Set SchedulerPluginsControl as the default implementation

Signed-off-by: Syulin7 <[email protected]>

cmd/training-operator.v1/main.go

@@ -73,7 +73,8 @@ func main() {
 	flag.StringVar(&leaderElectionID, "leader-election-id", "1ca428e5.training-operator.kubeflow.org", "The ID for leader election.")
 	flag.Var(&enabledSchemes, "enable-scheme", "Enable scheme(s) as --enable-scheme=tfjob --enable-scheme=pytorchjob, case insensitive."+
 		" Now supporting TFJob, PyTorchJob, MXNetJob, XGBoostJob, PaddleJob. By default, all supported schemes will be enabled.")
-	flag.StringVar(&gangSchedulerName, "gang-scheduler-name", "none", "The scheduler to gang-schedule kubeflow jobs, defaults to none")
+	flag.StringVar(&gangSchedulerName, "gang-scheduler-name", "", "The scheduler to gang-schedule kubeflow jobs."+
+		" Now supporting volcano, default-scheduler, scheduler-plugins, koord-scheduler.")
 	flag.StringVar(&namespace, "namespace", os.Getenv(commonutil.EnvKubeflowNamespace), "The namespace to monitor kubeflow jobs. If unset, it monitors all namespaces cluster-wide."+
 		"If set, it only monitors kubeflow jobs in the given namespace.")
 	flag.IntVar(&monitoringPort, "monitoring-port", 9443, "Endpoint port for displaying monitoring metrics. "+
@@ -121,8 +122,8 @@ func main() {
 		cfg := mgr.GetConfig()
 		volcanoClientSet := volcanoclient.NewForConfigOrDie(cfg)
 		gangSchedulingSetupFunc = common.GenVolcanoSetupFunc(volcanoClientSet)
-	} else if strings.EqualFold(gangSchedulerName, string(common.GangSchedulerSchedulerPlugins)) {
-		gangSchedulingSetupFunc = common.GenSchedulerPluginsSetupFunc(mgr.GetClient())
+	} else if gangSchedulerName != "" {
+		gangSchedulingSetupFunc = common.GenSchedulerPluginsSetupFunc(mgr.GetClient(), gangSchedulerName)
 	}
 
 	// TODO: We need a general manager. all rest reconciler addsToManager

go.mod

@@ -89,3 +89,5 @@ require (
 	sigs.k8s.io/json v0.0.0-20220713155537-f223a00ba0e2 // indirect
 	sigs.k8s.io/structured-merge-diff/v4 v4.2.3 // indirect
 )
+
+replace github.com/kubeflow/common v0.4.6 => github.com/Syulin7/common v0.0.0-20230314024246-f6d94fbd12fa

go.sum

@@ -83,6 +83,8 @@ github.com/PuerkitoBio/purell v1.1.1/go.mod h1:c11w/QuzBsJSee3cPx9rAFu61PvFxuPbt
 github.com/PuerkitoBio/urlesc v0.0.0-20160726150825-5bd2802263f2/go.mod h1:uGdkoq3SwY9Y+13GIhn11/XLaGBb4BfwItxLd5jeuXE=
 github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578 h1:d+Bc7a5rLufV/sSk/8dngufqelfh6jnri85riMAaF/M=
 github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578/go.mod h1:uGdkoq3SwY9Y+13GIhn11/XLaGBb4BfwItxLd5jeuXE=
+github.com/Syulin7/common v0.0.0-20230314024246-f6d94fbd12fa h1:XFgorzovrtSmkaIjhmO0ncF4Sg25JV/dpENgk4tV0Bs=
+github.com/Syulin7/common v0.0.0-20230314024246-f6d94fbd12fa/go.mod h1:43MAof/uhpJA2C0urynqatE3oKFQc7m2HLmJty7waqY=
 github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
@@ -327,8 +329,6 @@ github.com/kr/pty v1.1.5/go.mod h1:9r2w37qlBe7rQ6e1fg1S/9xpWHSnaqNdHD3WcMdbPDA=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
-github.com/kubeflow/common v0.4.6 h1:yzJf/HEdS6ginD0GlVkgbOFie0Sp66VdGjXidAGZIlk=
-github.com/kubeflow/common v0.4.6/go.mod h1:43MAof/uhpJA2C0urynqatE3oKFQc7m2HLmJty7waqY=
 github.com/mailru/easyjson v0.0.0-20160728113105-d5b7844b561a/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/mailru/easyjson v0.0.0-20190614124828-94de47d64c63/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/mailru/easyjson v0.0.0-20190626092158-b2ccc519800e/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=

hack/python-sdk/swagger.json

@@ -743,7 +743,7 @@
           "format": "int32"
         },
         "cleanPodPolicy": {
-          "description": "CleanPodPolicy defines the policy to kill pods after the job completes. Default to Running.",
+          "description": "CleanPodPolicy defines the policy to kill pods after the job completes. Default to None.",
           "type": "string"
         },
         "schedulingPolicy": {

manifests/base/crds/kubeflow.org_mpijobs.yaml

@@ -7374,7 +7374,7 @@ spec:
                     type: integer
                   cleanPodPolicy:
                     description: CleanPodPolicy defines the policy to kill pods after
-                      the job completes. Default to Running.
+                      the job completes. Default to None.
                     type: string
                   schedulingPolicy:
                     description: SchedulingPolicy defines the policy related to scheduling,

manifests/base/crds/kubeflow.org_mxjobs.yaml

@@ -7374,7 +7374,7 @@ spec:
                     type: integer
                   cleanPodPolicy:
                     description: CleanPodPolicy defines the policy to kill pods after
-                      the job completes. Default to Running.
+                      the job completes. Default to None.
                     type: string
                   schedulingPolicy:
                     description: SchedulingPolicy defines the policy related to scheduling,

manifests/base/crds/kubeflow.org_paddlejobs.yaml

@@ -7881,7 +7881,7 @@ spec:
                     type: integer
                   cleanPodPolicy:
                     description: CleanPodPolicy defines the policy to kill pods after
-                      the job completes. Default to Running.
+                      the job completes. Default to None.
                     type: string
                   schedulingPolicy:
                     description: SchedulingPolicy defines the policy related to scheduling,

manifests/base/crds/kubeflow.org_pytorchjobs.yaml

@@ -7910,7 +7910,7 @@ spec:
                     type: integer
                   cleanPodPolicy:
                     description: CleanPodPolicy defines the policy to kill pods after
-                      the job completes. Default to Running.
+                      the job completes. Default to None.
                     type: string
                   schedulingPolicy:
                     description: SchedulingPolicy defines the policy related to scheduling,

manifests/base/crds/kubeflow.org_tfjobs.yaml

@@ -63,7 +63,7 @@ spec:
                     type: integer
                   cleanPodPolicy:
                     description: CleanPodPolicy defines the policy to kill pods after
-                      the job completes. Default to Running.
+                      the job completes. Default to None.
                     type: string
                   schedulingPolicy:
                     description: SchedulingPolicy defines the policy related to scheduling,

manifests/base/crds/kubeflow.org_xgboostjobs.yaml

@@ -59,7 +59,7 @@ spec:
                     type: integer
                   cleanPodPolicy:
                     description: CleanPodPolicy defines the policy to kill pods after
-                      the job completes. Default to Running.
+                      the job completes. Default to None.
                     type: string
                   schedulingPolicy:
                     description: SchedulingPolicy defines the policy related to scheduling,

sdk/python/docs/V1RunPolicy.md

@@ -6,7 +6,7 @@ Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
 **active_deadline_seconds** | **int** | Specifies the duration in seconds relative to the startTime that the job may be active before the system tries to terminate it; value must be positive integer. | [optional] 
 **backoff_limit** | **int** | Optional number of retries before marking this job failed. | [optional] 
-**clean_pod_policy** | **str** | CleanPodPolicy defines the policy to kill pods after the job completes. Default to Running. | [optional] 
+**clean_pod_policy** | **str** | CleanPodPolicy defines the policy to kill pods after the job completes. Default to None. | [optional] 
 **scheduling_policy** | [**V1SchedulingPolicy**](V1SchedulingPolicy.md) |  | [optional] 
 **ttl_seconds_after_finished** | **int** | TTLSecondsAfterFinished is the TTL to clean up jobs. It may take extra ReconcilePeriod seconds for the cleanup, since reconcile gets called periodically. Default to infinite. | [optional] 
 

sdk/python/kubeflow/training/models/v1_run_policy.py

@@ -122,7 +122,7 @@ def backoff_limit(self, backoff_limit):
     def clean_pod_policy(self):
         """Gets the clean_pod_policy of this V1RunPolicy.  # noqa: E501
 
-        CleanPodPolicy defines the policy to kill pods after the job completes. Default to Running.  # noqa: E501
+        CleanPodPolicy defines the policy to kill pods after the job completes. Default to None.  # noqa: E501
 
         :return: The clean_pod_policy of this V1RunPolicy.  # noqa: E501
         :rtype: str
@@ -133,7 +133,7 @@ def clean_pod_policy(self):
     def clean_pod_policy(self, clean_pod_policy):
         """Sets the clean_pod_policy of this V1RunPolicy.
 
-        CleanPodPolicy defines the policy to kill pods after the job completes. Default to Running.  # noqa: E501
+        CleanPodPolicy defines the policy to kill pods after the job completes. Default to None.  # noqa: E501
 
         :param clean_pod_policy: The clean_pod_policy of this V1RunPolicy.  # noqa: E501
         :type: str