prometheus ceph.rules are obsolete

Bug #1800548 reported by kranthi kiran guttikonda
6
This bug affects 1 person
Affects Status Importance Assigned to Milestone
openstack-helm-infra
Fix Released
Undecided
kranthi kiran guttikonda

Bug Description

With ceph luminous module prometheus ceph.rules are obsolete. current rules are below

ceph:
        groups:
        - name: ceph.rules
          rules:
          - alert: ceph_monitor_quorum_low
            expr: ceph_monitor_quorum_count < 3
            for: 5m
            labels:
              severity: page
            annotations:
              description: 'ceph monitor quorum has been less than 3 for more than 5 minutes'
              summary: 'ceph high availability is at risk'
          - alert: ceph_cluster_usage_high
            expr: 100* ceph_cluster_used_bytes/ceph_cluster_capacity_bytes > 80
            for: 5m
            labels:
              severity: page
            annotations:
              description: 'ceph cluster capacity usage more than 80 percent'
              summary: 'ceph cluster usage is more than 80 percent'
          - alert: ceph_placement_group_degrade_pct_high
            expr: 100*ceph_degraded_pgs/ceph_total_pgs > 80
            for: 5m
            labels:
              severity: page
            annotations:
              description: 'ceph placement group degradation is more than 80 percent'
              summary: 'ceph placement groups degraded'
          - alert: ceph_osd_down_pct_high
            expr: 100* ceph_osds_down/(ceph_osds_down+ceph_osds_up) > 80
            for: 5m
            labels:
              severity: page
            annotations:
              description: 'ceph OSDs down percent is more than 80 percent'
              summary: 'ceph OSDs down percent is high'
          - alert: ceph_monitor_clock_skew_high
            expr: ceph_monitor_clock_skew_seconds > 2
            for: 5m
            labels:
              severity: page
            annotations:
              description: 'ceph monitors clock skew on {{$labels.instance}} is more than 2 seconds'
              summary: 'ceph monitor clock skew high'

There are only following metrics are available

"ceph_cluster_total_bytes",
        "ceph_cluster_total_objects",
        "ceph_cluster_total_used_bytes",
        "ceph_disk_occupation",
        "ceph_health_status",
        "ceph_mds_cache_num_recovering_enqueued",
        "ceph_mds_cache_num_strays",
        "ceph_mds_cache_recovery_completed",
        "ceph_mds_caps",
        "ceph_mds_exported_inodes",
        "ceph_mds_forward",
        "ceph_mds_imported_inodes",
        "ceph_mds_inodes",
        "ceph_mds_log_ev",
        "ceph_mds_log_evadd",
        "ceph_mds_log_seg",
        "ceph_mds_mem_dn",
        "ceph_mds_mem_ino",
        "ceph_mds_request",
        "ceph_mds_server_handle_client_request",
        "ceph_mds_server_handle_client_session",
        "ceph_mds_server_handle_slave_request",
        "ceph_mds_sessions_session_count",
        "ceph_mon_election_call",
        "ceph_mon_election_lose",
        "ceph_mon_election_win",
        "ceph_mon_num_elections",
        "ceph_mon_num_sessions",
        "ceph_mon_quorum_count",
        "ceph_mon_session_add",
        "ceph_mon_session_rm",
        "ceph_mon_session_trim",
        "ceph_objecter_op_active",
        "ceph_objecter_op_r",
        "ceph_objecter_op_rmw",
        "ceph_objecter_op_w",
        "ceph_osd_apply_latency_ms",
        "ceph_osd_commit_latency_ms",
        "ceph_osd_in",
        "ceph_osd_metadata",
        "ceph_osd_numpg",
        "ceph_osd_op",
        "ceph_osd_op_in_bytes",
        "ceph_osd_op_out_bytes",
        "ceph_osd_op_r",
        "ceph_osd_op_r_out_bytes",
        "ceph_osd_op_rw",
        "ceph_osd_op_rw_in_bytes",
        "ceph_osd_op_rw_out_bytes",
        "ceph_osd_op_w",
        "ceph_osd_op_w_in_bytes",
        "ceph_osd_op_wip",
        "ceph_osd_recovery_ops",
        "ceph_osd_stat_bytes",
        "ceph_osd_stat_bytes_used",
        "ceph_osd_up",
        "ceph_osd_weight",
        "ceph_paxos_accept_timeout",
        "ceph_paxos_begin",
        "ceph_paxos_begin_bytes",
        "ceph_paxos_begin_keys",
        "ceph_paxos_collect",
        "ceph_paxos_collect_bytes",
        "ceph_paxos_collect_keys",
        "ceph_paxos_collect_timeout",
        "ceph_paxos_collect_uncommitted",
        "ceph_paxos_commit",
        "ceph_paxos_commit_bytes",
        "ceph_paxos_commit_keys",
        "ceph_paxos_lease_ack_timeout",
        "ceph_paxos_lease_timeout",
        "ceph_paxos_new_pn",
        "ceph_paxos_refresh",
        "ceph_paxos_restart",
        "ceph_paxos_share_state",
        "ceph_paxos_share_state_bytes",
        "ceph_paxos_share_state_keys",
        "ceph_paxos_start_leader",
        "ceph_paxos_start_peon",
        "ceph_paxos_store_state",
        "ceph_paxos_store_state_bytes",
        "ceph_paxos_store_state_keys",
        "ceph_pg_active",
        "ceph_pg_backfill",
        "ceph_pg_backfill_toofull",
        "ceph_pg_clean",
        "ceph_pg_creating",
        "ceph_pg_deep",
        "ceph_pg_degraded",
        "ceph_pg_down",
        "ceph_pg_forced_backfill",
        "ceph_pg_forced_recovery",
        "ceph_pg_incomplete",
        "ceph_pg_inconsistent",
        "ceph_pg_peered",
        "ceph_pg_peering",
        "ceph_pg_recovering",
        "ceph_pg_remapped",
        "ceph_pg_repair",
        "ceph_pg_scrubbing",
        "ceph_pg_stale",
        "ceph_pg_undersized",
        "ceph_pg_wait_backfill",
        "ceph_pool_bytes_used",
        "ceph_pool_dirty",
        "ceph_pool_max_avail",
        "ceph_pool_metadata",
        "ceph_pool_objects",
        "ceph_pool_quota_bytes",
        "ceph_pool_quota_objects",
        "ceph_pool_raw_bytes_used",
        "ceph_pool_rd",
        "ceph_pool_rd_bytes",
        "ceph_pool_wr",
        "ceph_pool_wr_bytes",
        "ceph_purge_queue_pq_executed",
        "ceph_rocksdb_compact",
        "ceph_rocksdb_compact_queue_len",
        "ceph_rocksdb_compact_queue_merge",
        "ceph_rocksdb_compact_range",
        "ceph_rocksdb_get",
        "ceph_rocksdb_submit_transaction",
        "ceph_rocksdb_submit_transaction_sync"

Tags: prometheus
Changed in openstack-helm-infra:
assignee: nobody → kranthi kiran guttikonda (kranthi-guttikonda9)
status: New → In Progress
Revision history for this message
kranthi kiran guttikonda (kranthi-guttikonda9) wrote :
Changed in openstack-helm-infra:
status: In Progress → Fix Released
To post a comment you must log in.
This report contains Public information  
Everyone can see this information.

Other bug subscribers

Remote bug watches

Bug watches keep track of this bug in other bug trackers.