Makefile

@@ -48,17 +48,17 @@ init:
 	mkdir -p ${SERVER_BINARY_DIR}
 
 base-server_build: init
-	cd ./server && go mod download && go generate
+	cd ./server && go generate
 
 	cd ./server/base-server && go build -ldflags ${LD_FLAGS} -o ${SERVER_BINARY_DIR} ./...
 
 admin-server_build: init
-	cd ./server && go mod download && go generate
+	cd ./server && go generate
 
 	cd ./server/admin-server && go build -ldflags ${LD_FLAGS} -o ${SERVER_BINARY_DIR} ./...
 
 openai-server_build: init
-	cd ./server && go mod download && go generate
+	cd ./server && go generate
 
 	cd ./server/openai-server && go build -ldflags ${LD_FLAGS} -o ${SERVER_BINARY_DIR} ./...
 
@@ -71,7 +71,7 @@ scheduler_build: init
 	cd ./server/volcano && go build -ldflags ${LD_FLAGS} -o ${SERVER_BINARY_DIR} ./cmd/scheduler
 
 api-doc_build: init
-	cd ./server && go mod download && go generate
+	cd ./server && go generate
 # 运行
 all_run: server_run
 
@@ -139,7 +139,7 @@ lint_init:
 	golangci-lint version
 
 lint: lint_init
-	cd ./server && go mod download && golangci-lint run ./...
+	cd ./server && golangci-lint run ./...
 
 common_lint: lint_init
 	cd ./server/common && golangci-lint run ./...
@@ -160,33 +160,33 @@ volcano_lint: lint_init
 images: base-server_image admin-server_image openai-server_image volcano_image admin-portal_image openai-portal_image api-doc_image node-agent_image
 
 base-server_image:
-	docker build --no-cache -t base-server:${RELEASE_VER} -f ./build/application/base-server/dockerfile .
+	docker build -t base-server:${RELEASE_VER} -f ./build/application/base-server/dockerfile .
 
 admin-server_image:
-	docker build --no-cache -t admin-server:${RELEASE_VER} -f ./build/application/admin-server/dockerfile .
+	docker build -t admin-server:${RELEASE_VER} -f ./build/application/admin-server/dockerfile .
 
 openai-server_image:
-	docker build --no-cache -t openai-server:${RELEASE_VER} -f ./build/application/openai-server/dockerfile .
+	docker build -t openai-server:${RELEASE_VER} -f ./build/application/openai-server/dockerfile .
 
 volcano_image: vc-controller_image scheduler_image
 
 vc-controller_image:
-	docker build --no-cache -t vc-controller:${RELEASE_VER} -f ./build/application/volcano/vc-controller/dockerfile .
+	docker build -t vc-controller:${RELEASE_VER} -f ./build/application/volcano/vc-controller/dockerfile .
 
 scheduler_image:
-	docker build --no-cache -t scheduler:${RELEASE_VER} -f ./build/application/volcano/scheduler/dockerfile .
+	docker build -t scheduler:${RELEASE_VER} -f ./build/application/volcano/scheduler/dockerfile .
 
 admin-portal_image:
-	docker build --no-cache -t admin-portal:${RELEASE_VER} -f ./build/application/admin-portal/dockerfile .
+	docker build -t admin-portal:${RELEASE_VER} -f ./build/application/admin-portal/dockerfile .
 
 openai-portal_image:
-	docker build --no-cache -t openai-portal:${RELEASE_VER} -f ./build/application/openai-portal/dockerfile .
+	docker build -t openai-portal:${RELEASE_VER} -f ./build/application/openai-portal/dockerfile .
 
 api-doc_image:
-	docker build --no-cache -t api-doc:${RELEASE_VER} -f ./build/application/api-doc/dockerfile .
+	docker build -t api-doc:${RELEASE_VER} -f ./build/application/api-doc/dockerfile .
 
 node-agent_image:
-	docker build --no-cache -t node-agent:${RELEASE_VER} -f ./build/application/nodeagent/dockerfile ./controller/nodeagent
+	docker build -t node-agent:${RELEASE_VER} -f ./build/application/nodeagent/dockerfile ./controller/nodeagent
 
 # 镜像推送
 images_push: base-server_image_push admin-server_image_push openai-server_image_push volcano_image_push admin-portal_image_push openai-portal_image_push api-doc_image_push node-agent_image_push

admin-portal/src/views/devManager/components/notebook/detailDialog.vue

@@ -19,6 +19,9 @@ v<template>
         <el-tab-pane label="事件记录">
           <notebookEventRecord :notebook-data="notebookData" />
         </el-tab-pane>
+        <el-tab-pane label="退出信息">
+          <notebookExit :notebook-data="notebookData" />
+        </el-tab-pane>
       </el-tabs>
     </el-dialog>
   </div>
@@ -27,6 +30,7 @@ v<template>
 import notebookInfo from "./notebookInfo.vue"
 import notebookProfile from "./notebookProfile.vue"
 import notebookEventRecord from "./notebookEventRecord.vue"
+  import notebookExit from "./notebookExit.vue"
 export default {
   name: "DetailDialog",
   props: {
@@ -38,7 +42,8 @@ export default {
   components: {
     notebookInfo,
     notebookProfile,
-    notebookEventRecord
+    notebookEventRecord,
+    notebookExit
   },
   data() {
     return {

admin-portal/src/views/devManager/components/notebook/notebookExit.vue

@@ -0,0 +1,61 @@
+<template>
+  <div>
+    <div>
+      <el-row>
+        <el-col :span="12">
+          <div>任务名称:<span>{{ notebookInfo.name }}</span></div>
+        </el-col>
+        <el-col :span="12">
+          <div>是否分布式:<span>{{ this.notebookInfo.tasks.length > 1 ? '是' : '否'}}</span></div>
+        </el-col>
+
+      </el-row>
+      <el-input v-model="exitMsg" type="textarea" :readonly="true" :rows="20" />
+    </div>
+
+    <div slot="footer" class="dialog-footer" />
+  </div>
+</template>
+
+<script>
+  export default {
+    name: "NotebookExit",
+    props: {
+      notebookData: {
+        type: Object,
+        default: () => { }
+      }
+    },
+    data() {
+      return {
+        notebookInfo: {},
+        exitMsg: '暂无相关信息'
+      }
+    },
+    created() {
+      this.notebookInfo = this.notebookData
+      if(this.notebookInfo.exitMsg) {
+        this.exitMsg = this.notebookInfo.exitMsg
+      }
+    }
+  }
+</script>
+
+<style lang="scss" scoped>
+  .el-col {
+    margin: 10px 0 20px 0;
+    font-size: 15px;
+    font-weight: 800;
+
+    span {
+      font-weight: 400;
+      margin-left: 20px
+    }
+  }
+
+
+  .block {
+    float: right;
+    margin: 20px;
+  }
+</style>

admin-portal/vue.config.js

@@ -38,14 +38,14 @@ module.exports = {
     },
     proxy: {
       [process.env.VUE_APP_BASE_API]: {
-        target: 'http://192.168.203.154',
+        target: 'http://192.168.202.73',
         changeOrigin: true,
         pathRewrite: {
           ['^' + process.env.VUE_APP_BASE_API]: '/adminserver'
         }
       },
       [process.env.VUE_APP_BASE_API2]: {
-        target: 'http://192.168.203.154',
+        target: 'http://192.168.202.73',
         changeOrigin: true,
         pathRewrite: {
           ['^' + process.env.VUE_APP_BASE_API2]: ''

build/application/admin-portal/dockerfile

@@ -4,11 +4,11 @@ ENV PROJECT_ENV production
 ENV NODE_ENV production
 
 WORKDIR /admin-portal
-
-COPY ./admin-portal ./
+COPY ./admin-portal/package.json ./
 RUN npm config set registry https://registry.npm.taobao.org && \
-    npm install --dev && \
-    npm run build:prod
+    npm install --dev
+COPY ./admin-portal ./
+RUN npm run build:prod
 
 FROM nginx:1.21.0-alpine
 COPY --from=builder /admin-portal/dist/ /usr/share/nginx/html

build/application/admin-server/dockerfile

@@ -1,5 +1,12 @@
 from swr.cn-south-1.myhuaweicloud.com/openioctopus/kratos:v2 as builder
 WORKDIR /app
+COPY ./controller/nodeagent/go.mod ./controller/nodeagent/go.sum ./controller/nodeagent/
+RUN cd ./controller/nodeagent && go mod download
+COPY ./server/apis/go.mod ./server/apis/go.sum ./server/apis/
+RUN cd ./server/apis && go mod download
+COPY ./server/go.mod ./server/go.sum ./server/
+RUN cd ./server && go mod download
+
 COPY ./ ./
 
 RUN make admin-server_build binary_dir="/app/server/bin"

build/application/api-doc/dockerfile

@@ -1,5 +1,11 @@
 from swr.cn-south-1.myhuaweicloud.com/openioctopus/kratos:v2 as builder
 WORKDIR /app
+COPY ./controller/nodeagent/go.mod ./controller/nodeagent/go.sum ./controller/nodeagent/
+RUN cd ./controller/nodeagent && go mod download
+COPY ./server/apis/go.mod ./server/apis/go.sum ./server/apis/
+RUN cd ./server/apis && go mod download
+COPY ./server/go.mod ./server/go.sum ./server/
+RUN cd ./server && go mod download
 COPY ./ ./
 
 RUN make api-doc_build

build/application/base-server/dockerfile

@@ -1,5 +1,11 @@
 from swr.cn-south-1.myhuaweicloud.com/openioctopus/kratos:v2 as builder
 WORKDIR /app
+COPY ./controller/nodeagent/go.mod ./controller/nodeagent/go.sum ./controller/nodeagent/
+RUN cd ./controller/nodeagent && go mod download
+COPY ./server/apis/go.mod ./server/apis/go.sum ./server/apis/
+RUN cd ./server/apis && go mod download
+COPY ./server/go.mod ./server/go.sum ./server/
+RUN cd ./server && go mod download
 COPY ./ ./
 
 RUN make base-server_build binary_dir="/app/server/bin"

build/application/openai-portal/dockerfile

@@ -4,11 +4,11 @@ ENV PROJECT_ENV production
 ENV NODE_ENV production
 
 WORKDIR /openai-portal
-
-COPY ./openai-portal ./
+COPY ./openai-portal/package.json ./
 RUN npm config set registry https://registry.npm.taobao.org && \
-    npm install --dev && \
-    npm run build:prod
+    npm install --dev
+COPY ./openai-portal ./
+RUN npm run build:prod
 
 FROM nginx:1.21.0-alpine
 COPY --from=builder /openai-portal/dist/ /usr/share/nginx/html

build/application/openai-server/dockerfile

@@ -1,5 +1,11 @@
 from swr.cn-south-1.myhuaweicloud.com/openioctopus/kratos:v2 as builder
 WORKDIR /app
+COPY ./controller/nodeagent/go.mod ./controller/nodeagent/go.sum ./controller/nodeagent/
+RUN cd ./controller/nodeagent && go mod download
+COPY ./server/apis/go.mod ./server/apis/go.sum ./server/apis/
+RUN cd ./server/apis && go mod download
+COPY ./server/go.mod ./server/go.sum ./server/
+RUN cd ./server && go mod download
 COPY ./ ./
 
 RUN make openai-server_build binary_dir="/app/server/bin"

build/application/volcano/scheduler/dockerfile

@@ -1,5 +1,9 @@
 from swr.cn-south-1.myhuaweicloud.com/openioctopus/kratos:v2 as builder
 WORKDIR /app
+COPY ./server/apis/go.mod ./server/apis/go.sum ./server/apis/
+RUN cd ./server/apis && go mod download
+COPY ./server/volcano/go.mod ./server/volcano/go.sum ./server/volcano/
+RUN cd ./server/volcano && go mod download
 COPY ./ ./
 
 ENV GOPATH /go

build/application/volcano/vc-controller/dockerfile

@@ -1,5 +1,9 @@
 from swr.cn-south-1.myhuaweicloud.com/openioctopus/kratos:v2 as builder
 WORKDIR /app
+COPY ./server/apis/go.mod ./server/apis/go.sum ./server/apis/
+RUN cd ./server/apis && go mod download
+COPY ./server/volcano/go.mod ./server/volcano/go.sum ./server/volcano/
+RUN cd ./server/volcano && go mod download
 COPY ./ ./
 
 ENV GOPATH /go

deploy/charts/octopus/crds/fluid-system.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: fluid-system

deploy/charts/octopus/templates/logger.yaml

@@ -289,7 +289,7 @@ spec:
       {{- end }}
       containers:
         - name: logstash
-          image: docker.elastic.co/logstash/logstash:7.13.0
+          image: docker.elastic.co/logstash/logstash:7.17.13
           args: [
             "bin/logstash","-f", "/usr/share/logstash/pipeline/logstash.conf",
           ]

openai-portal/src/views/modelDev/components/notebook/detailDialog.vue

@@ -12,6 +12,9 @@
         <el-tab-pane label="事件记录">
           <notebookEventRecord :notebook-data="notebookData" />
         </el-tab-pane>
+        <el-tab-pane label="退出信息">
+          <notebookExit :notebook-data="notebookData" />
+        </el-tab-pane>
       </el-tabs>
     </el-dialog>
   </div>
@@ -20,12 +23,14 @@
   import notebookInfo from "./notebookInfo.vue"
   import notebookProfile from "./notebookProfile.vue"
   import notebookEventRecord from "./notebookEventRecord.vue"
+  import notebookExit from "./notebookExit.vue"
   export default {
     name: "DetailDialog",
     components: {
       notebookInfo,
       notebookProfile,
-      notebookEventRecord
+      notebookEventRecord,
+      notebookExit
     },
     props: {
       detailData: {

openai-portal/src/views/modelDev/components/notebook/notebookExit.vue

@@ -0,0 +1,61 @@
+<template>
+  <div>
+    <div>
+      <el-row>
+        <el-col :span="12">
+          <div>任务名称:<span>{{ notebookInfo.name }}</span></div>
+        </el-col>
+        <el-col :span="12">
+          <div>是否分布式:<span>{{ this.notebookInfo.tasks.length > 1 ? '是' : '否'}}</span></div>
+        </el-col>
+
+      </el-row>
+      <el-input v-model="exitMsg" type="textarea" :readonly="true" :rows="20" />
+    </div>
+
+    <div slot="footer" class="dialog-footer" />
+  </div>
+</template>
+
+<script>
+  export default {
+    name: "NotebookExit",
+    props: {
+      notebookData: {
+        type: Object,
+        default: () => { }
+      }
+    },
+    data() {
+      return {
+        notebookInfo: {},
+        exitMsg: '暂无相关信息'
+      }
+    },
+    created() {
+      this.notebookInfo = this.notebookData
+      if(this.notebookInfo.exitMsg) {
+        this.exitMsg = this.notebookInfo.exitMsg
+      }
+    }
+  }
+</script>
+
+<style lang="scss" scoped>
+  .el-col {
+    margin: 10px 0 20px 0;
+    font-size: 15px;
+    font-weight: 800;
+
+    span {
+      font-weight: 400;
+      margin-left: 20px
+    }
+  }
+
+
+  .block {
+    float: right;
+    margin: 20px;
+  }
+</style>

server/admin-server/api/v1/develop.proto

@@ -91,6 +91,7 @@ message Notebook {
   repeated Task tasks = 25;
   string userEmail = 26;
   string  resourcePool=27;
+  string exitMsg = 28;
 }
 
 message ListNotebookReply {

server/base-server/api/v1/develop.proto

@@ -123,6 +123,7 @@ message Notebook {
   repeated Task tasks = 23;
   string resourcePool=24;
   string imageUrl = 25;
+  string exitMsg = 26;
 }
 
 message ListNotebookReply {

server/base-server/internal/data/registry/harbor.go

@@ -5,6 +5,7 @@ import (
 	"crypto/tls"
 	"net/http"
 	"net/url"
+	"path"
 	"server/base-server/internal/conf"
 	"server/common/errors"
 	"strconv"
@@ -138,6 +139,17 @@ func (h *v1Registry) CreateProject(projectReq *ProjectReq) error {
 	}
 }
 
+func (h *v1Registry) DeleteArtifact(projectName string, repositoryName string, reference string) error {
+	if projectName == "" || repositoryName == "" || reference == "" {
+		return errors.Errorf(nil, errors.ErrorInvalidRequestParameter)
+	}
+	_, err := h.client.ProductsApi.RepositoriesRepoNameTagsTagDelete(h.GetAuth(nil), path.Join(projectName, repositoryName), reference)
+	if err != nil {
+		return errors.Errorf(err, errors.ErrorHarborDeleteArtifactFailed)
+	}
+	return nil
+}
+
 func (h *v1Registry) GetAuth(ctx context.Context) context.Context {
 	if ctx == nil {
 		ctx = context.TODO()
@@ -172,3 +184,14 @@ func (h *v2Registry) CreateProject(projectReq *ProjectReq) error {
 		return errors.Errorf(err1, errors.ErrorHarborCheckProjectFailed)
 	}
 }
+
+func (h *v2Registry) DeleteArtifact(projectName string, repositoryName string, reference string) error {
+	if projectName == "" || repositoryName == "" || reference == "" {
+		return errors.Errorf(nil, errors.ErrorInvalidRequestParameter)
+	}
+	_, err := h.client.ArtifactApi.DeleteArtifact(h.GetAuth(nil), projectName, url.PathEscape(url.PathEscape(repositoryName)), reference, nil)
+	if err != nil {
+		return errors.Errorf(err, errors.ErrorHarborDeleteArtifactFailed)
+	}
+	return nil
+}

server/base-server/internal/data/registry/registry.go

@@ -2,4 +2,5 @@ package registry
 
 type ArtifactRegistry interface {
 	CreateProject(projectReq *ProjectReq) error
+	DeleteArtifact(projectName string, repositoryName string, reference string) error
 }

server/base-server/internal/service/develop/develop.go

@@ -925,8 +925,10 @@ func (s *developService) convertNotebook(ctx context.Context, notebooksTbl []*mo
 		return nil, err
 	}
 	priceMap := make(map[string]float64)
+	jobMap := make(map[string]*model.NotebookJob)
 	for _, j := range notebookJobs {
 		priceMap[j.Id] = j.ResourceSpecPrice
+		jobMap[j.Id] = j
 	}
 
 	notebooks := make([]*api.Notebook, 0)
@@ -942,11 +944,22 @@ func (s *developService) convertNotebook(ctx context.Context, notebooksTbl []*mo
 		for i := 0; i < n.TaskNumber; i++ {
 			notebook.Tasks = append(notebook.Tasks, &api.Notebook_Task{Name: buildTaskName(i), Url: buildNotebookUrl(n.NotebookJobId, i)})
 		}
+		notebook.ExitMsg = s.getExitMsg(ctx, jobMap[n.NotebookJobId])
 		notebooks = append(notebooks, notebook)
 	}
 	return notebooks, nil
 }
 
+func (s *developService) getExitMsg(ctx context.Context, job *model.NotebookJob) string {
+	detail := &typeJob.JobStatusDetail{}
+	err := json.Unmarshal([]byte(job.Detail), detail)
+	if err != nil || detail.Job == nil {
+		return ""
+	}
+
+	return detail.Job.ExitDiagnostics
+}
+
 func (s *developService) GetNotebook(ctx context.Context, req *api.GetNotebookRequest) (*api.GetNotebookReply, error) {
 	notebookTbl, err := s.data.DevelopDao.GetNotebook(ctx, req.Id)
 	if err != nil {

server/base-server/internal/service/image/image.go

@@ -345,7 +345,21 @@ func (s *ImageService) DeleteImage(ctx context.Context, req *pb.DeleteImageReque
 		}
 	}
 
-	_, err := s.data.ImageDao.Delete(ctx, &model.ImageDel{
+	image, err := s.data.ImageDao.Find(ctx, &model.ImageQuery{Id: req.ImageId})
+	if err != nil {
+		return nil, err
+	}
+
+	if (image.SourceType == int32(pb.ImageSourceType_IMAGE_SOURCE_TYPE_UPLOADED) || image.SourceType == int32(pb.ImageSourceType_IMAGE_SOURCE_TYPE_SAVED)) &&
+		image.Status == int32(pb.ImageStatus_IMAGE_STATUS_MADE) {
+		index := strings.Index(image.ImageAddr, "/")
+		err := s.data.Registry.DeleteArtifact(image.ImageAddr[:index], image.ImageAddr[index+1:], image.ImageVersion)
+		if err != nil {
+			log.Error(ctx, err)
+		}
+	}
+
+	_, err = s.data.ImageDao.Delete(ctx, &model.ImageDel{
 		Id: req.ImageId,
 	})
 	if err != nil {

server/common/errors/codes.go

@@ -62,9 +62,11 @@ const (
 	ErrorK8sDeleteSecretFailed  = 10076 // k8s删除Secret失败
 	ErrorFluidInitFailed        = 10077 // Fluid初始化失败
 	// Harbor操作相关错误
-	ErrorHarborProjectExists       = 10080 // harbor项目已存在
-	ErrorHarborCreateProjectFailed = 10081 // harbor创建项目失败
-	ErrorHarborCheckProjectFailed  = 10082 // harbor查询项目失败
+	ErrorHarborProjectExists        = 10080 // harbor项目已存在
+	ErrorHarborCreateProjectFailed  = 10081 // harbor创建项目失败
+	ErrorHarborCheckProjectFailed   = 10082 // harbor查询项目失败
+	ErrorHarborDeleteArtifactFailed = 10083 // harbor删除镜像失败
+
 	// redis操作相关错误
 	ErroRedisParseUrlFailed    = 10100 // redis解析url失败
 	ErroRedisHSetFailed        = 10101 // redisHSet失败
@@ -298,9 +300,10 @@ var codeMsgMap = map[int]codeMsg{
 	ErrorK8sCreateIngressFailed: {codeType: Internal, msg: "create k8s ingress failed"},
 	ErrorK8sDeleteIngressFailed: {codeType: Internal, msg: "delete k8s ingress failed"},
 	// Harbor操作相关错误
-	ErrorHarborProjectExists:       {codeType: AlreadyExists, msg: "harbor project exists"},
-	ErrorHarborCreateProjectFailed: {codeType: Internal, msg: "create harbor project failed"},
-	ErrorHarborCheckProjectFailed:  {codeType: Internal, msg: "check harbor project failed"},
+	ErrorHarborProjectExists:        {codeType: AlreadyExists, msg: "harbor project exists"},
+	ErrorHarborCreateProjectFailed:  {codeType: Internal, msg: "create harbor project failed"},
+	ErrorHarborCheckProjectFailed:   {codeType: Internal, msg: "check harbor project failed"},
+	ErrorHarborDeleteArtifactFailed: {codeType: Internal, msg: "delete harbor image failed"},
 	// redis操作相关错误
 	ErroRedisParseUrlFailed:    {codeType: Internal, msg: "redis parse url failed"},
 	ErroRedisHSetFailed:        {codeType: Internal, msg: "redis HSet failed"},

server/openai-server/api/v1/develop.proto

@@ -163,6 +163,7 @@ message Notebook {
   string imageVersion = 22;
   repeated Task tasks = 23;
   string imageUrl = 24;
+  string exitMsg = 25;
 }
 
 message ListNotebookReply {