is set independently for TLS connections. +# +# By default, up to 10 new connection will be accepted per event-loop cycle for normal connections +# and up to 1 new connection per event-loop cycle for TLS connections. +# +# Adjusting this to a larger number can slightly improve efficiency for new connections +# at the risk of causing timeouts for regular commands on established connections. It is +# not advised to change this without ensuring that all clients have limited connection +# pools and exponential backoff in the case of command/connection timeouts. +# +# If your application is establishing a large number of new connections per second you should +# also consider tuning the value of tcp-backlog, which allows the kernel to buffer more +# pending connections before dropping or rejecting connections. +# +# max-new-connections-per-cycle 10 +# max-new-tls-connections-per-cycle 1 + +# Memory prefetching is used when multiple commands are parsed and ready for +# execution. We take advantage of knowing the next set of commands and prefetch +# their required hash table entries in a batch. This reduces the time spent on +# memory accesses. +# +# When I/O threads are used, the keys of multiple commands from multiple clients +# are prefetched together. When I/O threads are not used, only the commands from +# a single client's command pipeline is prefetched. +# +# The optimal batch size depends on the specific workflow of the user and on the +# hardware used. The default batch size is 16, which can be modified using the +# 'prefetch-batch-max-size' config. +# +# When the config is set to 0, prefetching is disabled. +# +# prefetch-batch-max-size 16 + +# It is possible to pin different threads and processes of the server to specific +# CPUs in your system, in order to maximize the performances of the server. +# This is useful both in order to pin different server threads in different +# CPUs, but also in order to make sure that multiple server instances running +# in the same host will be pinned to different CPUs. +# +# Normally you can do this using the "taskset" command, however it is also +# possible to do this via the server configuration directly, both in Linux and FreeBSD. +# +# You can pin the server/IO threads, bio threads, aof rewrite child process, +# bgsave child process and the slot migration process. +# The syntax to specify the cpu list is the same as the taskset command: +# +# Set server/io threads to cpu affinity 0,2,4,6: +# server-cpulist 0-7:2 +# +# Set bio threads to cpu affinity 1,3: +# bio-cpulist 1,3 +# +# Set aof rewrite child process to cpu affinity 8,9,10,11: +# aof-rewrite-cpulist 8-11 +# +# Set bgsave (or slot migration) child process to cpu affinity 1,10,11: +# bgsave-cpulist 1,10-11 + +# In some cases the server will emit warnings and even refuse to start if it detects +# that the system is in bad state, it is possible to suppress these warnings +# by setting the following config which takes a space delimited list of warnings +# to suppress +# +# ignore-warnings ARM64-COW-BUG + + +########################### ACTIVE DEFRAGMENTATION ####################### +# +# What is active defragmentation? +# ------------------------------- +# +# Active (online) defragmentation allows a server to compact the +# spaces left between small allocations and deallocations of data in memory, +# thus allowing to reclaim back memory. +# +# Fragmentation is a natural process that happens with every allocator (but +# less so with Jemalloc, fortunately) and certain workloads. Normally a server +# restart is needed in order to lower the fragmentation, or at least to flush +# away all the data and create it again. However thanks to this feature, this +# process can happen at runtime in a "hot" way, while the server is running. +# +# Basically when the fragmentation is over a certain level (see the +# configuration options below) the server will start to create new copies of the +# values in contiguous memory regions by exploiting certain specific Jemalloc +# features (in order to understand if an allocation is causing fragmentation +# and to allocate it in a better place), and at the same time, will release the +# old copies of the data. This process, repeated incrementally for all the keys +# will cause the fragmentation to drop back to normal values. +# +# Important things to understand: +# +# 1. This feature is disabled by default, and only works if you compiled the server +# to use the copy of Jemalloc we ship with the source code of the server. +# This is the default with Linux builds. +# +# 2. You never need to enable this feature if you don't have fragmentation +# issues. +# +# 3. Once you experience fragmentation, you can enable this feature when +# needed with the command "CONFIG SET activedefrag yes". +# +# The configuration parameters are able to fine tune the behavior of the +# defragmentation process. If you are not sure about what they mean it is +# a good idea to leave the defaults untouched. + +# Active defragmentation is disabled by default +# activedefrag no + +# Minimum amount of fragmentation waste to start active defrag +# active-defrag-ignore-bytes 100mb + +# Minimum percentage of fragmentation to start active defrag +# active-defrag-threshold-lower 10 + +# Maximum percentage of fragmentation at which we use maximum effort +# active-defrag-threshold-upper 100 + +# Minimal effort for defrag in CPU percentage, not cycle time as the name might +# suggest, to be used when the lower threshold is reached. +# active-defrag-cycle-min 1 + +# Maximal effort for defrag in CPU percentage, not cycle time as the name might +# suggest, to be used when the upper threshold is reached. +# active-defrag-cycle-max 25 + +# Maximum number of set/hash/zset/list fields that will be processed from +# the main dictionary scan +# active-defrag-max-scan-fields 1000 + +# The time spent (in microseconds) of the periodic active defrag process. This +# affects the latency impact of active defrag on client commands. Smaller numbers +# will result in less latency impact at the cost of increased defrag overhead. +# active-defrag-cycle-us 500 + +# Jemalloc background thread for purging will be enabled by default +jemalloc-bg-thread yes diff --git a/infrastructure/configs/victoriametrics/vmagent.yaml b/infrastructure/configs/victoriametrics/vmagent.yaml new file mode 100644 index 0000000..36305f1 --- /dev/null +++ b/infrastructure/configs/victoriametrics/vmagent.yaml @@ -0,0 +1,24 @@ +global: + scrape_interval: 5s + +scrape_configs: + - job_name: postgres + static_configs: + - targets: + - postgres-exporter:9187 + - job_name: valkey + static_configs: + - targets: + - redis-exporter:9121 + - job_name: otel-collector + static_configs: + - targets: + - otel-collector:8888 + - job_name: vmagent + static_configs: + - targets: + - localhost:8429 + - job_name: caddy + static_configs: + - targets: + - caddy:8404