Merge pull request #469 from FgForrest/dev

Optimization patch - request for rerunning performance tests

docker/evita-configuration.yaml

@@ -74,4 +74,14 @@ api:
       gui:
         enabled: ${api.endpoints.lab.gui.enabled:true}
         readOnly: ${api.endpoints.lab.gui.readOnly:false}
-        preconfiguredConnections: !include ${api.endpoints.lab.gui.preconfiguredConnections:null}
+        preconfiguredConnections: !include ${api.endpoints.lab.gui.preconfiguredConnections:null}
+    observability:
+      enabled: ${api.endpoints.observability.enabled:true}
+      host: ${api.endpoints.observability.host:localhost:5557}
+      exposedHost: ${api.endpoints.observability.exposedHost:null}
+      tlsEnabled: ${api.endpoints.observability.tlsEnabled:false}
+      allowedOrigins: ${api.endpoints.observability.allowedOrigins:null}
+      tracing:
+        endpoint: ${api.endpoints.observability.tracing.endpoint:null}
+        protocol: ${api.endpoints.observability.tracing.protocol:null}
+      allowedEvents: !include ${api.endpoints.observability.allowedEvents:null}

docker/observability/collector-config.yaml

@@ -0,0 +1,33 @@
+receivers:
+  otlp:
+    protocols:
+      http:
+        include_metadata: true
+        cors:
+          allowed_origins:
+            - "*"
+          allowed_headers:
+            - "*"
+          max_age: 7200
+  filelog:
+    include: [ "/tmp/evita-temp/*.log" ]
+    start_at: beginning
+
+exporters:
+  otlp:
+    endpoint: tempo:4317
+    tls:
+      insecure: true
+  logging:
+    loglevel: debug
+  loki:
+    endpoint: "http://loki:3100"
+
+service:
+  pipelines:
+    traces:
+      receivers: [ otlp ]
+      exporters: [ otlp, logging ]
+    logs:
+      receivers: [ filelog ]
+      exporters: [ loki ]

docker/observability/docker-compose.yml

@@ -0,0 +1,63 @@
+version: "3.7"
+
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./prometheus.yml:/etc/prometheus.yml
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    command:
+      - --config.file=/etc/prometheus.yml
+      - --web.enable-remote-write-receiver
+      - --enable-feature=exemplar-storage
+
+  grafana:
+    image: grafana/grafana:latest
+    ports:
+      - "3000:3000"
+    volumes:
+      - ./grafana-datasource.yml:/etc/grafana/provisioning/datasources/datasource.yml
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+      - GF_AUTH_DISABLE_LOGIN_FORM=true
+      - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor
+
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:latest
+    command: [ "--config=/etc/otel-collector.yaml" ]
+    ports:
+      - "4318:4318"
+    volumes:
+      - ./collector-config.yaml:/etc/otel-collector.yaml
+
+  promtail:
+    image: grafana/promtail:latest
+    volumes:
+      - ./promtail-config.yaml:/etc/promtail/config.yaml
+      - /tmp/evita-temp/evita_server.log:/var/log/logfile.log
+
+  # To eventually offload to Tempo...
+  tempo:
+    image: grafana/tempo:latest
+    command: [ "-config.file=/etc/tempo.yaml" ]
+    volumes:
+      - ./tempo.yaml:/etc/tempo.yaml
+      - ./tempo-data:/tmp/tempo
+      - /tmp/evita-temp:/tmp/evita-temp
+    ports:
+      #- "14268"  # jaeger ingest
+      - "3200:3200"   # tempo
+      - "4317:4317"  # otlp grpc
+      #- "4318"  # otlp http
+      #- "9411"   # zipkin
+
+  loki:
+    image: grafana/loki:latest
+    ports:
+      - "3100:3100"
+    volumes:
+      - ./loki-config.yaml:/etc/loki/config.yaml

docker/observability/grafana-datasource.yml

@@ -0,0 +1,40 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    access: proxy
+    orgId: 1
+    url: http://prometheus:9090
+    basicAuth: false
+    isDefault: false
+    version: 1
+    editable: true
+    jsonData:
+      httpMethod: GET
+  - name: Tempo
+    type: tempo
+    access: proxy
+    orgId: 1
+    url: http://tempo:3200
+    basicAuth: false
+    isDefault: true
+    version: 1
+    editable: true
+    apiVersion: 1
+    uid: tempo
+    jsonData:
+      httpMethod: GET
+      serviceMap:
+        datasourceUid: prometheus
+  - name: loki
+    type: loki
+    access: proxy
+    orgId: 1
+    url: http://loki:3100
+    basicAuth: false
+    isDefault: false
+    version: 1
+    editable: true
+    apiVersion: 1

docker/observability/loki-config.yaml

@@ -0,0 +1,32 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+ingester:
+  lifecycler:
+    address: 127.0.0.1
+    ring:
+      kvstore:
+        store: inmemory
+      replication_factor: 1
+  chunk_idle_period: 1h
+  max_transfer_retries: 0
+
+schema_config:
+  configs:
+    - from: 2020-10-24
+      store: boltdb_shipper
+      object_store: filesystem
+      schema: v11
+      index:
+        prefix: index_
+        period: 24h
+
+storage_config:
+  boltdb_shipper:
+    active_index_directory: /loki/index
+    cache_location: /loki/cache
+    shared_store: filesystem
+  filesystem:
+    directory: /loki/chunks

docker/observability/prometheus.yml

@@ -0,0 +1,12 @@
+global:
+  scrape_interval: 15s
+  scrape_timeout: 10s
+  evaluation_interval: 15s
+scrape_configs:
+  - job_name: prometheus
+    metrics_path: /observability/metrics
+    static_configs:
+      - targets: ['host.docker.internal:5557']
+  - job_name: tempo
+    static_configs:
+      - targets: [ 'tempo:3200' ]

docker/observability/promtail-config.yaml

@@ -0,0 +1,33 @@
+server:
+  http_listen_port: 9080
+  grpc_listen_port: 0
+
+positions:
+  filename: /tmp/positions.yaml
+
+clients:
+  - url: http://loki:3100/loki/api/v1/push
+
+scrape_configs:
+  - job_name: json-logs
+    static_configs:
+      - targets:
+          - localhost
+        labels:
+          job: varlogs
+          __path__: /var/log/logfile.log
+
+    pipeline_stages:
+      - json:
+          expressions:
+            time: timestamp
+            message: message
+            level: level
+            trace_id: trace_id
+            client_id: client_id
+      - timestamp:
+          source: time
+          format: RFC3339
+      - labels:
+          level: ""
+          request_id: ""

docker/observability/tempo.yaml

@@ -0,0 +1,56 @@
+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
+  trace_by_id:
+    duration_slo: 5s
+
+distributor:
+  receivers:                           # this configuration will listen on all ports and protocols that tempo is capable of.
+    jaeger:                            # the receives all come from the OpenTelemetry collector.  more configuration information can
+      protocols:                       # be found there: https://github.com/open-telemetry/opentelemetry-collector/tree/main/receiver
+        thrift_http:                   #
+        grpc:                          # for a production deployment you should only enable the receivers you need!
+        thrift_binary:
+        thrift_compact:
+    zipkin:
+    otlp:
+      protocols:
+        grpc:
+    opencensus:
+
+ingester:
+  max_block_duration: 5m               # cut the headblock when this much time passes. this is being set for demo purposes and should probably be left alone normally
+
+compactor:
+  compaction:
+    block_retention: 1h                # overall Tempo trace retention. set for demo purposes
+
+metrics_generator:
+  registry:
+    external_labels:
+      source: tempo
+      cluster: docker-compose
+  storage:
+    path: /tmp/tempo/generator/wal
+    remote_write:
+      - url: http://prometheus:9090/api/v1/write
+        send_exemplars: true
+
+storage:
+  trace:
+    backend: local                     # backend configuration to use
+    wal:
+      path: /tmp/tempo/wal             # where to store the the wal locally
+    local:
+      path: /tmp/tempo/blocks
+
+overrides:
+  defaults:
+    metrics_generator:
+      processors: [service-graphs, span-metrics] # enables metrics generator