Added loki with host logs forwarded

.github/workflows/stackhpc.yml

@@ -170,6 +170,11 @@ jobs:
         env:
           TESTUSER_PASSWORD: ${{ secrets.TEST_USER_PASSWORD }}
 
+      - name: Get timestamp in milliseconds before rebuild
+        id: timestamp
+        run: |
+          echo "TIME_BEFORE_REBUILD=$(date +%s%N | cut -b1-13)" >> $GITHUB_OUTPUT
+
       # - name: Build environment-specific compute image
       #   id: packer_build
       #   run: |
@@ -209,6 +214,14 @@ jobs:
           . environments/.stackhpc/activate
           ansible-playbook -vv ansible/ci/check_grafana.yml
 
+      - name: Check Loki Slurm logs persisted through rebuild
+        run: |
+          . venv/bin/activate
+          . environments/.stackhpc/activate
+          ansible-playbook -vv ansible/ci/check_loki.yml -e "end_timestamp=${{ steps.timestamp.outputs.TIME_BEFORE_REBUILD }} testuser_password=$TESTUSER_PASSWORD"
+        env:
+          TESTUSER_PASSWORD: ${{ secrets.TEST_USER_PASSWORD }}
+
       - name: Delete infrastructure
         run: |
           . venv/bin/activate

ansible/ci/check_loki.yml

@@ -0,0 +1,42 @@
+- hosts: control
+  gather_facts: no
+  become: no
+  tasks:
+    - name: Get Loki datasource uid
+      ansible.builtin.uri:
+        url: http://localhost:{{ grafana_port }}/api/datasources/name/Loki
+        url_username: 'testuser'
+        url_password: "{{ testuser_password }}"
+        follow_redirects: all
+      register: uid_response
+
+    - name: Get Loki logs from before rebuild
+      vars:
+        testuser_password: mypassword
+      ansible.builtin.uri:
+        url: http://localhost:{{ grafana_port }}/api/ds/query
+        follow_redirects: all
+        url_username: testuser
+        url_password: "{{ testuser_password }}"
+        method: POST	
+        body_format: json
+        headers:
+          Accept: application/json
+          Content-Type: application/json
+        # Queries from 20 mins before timestamp to timestamp
+        body: |
+          {
+            "queries":[
+              {
+                "expr":"{unit=\"slurmd.service\"} |= ``",
+                "datasource":{"uid":"{{ uid_response.json.uid }}"},
+                "format":"time_series"
+              }],
+            "from":"{{ end_timestamp | int - 1200000 }}",
+            "to":"{{ end_timestamp }}"
+          }
+      register: log_query_content
+
+    - name: Check that logs exist
+      ansible.builtin.assert:
+        that: log_query_content.json.results.A.frames[0].data['values'][2] | length > 0

ansible/roles/grafana-dashboards/files/loki-pod-logs-dashboard.json

@@ -0,0 +1,228 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "Search pod logs stored in Loki",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": 31,
+  "links": [],
+  "panels": [
+    {
+      "datasource": "Loki",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "hidden",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "bars",
+            "fillOpacity": 100,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "never",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 3,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 6,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": false
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": "Loki",
+          "expr": "sum(count_over_time({namespace=\"$namespace\", pod=~\"$pod\"} |~ \"$search\"[$__interval]))",
+          "refId": "A"
+        }
+      ],
+      "type": "timeseries"
+    },
+    {
+      "datasource": "Loki",
+      "gridPos": {
+        "h": 25,
+        "w": 24,
+        "x": 0,
+        "y": 3
+      },
+      "id": 2,
+      "maxDataPoints": "",
+      "options": {
+        "dedupStrategy": "none",
+        "enableLogDetails": true,
+        "prettifyLogMessage": false,
+        "showCommonLabels": false,
+        "showLabels": false,
+        "showTime": true,
+        "sortOrder": "Descending",
+        "wrapLogMessage": true
+      },
+      "targets": [
+        {
+          "datasource": "Loki",
+          "expr": "{namespace=\"$namespace\", pod=~\"$pod\"} |~ \"$search\"",
+          "refId": "A"
+        }
+      ],
+      "title": "Logs Panel",
+      "type": "logs"
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": [],
+  "templating": {
+    "list": [
+      {
+        "allValue": ".+",
+        "current": {
+          "selected": true,
+          "text": "ingress-nginx",
+          "value": "ingress-nginx"
+        },
+        "datasource": "Loki",
+        "definition": "label_values(namespace)",
+        "hide": 0,
+        "includeAll": false,
+        "multi": false,
+        "name": "namespace",
+        "options": [],
+        "query": "label_values(namespace)",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 0,
+        "tagValuesQuery": "",
+        "tagsQuery": "",
+        "type": "query",
+        "useTags": false
+      },
+      {
+        "allValue": ".+",
+        "current": {
+          "selected": false,
+          "text": "All",
+          "value": "$__all"
+        },
+        "datasource": "Loki",
+        "definition": "label_values({namespace=~\"$namespace\"}, pod)",
+        "hide": 0,
+        "includeAll": true,
+        "multi": true,
+        "name": "pod",
+        "options": [],
+        "query": "label_values({namespace=~\"$namespace\"}, pod)",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 0,
+        "tagValuesQuery": "",
+        "tagsQuery": "",
+        "type": "query",
+        "useTags": false
+      },
+      {
+        "current": {},
+        "hide": 0,
+        "name": "search",
+        "options": [],
+        "query": "",
+        "skipUrlSync": false,
+        "type": "textbox"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-6h",
+    "to": "now"
+  },
+  "timepicker": {
+    "refresh_intervals": [
+      "5s",
+      "10s",
+      "30s",
+      "1m",
+      "5m",
+      "15m",
+      "30m",
+      "1h",
+      "2h",
+      "1d"
+    ]
+  },
+  "timezone": "",
+  "title": "Loki / Pod Logs",
+  "uid": "209fd89b771c318dd442225414a50b59",
+  "version": 1,
+  "weekStart": ""
+}