docs: update docs and server ports

.gitlab-ci.yml

 variables:
   REGISTRY: registry.sensetime.com/cloudnative4ai
-  VERSION: v1.0.0
+  VERSION: v1.0.1
   PROJECT: di-orchestrator
   # dind config
   DOCKER_HOST: tcp://localhost:2376

Makefile

 
 # di-operator version
-VERSION ?= v1.0.0
+VERSION ?= v1.0.1
 MASTER_VERSION := $(VERSION)
 
 COMMIT_SHORT_SHA=$(shell git log -n 1 | head -n 1 | sed -e 's/^commit //' | head -c 8)

README.md

@@ -29,14 +29,34 @@ di-server-7b86ff8df4-jfgmp         1/1     Running   0          59s
 
 ```bash
 # submit DIJob
-$ kubectl create -f config/samples/dijob-cartpole.yaml
+$ kubectl create -f config/samples/dijob-gobigger.yaml
 
 # get pod and you will see coordinator is created by di-operator
 # a few seconds later, you will see collectors and learners created by di-server
 $ kubectl get pod
+NAME                READY   STATUS    RESTARTS   AGE
+gobigger-test-0-0   1/1     Running   0          4m17s
+gobigger-test-0-1   1/1     Running   0          4m17s
 
 # get logs of coordinator
-$ kubectl logs cartpole-dqn-coordinator
+$ kubectl logs -n xlab gobigger-test-0-0
+Bind subprocesses on these addresses: ['tcp://10.148.3.4:22270',
+'tcp://10.148.3.4:22271']
+[Warning] no enough data: 128/0
+...
+[Warning] no enough data: 128/120
+Current Training: Train Iter(0) Loss(102.256)
+Current Training: Train Iter(0) Loss(103.133)
+Current Training: Train Iter(20)        Loss(28.795)
+Current Training: Train Iter(20)        Loss(32.837)
+...
+Current Training: Train Iter(360)       Loss(12.850)
+Current Training: Train Iter(340)       Loss(11.812)
+Current Training: Train Iter(380)       Loss(12.892)
+Current Training: Train Iter(360)       Loss(13.621)
+Current Training: Train Iter(400)       Loss(15.183)
+Current Training: Train Iter(380)       Loss(14.187)
+Current Evaluation: Train Iter(404)     Eval Reward(-1788.326)
 ```
 
 ## User Guide

cmd/server/server.go

@@ -46,7 +46,7 @@ func NewCreateOptions(genFlags cmdcommon.GenericFlags) *CreateOptions {
 		GenericFlags:      genFlags,
 		ServerBindAddress: ":8081",
 		ProbeAddress:      ":8080",
-		MetricAddress:     ":8089",
+		MetricAddress:     ":8443",
 	}
 }
 

config/di-manager.yaml

@@ -4260,9 +4260,9 @@ metadata:
   namespace: di-system
 spec:
   ports:
-  - port: 8080
+  - port: 8081
     protocol: TCP
-    targetPort: 8080
+    targetPort: 8081
   selector:
     control-plane: di-server
 ---
@@ -4295,7 +4295,7 @@ spec:
         envFrom:
         - configMapRef:
             name: di-config
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         livenessProbe:
           httpGet:
@@ -4348,7 +4348,7 @@ spec:
         envFrom:
         - configMapRef:
             name: di-config
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         livenessProbe:
           httpGet:

config/manager/di_operator.yaml

@@ -30,7 +30,7 @@ spec:
         - "--probe-addr=:8080"
         - "--metric-addr=:8443"
         - "--leader-elect"
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         name: manager
         envFrom:

config/manager/di_server.yaml

@@ -21,7 +21,7 @@ spec:
         args:
         - --zap-devel=true
         - --server-bind-address=:8081
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         name: server
         envFrom:

config/manager/di_webhook.yaml

@@ -22,7 +22,7 @@ spec:
         - "--probe-addr=:8080"
         - "--metric-addr=:8443"
         - --port=9443
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         name: webhook
         securityContext:

config/manager/kustomization.yaml

@@ -8,4 +8,4 @@ kind: Kustomization
 images:
 - name: registry.sensetime.com/cloudnative4ai/di-orchestrator
   newName: registry.sensetime.com/cloudnative4ai/di-orchestrator
-  newTag: v1.0.0
+  newTag: v1.0.1

config/rbac/di_server_service.yaml

@@ -8,5 +8,5 @@ spec:
     control-plane: di-server
   ports:
     - protocol: TCP
-      port: 8080
-      targetPort: 8080
+      port: 8081
+      targetPort: 8081

config/v1.15.5/di-manager.yaml

@@ -326,7 +326,7 @@ spec:
         command:
         - /di-orchestrator
         - operator
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         livenessProbe:
           httpGet:
@@ -376,7 +376,7 @@ spec:
         command:
         - /di-orchestrator
         - server
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         livenessProbe:
           httpGet:
@@ -421,7 +421,7 @@ spec:
         command:
         - /di-orchestrator
         - webhook
-        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.0
+        image: registry.sensetime.com/cloudnative4ai/di-orchestrator:v1.0.1
         imagePullPolicy: Always
         livenessProbe:
           httpGet:

docs/architecture.md

@@ -151,13 +151,13 @@ The following http interfaces are provided:
 
 | method  |  path |  description |
 |---|---|---|
-| GET  | /v1alpha2/replicas  |  list all collectors and learners |
-| GET  | /v1alpha2/replicas?namespace=xxx  | list all collectors and learners in namespace  |
-| GET  | /v1alpha2/replicas?namespace=xxx&coordinator=xxx  | list all replicas belongs to coordinator  |
-| GET  | /v1alpha2/replicas?namespace=xxx&aggregator=xxx  | get learners belongs to aggregator  |
-| DELETE  | /v1alpha2/replicas  | delete some replicas. put data in request body  |
-| POST  | /v1alpha2/replicas  | create replicas. put data in request body  |
-| POST  | /v1alpha2/replicas/failed  | post failed replicas and request for recreation. put data in request body  |
+| GET  | /v2alpha1/replicas  |  list all collectors and learners |
+| GET  | /v2alpha1/replicas?namespace=xxx  | list all collectors and learners in namespace  |
+| GET  | /v2alpha1/replicas?namespace=xxx&coordinator=xxx  | list all replicas belongs to coordinator  |
+| GET  | /v2alpha1/replicas?namespace=xxx&aggregator=xxx  | get learners belongs to aggregator  |
+| DELETE  | /v2alpha1/replicas  | delete some replicas. put data in request body  |
+| POST  | /v2alpha1/replicas  | create replicas. put data in request body  |
+| POST  | /v2alpha1/replicas/failed  | post failed replicas and request for recreation. put data in request body  |
 
 
 ## Advantages of DI Orchestrator

pkg/api/v2alpha1/dijob_types.go

@@ -149,11 +149,10 @@ type Phase string
 
 const (
 	// JobPending means the job has been submitted to the cluster,
-	// but not all the pods and services have been created,
-	// or not pods are running
+	// but not all the pods and services have been created
 	JobPending Phase = "Pending"
 
-	// JobStarted means the job has been scheduled and waits for running.
+	// JobStarted means the job has been created and waits for running.
 	JobStarting Phase = "Starting"
 
 	// JobRestarting means the job has been rescheduled and waits for restarting.