monitoring: remove cephadm ruleset

Remove cephadm ruleset, as they don't apply to rook

Signed-off-by: ahgraber <ahgraber@ninerealmlabs.com>
(cherry picked from commit 568623d92b)

deploy/charts/rook-ceph-cluster/prometheus/localrules.yaml

@@ -583,38 +583,6 @@ groups:
           summary: "{{ $labels.ceph_daemon }} operations are slow to complete"
           description: "{{ $labels.ceph_daemon }} operations are taking too long to process (complaint time exceeded)"
           documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops"
-  - name: "cephadm"
-    rules:
-      - alert: "CephadmUpgradeFailed"
-        annotations:
-          description: "The cephadm cluster upgrade process has failed. The cluster remains in an undetermined state. Please review the cephadm logs, to understand the nature of the issue"
-          summary: "Ceph version upgrade has failed"
-        expr: "ceph_health_detail{name=\"UPGRADE_EXCEPTION\"} > 0"
-        for: "30s"
-        labels:
-          oid: "1.3.6.1.4.1.50495.1.2.1.11.2"
-          severity: "critical"
-          type: "ceph_default"
-      - alert: "CephadmDaemonFailed"
-        annotations:
-          description: "A daemon managed by cephadm is no longer active. Determine, which daemon is down with 'ceph health detail'. you may start daemons with the 'ceph orch daemon start <daemon_id>'"
-          summary: "A ceph daemon manged by cephadm is down"
-        expr: "ceph_health_detail{name=\"CEPHADM_FAILED_DAEMON\"} > 0"
-        for: "30s"
-        labels:
-          oid: "1.3.6.1.4.1.50495.1.2.1.11.1"
-          severity: "critical"
-          type: "ceph_default"
-      - alert: "CephadmPaused"
-        annotations:
-          description: "Cluster management has been paused manually. This will prevent the orchestrator from service management and reconciliation. If this is not intentional, resume cephadm operations with 'ceph orch resume'"
-          documentation: "https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused"
-          summary: "Orchestration tasks via cephadm are PAUSED"
-        expr: "ceph_health_detail{name=\"CEPHADM_PAUSED\"} > 0"
-        for: "1m"
-        labels:
-          severity: "warning"
-          type: "ceph_default"
   - name: "PrometheusServer"
     rules:
       - alert: "PrometheusJobMissing"

deploy/examples/monitoring/localrules.yaml

@@ -592,38 +592,6 @@ spec:
             summary: "{{ $labels.ceph_daemon }} operations are slow to complete"
             description: "{{ $labels.ceph_daemon }} operations are taking too long to process (complaint time exceeded)"
             documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops"
-    - name: "cephadm"
-      rules:
-        - alert: "CephadmUpgradeFailed"
-          annotations:
-            description: "The cephadm cluster upgrade process has failed. The cluster remains in an undetermined state. Please review the cephadm logs, to understand the nature of the issue"
-            summary: "Ceph version upgrade has failed"
-          expr: "ceph_health_detail{name=\"UPGRADE_EXCEPTION\"} > 0"
-          for: "30s"
-          labels:
-            oid: "1.3.6.1.4.1.50495.1.2.1.11.2"
-            severity: "critical"
-            type: "ceph_default"
-        - alert: "CephadmDaemonFailed"
-          annotations:
-            description: "A daemon managed by cephadm is no longer active. Determine, which daemon is down with 'ceph health detail'. you may start daemons with the 'ceph orch daemon start <daemon_id>'"
-            summary: "A ceph daemon manged by cephadm is down"
-          expr: "ceph_health_detail{name=\"CEPHADM_FAILED_DAEMON\"} > 0"
-          for: "30s"
-          labels:
-            oid: "1.3.6.1.4.1.50495.1.2.1.11.1"
-            severity: "critical"
-            type: "ceph_default"
-        - alert: "CephadmPaused"
-          annotations:
-            description: "Cluster management has been paused manually. This will prevent the orchestrator from service management and reconciliation. If this is not intentional, resume cephadm operations with 'ceph orch resume'"
-            documentation: "https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused"
-            summary: "Orchestration tasks via cephadm are PAUSED"
-          expr: "ceph_health_detail{name=\"CEPHADM_PAUSED\"} > 0"
-          for: "1m"
-          labels:
-            severity: "warning"
-            type: "ceph_default"
     - name: "PrometheusServer"
       rules:
         - alert: "PrometheusJobMissing"