This is an automated email from the ASF dual-hosted git repository.
Tejaskriya pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/ozone-helm-charts.git
The following commit(s) were added to refs/heads/main by this push:
new add054f HDDS-15874. Adding readinessProbe for helm HA deployments
(#43)
add054f is described below
commit add054fa4d93e2e379b606d334966031394e6948
Author: Mark Tsai <[email protected]>
AuthorDate: Tue Sep 15 16:52:08 2026 +0800
HDDS-15874. Adding readinessProbe for helm HA deployments (#43)
---
charts/ozone/templates/om/om-statefulset.yaml | 12 ++++++++++++
charts/ozone/templates/scm/scm-statefulset.yaml | 11 +++++++++++
charts/ozone/values.yaml | 12 ++++++++++++
3 files changed, 35 insertions(+)
diff --git a/charts/ozone/templates/om/om-statefulset.yaml
b/charts/ozone/templates/om/om-statefulset.yaml
index 3964f77..9c3c74d 100644
--- a/charts/ozone/templates/om/om-statefulset.yaml
+++ b/charts/ozone/templates/om/om-statefulset.yaml
@@ -33,6 +33,7 @@ metadata:
app.kubernetes.io/component: om
spec:
replicas: {{ .Values.om.replicas }}
+ podManagementPolicy: Parallel
serviceName: {{ .Release.Name }}-om-headless
selector:
matchLabels:
@@ -118,6 +119,17 @@ spec:
ozone admin om transfer -id {{ .Values.clusterId }} -r
|| true
sleep 10
fi
+ readinessProbe:
+ exec:
+ command:
+ - sh
+ - -c
+ - |
+ ozone admin om roles -id {{ .Values.clusterId }} 2>/dev/null
| grep $(hostname) | grep -qE 'LEADER|FOLLOWER' && exit 0 || exit 1
+ initialDelaySeconds: {{
.Values.om.readinessProbe.initialDelaySeconds }}
+ periodSeconds: {{ .Values.om.readinessProbe.periodSeconds }}
+ timeoutSeconds: {{ .Values.om.readinessProbe.timeoutSeconds }}
+ failureThreshold: {{ .Values.om.readinessProbe.failureThreshold }}
{{- end }}
livenessProbe:
httpGet:
diff --git a/charts/ozone/templates/scm/scm-statefulset.yaml
b/charts/ozone/templates/scm/scm-statefulset.yaml
index a0f4c11..ac1bc81 100644
--- a/charts/ozone/templates/scm/scm-statefulset.yaml
+++ b/charts/ozone/templates/scm/scm-statefulset.yaml
@@ -137,6 +137,17 @@ spec:
ozone admin scm transfer -id {{ .Values.clusterId }} -r
|| true
sleep 10
fi
+ readinessProbe:
+ exec:
+ command:
+ - sh
+ - -c
+ - |
+ ozone admin scm roles 2>/dev/null | grep $(hostname -f) |
grep -qE 'LEADER|FOLLOWER' && exit 0 || exit 1
+ initialDelaySeconds: {{
.Values.scm.readinessProbe.initialDelaySeconds }}
+ periodSeconds: {{ .Values.scm.readinessProbe.periodSeconds }}
+ timeoutSeconds: {{ .Values.scm.readinessProbe.timeoutSeconds }}
+ failureThreshold: {{ .Values.scm.readinessProbe.failureThreshold }}
{{- end }}
livenessProbe:
httpGet:
diff --git a/charts/ozone/values.yaml b/charts/ozone/values.yaml
index d89032a..bcef322 100644
--- a/charts/ozone/values.yaml
+++ b/charts/ozone/values.yaml
@@ -146,6 +146,12 @@ om:
tolerations: []
# Ozone Manager security context (overwrites common security context)
securityContext: {}
+ # Readiness probe for Ozone Manager HA (used when om.replicas > 1)
+ readinessProbe:
+ initialDelaySeconds: 10
+ periodSeconds: 10
+ timeoutSeconds: 20
+ failureThreshold: 3
# Ozone Manager service configuration
service:
type: ClusterIP
@@ -202,6 +208,12 @@ scm:
tolerations: []
# Storage Container Manager security context (overwrites common security
context)
securityContext: {}
+ # Readiness probe for Storage Container Manager HA (used when scm.replicas >
1)
+ readinessProbe:
+ initialDelaySeconds: 10
+ periodSeconds: 10
+ timeoutSeconds: 20
+ failureThreshold: 3
# Storage Container Manager service configuration
service:
type: ClusterIP
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
