Merge pull request #473 from gitpod-io/roboquat/automated-dependency-…

…update-main

[bot] [main] Automated dependencies update

jsonnetfile.lock.json

@@ -18,7 +18,7 @@
           "subdir": "contrib/mixin"
         }
       },
-      "version": "57a583d14021c3f2ffd25ceae6993a28a3a0a691",
+      "version": "82f6cb4635fe7db3e74b6e332b7078cdfed7b9c1",
       "sum": "GdePvMDfLQcVhwzk/Ephi/jC27ywGObLB5t0eC0lXd4="
     },
     {
@@ -28,8 +28,8 @@
           "subdir": "operations/observability/mixins"
         }
       },
-      "version": "2933eeef5476b6a142691ed72a236c0df2abd197",
-      "sum": "NzRQn9P2uTW42KbRRt/qJceIhOB2ZDIZ3iCGJm4Cj2g=",
+      "version": "9912fdca56a39f5d5c1b9fa5df586befa952f51e",
+      "sum": "JnG7mzgMCfzQmntsG8nnmWkpcyX4kPZIpW7+gBGRVjo=",
       "name": "gitpod"
     },
     {
@@ -69,7 +69,7 @@
           "subdir": "grafana-builder"
         }
       },
-      "version": "6621ddc23751d828e9d4b78fda38c1fa3f6bdc84",
+      "version": "f33dff93db677a32303630c3e0910cf6d46a92cc",
       "sum": "RJjFQa1n8CDbB6m1fBQQzPye7jhOhGTUbma27Gil81I="
     },
     {
@@ -119,7 +119,7 @@
           "subdir": "jsonnet/mixin"
         }
       },
-      "version": "5457c5c34c034316dc982d6b882bb4a77ae34002",
+      "version": "d53cae45a3a2516bc21f5f05bed34e2e1e522de1",
       "sum": "n3flMIzlADeyygb0uipZ4KPp2uNSjdtkrwgHjTC7Ca4=",
       "name": "prometheus-operator-mixin"
     },
@@ -130,8 +130,8 @@
           "subdir": "jsonnet/prometheus-operator"
         }
       },
-      "version": "5457c5c34c034316dc982d6b882bb4a77ae34002",
-      "sum": "RgD961BWKDlZ0W+gp7RaAWP/HoYlTusbnkhoRFjjg+g="
+      "version": "d53cae45a3a2516bc21f5f05bed34e2e1e522de1",
+      "sum": "A5QkHp+O+Xfcw+pSlSnVLfo6kfnaX7ynnxGfG31UTCs="
     },
     {
       "source": {
@@ -140,7 +140,7 @@
           "subdir": "doc/alertmanager-mixin"
         }
       },
-      "version": "11e0edb1d2d21e80325a64a4a14ec088d521aea6",
+      "version": "487db1383b8cc5c2867c77f110431605bb8ce247",
       "sum": "PsK+V7oETCPKu2gLoPfqY0wwPKH9TzhNj6o2xezjjXc=",
       "name": "alertmanager"
     },
@@ -151,8 +151,8 @@
           "subdir": "docs/node-mixin"
         }
       },
-      "version": "c31ebb43590cb0055acd4bc00a432f6a2dafdd08",
-      "sum": "aFUI56y6Y8EpniS4cfYqrSaHFnxeomIw4S4+Sz8yPtQ="
+      "version": "8b4dc8248891d1e08d502e74e5c49452da59e447",
+      "sum": "By6n6U10hYDogUsyhsaKZehbhzxBZZobJloiKyKadgM="
     },
     {
       "source": {
@@ -161,7 +161,7 @@
           "subdir": "documentation/prometheus-mixin"
         }
       },
-      "version": "031d22df9e43f1c3014b8344337e133099902ae8",
+      "version": "26c354de0b46d14f922f5d37c24513596dff56b0",
       "sum": "WkRzFpnseUc/Ev8I2QBLxAC4vkPwLHeOGUw5QemCsMU=",
       "name": "prometheus"
     },
@@ -182,7 +182,7 @@
           "subdir": "mixin"
         }
       },
-      "version": "37cf55964d88c2afd305e635e8dd0045826610db",
+      "version": "ca308b0d51a07987671804b4e06487f3b4173b51",
       "sum": "WhheqsiX0maUXByZFsb9xhCEsGXK2955bPmPPf1x+Cs=",
       "name": "thanos-mixin"
     },

monitoring-satellite/manifests/kube-prometheus-rules/rules.yaml

@@ -779,7 +779,76 @@ spec:
         quantile: "0.5"
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
   - name: node-exporter
-    rules: []
+    rules:
+    - alert: NodeCPUHighUsage
+      annotations:
+        description: |
+          CPU usage at {{ $labels.instance }} has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodecpuhighusage
+        summary: High CPU usage.
+      expr: |
+        sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job="node-exporter", mode!="idle"}[2m]))) * 100 > 90
+      for: 15m
+      labels:
+        severity: info
+    - alert: NodeSystemSaturation
+      annotations:
+        description: |
+          System load per core at {{ $labels.instance }} has been above 2 for the last 15 minutes, is currently at {{ printf "%.2f" $value }}.
+          This might indicate this instance resources saturation and can cause it becoming unresponsive.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemsaturation
+        summary: System saturated, load per core is very high.
+      expr: |
+        node_load1{job="node-exporter"}
+        / count without (cpu, mode) (node_cpu_seconds_total{job="node-exporter", mode="idle"}) > 2
+      for: 15m
+      labels:
+        severity: warning
+    - alert: NodeMemoryMajorPagesFaults
+      annotations:
+        description: |
+          Memory major pages are occurring at very high rate at {{ $labels.instance }}, 500 major page faults per second for the last 15 minutes, is currently at {{ printf "%.2f" $value }}.
+          Please check that there is enough memory available at this instance.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememorymajorpagesfaults
+        summary: Memory major page faults are occurring at very high rate.
+      expr: |
+        rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) > 500
+      for: 15m
+      labels:
+        severity: warning
+    - alert: NodeMemoryHighUtilization
+      annotations:
+        description: |
+          Memory is filling up at {{ $labels.instance }}, has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememoryhighutilization
+        summary: Host is running out of memory.
+      expr: |
+        100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"} * 100) > 90
+      for: 15m
+      labels:
+        severity: warning
+    - alert: NodeDiskIOSaturation
+      annotations:
+        description: |
+          Disk IO queue (aqu-sq) is high on {{ $labels.device }} at {{ $labels.instance }}, has been above 10 for the last 15 minutes, is currently at {{ printf "%.2f" $value }}.
+          This symptom might indicate disk saturation.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodediskiosaturation
+        summary: Disk IO queue is high.
+      expr: |
+        rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) > 10
+      for: 30m
+      labels:
+        severity: warning
+    - alert: NodeSystemdServiceFailed
+      annotations:
+        description: Systemd service {{ $labels.name }} has entered failed state at {{ $labels.instance }}
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicefailed
+        summary: Systemd service has entered failed state.
+      expr: |
+        node_systemd_unit_state{job="node-exporter", state="failed"} == 1
+      for: 5m
+      labels:
+        severity: warning
   - name: node-exporter.rules
     rules:
     - expr: |