github/node-problem-detector
1
0
Fork 0
mirror of https://github.com/kubernetes/node-problem-detector.git synced 2026-02-14 18:09:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add comment to health checker repair function to explain the need of kill instead of restart

Browse Source
This commit is contained in:
Zhen Wang
2024-04-05 16:48:49 +00:00
parent 13b65d06e9
commit aed88103f1
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
pkg/healthchecker/health_checker_linux.go
View File

@@ -56,6 +56,11 @@ func getUptimeFunc(service string) func() (time.Duration, error) {
// getRepairFunc returns the repair function based on the component.
func getRepairFunc(hco *options.HealthCheckerOptions) func() {
// Use `systemctl kill` instead of `systemctl restart` for the repair function.
// We start to rely on the kernel message difference for the two commands to
// indicate if the component restart is due to an administrative plan (restart)
// or a system issue that needs repair (kill).
// See https://github.com/kubernetes/node-problem-detector/issues/847.
switch hco.Component {
case types.DockerComponent:
// Use "docker ps" for docker health check. Not using crictl for docker to remove