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

ROX-27130: rename operator pod prefix #293

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

ROX-27130: rename operator pod prefix #293

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
4 changes: 2 additions & 2 deletions resources/prometheus/prometheus-rules.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ spec:
rules:
- alert: RHACSFleetshardOperatorContainerDown
expr: |
avg_over_time(kube_pod_container_status_ready{pod=~"rhacs-operator-controller-manager-.*"}[10m]) < 0.5
avg_over_time(kube_pod_container_status_ready{pod=~"rhacs-operator-.*"}[10m]) < 0.5
for: 20m
labels:
severity: critical
Expand All @@ -94,7 +94,7 @@ spec:
sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-managed-service-runbooks/blob/master/sops/dp-011-rhacs-operator-unavailable.md"
- alert: RHACSFleetshardOperatorContainerFrequentlyRestarting
expr: |
increase(kube_pod_container_status_restarts_total{pod=~"rhacs-operator-controller-manager-.*"}[30m]) > 3
increase(kube_pod_container_status_restarts_total{pod=~"rhacs-operator-.*"}[30m]) > 3
labels:
severity: critical
annotations:
Expand Down
16 changes: 8 additions & 8 deletions resources/prometheus/unit_tests/RHACSFleetshardOperatorContainerDown.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,9 @@ evaluation_interval: 1m
tests:
- interval: 1m
input_series:
- series: kube_pod_container_status_ready{namespace="rhacs", pod="rhacs-operator-controller-manager-1234", container="manager"}
- series: kube_pod_container_status_ready{namespace="rhacs", pod="rhacs-operator-1234", container="manager"}
values: "1+0x10 0+0x50"
- series: kube_pod_container_status_ready{namespace="rhacs", pod="rhacs-operator-controller-manager-1234", container="kube-rbac-proxy"}
- series: kube_pod_container_status_ready{namespace="rhacs", pod="rhacs-operator-1234", container="kube-rbac-proxy"}
values: "1+0x10 0+0x50"
alert_rule_test:
- eval_time: 15m
Expand All @@ -21,19 +21,19 @@ tests:
alertname: RHACSFleetshardOperatorContainerDown
container: manager
namespace: rhacs
pod: rhacs-operator-controller-manager-1234
pod: rhacs-operator-1234
severity: critical
exp_annotations:
summary: "Fleetshard operator container `rhacs-operator-controller-manager-1234/manager` in namespace `rhacs` is down or in a CrashLoopBackOff status."
description: "Fleetshard operator container `rhacs-operator-controller-manager-1234/manager` in namespace `rhacs` has been down or in a CrashLoopBackOff status for at least 10 minutes."
summary: "Fleetshard operator container `rhacs-operator-1234/manager` in namespace `rhacs` is down or in a CrashLoopBackOff status."
description: "Fleetshard operator container `rhacs-operator-1234/manager` in namespace `rhacs` has been down or in a CrashLoopBackOff status for at least 10 minutes."
sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-managed-service-runbooks/blob/master/sops/dp-011-rhacs-operator-unavailable.md"
- exp_labels:
alertname: RHACSFleetshardOperatorContainerDown
container: kube-rbac-proxy
namespace: rhacs
pod: rhacs-operator-controller-manager-1234
pod: rhacs-operator-1234
severity: critical
exp_annotations:
summary: "Fleetshard operator container `rhacs-operator-controller-manager-1234/kube-rbac-proxy` in namespace `rhacs` is down or in a CrashLoopBackOff status."
description: "Fleetshard operator container `rhacs-operator-controller-manager-1234/kube-rbac-proxy` in namespace `rhacs` has been down or in a CrashLoopBackOff status for at least 10 minutes."
summary: "Fleetshard operator container `rhacs-operator-1234/kube-rbac-proxy` in namespace `rhacs` is down or in a CrashLoopBackOff status."
description: "Fleetshard operator container `rhacs-operator-1234/kube-rbac-proxy` in namespace `rhacs` has been down or in a CrashLoopBackOff status for at least 10 minutes."
sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-managed-service-runbooks/blob/master/sops/dp-011-rhacs-operator-unavailable.md"
16 changes: 8 additions & 8 deletions resources/prometheus/unit_tests/RHACSFleetshardOperatorContainerFrequentlyRestarting.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,9 @@ evaluation_interval: 1m
tests:
- interval: 1m
input_series:
- series: kube_pod_container_status_restarts_total{namespace="rhacs", pod="rhacs-operator-controller-manager-1234", container="manager"}
- series: kube_pod_container_status_restarts_total{namespace="rhacs", pod="rhacs-operator-1234", container="manager"}
values: "0+0x30 1+1x10 4+1x20"
- series: kube_pod_container_status_restarts_total{namespace="rhacs", pod="rhacs-operator-controller-manager-1234", container="kube-rbac-proxy"}
- series: kube_pod_container_status_restarts_total{namespace="rhacs", pod="rhacs-operator-1234", container="kube-rbac-proxy"}
values: "0+0x30 1+1x10 4+1x20"
alert_rule_test:
- eval_time: 30m
Expand All @@ -21,19 +21,19 @@ tests:
alertname: RHACSFleetshardOperatorContainerFrequentlyRestarting
container: manager
namespace: rhacs
pod: rhacs-operator-controller-manager-1234
pod: rhacs-operator-1234
severity: critical
exp_annotations:
summary: "Fleetshard operator container `rhacs-operator-controller-manager-1234/manager` in namespace `rhacs` restarted more than 3 times."
description: "Fleetshard operator container `rhacs-operator-controller-manager-1234/manager` in namespace `rhacs` has restarted more than 3 times during the last 30 minutes."
summary: "Fleetshard operator container `rhacs-operator-1234/manager` in namespace `rhacs` restarted more than 3 times."
description: "Fleetshard operator container `rhacs-operator-1234/manager` in namespace `rhacs` has restarted more than 3 times during the last 30 minutes."
sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-managed-service-runbooks/blob/master/sops/dp-011-rhacs-operator-unavailable.md"
- exp_labels:
alertname: RHACSFleetshardOperatorContainerFrequentlyRestarting
container: kube-rbac-proxy
namespace: rhacs
pod: rhacs-operator-controller-manager-1234
pod: rhacs-operator-1234
severity: critical
exp_annotations:
summary: "Fleetshard operator container `rhacs-operator-controller-manager-1234/kube-rbac-proxy` in namespace `rhacs` restarted more than 3 times."
description: "Fleetshard operator container `rhacs-operator-controller-manager-1234/kube-rbac-proxy` in namespace `rhacs` has restarted more than 3 times during the last 30 minutes."
summary: "Fleetshard operator container `rhacs-operator-1234/kube-rbac-proxy` in namespace `rhacs` restarted more than 3 times."
description: "Fleetshard operator container `rhacs-operator-1234/kube-rbac-proxy` in namespace `rhacs` has restarted more than 3 times during the last 30 minutes."
sop_url: "https://gitlab.cee.redhat.com/stackrox/acs-managed-service-runbooks/blob/master/sops/dp-011-rhacs-operator-unavailable.md"
Loading