Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[release-4.18] DFBUGS-1188: Fix 'ceph_disk_occupation' query expressions #2933

Open
wants to merge 1 commit into
base: release-4.18
Choose a base branch
from
Open

[release-4.18] DFBUGS-1188: Fix 'ceph_disk_occupation' query expressions #2933

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions controllers/storagecluster/prometheus/localcephrules.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,10 @@ spec:
- name: ceph.rules
rules:
- expr: |
kube_node_status_condition{condition="Ready",job="kube-state-metrics",status="true"} * on (node) group_right() max by (node, namespace) (label_replace(ceph_disk_occupation{job="rook-ceph-mgr"},"node","$1","exported_instance","(.*)"))
kube_node_status_condition{condition="Ready",job="kube-state-metrics",status="true"} * on (node) group_right() max by (node, namespace) (label_replace(ceph_disk_occupation{job="rook-ceph-mgr"},"node","$1","instance","(.*)"))
record: cluster:ceph_node_down:join_kube
- expr: |
avg by (namespace) (topk by (ceph_daemon, namespace) (1, label_replace(label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "instance", "$1", "exported_instance", "(.*)"), "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_right(ceph_daemon, namespace) topk by (instance, device, namespace) (1,(irate(node_disk_read_time_seconds_total[1m]) + irate(node_disk_write_time_seconds_total[1m]) / (clamp_min(irate(node_disk_reads_completed_total[1m]), 1) + irate(node_disk_writes_completed_total[1m])))))
avg by (namespace) (topk by (ceph_daemon, namespace) (1, label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_right(ceph_daemon, namespace) topk by (instance, device, namespace) (1,(irate(node_disk_read_time_seconds_total[1m]) + irate(node_disk_write_time_seconds_total[1m]) / (clamp_min(irate(node_disk_reads_completed_total[1m]), 1) + irate(node_disk_writes_completed_total[1m])))))
record: cluster:ceph_disk_latency:join_ceph_node_disk_irate1m
- name: telemeter.rules
rules:
Expand Down Expand Up @@ -171,7 +171,7 @@ spec:
storage_type: ceph
runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/openshift-container-storage-operator/CephOSDDiskNotResponding.md
expr: |
label_replace((ceph_osd_in == 1 and ceph_osd_up == 0),"disk","$1","ceph_daemon","osd.(.*)") + on(ceph_daemon, namespace, managedBy) group_left(host, device) label_replace(ceph_disk_occupation{job=~"rook-ceph-mgr|rook-ceph-mgr-external"},"host","$1","exported_instance","(.*)")
label_replace((ceph_osd_in == 1 and ceph_osd_up == 0),"disk","$1","ceph_daemon","osd.(.*)") + on(ceph_daemon, namespace, managedBy) group_left(host, device) label_replace(ceph_disk_occupation{job=~"rook-ceph-mgr|rook-ceph-mgr-external"},"host","$1","instance","(.*)")
for: 15m
labels:
severity: critical
Expand All @@ -183,7 +183,7 @@ spec:
storage_type: ceph
runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/openshift-container-storage-operator/CephOSDDiskUnavailable.md
expr: |
label_replace((ceph_osd_in == 0 and ceph_osd_up == 0),"disk","$1","ceph_daemon","osd.(.*)") + on(ceph_daemon, namespace, managedBy) group_left(host, device) label_replace(ceph_disk_occupation{job=~"rook-ceph-mgr|rook-ceph-mgr-external"},"host","$1","exported_instance","(.*)")
label_replace((ceph_osd_in == 0 and ceph_osd_up == 0),"disk","$1","ceph_daemon","osd.(.*)") + on(ceph_daemon, namespace, managedBy) group_left(host, device) label_replace(ceph_disk_occupation{job=~"rook-ceph-mgr|rook-ceph-mgr-external"},"host","$1","instance","(.*)")
for: 1m
labels:
severity: critical
Expand Down
24 changes: 6 additions & 18 deletions metrics/deploy/prometheus-ocs-rules-external.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,17 +10,11 @@ spec:
groups:
- name: ocs_performance.rules
rules:
- expr: "sum by (namespace, managedBy) (\n topk by (ceph_daemon) (1, label_replace(label_replace(ceph_disk_occupation{job=\"rook-ceph-mgr\"},
\"instance\", \"$1\", \"exported_instance\", \"(.*)\"), \"device\", \"$1\",
\"device\", \"/dev/(.*)\")) \n * on(instance, device) group_left topk by
(instance,device) \n (1,\n (\n rate(node_disk_read_time_seconds_total[1m])
/ (clamp_min(rate(node_disk_reads_completed_total[1m]), 1))\n )\n )\n)\n"
- expr: |
sum by (namespace, managedBy) (topk by (ceph_daemon) (1, label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_left topk by (instance,device) (1, (rate(node_disk_read_time_seconds_total[1m]) / (clamp_min(rate(node_disk_reads_completed_total[1m]), 1)))))
record: cluster:ceph_disk_latency_read:join_ceph_node_disk_rate1m
- expr: "sum by (namespace, managedBy) (\n topk by (ceph_daemon) (1, label_replace(label_replace(ceph_disk_occupation{job=\"rook-ceph-mgr\"},
\"instance\", \"$1\", \"exported_instance\", \"(.*)\"), \"device\", \"$1\",
\"device\", \"/dev/(.*)\")) \n * on(instance, device) group_left topk by
(instance,device) \n (1,\n (\n rate(node_disk_write_time_seconds_total[1m])
/ (clamp_min(rate(node_disk_writes_completed_total[1m]), 1))\n )\n )\n)\n"
- expr: |
sum by (namespace, managedBy) (topk by (ceph_daemon) (1, label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_left topk by (instance,device) (1, (rate(node_disk_write_time_seconds_total[1m]) / (clamp_min(rate(node_disk_writes_completed_total[1m]), 1)))))
record: cluster:ceph_disk_latency_write:join_ceph_node_disk_rate1m
- name: ODF_standardized_metrics.rules
rules:
Expand Down Expand Up @@ -54,14 +48,8 @@ spec:
system_type: OCS
system_vendor: Red Hat
record: odf_system_throughput_total_bytes
- expr: "sum by (namespace, managedBy, job, service)\n(\n topk by (ceph_daemon)
(1, label_replace(label_replace(ceph_disk_occupation{job=\"rook-ceph-mgr\"},
\"instance\", \"$1\", \"exported_instance\", \"(.*)\"), \"device\", \"$1\",
\"device\", \"/dev/(.*)\")) \n * on(instance, device) group_left() topk by
(instance,device) \n (1,\n (\n ( \n rate(node_disk_read_time_seconds_total[1m])
/ (clamp_min(rate(node_disk_reads_completed_total[1m]), 1))\n ) +\n (\n
\ rate(node_disk_write_time_seconds_total[1m]) / (clamp_min(rate(node_disk_writes_completed_total[1m]),
1))\n )\n )\n )\n)\n"
- expr: |
sum by (namespace, managedBy, job, service) (topk by (ceph_daemon) (1, label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_left() topk by (instance,device) (1, ((rate(node_disk_read_time_seconds_total[1m]) / (clamp_min(rate(node_disk_reads_completed_total[1m]), 1))) + (rate(node_disk_write_time_seconds_total[1m]) / (clamp_min(rate(node_disk_writes_completed_total[1m]), 1))))))
labels:
system_type: OCS
system_vendor: Red Hat
Expand Down
24 changes: 6 additions & 18 deletions metrics/deploy/prometheus-ocs-rules.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,17 +10,11 @@ spec:
groups:
- name: ocs_performance.rules
rules:
- expr: "sum by (namespace, managedBy) (\n topk by (ceph_daemon) (1, label_replace(label_replace(ceph_disk_occupation{job=\"rook-ceph-mgr\"},
\"instance\", \"$1\", \"exported_instance\", \"(.*)\"), \"device\", \"$1\",
\"device\", \"/dev/(.*)\")) \n * on(instance, device) group_left topk by
(instance,device) \n (1,\n (\n rate(node_disk_read_time_seconds_total[1m])
/ (clamp_min(rate(node_disk_reads_completed_total[1m]), 1))\n )\n )\n)\n"
- expr: |
sum by (namespace, managedBy) (topk by (ceph_daemon) (1, label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_left topk by (instance,device) (1, (rate(node_disk_read_time_seconds_total[1m]) / (clamp_min(rate(node_disk_reads_completed_total[1m]), 1)))))
record: cluster:ceph_disk_latency_read:join_ceph_node_disk_rate1m
- expr: "sum by (namespace, managedBy) (\n topk by (ceph_daemon) (1, label_replace(label_replace(ceph_disk_occupation{job=\"rook-ceph-mgr\"},
\"instance\", \"$1\", \"exported_instance\", \"(.*)\"), \"device\", \"$1\",
\"device\", \"/dev/(.*)\")) \n * on(instance, device) group_left topk by
(instance,device) \n (1,\n (\n rate(node_disk_write_time_seconds_total[1m])
/ (clamp_min(rate(node_disk_writes_completed_total[1m]), 1))\n )\n )\n)\n"
- expr: |
sum by (namespace, managedBy) (topk by (ceph_daemon) (1, label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_left topk by (instance,device) (1, (rate(node_disk_write_time_seconds_total[1m]) / (clamp_min(rate(node_disk_writes_completed_total[1m]), 1)))))
record: cluster:ceph_disk_latency_write:join_ceph_node_disk_rate1m
- name: ODF_standardized_metrics.rules
rules:
Expand Down Expand Up @@ -54,14 +48,8 @@ spec:
system_type: OCS
system_vendor: Red Hat
record: odf_system_throughput_total_bytes
- expr: "sum by (namespace, managedBy, job, service)\n(\n topk by (ceph_daemon)
(1, label_replace(label_replace(ceph_disk_occupation{job=\"rook-ceph-mgr\"},
\"instance\", \"$1\", \"exported_instance\", \"(.*)\"), \"device\", \"$1\",
\"device\", \"/dev/(.*)\")) \n * on(instance, device) group_left() topk by
(instance,device) \n (1,\n (\n ( \n rate(node_disk_read_time_seconds_total[1m])
/ (clamp_min(rate(node_disk_reads_completed_total[1m]), 1))\n ) +\n (\n
\ rate(node_disk_write_time_seconds_total[1m]) / (clamp_min(rate(node_disk_writes_completed_total[1m]),
1))\n )\n )\n )\n)\n"
- expr: |
sum by (namespace, managedBy, job, service) (topk by (ceph_daemon) (1, label_replace(ceph_disk_occupation{job="rook-ceph-mgr"}, "device", "$1", "device", "/dev/(.*)")) * on(instance, device) group_left() topk by (instance,device) (1, ((rate(node_disk_read_time_seconds_total[1m]) / (clamp_min(rate(node_disk_reads_completed_total[1m]), 1))) + (rate(node_disk_write_time_seconds_total[1m]) / (clamp_min(rate(node_disk_writes_completed_total[1m]), 1))))))
labels:
system_type: OCS
system_vendor: Red Hat
Expand Down
Loading