Fix node_exporter options (#41)

Changes: - The `--web.config` command line option for `node_exporter` is actually `--web.config.file` Closes #39 --------- Co-authored-by: Haroon Chughtai <[email protected]>
UCL-MIRSG · Jan 8, 2024 · 814f84b · 814f84b
1 parent 9807009
commit 814f84b
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 7 deletions.
diff --git a/roles/monitoring_client/templates/node_exporter.service.j2 b/roles/monitoring_client/templates/node_exporter.service.j2
@@ -7,7 +7,7 @@ After=syslog.target network.target
 User= {{ monitoring_client_owner }}
 Group= {{ monitoring_client_group }}
 
-ExecStart={{ monitoring_client_node_exporter_install_dir }}/node_exporter --web.config={{ monitoring_client_node_exporter_web_config }}
+ExecStart={{ monitoring_client_node_exporter_install_dir }}/node_exporter --web.config.file={{ monitoring_client_node_exporter_web_config }}
 
 [Install]
 WantedBy=multi-user.target
diff --git a/roles/monitoring_server/templates/prometheus_rules.yml.j2 b/roles/monitoring_server/templates/prometheus_rules.yml.j2
@@ -31,22 +31,22 @@ groups:
   - name: metrics
     rules:
       - alert: MemoryUsageHigh
-        expr: 100- node_memory_MemAvailable_bytes/node_memory_MemTotal_bytes*100 > 80
+        expr: 100- node_memory_MemAvailable_bytes/node_memory_MemTotal_bytes*100 > 90
         for: 5m
         labels:
           severity: warning
         annotations:
           summary: Instance memory usage high (Instance:{{ $labels.instance }})
-          description: "Instance memory usage more than 80% within 5 minutus, value:{{ $labels.value }}%"
+          description: "Instance memory usage more than 90% within 5 minutes, value:{{ $labels.value }}%"
 
       - alert: CpuLoadHigh
-        expr: 100 - avg by(instance)(rate(node_cpu_seconds_total{mode="idle"}[5m]))*100 > 80
+        expr: 100 - avg by(instance)(rate(node_cpu_seconds_total{mode="idle"}[5m]))*100 > 90
         for: 0m
         labels:
           severity: warning
         annotations:
           summary: Instance cpu load high (Instance:{{ $labels.instance }})
-          description: "Instance cpu load more than 80% within 5 minutes, value: {{ $labels.value }}%"
+          description: "Instance cpu load more than 90% within 5 minutes, value: {{ $labels.value }}%"
 
       - alert: FilesystemFull
         expr: 100 - node_filesystem_free_bytes{mountpoint!~"/*|/boot.*|/run.*"}/node_filesystem_size_bytes*100 > 90
@@ -58,10 +58,10 @@ groups:
           description: "The used space of the mounted filestore (mountpoint:{{ $labels.mountpoint }}) is more than 90%, value: {{ $labels.value }}%"
 
       - alert: InodeUsageHigh
-        expr: 100 - node_filesystem_files_free/node_filesystem_files*100 > 80
+        expr: 100 - node_filesystem_files_free/node_filesystem_files*100 > 90
         for: 0m
         labels:
           severity: warning
         annotations:
           summary: Instance inode usage high (Instance:{{ $labels.instance }})
-          description: "The used file nodes(inodes) of the filesystem(filesystem:{{ $labels.mountpoint }}) is more than 80%, value: {{ $labels.value }}%"
+          description: "The used file nodes(inodes) of the filesystem(filesystem:{{ $labels.mountpoint }}) is more than 90%, value: {{ $labels.value }}%"