trufnetwork · outerlook · Nov 8, 2024 · Nov 8, 2024 · Nov 8, 2024
diff --git a/compose.yaml b/compose.yaml
@@ -18,6 +18,12 @@ services:
       - ${POSTGRES_VOLUME:-data-kwil-postgres}:/var/lib/postgresql/data
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   tsn-conf:
     # this service permits us to use the best approach for configuration:
@@ -37,6 +43,12 @@ services:
       - ${TSN_VOLUME:-data-tsn-db}:/root/.kwild
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   tsn-db:
     container_name: tsn-db
@@ -82,6 +94,12 @@ services:
       - ${TSN_VOLUME:-data-tsn-db}:/root/.kwild
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
 networks:
   tsn-network:

diff --git a/deployments/dev-gateway/dev-gateway-compose.yaml b/deployments/dev-gateway/dev-gateway-compose.yaml
@@ -33,6 +33,12 @@ services:
       META_LOG_OTEL_PROCESSOR: "batch"
       OTEL_EXPORTER_OTLP_ENDPOINT: "vector:4317"
       META_LOG_OTEL_COLLECTOR_TLS: "false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   nginx:
     container_name: nginx
@@ -54,6 +60,12 @@ services:
       - kwil-gateway
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   vector:
     image: timberio/vector:latest-alpine
@@ -63,6 +75,12 @@ services:
 
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   prometheus:
     image: prom/prometheus:v2.30.3
@@ -74,6 +92,12 @@ services:
       - "9090:9090"
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   grafana:
     image: grafana/grafana:8.2.2
@@ -85,6 +109,12 @@ services:
       - grafana-storage:/var/lib/grafana
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
 volumes:
   grafana-storage:

diff --git a/deployments/dev-net/devnet-compose.yaml b/deployments/dev-net/devnet-compose.yaml
@@ -19,6 +19,12 @@ services:
           nocopy: true
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   kwil-postgres-2:
     image: "kwildb/postgres:latest"
@@ -40,6 +46,12 @@ services:
           nocopy: true
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   tsn-conf:
     container_name: tsn-conf
@@ -60,6 +72,12 @@ services:
       - type: volume
         source: tsn-conf
         target: /app/config
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   tsn-db-1:
     container_name: tsn-db-1
@@ -90,6 +108,12 @@ services:
       - type: volume
         source: tsn-conf
         target: /root/.kwild
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   tsn-db-2:
     container_name: tsn-db-2
@@ -120,6 +144,12 @@ services:
       - type: volume
         source: tsn-conf
         target: /root/.kwild
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
 networks:
   tsn-network:

diff --git a/deployments/gateway/gateway-compose.yaml b/deployments/gateway/gateway-compose.yaml
@@ -24,4 +24,10 @@ services:
         target: /app/kgw
       - type: bind
         source: ./kgw-config.pkl
-        target: /app/kgw-config.pkl
+        target: /app/kgw-config.pkl
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
diff --git a/deployments/indexer/dev-indexer-compose.yaml b/deployments/indexer/dev-indexer-compose.yaml
@@ -11,6 +11,12 @@ services:
         target: /etc/caddy/Caddyfile
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
   indexer-postgres:
     image: "postgres:latest"
     hostname: indexer-postgres
@@ -34,6 +40,12 @@ services:
           nocopy: true
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
   indexer:
     hostname: indexer
     restart: unless-stopped
@@ -55,6 +67,12 @@ services:
       interval: 5s
       retries: 5
       timeout: 5s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
 networks:
   tsn-network:

diff --git a/deployments/indexer/indexer-compose.yaml b/deployments/indexer/indexer-compose.yaml
@@ -12,6 +12,12 @@ services:
         target: /etc/caddy/Caddyfile
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   indexer-postgres:
     image: "postgres:latest"
@@ -32,6 +38,13 @@ services:
       - ${POSTGRES_VOLUME:-data-indexer}:/var/lib/postgresql/data
     networks:
       - tsn-network
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
+
   indexer:
     restart: unless-stopped
     build:
@@ -52,6 +65,12 @@ services:
       interval: 5s
       retries: 5
       timeout: 5s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
 networks:
   tsn-network:

diff --git a/deployments/observer/dev-observer-compose.yml b/deployments/observer/dev-observer-compose.yml
@@ -24,15 +24,28 @@ services:
       PROCFS_ROOT: /mnt/host/proc
       SYSFS_ROOT: /mnt/host/sys
       DOCKER_HOST: unix:///var/run/docker.sock
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   prometheus:
     image: prom/prometheus:v2.30.3
     command:
       - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--web.enable-remote-write-receiver'
     volumes:
       - ./dev-prometheus.yml:/etc/prometheus/prometheus.yml
     ports:
       - '9090:9090'
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   grafana:
     image: grafana/grafana:8.2.2
@@ -44,7 +57,12 @@ services:
       - grafana-storage:/var/lib/grafana
       # provision our sources
       - ./dev-grafana/provisioning/datasources/sources.yaml:/etc/grafana/provisioning/datasources/sources.yaml
-
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
   loki:
     image: grafana/loki:2.7.1
@@ -53,6 +71,12 @@ services:
     command: -config.file=/etc/loki/local-config.yaml
     volumes:
       - ./loki-config.yaml:/etc/loki/local-config.yaml
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
 
 volumes:
   grafana-storage: null
diff --git a/deployments/observer/observer-compose.yml b/deployments/observer/observer-compose.yml
@@ -30,3 +30,11 @@ services:
       INSTANCE_NAME: ${INSTANCE_NAME}
       SERVICE_NAME: ${SERVICE_NAME}
       ENV: ${ENV}
+    network_mode: host
+    restart: unless-stopped
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "2"
+        tag: "{{.Name}}"
diff --git a/deployments/observer/vector-dev-destination.yml b/deployments/observer/vector-dev-destination.yml
@@ -1,18 +1,19 @@
 # Dev destination for Vector, sends metrics to Prometheus
 sinks:
   prometheus:
-    type: prometheus_exporter
+    # use this to mimic prod destination
+    type: prometheus_remote_write
+    batch:
+      timeout_secs: 30 # preventing excess here
     inputs:
       - out-metrics-*
-    address: 0.0.0.0:8686
-    default_namespace: dev-observer
-    flush_period_secs: 60
+    endpoint: http://localhost:9090/api/v1/write
 
   loki:
     type: loki
     inputs:
       - out-logs-*
-    endpoint: "http://loki:3100"
+    endpoint: "http://localhost:3100"
     labels:
       job: vector
     encoding:

diff --git a/deployments/observer/vector-prod-destination.yml b/deployments/observer/vector-prod-destination.yml
@@ -15,6 +15,8 @@ sinks:
     inputs:
       - out-transformed-metrics
     endpoint: ${GRAFANA_CLOUD_PROMETHEUS_ENDPOINT?}
+    batch:
+      timeout_secs: 30 # preventing excess here
     auth:
       strategy: basic
       user: "${GRAFANA_CLOUD_PROMETHEUS_USER?}"

diff --git a/deployments/observer/vector-sources.yml b/deployments/observer/vector-sources.yml
@@ -1,9 +1,10 @@
 # Vector sources configuration
 # Should be used for both development and production
 sources:
-  out-metrics-hostmetrics:
+  in-metrics-hostmetrics:
     # https://vector.dev/docs/reference/configuration/sources/host_metrics/
     type: host_metrics
+    scrape_interval_secs: 60
     collectors: # default are [cpu disk filesystem load host memory network cgroups]
       - cpu
       - disk
@@ -35,6 +36,7 @@ sources:
   # It uses too many metrics
   in-metrics-internal:
     type: internal_metrics
+    scrape_interval_secs: 60
 
   out-logs-journald:
     # https://vector.dev/docs/reference/configuration/sources/journald/
@@ -91,3 +93,12 @@ transforms:
       source: |
         .name == "component_discarded_events_total" ||
         .name == "component_errors_total"
+
+  out-metrics-hostmetrics:
+    # filter out filesystem and mountpoint tags as not needed
+    type: remap
+    inputs:
+      - in-metrics-hostmetrics
+    source: |
+      del(.filesystem)
+      del(.mountpoint)