Это старая версия документа!
Docker Swarm + Loki + Protmail + Grafana
Версии:
- grafana/loki:3.5.8
- grafana/promtail:3.5.8
- grafana/grafana:10.2.2
Настройки
loki_config
auth_enabled: false server: http_listen_port: 3100 grpc_listen_port: 9096 log_level: info # Таймауты для стабильности http_server_read_timeout: 300s http_server_write_timeout: 300s common: path_prefix: /loki storage: filesystem: chunks_directory: /loki/chunks rules_directory: /loki/rules replication_factor: 1 ring: instance_addr: 0.0.0.0 kvstore: store: inmemory # Критически важные настройки для query-frontend query_scheduler: max_outstanding_requests_per_tenant: 2048 frontend: # Параметр max_outstanding_per_tenant удален из этой секции log_queries_longer_than: 30s compress_responses: true query_range: parallelise_shardable_queries: true results_cache: cache: embedded_cache: enabled: true max_size_mb: 100 max_retries: 5 limits_config: # Таймаут запросов теперь настраивается здесь query_timeout: 5m ingestion_rate_mb: 1000 ingestion_burst_size_mb: 2000 max_line_size: 256000 reject_old_samples: true reject_old_samples_max_age: 168h max_entries_limit_per_query: 50000 retention_period: 8760h max_query_length: 721h max_query_parallelism: 32 schema_config: configs: - from: 2024-01-01 store: tsdb object_store: filesystem schema: v13 index: prefix: index_ period: 24h ingester: wal: enabled: true dir: /loki/wal flush_on_shutdown: true lifecycler: ring: kvstore: store: inmemory replication_factor: 1 heartbeat_timeout: 1m chunk_idle_period: 1h max_chunk_age: 2h chunk_target_size: 1572864 chunk_retain_period: 30s storage_config: tsdb_shipper: active_index_directory: /loki/index cache_location: /loki/tsdb-shipper-cache filesystem: directory: /loki/chunks compactor: working_directory: /loki/boltdb-shipper-compactor retention_enabled: true compaction_interval: 30m # ИСПРАВЛЕНИЕ: Добавляем конфигурацию для delete request store delete_request_store: filesystem delete_request_cancel_period: 24h querier: max_concurrent: 256 tail_max_duration: 1h analytics: reporting_enabled: false
promtail_config
server: http_listen_port: 9080 http_listen_address: 0.0.0.0 positions: filename: /tmp/positions.yaml # Запись позиций каждые 15 секунд sync_period: 15s clients: - url: http://loki:3100/loki/api/v1/push backoff_config: min_period: 10s max_period: 5m max_retries: 50 batchwait: 30s batchsize: 2097152 timeout: 60s external_labels: cluster: docker-swarm host: "${HOSTNAME}" scrape_configs: - job_name: docker_containers docker_sd_configs: - host: unix:///var/run/docker.sock refresh_interval: 60s filters: - name: status values: ["running"] relabel_configs: - source_labels: [__meta_docker_container_name] regex: '/(.*)' target_label: container action: replace - target_label: job replacement: docker_containers action: replace - source_labels: [__meta_docker_container_label_com_docker_swarm_service_name] target_label: service regex: ".+" action: keep - source_labels: [__meta_docker_container_label_com_docker_swarm_service_name] target_label: service action: replace - source_labels: [__meta_docker_stack_namespace] target_label: stack action: replace - source_labels: [__meta_docker_swarm_node_id] target_label: node_id action: replace - source_labels: [__meta_docker_container_label_com_docker_swarm_node_hostname] target_label: node action: replace - source_labels: [__meta_docker_container_log_stream] target_label: log_stream action: replace - source_labels: [__meta_docker_container_id] target_label: container_id action: replace - source_labels: [__meta_docker_container_image] target_label: image action: replace - source_labels: [__meta_docker_container_status] regex: '(running)' action: keep - source_labels: [__meta_docker_container_name] regex: '/(monitoring_(loki|promtail|grafana)|loki|promtail|grafana)' action: drop pipeline_stages: - docker: {} - timestamp: source: current_time format: RFC3339 - job_name: system_logs journal: labels: job: system_logs static_configs: - targets: - localhost labels: job: system __path__: /var/log/syslog,/var/log/auth.log,/var/log/kern.log pipeline_stages: - multiline: firstline: '^\w{3}\s+\d{1,2}\s+\d{2}:\d{2}:\d{2}' max_wait_time: 10s - timestamp: source: current_time format: RFC3339 - job_name: journal_logs journal: max_age: 24h path: /var/log/journal labels: job: systemd_journal relabel_configs: - source_labels: [__journal__hostname] target_label: node - source_labels: [__journal__systemd_unit] target_label: unit - source_labels: [__journal__syslog_identifier] target_label: component pipeline_stages: - timestamp: source: current_time format: RFC3339
Docker Compose
monitoring
version: "3.8" services: loki: image: grafana/loki:3.5.8 ports: - "3100:3100" configs: - source: loki_config target: /etc/loki/local-config.yaml volumes: - loki_data:/loki - /etc/localtime:/etc/localtime:ro - /etc/timezone:/etc/timezone:ro command: - -config.file=/etc/loki/local-config.yaml - -config.expand-env=true - -target=all networks: - monitoring deploy: placement: constraints: - node.role == manager resources: limits: memory: 2G # Уменьшаем память cpus: '1.0' reservations: memory: 1G cpus: '0.5' restart_policy: condition: on-failure delay: 10s max_attempts: 3 promtail: image: grafana/promtail:3.5.8 configs: - source: promtail_config target: /etc/promtail/config.yaml volumes: - /var/run/docker.sock:/var/run/docker.sock:ro - /var/log:/var/log:ro - /var/lib/docker/containers:/var/lib/docker/containers:ro - /var/log/journal:/var/log/journal:ro - /run/systemd/journal:/run/systemd/journal:ro - promtail_positions:/tmp - /etc/localtime:/etc/localtime:ro - /etc/timezone:/etc/timezone:ro command: - -config.file=/etc/promtail/config.yaml - -client.external-labels=host=${HOSTNAME} - -config.expand-env=true #- -log.level=info environment: - HOSTNAME={{.Node.Hostname}} networks: - monitoring deploy: mode: global resources: limits: memory: 512M cpus: '0.5' reservations: memory: 256M cpus: '0.25' restart_policy: condition: any delay: 30s max_attempts: 10 grafana: image: grafana/grafana:10.2.2 ports: - "3000:3000" environment: - GF_SECURITY_ADMIN_PASSWORD=admin - GF_SECURITY_ADMIN_USER=admin - GF_USERS_ALLOW_SIGN_UP=false # Добавьте настройки анонимного доступа - GF_AUTH_ANONYMOUS_ENABLED=true - GF_AUTH_ANONYMOUS_ORG_ROLE=Viewer volumes: - grafana_data:/var/lib/grafana - /etc/localtime:/etc/localtime:ro - /etc/timezone:/etc/timezone:ro networks: - monitoring deploy: placement: constraints: - node.role == manager resources: limits: memory: 512M cpus: '0.5' reservations: memory: 256M cpus: '0.25' configs: loki_config: external: true promtail_config: external: true networks: monitoring: driver: overlay attachable: true volumes: promtail_positions: driver: local loki_data: driver: local grafana_data: driver: local