Thanks to visit codestin.com
Credit goes to github.com

Skip to content

[release-1.22] Use timeout for conmon cgroup move #5545

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

Merged
openshift-merge-robot merged 1 commit into from
Jan 18, 2022
Merged

[release-1.22] Use timeout for conmon cgroup move #5545

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
20 changes: 15 additions & 5 deletions utils/utils.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ import (
"strconv"
"strings"
"syscall"
"time"

"github.com/containers/podman/v3/pkg/lookup"
"github.com/cri-o/cri-o/internal/dbusmgr"
Expand Down Expand Up @@ -54,9 +55,8 @@ func StatusToExitCode(status int) int {
}

// RunUnderSystemdScope adds the specified pid to a systemd scope
func RunUnderSystemdScope(mgr *dbusmgr.DbusConnManager, pid int, slice, unitName string, properties ...systemdDbus.Property) error {
func RunUnderSystemdScope(mgr *dbusmgr.DbusConnManager, pid int, slice, unitName string, properties ...systemdDbus.Property) (err error) {
ctx := context.Background()
var err error
// sanity check
if mgr == nil {
return errors.New("dbus manager is nil")
Expand All @@ -73,14 +73,24 @@ func RunUnderSystemdScope(mgr *dbusmgr.DbusConnManager, pid int, slice, unitName
ch := make(chan string)
if err := mgr.RetryOnDisconnect(func(c *systemdDbus.Conn) error {
_, err = c.StartTransientUnitContext(ctx, unitName, "replace", properties, ch)
return err
return errors.Wrap(err, "start transient unit")
}); err != nil {
return err
}

// Block until job is started
<-ch
close(ch)
select {
case <-ch:
close(ch)
case <-time.After(time.Minute * 6):
// This case is a work around to catch situations where the dbus library sends the
// request but it unexpectedly disappears. We set the timeout very high to make sure
// we wait as long as possible to catch situations where dbus is overwhelmed.
// We also don't use the native context cancelling behavior of the dbus library,
// because experience has shown that it does not help.
// TODO: Find cause of the request being dropped in the dbus library and fix it.
return errors.Errorf("timed out moving conmon with pid %d to cgroup", pid)
}

return nil
}
Expand Down