Skip to content

Commit

Permalink
Merge pull request #128 from projectsyn/feat/ceph-recording-rules
Browse files Browse the repository at this point in the history
Configure recording rules for centralized Ceph dashboard
  • Loading branch information
simu committed Jun 30, 2023
2 parents 2c46612 + dcf5062 commit 32cfe61
Show file tree
Hide file tree
Showing 3 changed files with 88 additions and 0 deletions.
28 changes: 28 additions & 0 deletions class/defaults.yml
Original file line number Diff line number Diff line change
Expand Up @@ -185,6 +185,34 @@ parameters:
summary: rook-ceph operator scaled to 0 for more than 1 hour.
labels:
severity: warning
"record:ceph_osd_op_w_in_bytes:irate5m":
expr: sum(irate(ceph_osd_op_w_in_bytes{}[5m]))
"record:ceph_osd_op_r_out_bytes:irate5m":
expr: sum(irate(ceph_osd_op_r_out_bytes{}[5m]))
"record:ceph_pool_objects:sum":
expr: sum(ceph_pool_objects{})
"record:ceph_mon_num_sessions:sum":
expr: sum(ceph_mon_num_sessions{})
"record:ceph_mon_quorum_status:count":
expr: count(ceph_mon_quorum_status{})
"record:ceph_osd_op_w_in_bytes:sum":
expr: sum(ceph_osd_op_w_in_bytes{})
"record:ceph_osd_op_r_out_bytes:sum":
expr: sum(ceph_osd_op_r_out_bytes{})
"record:ceph_osd_numpg:sum":
expr: sum(ceph_osd_numpg{})
"record:ceph_osd_apply_latency_ms:avg":
expr: avg(ceph_osd_apply_latency_ms{})
"record:ceph_osd_commit_latency_ms:avg":
expr: avg(ceph_osd_commit_latency_ms{})
"record:ceph_osd_op_w_latency:avg5m":
expr: avg(rate(ceph_osd_op_w_latency_sum{}[5m]) / rate(ceph_osd_op_w_latency_count{}[5m]) >= 0)
"record:ceph_osd_op_r_latency:avg5m":
expr: avg(rate(ceph_osd_op_r_latency_sum{}[5m]) / rate(ceph_osd_op_r_latency_count{}[5m]) >= 0)
"record:ceph_osd_op_w:irate5m":
expr: sum(irate(ceph_osd_op_w{}[5m]))
"record:ceph_osd_op_r:irate5m":
expr: sum(irate(ceph_osd_op_r{}[5m]))

node_selector:
node-role.kubernetes.io/storage: ''
Expand Down
30 changes: 30 additions & 0 deletions tests/golden/defaults/rook-ceph/rook-ceph/40_alertrules.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -427,3 +427,33 @@ spec:
severity: warning
syn: 'true'
syn_component: rook-ceph
- expr: sum(ceph_mon_num_sessions{})
record: ceph_mon_num_sessions:sum
- expr: count(ceph_mon_quorum_status{})
record: ceph_mon_quorum_status:count
- expr: avg(ceph_osd_apply_latency_ms{})
record: ceph_osd_apply_latency_ms:avg
- expr: avg(ceph_osd_commit_latency_ms{})
record: ceph_osd_commit_latency_ms:avg
- expr: sum(ceph_osd_numpg{})
record: ceph_osd_numpg:sum
- expr: sum(irate(ceph_osd_op_r{}[5m]))
record: ceph_osd_op_r:irate5m
- expr: avg(rate(ceph_osd_op_r_latency_sum{}[5m]) / rate(ceph_osd_op_r_latency_count{}[5m])
>= 0)
record: ceph_osd_op_r_latency:avg5m
- expr: sum(irate(ceph_osd_op_r_out_bytes{}[5m]))
record: ceph_osd_op_r_out_bytes:irate5m
- expr: sum(ceph_osd_op_r_out_bytes{})
record: ceph_osd_op_r_out_bytes:sum
- expr: sum(irate(ceph_osd_op_w{}[5m]))
record: ceph_osd_op_w:irate5m
- expr: sum(irate(ceph_osd_op_w_in_bytes{}[5m]))
record: ceph_osd_op_w_in_bytes:irate5m
- expr: sum(ceph_osd_op_w_in_bytes{})
record: ceph_osd_op_w_in_bytes:sum
- expr: avg(rate(ceph_osd_op_w_latency_sum{}[5m]) / rate(ceph_osd_op_w_latency_count{}[5m])
>= 0)
record: ceph_osd_op_w_latency:avg5m
- expr: sum(ceph_pool_objects{})
record: ceph_pool_objects:sum
30 changes: 30 additions & 0 deletions tests/golden/openshift4/rook-ceph/rook-ceph/40_alertrules.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -427,3 +427,33 @@ spec:
severity: warning
syn: 'true'
syn_component: rook-ceph
- expr: sum(ceph_mon_num_sessions{})
record: ceph_mon_num_sessions:sum
- expr: count(ceph_mon_quorum_status{})
record: ceph_mon_quorum_status:count
- expr: avg(ceph_osd_apply_latency_ms{})
record: ceph_osd_apply_latency_ms:avg
- expr: avg(ceph_osd_commit_latency_ms{})
record: ceph_osd_commit_latency_ms:avg
- expr: sum(ceph_osd_numpg{})
record: ceph_osd_numpg:sum
- expr: sum(irate(ceph_osd_op_r{}[5m]))
record: ceph_osd_op_r:irate5m
- expr: avg(rate(ceph_osd_op_r_latency_sum{}[5m]) / rate(ceph_osd_op_r_latency_count{}[5m])
>= 0)
record: ceph_osd_op_r_latency:avg5m
- expr: sum(irate(ceph_osd_op_r_out_bytes{}[5m]))
record: ceph_osd_op_r_out_bytes:irate5m
- expr: sum(ceph_osd_op_r_out_bytes{})
record: ceph_osd_op_r_out_bytes:sum
- expr: sum(irate(ceph_osd_op_w{}[5m]))
record: ceph_osd_op_w:irate5m
- expr: sum(irate(ceph_osd_op_w_in_bytes{}[5m]))
record: ceph_osd_op_w_in_bytes:irate5m
- expr: sum(ceph_osd_op_w_in_bytes{})
record: ceph_osd_op_w_in_bytes:sum
- expr: avg(rate(ceph_osd_op_w_latency_sum{}[5m]) / rate(ceph_osd_op_w_latency_count{}[5m])
>= 0)
record: ceph_osd_op_w_latency:avg5m
- expr: sum(ceph_pool_objects{})
record: ceph_pool_objects:sum

0 comments on commit 32cfe61

Please sign in to comment.