Merge branch 'master' of https://gitlink.org.cn/JointCloud/pcm-coordinator

# Conflicts:
#	Dockerfile
#	etc/pcm.yaml
#	go.mod
#	go.sum
#	internal/logic/inference/deployinstancelistlogic.go
#	internal/logic/inference/getdeploytasksbytypelogic.go
#	internal/logic/inference/startallbydeploytaskidlogic.go
#	internal/logic/inference/stopallbydeploytaskidlogic.go
#	internal/storeLink/modelarts.go
#	internal/storeLink/storeLink.go


Former-commit-id: 6bcef559a95de140a7790257734f2838e8e92bad

.devops/aly.yml

@@ -0,0 +1,53 @@
+version: 2
+name: aly
+description: 发布环境：https://comnet.jointcloud.net
+global:
+  concurrent: 1
+workflow:
+  - ref: start
+    name: 开始
+    task: start
+  - ref: end
+    name: 结束
+    task: end
+    needs:
+      - ssh_cmd_0
+  - ref: git_clone_0
+    name: git clone
+    task: git_clone@1.2.9
+    input:
+      remote_url: '"https://gitlink.org.cn/JointCloud/pcm-coordinator.git"'
+      ref: '"refs/heads/master"'
+      commit_id: '""'
+      depth: 1
+    needs:
+      - start
+  - ref: docker_image_build_0
+    name: docker镜像构建
+    task: docker_image_build@1.6.0
+    input:
+      docker_username: ((aly.docker_user))
+      docker_password: ((aly.docker_password))
+      image_name: '"registry.cn-hangzhou.aliyuncs.com/jcce/pcm-core-api"'
+      image_tag: '"latest"'
+      registry_address: '"registry.cn-hangzhou.aliyuncs.com"'
+      docker_file: '"Dockerfile"'
+      docker_build_path: '"."'
+      workspace: git_clone_0.git_path
+      image_clean: true
+      image_push: true
+      build_args: '""'
+    needs:
+      - git_clone_0
+  - ref: ssh_cmd_0
+    name: ssh执行命令
+    task: ssh_cmd@1.1.1
+    input:
+      ssh_private_key: ((aly.ssh_private_key))
+      ssh_ip: '"47.92.39.128"'
+      ssh_port: '"22"'
+      ssh_user: '"root"'
+      ssh_cmd: '"kubectl rollout restart deployment pcm-core-api -n ns-admin"'
+    needs:
+      - docker_image_build_0
+

.github/workflows/docker-publish.yml

@@ -0,0 +1,55 @@
+name: Docker
+
+on:
+  push:
+    branches: [ "master" ]
+    tags: [ 'v*.*.*' ]
+  pull_request:
+    branches: [ "master" ]
+  workflow_dispatch:  # 允许手动触发
+
+env:
+  REGISTRY: registry.cn-hangzhou.aliyuncs.com  # 修改为你的阿里云镜像仓库地址
+  IMAGE_NAME: jcce/pcm-core-api  # 修改为你的阿里云镜像仓库名称
+  IMAGE_TAG: latest
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ secrets.ALIYUN_USERNAME }}
+          password: ${{ secrets.ALIYUN_PASSWORD }}
+
+      - name: Build and push
+        run: |
+          docker build -t ${{env.REGISTRY}}/${{env.IMAGE_NAME}}:${{env.IMAGE_TAG}} .
+          docker push ${{env.REGISTRY}}/${{env.IMAGE_NAME}}:${{env.IMAGE_TAG}}
+
+      - name: Set up SSH key
+        run: |
+          mkdir -p ~/.ssh
+          echo "${{ secrets.SSH_PRIVATE_KEY }}" > ~/.ssh/id_rsa
+          chmod 600 ~/.ssh/id_rsa
+          echo -e "Host *\n\tStrictHostKeyChecking no\n\n" > ~/.ssh/config
+
+      - name: SSH to remote server and restart deployment
+        if: github.event_name != 'pull_request'
+        run: ssh ${{ secrets.SSH_USER }}@${{ secrets.SSH_HOST }} "kubectl rollout restart deployment ${{ secrets.SSH_DEPLOYMENT }} -n ${{ secrets.SSH_NAMESPACE }}"

.github/workflows/sync.yml

@@ -0,0 +1,25 @@
+name: Sync Mirror Repository
+
+on:
+  schedule:
+    - cron: '0 * * * *'  # 每小时同步一次
+  workflow_dispatch:  # 允许手动触发
+
+jobs:
+  mirror:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout target repository
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 1  # 获取完整的提交历史
+
+      - name: Mirror source repository
+        uses: wearerequired/git-mirror-action@v1
+        with:
+          source-repo: "https://gitlink.org.cn/JointCloud/pcm-coordinator.git"  # 源仓库的URL
+          destination-repo: "git@github.com:${{ github.repository }}.git"  # 目标仓库的URL
+          ssh: true
+        env:
+          SSH_PRIVATE_KEY: ${{ secrets.SSH_PRIVATE_KEY }}

Dockerfile

@@ -1,4 +1,4 @@
-FROM registry.cn-hangzhou.aliyuncs.com/jcce-images/golang:1.22.4-alpine3.20 AS builder
+FROM golang:1.22.4-alpine3.20 AS builder
 
 WORKDIR /app
 COPY . .
@@ -9,12 +9,11 @@ RUN go mod download
 RUN CGO_ENABLED=0 go build -ldflags="-w -s" -o pcm-core-api
 
 
-FROM registry.cn-hangzhou.aliyuncs.com/jcce-images/alpine:3.20
+FROM alpine:latest
 WORKDIR /app
 
 #修改alpine源为上海交通大学
-RUN sed -i 's/dl-cdn.alpinelinux.org/mirrors.sjtug.sjtu.edu.cn/g' /etc/apk/repositories && \
+RUN apk add --no-cache ca-certificates && update-ca-certificates && \
-  apk add --no-cache ca-certificates && update-ca-certificates && \
   apk add --update tzdata && \
   rm -rf /var/cache/apk/*
 

etc/pcm.yaml

@@ -3,11 +3,11 @@ Host: 0.0.0.0
 Port: 8999
 MaxBytes: 524288000
 
-Timeout: 50000
+Timeout: 500000
 
 DB:
-#  DataSource: root:uJpLd6u-J?HC1@(10.206.0.12:3306)/pcm?parseTime=true&loc=Local
+   DataSource: root:uJpLd6u-J?HC1@(10.206.0.12:3306)/pcm?parseTime=true&loc=Local
-   DataSource: root:uJpLd6u-J?HC1@(47.92.88.143:3306)/pcm?parseTime=true&loc=Local
+   #DataSource: root:uJpLd6u-J?HC1@(47.92.88.143:3306)/pcm?parseTime=true&loc=Local
 Redis:
   Host: 10.206.0.12:6379
   Pass: redisPW123
@@ -27,7 +27,7 @@ ModelArtsRpcConf:
   Endpoints:
     - 127.0.0.1:2002
   NonBlock: true
-  Timeout: 20000
+  Timeout: 500000
 
 #rpc
 ModelArtsImgRpcConf:

go.mod

@@ -14,12 +14,12 @@ require (
 	github.com/pkg/errors v0.9.1
 	github.com/prometheus-operator/prometheus-operator/pkg/apis/monitoring v0.71.2
 	github.com/prometheus/alertmanager v0.27.0
-	github.com/prometheus/client_golang v1.20.2
+	github.com/prometheus/client_golang v1.20.3
-	github.com/prometheus/common v0.57.0
+	github.com/prometheus/common v0.59.1
 	github.com/robfig/cron/v3 v3.0.1
-	github.com/zeromicro/go-zero v1.7.0
+	github.com/zeromicro/go-zero v1.7.2
 	gitlink.org.cn/JointCloud/pcm-ac v0.0.0-20240725071305-f751eec4dde1
-	gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240831031531-89bdb156378a
+	gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240909072501-939c3144cd9e
 	gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240817071412-44397870b110
 	gitlink.org.cn/JointCloud/pcm-openstack v0.0.0-20240403033338-e7edabad4203
 	gitlink.org.cn/JointCloud/pcm-slurm v0.0.0-20240301080743-8b94bbaf57f5
@@ -126,7 +126,7 @@ require (
 	go.etcd.io/etcd/api/v3 v3.5.15 // indirect
 	go.etcd.io/etcd/client/pkg/v3 v3.5.15 // indirect
 	go.etcd.io/etcd/client/v3 v3.5.15 // indirect
-	go.mongodb.org/mongo-driver v1.16.0 // indirect
+	go.mongodb.org/mongo-driver v1.16.1 // indirect
 	go.opentelemetry.io/otel v1.29.0 // indirect
 	go.opentelemetry.io/otel/exporters/jaeger v1.17.0 // indirect
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.29.0 // indirect
@@ -140,27 +140,27 @@ require (
 	go.uber.org/automaxprocs v1.5.3 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
-	golang.org/x/crypto v0.26.0 // indirect
+	golang.org/x/crypto v0.27.0 // indirect
 	golang.org/x/exp v0.0.0-20240119083558-1b970713d09a // indirect
-	golang.org/x/mod v0.20.0 // indirect
+	golang.org/x/mod v0.21.0 // indirect
-	golang.org/x/net v0.28.0 // indirect
+	golang.org/x/net v0.29.0 // indirect
-	golang.org/x/oauth2 v0.22.0 // indirect
+	golang.org/x/oauth2 v0.23.0 // indirect
 	golang.org/x/sync v0.8.0 // indirect
-	golang.org/x/sys v0.24.0 // indirect
+	golang.org/x/sys v0.25.0 // indirect
-	golang.org/x/term v0.23.0 // indirect
+	golang.org/x/term v0.24.0 // indirect
-	golang.org/x/text v0.17.0 // indirect
+	golang.org/x/text v0.18.0 // indirect
 	golang.org/x/time v0.6.0 // indirect
 	golang.org/x/tools v0.24.0 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20240827150818-7e3bb234dfed // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20240903143218-8af14fe29dc1 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20240827150818-7e3bb234dfed // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 // indirect
 	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	k8s.io/api v0.31.0 // indirect
 	k8s.io/klog/v2 v2.130.1 // indirect
-	k8s.io/kube-openapi v0.0.0-20240827152857-f7e401e7b4c2 // indirect
+	k8s.io/kube-openapi v0.0.0-20240903163716-9e1beecbcb38 // indirect
-	k8s.io/utils v0.0.0-20240821151609-f90d01438635 // indirect
+	k8s.io/utils v0.0.0-20240902221715-702e33fdd3c3 // indirect
 	sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd // indirect
 	sigs.k8s.io/structured-merge-diff/v4 v4.4.1 // indirect
 )

go.sum

@@ -393,8 +393,8 @@ github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5Fsn
 github.com/prometheus/client_golang v1.4.0/go.mod h1:e9GMxYsXl05ICDXkRhurwBS4Q3OK1iX/F2sw+iXX5zU=
 github.com/prometheus/client_golang v1.7.1/go.mod h1:PY5Wy2awLA44sXw4AOSfFBetzPP4j5+D6mVACh+pe2M=
 github.com/prometheus/client_golang v1.11.0/go.mod h1:Z6t4BnS23TR94PD6BsDNk8yVqroYurpAkEiz0P2BEV0=
-github.com/prometheus/client_golang v1.20.2 h1:5ctymQzZlyOON1666svgwn3s6IKWgfbjsejTMiXIyjg=
+github.com/prometheus/client_golang v1.20.3 h1:oPksm4K8B+Vt35tUhw6GbSNSgVlVSBH0qELP/7u83l4=
-github.com/prometheus/client_golang v1.20.2/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
+github.com/prometheus/client_golang v1.20.3/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
 github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
 github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
@@ -406,8 +406,8 @@ github.com/prometheus/common v0.9.1/go.mod h1:yhUN8i9wzaXS3w1O07YhxHEBxD+W35wd8b
 github.com/prometheus/common v0.10.0/go.mod h1:Tlit/dnDKsSWFlCLTWaA1cyBgKHSMdTB80sz/V91rCo=
 github.com/prometheus/common v0.26.0/go.mod h1:M7rCNAaPfAosfx8veZJCuw84e35h3Cfd9VFqTh1DIvc=
 github.com/prometheus/common v0.29.0/go.mod h1:vu+V0TpY+O6vW9J44gczi3Ap/oXXR10b+M/gUGO4Hls=
-github.com/prometheus/common v0.57.0 h1:Ro/rKjwdq9mZn1K5QPctzh+MA4Lp0BuYk5ZZEVhoNcY=
+github.com/prometheus/common v0.59.1 h1:LXb1quJHWm1P6wq/U824uxYi4Sg0oGvNeUm1z5dJoX0=
-github.com/prometheus/common v0.57.0/go.mod h1:7uRPFSUTbfZWsJ7MHY56sqt7hLQu3bxXHDnNhl8E9qI=
+github.com/prometheus/common v0.59.1/go.mod h1:GpWM7dewqmVYcd7SmRaiWVe9SSqjf0UrwnYnpEZNuT0=
 github.com/prometheus/common/sigv4 v0.1.0 h1:qoVebwtwwEhS85Czm2dSROY5fTo2PAPEVdDeppTwGX4=
 github.com/prometheus/common/sigv4 v0.1.0/go.mod h1:2Jkxxk9yYvCkE5G1sQT7GuEXm57JrvHu9k5YwTjsNtI=
 github.com/prometheus/exporter-toolkit v0.11.0 h1:yNTsuZ0aNCNFQ3aFTD2uhPOvr4iD7fdBvKPAEGkNf+g=
@@ -464,12 +464,12 @@ github.com/yuin/goldmark v1.3.5/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 github.com/yuin/gopher-lua v1.1.1 h1:kYKnWBjvbNP4XLT3+bPEwAXJx262OhaHDWDVOPjL46M=
 github.com/yuin/gopher-lua v1.1.1/go.mod h1:GBR0iDaNXjAgGg9zfCvksxSRnQx76gclCIb7kdAd1Pw=
-github.com/zeromicro/go-zero v1.7.0 h1:B+y7tUVlo3qVQ6F0I0R9bi+Dq4I1QdO9ZB+dz1r0p1s=
+github.com/zeromicro/go-zero v1.7.2 h1:a8lyVOG3KXG4LrAy6ZmtJTJtisX4Ostc4Pst4fE704I=
-github.com/zeromicro/go-zero v1.7.0/go.mod h1:ypW4PzQI+jUrMcNJDDQ+7YW+pE+tMua9Xj/pmtmS1Dc=
+github.com/zeromicro/go-zero v1.7.2/go.mod h1:WFXfF92Exw0O7WECifS6r99JSzv4KEN49x9RhAfgkMc=
 gitlink.org.cn/JointCloud/pcm-ac v0.0.0-20240725071305-f751eec4dde1 h1:DicBXoQiC6mumMBeyqSPNrsjtqJIgk5Pv2hscu2xryw=
 gitlink.org.cn/JointCloud/pcm-ac v0.0.0-20240725071305-f751eec4dde1/go.mod h1:3eECiw9O2bIFkkePlloKyLNXiqBAhOxNrDoGaaGseGY=
-gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240831031531-89bdb156378a h1:x3qNoZu7leHTx5gaDuLNR/T9ubwIpCXZH5hS6ZfwltQ=
+gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240909072501-939c3144cd9e h1:6LYJggBoeAQxy/otzWjt40Pa7gnVvUR4c5YMi6A/NdU=
-gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240831031531-89bdb156378a/go.mod h1:/eOmBFZKWGoabG3sRVkVvIbLwsd2631k4jkUBR6x1AA=
+gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240909072501-939c3144cd9e/go.mod h1:/eOmBFZKWGoabG3sRVkVvIbLwsd2631k4jkUBR6x1AA=
 gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240817071412-44397870b110 h1:GaXwr5sgDh0raHjUf9IewTvnRvajYea7zbLsaerYyXo=
 gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240817071412-44397870b110/go.mod h1:QOD5+/l2D+AYBjF2h5T0mdJyfGAmF78QmeKdbBXbjLQ=
 gitlink.org.cn/JointCloud/pcm-openstack v0.0.0-20240403033338-e7edabad4203 h1:s6PsZ1+bev294IWdZRlV7mnOwI1+UzFcldVW/BqhQzI=
@@ -484,8 +484,8 @@ go.etcd.io/etcd/client/pkg/v3 v3.5.15 h1:fo0HpWz/KlHGMCC+YejpiCmyWDEuIpnTDzpJLB5
 go.etcd.io/etcd/client/pkg/v3 v3.5.15/go.mod h1:mXDI4NAOwEiszrHCb0aqfAYNCrZP4e9hRca3d1YK8EU=
 go.etcd.io/etcd/client/v3 v3.5.15 h1:23M0eY4Fd/inNv1ZfU3AxrbbOdW79r9V9Rl62Nm6ip4=
 go.etcd.io/etcd/client/v3 v3.5.15/go.mod h1:CLSJxrYjvLtHsrPKsy7LmZEE+DK2ktfd2bN4RhBMwlU=
-go.mongodb.org/mongo-driver v1.16.0 h1:tpRsfBJMROVHKpdGyc1BBEzzjDUWjItxbVSZ8Ls4BQ4=
+go.mongodb.org/mongo-driver v1.16.1 h1:rIVLL3q0IHM39dvE+z2ulZLp9ENZKThVfuvN/IiN4l8=
-go.mongodb.org/mongo-driver v1.16.0/go.mod h1:oB6AhJQvFQL4LEHyXi6aJzQJtBiTQHiAd83l0GdFaiw=
+go.mongodb.org/mongo-driver v1.16.1/go.mod h1:oB6AhJQvFQL4LEHyXi6aJzQJtBiTQHiAd83l0GdFaiw=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
 go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
@@ -533,8 +533,8 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
 golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
-golang.org/x/crypto v0.26.0 h1:RrRspgV4mU+YwB4FYnuBoKsUapNIL5cohGAmSH3azsw=
+golang.org/x/crypto v0.27.0 h1:GXm2NjJrPaiv/h1tb2UH8QfgC/hOf/+z0p6PT8o1w7A=
-golang.org/x/crypto v0.26.0/go.mod h1:GY7jblb9wI+FOo5y8/S2oY4zWP07AkOJ4+jxCqdqn54=
+golang.org/x/crypto v0.27.0/go.mod h1:1Xngt8kV6Dvbssa53Ziq6Eqn0HqbZi5Z6R0ZpwQzt70=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190510132918-efd6b22b2522/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
@@ -570,8 +570,8 @@ golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
-golang.org/x/mod v0.20.0 h1:utOm6MM3R3dnawAiJgn0y+xvuYRsm1RKM/4giyfDgV0=
+golang.org/x/mod v0.21.0 h1:vvrHzRwRfVKSiLrG+d4FMl/Qi4ukBCE6kZlTUkDYRT0=
-golang.org/x/mod v0.20.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
+golang.org/x/mod v0.21.0/go.mod h1:6SkKJ3Xj0I0BrPOZoBy3bdMptDDU9oJrpohJ3eWZ1fY=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -611,16 +611,16 @@ golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
 golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
 golang.org/x/net v0.22.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
-golang.org/x/net v0.28.0 h1:a9JDOJc5GMUJ0+UDqmLT86WiEy7iWyIhz8gz8E4e5hE=
+golang.org/x/net v0.29.0 h1:5ORfpBpCs4HzDYoodCDBbwHzdR5UrLBZ3sOnUJmFoHo=
-golang.org/x/net v0.28.0/go.mod h1:yqtgsTWOOnlGLG9GFRrK3++bGOUEkNBoHZc8MEDWPNg=
+golang.org/x/net v0.29.0/go.mod h1:gLkgy8jTGERgjzMic6DS9+SP0ajcu6Xu3Orq/SpETg0=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20191202225959-858c2ad4c8b6/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20210514164344-f6687ab2804c/go.mod h1:KelEdhl1UZF7XfJ4dDtk6s++YSgaE7mD/BuKKDLBl4A=
-golang.org/x/oauth2 v0.22.0 h1:BzDx2FehcG7jJwgWLELCdmLuxk2i+x9UDpSiss2u0ZA=
+golang.org/x/oauth2 v0.23.0 h1:PbgcYx2W7i4LvjJWEbf0ngHV6qJYr86PkAV3bXdLEbs=
-golang.org/x/oauth2 v0.22.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
+golang.org/x/oauth2 v0.23.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -686,16 +686,16 @@ golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.24.0 h1:Twjiwq9dn6R1fQcyiK+wQyHWfaz/BJB+YIpzU/Cv3Xg=
+golang.org/x/sys v0.25.0 h1:r+8e+loiHxRqhXVl6ML1nO3l1+oFoWbnlu2Ehimmi34=
-golang.org/x/sys v0.24.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.25.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
 golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
 golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
 golang.org/x/term v0.18.0/go.mod h1:ILwASektA3OnRv7amZ1xhE/KTR+u50pbXfZ03+6Nx58=
-golang.org/x/term v0.23.0 h1:F6D4vR+EHoL9/sWAWgAR1H2DcHr4PareCbAaCo1RpuU=
+golang.org/x/term v0.24.0 h1:Mh5cbb+Zk2hqqXNO7S1iTjEphVL+jb8ZWaqh/g+JWkM=
-golang.org/x/term v0.23.0/go.mod h1:DgV24QBUrK6jhZXl+20l6UWznPlwAHm1Q1mGHtydmSk=
+golang.org/x/term v0.24.0/go.mod h1:lOBK/LVxemqiMij05LGJ0tzNr8xlmwBRJ81PX6wVLH8=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -706,8 +706,8 @@ golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
-golang.org/x/text v0.17.0 h1:XtiM5bkSOt+ewxlOE/aE/AKEHibwj/6gvWMl9Rsh0Qc=
+golang.org/x/text v0.18.0 h1:XvMDiNzPAl0jr17s6W9lcaIhGUfUORdGCNsuLmPG224=
-golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
+golang.org/x/text v0.18.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
@@ -819,10 +819,10 @@ google.golang.org/genproto v0.0.0-20200618031413-b414f8b61790/go.mod h1:jDfRM7Fc
 google.golang.org/genproto v0.0.0-20200729003335-053ba62fc06f/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
 google.golang.org/genproto v0.0.0-20200804131852-c06518451d9c/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
 google.golang.org/genproto v0.0.0-20200825200019-8632dd797987/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
-google.golang.org/genproto/googleapis/api v0.0.0-20240827150818-7e3bb234dfed h1:3RgNmBoI9MZhsj3QxC+AP/qQhNwpCLOvYDYYsFrhFt0=
+google.golang.org/genproto/googleapis/api v0.0.0-20240903143218-8af14fe29dc1 h1:hjSy6tcFQZ171igDaN5QHOw2n6vx40juYbC/x67CEhc=
-google.golang.org/genproto/googleapis/api v0.0.0-20240827150818-7e3bb234dfed/go.mod h1:OCdP9MfskevB/rbYvHTsXTtKC+3bHWajPdoKgjcYkfo=
+google.golang.org/genproto/googleapis/api v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:qpvKtACPCQhAdu3PyQgV4l3LMXZEtft7y8QcarRsp9I=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20240827150818-7e3bb234dfed h1:J6izYgfBXAI3xTKLgxzTmUltdYaLsuBxFCgDHWJ/eXg=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 h1:pPJltXNxVzT4pK9yD8vR9X75DaWYYmLGMsEvBfFQZzQ=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20240827150818-7e3bb234dfed/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.20.1/go.mod h1:10oTOabMzJvdu6/UiuZezV6QK5dSlG84ov/aaiqXj38=
 google.golang.org/grpc v1.21.1/go.mod h1:oYelfM1adQP15Ek0mdvEgi9Df8B9CZIaU1084ijfRaM=
@@ -902,10 +902,10 @@ k8s.io/client-go v0.31.0 h1:QqEJzNjbN2Yv1H79SsS+SWnXkBgVu4Pj3CJQgbx0gI8=
 k8s.io/client-go v0.31.0/go.mod h1:Y9wvC76g4fLjmU0BA+rV+h2cncoadjvjjkkIGoTLcGU=
 k8s.io/klog/v2 v2.130.1 h1:n9Xl7H1Xvksem4KFG4PYbdQCQxqc/tTUyrgXaOhHSzk=
 k8s.io/klog/v2 v2.130.1/go.mod h1:3Jpz1GvMt720eyJH1ckRHK1EDfpxISzJ7I9OYgaDtPE=
-k8s.io/kube-openapi v0.0.0-20240827152857-f7e401e7b4c2 h1:GKE9U8BH16uynoxQii0auTjmmmuZ3O0LFMN6S0lPPhI=
+k8s.io/kube-openapi v0.0.0-20240903163716-9e1beecbcb38 h1:1dWzkmJrrprYvjGwh9kEUxmcUV/CtNU8QM7h1FLWQOo=
-k8s.io/kube-openapi v0.0.0-20240827152857-f7e401e7b4c2/go.mod h1:coRQXBK9NxO98XUv3ZD6AK3xzHCxV6+b7lrquKwaKzA=
+k8s.io/kube-openapi v0.0.0-20240903163716-9e1beecbcb38/go.mod h1:coRQXBK9NxO98XUv3ZD6AK3xzHCxV6+b7lrquKwaKzA=
-k8s.io/utils v0.0.0-20240821151609-f90d01438635 h1:2wThSvJoW/Ncn9TmQEYXRnevZXi2duqHWf5OX9S3zjI=
+k8s.io/utils v0.0.0-20240902221715-702e33fdd3c3 h1:b2FmK8YH+QEwq/Sy2uAEhmqL5nPfGYbJOcaqjeYYZoA=
-k8s.io/utils v0.0.0-20240821151609-f90d01438635/go.mod h1:OLgZIPagt7ERELqWJFomSt595RzquPNLL48iOWgYOg0=
+k8s.io/utils v0.0.0-20240902221715-702e33fdd3c3/go.mod h1:OLgZIPagt7ERELqWJFomSt595RzquPNLL48iOWgYOg0=
 rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=
 rsc.io/quote/v3 v3.1.0/go.mod h1:yEA65RcK8LyAZtP9Kv3t0HmxON59tX3rD+tICJqUlj0=
 rsc.io/sampler v1.3.0/go.mod h1:T1hPZKmBbMNahiBKFy5HrXp6adAjACjK9JXDnKaTXpA=

internal/logic/inference/deployinstancelistlogic.go

@@ -38,6 +38,14 @@ func (l *DeployInstanceListLogic) DeployInstanceList(req *types.DeployInstanceLi
 		return nil, tx.Error
 	}
 
+	if len(tasklist) == 0 {
+		resp.List = nil
+		resp.PageSize = req.PageSize
+		resp.PageNum = req.PageNum
+		resp.Total = 0
+		return
+	}
+
 	//count total
 	var total int64
 	err = tx.Count(&total).Error

internal/logic/inference/getdeploytasksbytypelogic.go

@@ -70,12 +70,6 @@ func removeItem(items *[]*models.AiDeployInstanceTask, id int64) {
 	if len(*items) == 0 {
 		return
 	}
-	if len(*items) == 1 {
-		if (*items)[0].Id == id {
-			(*items) = nil
-			return
-		}
-	}
 	for i := len(*items) - 1; i >= 0; i-- {
 		if (*items)[i].Id == id {
 			*items = append((*items)[:i], (*items)[i+1:]...)

internal/logic/inference/startallbydeploytaskidlogic.go

@@ -3,12 +3,15 @@ package inference
 import (
 	"context"
 	"errors"
+	"fmt"
 	"github.com/zeromicro/go-zero/core/logx"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/inference"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/storeLink"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/models"
 	"strconv"
+	"sync"
 )
 
 type StartAllByDeployTaskIdLogic struct {
@@ -35,17 +38,8 @@ func (l *StartAllByDeployTaskIdLogic) StartAllByDeployTaskId(req *types.StartAll
 		return nil, err
 	}
 
-	for _, ins := range list {
+	if len(list) == 0 {
-		in, err := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].GetInferDeployInstance(l.ctx, ins.InstanceId)
+		return nil, errors.New("instances are empty")
-		if err != nil {
-			return nil, err
-		}
-		if checkStopStatus(in) {
-			success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].StartInferDeployInstance(l.ctx, ins.InstanceId)
-			if !success {
-				return nil, errors.New(ins.InstanceName + " start failed")
-			}
-		}
 	}
 
 	err = l.svcCtx.Scheduler.AiStorages.UpdateDeployTaskById(id)
@@ -53,9 +47,96 @@ func (l *StartAllByDeployTaskIdLogic) StartAllByDeployTaskId(req *types.StartAll
 		return nil, err
 	}
 
+	err = l.startAll(list)
+	if err != nil {
+		return nil, err
+	}
+
 	return resp, nil
 }
 
+func (l *StartAllByDeployTaskIdLogic) startAll(list []*models.AiInferDeployInstance) error {
+	var wg sync.WaitGroup
+	var errCh = make(chan interface{}, len(list))
+	var errs []interface{}
+	buf := make(chan bool, 2)
+
+	for _, instance := range list {
+		wg.Add(1)
+		ins := instance
+		buf <- true
+		go func() {
+			in, err := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].GetInferDeployInstance(l.ctx, ins.InstanceId)
+			if err != nil {
+				e := struct {
+					errTyp       uint8
+					err          error
+					instanceName string
+					clusterName  string
+				}{
+					errTyp:       1,
+					err:          err,
+					instanceName: ins.InstanceName,
+					clusterName:  ins.ClusterName,
+				}
+				errCh <- e
+				wg.Done()
+				<-buf
+				return
+			}
+			if checkStopStatus(in) {
+				success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].StartInferDeployInstance(l.ctx, ins.InstanceId)
+				if !success {
+					e := struct {
+						errTyp       uint8
+						err          error
+						instanceName string
+						clusterName  string
+					}{
+						errTyp:       2,
+						err:          err,
+						instanceName: ins.InstanceName,
+						clusterName:  ins.ClusterName,
+					}
+					errCh <- e
+					wg.Done()
+					<-buf
+					return
+				}
+			}
+			wg.Done()
+			<-buf
+		}()
+	}
+	wg.Wait()
+	close(errCh)
+
+	for e := range errCh {
+		errs = append(errs, e)
+	}
+
+	if len(errs) != 0 {
+		var msg string
+		for _, err := range errs {
+			e := (err).(struct {
+				errTyp       uint8
+				err          error
+				instanceName string
+				clusterName  string
+			})
+			switch e.errTyp {
+			case 1:
+				msg += fmt.Sprintf("GetInstance Failed # clusterName: %v , instanceName: %v , error: %v \n", e.clusterName, e.instanceName, e.err.Error())
+			case 2:
+				msg += fmt.Sprintf("StartInstance Failed # clusterName: %v , instanceName: %v , error: %v \n", e.clusterName, e.instanceName, e.err.Error())
+			}
+		}
+		return errors.New(msg)
+	}
+
+	return nil
+}
+
 func checkStopStatus(in *inference.DeployInstance) bool {
 	switch in.ClusterType {
 	case storeLink.TYPE_OCTOPUS:

internal/logic/inference/stopallbydeploytaskidlogic.go

@@ -3,11 +3,14 @@ package inference
 import (
 	"context"
 	"errors"
+	"fmt"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/inference"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/storeLink"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/models"
 	"strconv"
+	"sync"
 
 	"github.com/zeromicro/go-zero/core/logx"
 )
@@ -36,17 +39,8 @@ func (l *StopAllByDeployTaskIdLogic) StopAllByDeployTaskId(req *types.StopAllByD
 		return nil, err
 	}
 
-	for _, ins := range list {
+	if len(list) == 0 {
-		in, err := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].GetInferDeployInstance(l.ctx, ins.InstanceId)
+		return nil, errors.New("instances are empty")
-		if err != nil {
-			return nil, err
-		}
-		if checkStatus(in) {
-			success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].StopInferDeployInstance(l.ctx, ins.InstanceId)
-			if !success {
-				return nil, errors.New(ins.InstanceName + " stop failed")
-			}
-		}
 	}
 
 	err = l.svcCtx.Scheduler.AiStorages.UpdateDeployTaskById(id)
@@ -54,9 +48,96 @@ func (l *StopAllByDeployTaskIdLogic) StopAllByDeployTaskId(req *types.StopAllByD
 		return nil, err
 	}
 
+	err = l.stopAll(list)
+	if err != nil {
+		return nil, err
+	}
+
 	return resp, nil
 }
 
+func (l *StopAllByDeployTaskIdLogic) stopAll(list []*models.AiInferDeployInstance) error {
+	var wg sync.WaitGroup
+	var errCh = make(chan interface{}, len(list))
+	var errs []interface{}
+	buf := make(chan bool, 2)
+
+	for _, instance := range list {
+		wg.Add(1)
+		ins := instance
+		buf <- true
+		go func() {
+			in, err := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].GetInferDeployInstance(l.ctx, ins.InstanceId)
+			if err != nil {
+				e := struct {
+					errTyp       uint8
+					err          error
+					instanceName string
+					clusterName  string
+				}{
+					errTyp:       1,
+					err:          err,
+					instanceName: ins.InstanceName,
+					clusterName:  ins.ClusterName,
+				}
+				errCh <- e
+				wg.Done()
+				<-buf
+				return
+			}
+			if checkStatus(in) {
+				success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].StopInferDeployInstance(l.ctx, ins.InstanceId)
+				if !success {
+					e := struct {
+						errTyp       uint8
+						err          error
+						instanceName string
+						clusterName  string
+					}{
+						errTyp:       2,
+						err:          err,
+						instanceName: ins.InstanceName,
+						clusterName:  ins.ClusterName,
+					}
+					errCh <- e
+					wg.Done()
+					<-buf
+					return
+				}
+			}
+			wg.Done()
+			<-buf
+		}()
+	}
+	wg.Wait()
+	close(errCh)
+
+	for e := range errCh {
+		errs = append(errs, e)
+	}
+
+	if len(errs) != 0 {
+		var msg string
+		for _, err := range errs {
+			e := (err).(struct {
+				errTyp       uint8
+				err          error
+				instanceName string
+				clusterName  string
+			})
+			switch e.errTyp {
+			case 1:
+				msg += fmt.Sprintf("GetInstance Failed # clusterName: %v , instanceName: %v , error: %v \n", e.clusterName, e.instanceName, e.err.Error())
+			case 2:
+				msg += fmt.Sprintf("StopInstance Failed # clusterName: %v , instanceName: %v , error: %v \n", e.clusterName, e.instanceName, e.err.Error())
+			}
+		}
+		return errors.New(msg)
+	}
+
+	return nil
+}
+
 func checkStatus(in *inference.DeployInstance) bool {
 	switch in.ClusterType {
 	case storeLink.TYPE_OCTOPUS:

internal/storeLink/modelarts.go

@@ -16,6 +16,7 @@ package storeLink
 
 import (
 	"context"
+	"fmt"
 	"github.com/pkg/errors"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/schedulers/option"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/collector"
@@ -27,15 +28,19 @@ import (
 	"gitlink.org.cn/JointCloud/pcm-modelarts/client/modelartsservice"
 	"gitlink.org.cn/JointCloud/pcm-modelarts/modelarts"
 	modelartsclient "gitlink.org.cn/JointCloud/pcm-modelarts/modelarts"
+	"log"
 	"mime/multipart"
 	"strconv"
 	"strings"
+	"sync"
 	"time"
 )
 
 const (
-	Ascend = "Ascend"
+	Ascend              = "Ascend"
-	Npu    = "npu"
+	Npu                 = "npu"
+	ImageNetResnet50Cmd = "cd /home/ma-user & python ./inference_ascend.py"
+	ChatGLM6BCmd        = "cd /home/ma-user && python ./download_model.py && python ./inference_chatGLM.py"
 )
 
 type ModelArtsLink struct {
@@ -45,6 +50,60 @@ type ModelArtsLink struct {
 	participantId   int64
 	pageIndex       int32
 	pageSize        int32
+	SourceLocation  string
+	Version         string
+	ModelId         string
+	ModelType       string
+}
+
+// Version 结构体表示版本号
+type Version struct {
+	Major, Minor, Patch int
+}
+
+// ParseVersion 从字符串解析版本号
+func ParseVersion(versionStr string) (*Version, error) {
+	parts := strings.Split(versionStr, ".")
+	if len(parts) != 3 {
+		return nil, fmt.Errorf("invalid version format: %s", versionStr)
+	}
+
+	major, err := strconv.Atoi(parts[0])
+	if err != nil {
+		return nil, err
+	}
+
+	minor, err := strconv.Atoi(parts[1])
+	if err != nil {
+		return nil, err
+	}
+
+	patch, err := strconv.Atoi(parts[2])
+	if err != nil {
+		return nil, err
+	}
+
+	return &Version{Major: major, Minor: minor, Patch: patch}, nil
+}
+
+// Increment 根据给定规则递增版本号
+func (v *Version) Increment() {
+	if v.Patch < 9 {
+		v.Patch++
+	} else {
+		v.Patch = 0
+		if v.Minor < 9 {
+			v.Minor++
+		} else {
+			v.Minor = 0
+			v.Major++
+		}
+	}
+}
+
+// String 将版本号转换回字符串格式
+func (v *Version) String() string {
+	return fmt.Sprintf("%d.%d.%d", v.Major, v.Minor, v.Patch)
 }
 
 func NewModelArtsLink(modelArtsRpc modelartsservice.ModelArtsService, modelArtsImgRpc imagesservice.ImagesService, name string, id int64, nickname string) *ModelArtsLink {
@@ -260,39 +319,142 @@ func (m *ModelArtsLink) UploadAlgorithmCode(ctx context.Context, resourceType st
 	return nil
 }
 
+// Determine whether there is a necessary image in image management and query the image name based on the image name
+func (m *ModelArtsLink) getSourceLocationFromImages(ctx context.Context, option *option.InferOption) error {
+	req := &modelarts.ListImagesReq{
+		//Platform:  m.platform,
+		Limit:  50,
+		Offset: 0,
+	}
+
+	ListImagesResp, err := m.modelArtsRpc.ListImages(ctx, req)
+	if err != nil {
+		return err
+	}
+	if ListImagesResp.Code != 200 {
+		return errors.New("failed to get ListImages")
+	}
+
+	for _, ListImages := range ListImagesResp.Data {
+		if option.ModelName == "ChatGLM-6B" {
+			if ListImages.Name == "chatglm-6b" {
+				m.SourceLocation = ListImages.SwrPath
+				return nil
+			}
+		} else {
+			if ListImages.Name == option.ModelName {
+				m.SourceLocation = ListImages.SwrPath
+				return nil
+			}
+		}
+	}
+	return errors.New("SourceLocation not set")
+}
+
 // Get AI Application List
 func (m *ModelArtsLink) GetModelId(ctx context.Context, option *option.InferOption) error {
 	req := &modelarts.ListModelReq{
 		Platform:  m.platform,
 		ModelName: option.ModelName,
-		ModelType: "Image",
+		//ModelType: "Image",
-		Limit:     int64(m.pageIndex),
+		Limit:  int64(m.pageIndex),
-		Offset:    int64(m.pageSize),
+		Offset: int64(m.pageSize),
 	}
 	ListModelResp, err := m.modelArtsRpc.ListModels(ctx, req)
 	if err != nil {
 		return err
 	}
-	if ListModelResp.Code != 200 {
+	if ListModelResp.Code == 200 {
-		return errors.New("failed to get ModelId")
+		//return errors.New("failed to get ModelId")
-	}
+		for _, ListModel := range ListModelResp.Models {
-	for _, ListModel := range ListModelResp.Models {
+			if ListModel.ModelName == option.ModelName {
-		if ListModel.ModelName == option.ModelName {
+				option.ModelId = ListModel.ModelId
-			option.ModelId = ListModel.ModelId
+				m.Version = ListModel.ModelVersion
-			return nil
+				return nil
+			}
 		}
+
+	}
+	err = m.CreateModel(ctx, option)
+	if err != nil {
+		return err
 	}
 	return nil
 }
 
-// 创建ai应用
+func (m *ModelArtsLink) GetModel(ctx context.Context, option *option.InferOption) string {
+	req := &modelarts.ShowModelReq{
+		Platform: m.platform,
+		ModelId:  option.ModelId,
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), 50*time.Second)
+	defer cancel()
+	ShowModelsResp, err := m.modelArtsRpc.ShowModels(ctx, req)
+	if err != nil {
+		if err == context.DeadlineExceeded {
+			log.Println("Request timed out")
+			// 重试请求或其他处理
+		} else {
+			log.Fatalf("could not call method: %v", err)
+		}
+	}
+	if ShowModelsResp.Code != 200 {
+		errors.New("failed to get findModelsStatus")
+	}
+	m.ModelType = ShowModelsResp.ShowModelDetail.ModelAlgorithm
+	return ShowModelsResp.ShowModelDetail.ModelStatus
+}
+
+// Get AI Application List
+func (m *ModelArtsLink) GetModelStatus(ctx context.Context, option *option.InferOption) error {
+	var wg sync.WaitGroup
+	wg.Add(1)
+	// 使用goroutine进行轮询
+	//defer wg.Done()
+	for {
+		status := m.GetModel(ctx, option)
+		if status == "published" {
+			fmt.Println("Model is now published.")
+			break // 一旦状态变为published，就退出循环
+		}
+		fmt.Println("Waiting for model to be published...")
+		time.Sleep(5 * time.Second) // 等待一段时间后再次检查
+	}
+	// 在这里执行模型状态为published后需要进行的操作
+	fmt.Println("Continuing with the program...")
+	return nil
+}
+
+// Create an AI application
 func (m *ModelArtsLink) CreateModel(ctx context.Context, option *option.InferOption) error {
+	//Before creating an AI application, check if there are any images that can be created
+	err := m.getSourceLocationFromImages(ctx, option)
+	if err != nil { //
+		return errors.New("No image available for creationd")
+	}
+
+	//
+	var CMD string
+	if option.ModelName == "imagenet_resnet50" {
+		CMD = ImageNetResnet50Cmd
+	} else if option.ModelName == "ChatGLM-6B" {
+		CMD = ChatGLM6BCmd
+	}
+
+	if m.Version == "" {
+		m.Version = "0.0.1"
+	}
+	version, err := ParseVersion(m.Version)
+	version.Increment()
 	req := &modelarts.CreateModelReq{
 		Platform:       m.platform,
 		ModelName:      option.ModelName,
-		ModelType:      "PyTorch",
+		ModelType:      "Image",
-		ModelVersion:   "0.0.1",
+		ModelVersion:   version.String(),
-		SourceLocation: "",
+		SourceLocation: m.SourceLocation,
+		InstallType:    []string{"real-time"},
+		Cmd:            CMD,
+		ModelAlgorithm: option.ModelType,
 	}
 	ModelResp, err := m.modelArtsRpc.CreateModel(ctx, req)
 	if err != nil {
@@ -600,6 +762,8 @@ func (m *ModelArtsLink) GetInferDeployInstance(ctx context.Context, id string) (
 	ins.ClusterName = m.platform
 	ins.CreatedTime = string(resp.StartTime)
 	ins.ClusterType = TYPE_MODELARTS
+	ins.ModelName = resp.Config[0].ModelName
+	ins.ModelType = m.ModelType
 	return ins, nil
 }
 
@@ -609,7 +773,12 @@ func (m *ModelArtsLink) GetInferResult(ctx context.Context, url string, file mul
 
 func (m *ModelArtsLink) CreateInferDeployInstance(ctx context.Context, option *option.InferOption) (string, error) {
 
-	err := m.CreateModel(ctx, option)
+	err := m.GetModelId(ctx, option)
+	if err != nil {
+		return "", err
+	}
+
+	err = m.GetModelStatus(ctx, option)
 	if err != nil {
 		return "", err
 	}
@@ -626,8 +795,10 @@ func (m *ModelArtsLink) CreateInferDeployInstance(ctx context.Context, option *o
 		Platform:    m.platform,
 		Config:      configItems,
 		InferType:   "real-time",
-		ServiceName: option.TaskName,
+		ServiceName: option.ModelName + "_" + option.ModelType + "_" + Npu,
 	}
+	ctx, cancel := context.WithTimeout(context.Background(), 150*time.Second)
+	defer cancel()
 	resp, err := m.modelArtsRpc.CreateService(ctx, req)
 	if err != nil {
 		return "", err

internal/storeLink/storeLink.go

@@ -80,7 +80,7 @@ var (
 	}
 	ModelTypeMap = map[string][]string{
 		"image_classification": {"imagenet_resnet50"},
-		"text_to_text":         {"chatGLM_6B"},
+		"text_to_text":         {"ChatGLM-6B"},
 		"image_to_text":        {"blip-image-captioning-base"},
 		"text_to_image":        {"stable-diffusion-xl-base-1.0"},
 	}