Merge branch 'L2SS-1915-add-prometheus-tuna' into 'main'

Scrape qa-statistics-service, add prometheus

See merge request !11

.gitlab-ci.yml

@@ -113,6 +113,7 @@ deploy:
     - |
       levant deploy \
         -address="http://${SERVER}.control.lofar:4646" \
+        -var-file=infra/env.yaml \
         -var image_tag="${IMAGE_TAG}" \
         infra/${COMPONENT}-central.levant.nomad
 

infra/env.yaml

+registry:
+  astron:
+    url: git.astron.nl:5000/lofar2.0/tango
+
+monitoring:
+  prometheus:
+    version: latest

infra/metrics-central.levant.nomad

@@ -8,6 +8,67 @@ job "metrics" {
     max_parallel = 1
   }
 
+  group "prometheus" {
+    service {
+      tags         = ["haproxy", "scrape"]
+      name         = "prometheus"
+      port         = "9090"
+      address_mode = "alloc"
+
+
+      check {
+        type     = "http"
+        name     = "prometheus_health"
+        port     = "9090"
+        path     = "/-/healthy"
+        interval = "20s"
+        timeout  = "30s"
+        address_mode = "alloc"
+      }
+    }
+
+    task "prometheus" {
+      driver = "docker"
+
+      config {
+        image = "[[.registry.astron.url]]/prometheus:[[.monitoring.prometheus.version]]"
+        args  = [
+          "--config.file=/local/prometheus.yaml",
+          "--web.enable-remote-write-receiver",
+          "--storage.tsdb.retention.time=7d"
+        ]
+      }
+
+      template {
+        data          = <<EOH
+        global:
+          evaluation_interval: 10s
+          scrape_interval: 10s
+          scrape_timeout: 10s
+
+        remote_write:
+          - url: http://metrics.service.lofar-central.consul:9009/api/v1/push
+            headers:
+              "X-Scope-OrgID": lofar
+
+        scrape_configs:
+          - job_name: 'qa_statistics_service'
+            static_configs:
+              - targets: ['lcs129.control.lofar:8002']
+        EOH
+        change_mode   = "signal"
+        change_signal = "SIGHUP"
+        destination   = "local/prometheus.yaml"
+      }
+
+      resources {
+        cpu        = 500
+        memory     = 2048
+        memory_max = 8192
+      }
+    }
+  }
+
   group "mimir" {
     network {
       mode = "bridge"