This repository has been archived by the owner on Mar 9, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 348
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
reload cni network config if has fs change events
With go RWMutex design, no goroutine should expect to be able to acquire a read lock until the read lock has been released, if one goroutine call lock. The original design is to reload cni network config on every single Status CRI gRPC call. If one RunPodSandbox request holds read lock to allocate IP for too long, all other RunPodSandbox/StopPodSandbox requests will wait for the RunPodSandbox request to release read lock. And the Status CRI call will fail and kubelet becomes NOTReady. Reload cni network config at every single Status CRI call is not necessary and also brings NOTReady situation. To lower the possibility of NOTReady, CRI will reload cni network config if there is any valid fs change events from the cni network config dir. Signed-off-by: Wei Fu <fuweid89@gmail.com>
- Loading branch information
Showing
5 changed files
with
128 additions
and
17 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,100 @@ | ||
package server | ||
|
||
import ( | ||
"sync" | ||
|
||
cni "github.com/containerd/go-cni" | ||
"github.com/fsnotify/fsnotify" | ||
"github.com/pkg/errors" | ||
"github.com/sirupsen/logrus" | ||
) | ||
|
||
// cniNetConfSyncer is used to reload cni network conf triggered by fs change | ||
// events. | ||
type cniNetConfSyncer struct { | ||
// only used for lastSyncStatus | ||
sync.RWMutex | ||
lastSyncStatus error | ||
|
||
watcher *fsnotify.Watcher | ||
confDir string | ||
netPlugin cni.CNI | ||
loadOpts []cni.CNIOpt | ||
} | ||
|
||
// newCNINetConfSyncer creates cni network conf syncer. | ||
func newCNINetConfSyncer(confDir string, netPlugin cni.CNI, loadOpts []cni.CNIOpt) (*cniNetConfSyncer, error) { | ||
watcher, err := fsnotify.NewWatcher() | ||
if err != nil { | ||
return nil, errors.Wrap(err, "failed to create fsnotify watcher") | ||
} | ||
|
||
if err := watcher.Add(confDir); err != nil { | ||
return nil, errors.Wrapf(err, "failed to watch cni conf dir %s", confDir) | ||
} | ||
|
||
syncer := &cniNetConfSyncer{ | ||
watcher: watcher, | ||
confDir: confDir, | ||
netPlugin: netPlugin, | ||
loadOpts: loadOpts, | ||
} | ||
|
||
if err := syncer.netPlugin.Load(syncer.loadOpts...); err != nil { | ||
logrus.WithError(err).Error("failed to load cni during init, please check CRI plugin status before setting up network for pods") | ||
syncer.updateLastStatus(err) | ||
} | ||
return syncer, nil | ||
} | ||
|
||
// syncLoop monitors any fs change events from cni conf dir and tries to reload | ||
// cni configuration. | ||
func (syncer *cniNetConfSyncer) syncLoop() error { | ||
for { | ||
select { | ||
case event := <-syncer.watcher.Events: | ||
// Only reload config when receiving write/rename/remove | ||
// events | ||
// | ||
// FIXME(fuweid): Might only reload target cni config | ||
// files to prevent no-ops. | ||
if event.Op&(fsnotify.Chmod|fsnotify.Create) > 0 { | ||
logrus.Debugf("ignore event from cni conf dir: %s", event) | ||
continue | ||
} | ||
logrus.Debugf("receiving change event from cni conf dir: %s", event) | ||
|
||
lerr := syncer.netPlugin.Load(syncer.loadOpts...) | ||
if lerr != nil { | ||
logrus.WithError(lerr). | ||
Errorf("failed to reload cni configuration after receiving fs change event(%s)", event) | ||
} | ||
syncer.updateLastStatus(lerr) | ||
|
||
case err := <-syncer.watcher.Errors: | ||
if err != nil { | ||
logrus.WithError(err).Error("failed to continue sync cni conf change") | ||
return err | ||
} | ||
} | ||
} | ||
} | ||
|
||
// lastStatus retrieves last sync status. | ||
func (syncer *cniNetConfSyncer) lastStatus() error { | ||
syncer.RLock() | ||
defer syncer.RUnlock() | ||
return syncer.lastSyncStatus | ||
} | ||
|
||
// updateLastStatus will be called after every single cni load. | ||
func (syncer *cniNetConfSyncer) updateLastStatus(err error) { | ||
syncer.Lock() | ||
defer syncer.Unlock() | ||
syncer.lastSyncStatus = err | ||
} | ||
|
||
// stop stops watcher in the syncLoop. | ||
func (syncer *cniNetConfSyncer) stop() error { | ||
return syncer.watcher.Close() | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters