alexlebens/external-snapshotter
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: Implement distributed snapshotting

Browse Source
This commit is contained in:
Ubuntu
2021-12-24 19:57:49 +00:00
parent 138d310e5d
commit 21fc337b87
16 changed files with 870 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
cmd/snapshot-controller/main.go
View File

@@ -27,6 +27,7 @@ import (
"sync"
"time"
v1 "k8s.io/client-go/informers/core/v1"
"k8s.io/client-go/kubernetes"
"k8s.io/client-go/kubernetes/scheme"
"k8s.io/client-go/rest"
@@ -64,10 +65,11 @@ var (
kubeAPIQPS = flag.Float64("kube-api-qps", 5, "QPS to use while communicating with the kubernetes apiserver. Defaults to 5.0.")
kubeAPIBurst = flag.Int("kube-api-burst", 10, "Burst to use while communicating with the kubernetes apiserver. Defaults to 10.")
httpEndpoint = flag.String("http-endpoint", "", "The TCP network address where the HTTP server for diagnostics, including metrics, will listen (example: :8080). The default is empty string, which means the server is disabled.")
metricsPath = flag.String("metrics-path", "/metrics", "The HTTP path where prometheus metrics will be exposed. Default is `/metrics`.")
retryIntervalStart = flag.Duration("retry-interval-start", time.Second, "Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default is 1 second.")
retryIntervalMax = flag.Duration("retry-interval-max", 5*time.Minute, "Maximum retry interval of failed volume snapshot creation or deletion. Default is 5 minutes.")
httpEndpoint = flag.String("http-endpoint", "", "The TCP network address where the HTTP server for diagnostics, including metrics, will listen (example: :8080). The default is empty string, which means the server is disabled.")
metricsPath = flag.String("metrics-path", "/metrics", "The HTTP path where prometheus metrics will be exposed. Default is `/metrics`.")
retryIntervalStart = flag.Duration("retry-interval-start", time.Second, "Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default is 1 second.")
retryIntervalMax = flag.Duration("retry-interval-max", 5*time.Minute, "Maximum retry interval of failed volume snapshot creation or deletion. Default is 5 minutes.")
enableDistributedSnapshotting = flag.Bool("enable-distributed-snapshotting", false, "Enables each node to handle snapshotting for the local volumes created on that node")
)
var (
@@ -147,6 +149,11 @@ func main() {
factory := informers.NewSharedInformerFactory(snapClient, *resyncPeriod)
coreFactory := coreinformers.NewSharedInformerFactory(kubeClient, *resyncPeriod)
var nodeInformer v1.NodeInformer
if *enableDistributedSnapshotting {
nodeInformer = coreFactory.Core().V1().Nodes()
}
// Create and register metrics manager
metricsManager := metrics.NewMetricsManager()
@@ -174,10 +181,12 @@ func main() {
factory.Snapshot().V1().VolumeSnapshotContents(),
factory.Snapshot().V1().VolumeSnapshotClasses(),
coreFactory.Core().V1().PersistentVolumeClaims(),
nodeInformer,
metricsManager,
*resyncPeriod,
workqueue.NewItemExponentialFailureRateLimiter(*retryIntervalStart, *retryIntervalMax),
workqueue.NewItemExponentialFailureRateLimiter(*retryIntervalStart, *retryIntervalMax),
*enableDistributedSnapshotting,
)
if err := ensureCustomResourceDefinitionsExist(snapClient); err != nil {