wip

Signed-off-by: hagen1778 <roman@victoriametrics.com>

deployment/docker/docker-compose.yml

@@ -5,23 +5,25 @@ services:
     ports:
       - 9101:9101
     command:
-      -  "--metric-count=20"
+      -  "--metric-count=1"
       -  "--series-count=500"
-      -  "--label-count=25"
+      -  "--label-count=20"
+      -  "--series-interval=20000000"
+      -  "--metric-interval=100009999"
       -  "--port=9101"
     networks:
       - vm_net
     restart: always
-  vmagent-no-aggregation:
+  vmagent-monitoring:
-    container_name: vmagent-no-aggregation
+    container_name: vmagent-monitoring
     image: victoriametrics/vmagent:v1.103.0
     depends_on:
       - "victoriametrics"
     ports:
       - 8429
     volumes:
-      - vmagentdata-no-aggregation:/vmagentdata
+      - vmagent-monitoring:/vmagentdata
-      - ./prometheus.yml:/etc/prometheus/prometheus.yml
+      - ./monitoring.yml:/etc/prometheus/prometheus.yml
     command:
       - "--promscrape.config=/etc/prometheus/prometheus.yml"
       - "--remoteWrite.url=http://victoriametrics:8428/api/v1/write"
@@ -43,9 +45,29 @@ services:
       - "--promscrape.config=/etc/prometheus/prometheus.yml"
       - "--streamAggr.config=/etc/prometheus/stream_aggr_config.yml"
       - "--remoteWrite.url=http://victoriametrics:8428/api/v1/write"
+      - "--promscrape.config.strictParse=false"
     networks:
       - vm_net
     restart: always
+
+  prometheus:
+    container_name: prometheus
+    image: prom/prometheus:v2.54.1
+    depends_on:
+      - "victoriametrics"
+    ports:
+      - 9090:9090
+    volumes:
+      - prometheus:/prometheus
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml
+      - ./rules.yml:/etc/prometheus/rules.yml
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+    networks:
+      - vm_net
+    restart: always
+
   # VictoriaMetrics instance, a single process responsible for
   # storing metrics and serve read requests.
   victoriametrics:
@@ -81,50 +103,9 @@ services:
       - vm_net
     restart: always
 
-  # vmalert executes alerting and recording rules
-  vmalert:
-    container_name: vmalert
-    image: victoriametrics/vmalert:v1.103.0
-    depends_on:
-      - "victoriametrics"
-      - "alertmanager"
-    ports:
-      - 8880:8880
-    volumes:
-      - ./alerts.yml:/etc/alerts/alerts.yml
-      - ./alerts-health.yml:/etc/alerts/alerts-health.yml
-      - ./alerts-vmagent.yml:/etc/alerts/alerts-vmagent.yml
-      - ./alerts-vmalert.yml:/etc/alerts/alerts-vmalert.yml
-    command:
-      - "--datasource.url=http://victoriametrics:8428/"
-      - "--remoteRead.url=http://victoriametrics:8428/"
-      - "--remoteWrite.url=http://victoriametrics:8428/"
-      - "--notifier.url=http://alertmanager:9093/"
-      - "--rule=/etc/alerts/*.yml"
-      # display source of alerts in grafana
-      - "--external.url=http://127.0.0.1:3000" #grafana outside container
-      - '--external.alert.source=explore?orgId=1&left={"datasource":"VictoriaMetrics","queries":[{"expr":{{.Expr|jsonEscape|queryEscape}},"refId":"A"}],"range":{"from":"{{ .ActiveAt.UnixMilli }}","to":"now"}}'
-    networks:
-      - vm_net
-    restart: always
-
-  # alertmanager receives alerting notifications from vmalert
-  # and distributes them according to --config.file.
-  alertmanager:
-    container_name: alertmanager
-    image: prom/alertmanager:v0.27.0
-    volumes:
-      - ./alertmanager.yml:/config/alertmanager.yml
-    command:
-      - "--config.file=/config/alertmanager.yml"
-    ports:
-      - 9093:9093
-    networks:
-      - vm_net
-    restart: always
-
 volumes:
-  vmagentdata-no-aggregation: {}
+  prometheus: {}
+  vmagent-monitoring: {}
   vmagentdata-with-aggregation: {}
   vmdata: {}
   grafanadata: {}

deployment/docker/monitoring.yml

@@ -0,0 +1,16 @@
+global:
+  scrape_interval: 5s
+
+scrape_configs:
+- job_name: 'vmagent-monitoring'
+  static_configs:
+    - targets: ['vmagent-monitoring:8429']
+- job_name: 'prometheus'
+  static_configs:
+    - targets: ['prometheus:9090']
+- job_name: 'vmagent-with-aggregation'
+  static_configs:
+    - targets: ['vmagent-with-aggregation:8429']
+- job_name: 'victoriametrics'
+  static_configs:
+    - targets: ['victoriametrics:8428']

deployment/docker/prometheus.yml

@@ -1,16 +1,79 @@
 global:
-  scrape_interval: 5s
+  scrape_interval: 15s
+  evaluation_interval: 5m
+
+rule_files:
+  - "rules.yml"
+
+remote_write:
+  - url: http://victoriametrics:8428/api/v1/write
+    write_relabel_configs:
+      - source_labels: [ __name__ ]
+        regex: .*sum_over_time.*
+        action: keep
+    queue_config:
+      max_samples_per_send: 10000
+      capacity: 20000
+      max_shards: 30
 
 scrape_configs:
-  - job_name: 'vmagent'
+  - job_name: 'avalanche1'
     static_configs:
-      - targets: ['vmagent-no-aggregation:8429', 'vmagent-with-aggregation:8429']
+      - targets: ['avalanche:9101']
-  - job_name: 'vmalert'
+  - job_name: 'avalanche2'
     static_configs:
-      - targets: ['vmalert:8880']
+      - targets: ['avalanche:9101']
-  - job_name: 'victoriametrics'
+  - job_name: 'avalanche3'
     static_configs:
-      - targets: ['victoriametrics:8428']
+      - targets: ['avalanche:9101']
-  - job_name: 'avalanche'
+  - job_name: 'avalanche4'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche5'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche6'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche7'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche8'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche9'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche10'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche11'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche12'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche13'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche14'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche15'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche16'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche17'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche18'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche19'
+    static_configs:
+      - targets: ['avalanche:9101']
+  - job_name: 'avalanche20'
     static_configs:
       - targets: ['avalanche:9101']

deployment/docker/rules.yml

@@ -0,0 +1,5 @@
+groups:
+  - name: demo
+    rules:
+      - record: cycle:avalanche:sum_over_time:5m
+        expr: sum(sum_over_time(avalanche_metric_mmmmm_0_0[5m])) by(cycle_id)

deployment/docker/stream_aggr_config.yml

@@ -0,0 +1,5 @@
+- match: 'avalanche_metric_mmmmm_0_0'
+  interval: 5m
+  by: ["cycle_id"]
+  outputs:
+    - sum_samples