Skip to content

Commit

Permalink
Update dashboards and prometheus rules (#39)
Browse files Browse the repository at this point in the history 
grafana dashboards:

(changed) ceph-cluster-advanced.json:
"Added graph with title "Bad PGs". This graph helps to show PGs without ACTIVE and CLEAN status.
It separates view from major active, clean PGs and point out PGs with "bad" status at the moment."

(added) ceph_overview.json:
"This dashboard shows the top clients to ceph with read/write and throuput."

(added) ceph_pools.json:
"This dashboard shows the best of two other dashboards: 'ceph-cluster.json' and 'ceph-cluster-advanced.json'."

prometheus rules:

(changed) ceph.rules:
"Added group of rules Ceph Latency."

(changed) haproxy.rules:
"Added rules for backends, including Ceph Dashboard."

(changed) mysql.rules:
"Added rules for mariadb and slow logs."

(changed) openstack.rules:
"Added rules for OpenStack services, like: Cinder, Nova, Neutron, Keystone, Designate, Octavia etc."

(added) container.rules:
"Added rules related to containers life."

(added) fluentd-aggregator.rules:
"Added rules for fluentd aggregator.
fluentd-aggregator could help to forward the logs from OpenStack cluster to company's centralized log system."
In addition added '60-fluentd-aggregator.yml' jinja2 template and changed .yamllint.yml.

(added) hardware.rules:
"Added rules related to generic hardware."

Signed-off-by: Aleksandr Gerasimenko <aleksandr.gerasimenko@plusserver.com>
  • Loading branch information
@alexgesser
alexgesser authored Feb 10, 2024
1 parent 3265f1a commit 0bb81f3
Show file tree
Hide file tree
Showing 12 changed files with 4,643 additions and 9 deletions.
1 change: 1 addition & 0 deletions .yamllint.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ rules:
line-length: disable

ignore: |
prometheus/prometheus.yml.d/60-fluentd-aggregator.yml
prometheus/prometheus.yml.d/51-ceph-nodeexporter.yml
prometheus/prometheus.yml.d/50-ceph.yml
prometheus/prometheus.yml.d/10-redfish.yml
279 changes: 279 additions & 0 deletions grafana/dashboards/ceph/ceph-cluster-advanced.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3642,6 +3642,285 @@
}
],
"type": "table"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "",
"editable": true,
"error": false,
"fill": 1,
"fillGradient": 0,
"grid": {},
"gridPos": {
"h": 10,
"w": 24,
"x": 0,
"y": 41
},
"hiddenSeries": false,
"id": 43,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sort": "avg",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "/^Total.*$/",
"stack": false
}
],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "ceph_pg_active",
"format": "time_series",
"hide": true,
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Active",
"refId": "M"
},
{
"expr": "ceph_pg_clean",
"format": "time_series",
"hide": true,
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Clean",
"refId": "U"
},
{
"expr": "ceph_pg_peering",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Peering",
"refId": "I"
},
{
"expr": "ceph_pg_degraded",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Degraded",
"refId": "B",
"step": 300
},
{
"expr": "ceph_pg_stale",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Stale",
"refId": "C",
"step": 300
},
{
"expr": "ceph_unclean_pgs",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Unclean",
"refId": "D",
"step": 300
},
{
"expr": "ceph_pg_undersized",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Undersized",
"refId": "E",
"step": 300
},
{
"expr": "ceph_pg_incomplete",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Incomplete",
"refId": "G"
},
{
"expr": "ceph_pg_forced_backfill",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Forced Backfill",
"refId": "H"
},
{
"expr": "ceph_pg_inconsistent",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Inconsistent",
"refId": "F"
},
{
"expr": "ceph_pg_forced_recovery",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Forced Recovery",
"refId": "J"
},
{
"expr": "ceph_pg_creating",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Creating",
"refId": "K"
},
{
"expr": "ceph_pg_wait_backfill",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Wait Backfill",
"refId": "L"
},
{
"expr": "ceph_pg_deep",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Deep",
"refId": "N"
},
{
"expr": "ceph_pg_scrubbing",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Scrubbing",
"refId": "O"
},
{
"expr": "ceph_pg_recovering",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Recovering",
"refId": "P"
},
{
"expr": "ceph_pg_repair",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Repair",
"refId": "Q"
},
{
"expr": "ceph_pg_down",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Down",
"refId": "R"
},
{
"expr": "ceph_pg_peered",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Peered",
"refId": "S"
},
{
"expr": "ceph_pg_backfill",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Backfill",
"refId": "T"
},
{
"expr": "ceph_pg_remapped",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Remapped",
"refId": "V"
},
{
"expr": "ceph_pg_backfill_toofull",
"format": "time_series",
"interval": "$interval",
"intervalFactor": 1,
"legendFormat": "Backfill Toofull",
"refId": "W"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Bad PGs",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 1,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
}
],
"refresh": "1m",
Expand Down
Loading

0 comments on commit 0bb81f3

Please sign in to comment.