github/node-problem-detector
1
0
Fork 0
mirror of https://github.com/kubernetes/node-problem-detector.git synced 2026-03-02 17:50:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #444 from abansal4032/health-check-cooldown-fix

Browse Source 
Fix for cooldown time in health checker plugin
This commit is contained in:
Kubernetes Prow Robot
2020-07-17 18:32:54 -07:00
committed by GitHub
parent 27f1e774ef f56d0a929d
commit ca34880303
1 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
pkg/healthchecker/health_checker.go
View File

@@ -59,7 +59,13 @@ func NewHealthChecker(hco *options.HealthCheckerOptions) (types.HealthChecker, e
// getUptimeFunc returns the time for which the given service has been running.
func getUptimeFunc(service string) func() (time.Duration, error) {
return func() (time.Duration, error) {
out, err := execCommand(types.CmdTimeout, "systemctl", "show", service, "--property=ActiveEnterTimestamp")
// Using InactiveExitTimestamp to capture the exact time when systemd tried starting the service. The service will
// transition from inactive -> activating and the timestamp is captured.
// Source : https://www.freedesktop.org/wiki/Software/systemd/dbus/
// Using ActiveEnterTimestamp resulted in race condition where the service was repeatedly killed by plugin when
// RestartSec of systemd and invoke interval of plugin got in sync. The service was repeatedly killed in
// activating state and hence ActiveEnterTimestamp was never updated.
out, err := execCommand(types.CmdTimeout, "systemctl", "show", service, "--property=InactiveExitTimestamp")
if err != nil {
return time.Duration(0), err
}