starlingx/integ
Code Issues Proposed changes

Merge "Revert "Remove recover operations to "restart-on-reboot" pods""

Browse Source
This commit is contained in:
Zuul 2021-05-19 18:58:19 +00:00 committed by Gerrit Code Review
commit c9aaf25330
1 changed files with 33 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
kubernetes/k8s-pod-recovery/centos/files/k8s-pod-recovery
View File

@ -153,6 +153,36 @@ function _node_affinity_pods {
}
function _labeled_pods {
# $1: actions <recover|verify>
if [ "$1" == 'recover' ]; then
POLLING_INTERVAL=5
STABILITY_COUNT=6
_wait_for_pod_stabilization "--selector=restart-on-reboot=true --field-selector=spec.nodeName=${HOST}" $POLLING_INTERVAL $STABILITY_COUNT
# Delete pods with the restart-on-reboot=true label
PODS=$(kubectl get pods --all-namespaces --no-headers --field-selector=spec.nodeName=${HOST} --selector=restart-on-reboot=true 2>/dev/null | awk '{print $1"/"$2}')
for pod in $PODS; do
LOG "restart-on-reboot labeled pods: Recovering: ${pod//// }"
kubectl delete pods -n ${pod//// } --wait=false
done
elif [ "$1" == 'verify' ]; then
PODS=$(kubectl get pods --all-namespaces --no-headers --field-selector=spec.nodeName=${HOST} --selector=restart-on-reboot=true 2>/dev/null | awk '{print $1"/"$2}')
for pod in $PODS; do
LOG "restart-on-reboot labeled pods: Verifying: ${pod//// }"
STATUS=$(kubectl get pod --no-headers -n ${pod//// } 2>/dev/null | awk '{print $3}')
if [[ "${STATUS}" != "Running" ]]; then
ERROR "$pod: not recovered: $STATUS"
else
LOG "$pod: recovered"
fi
done
else
ERROR "Unknown action: $1"
fi
}
function _force_reset_pods {
# $1: actions <recover|verify>
@ -196,6 +226,9 @@ function _force_reset_pods {
function _examine_pods {
# $1: actions <recover|verify>
# Manage labeled pods first
_labeled_pods $1
# Wait for pods transitions to stop
_wait_for_pod_stabilization "" $SLEEP_DELAY_SEC 6