Add pai pipeline

test/config_test.py

@@ -112,7 +112,7 @@ def run(args):
     parser = argparse.ArgumentParser()
     parser.add_argument("--config", type=str, default=None)
     parser.add_argument("--exclude", type=str, default=None)
-    parser.add_argument("--ts", type=str, choices=['local', 'remote', 'pai', 'kubeflow', 'frameworkcontroller'], default='local')
+    parser.add_argument("--ts", type=str, choices=['local', 'remote', 'pai', 'paiYarn', 'kubeflow', 'frameworkcontroller'], default='local')
     parser.add_argument("--local_gpu", action='store_true')
     parser.add_argument("--preinstall", action='store_true')
     args = parser.parse_args()

test/generate_ts_config.py

@@ -12,7 +12,7 @@ def update_training_service_config(args):
     config = get_yml_content(TRAINING_SERVICE_FILE)
     if args.nni_manager_ip is not None:
         config[args.ts]['nniManagerIp'] = args.nni_manager_ip
-    if args.ts == 'pai':
+    if args.ts == 'paiYarn':
         if args.pai_user is not None:
             config[args.ts]['paiYarnConfig']['userName'] = args.pai_user
         if args.pai_pwd is not None:
@@ -27,6 +27,23 @@ def update_training_service_config(args):
             config[args.ts]['trial']['outputDir'] = args.output_dir
         if args.vc is not None:
             config[args.ts]['trial']['virtualCluster'] = args.vc
+    if args.ts == 'pai':
+        if args.pai_user is not None:
+            config[args.ts]['paiConfig']['userName'] = args.pai_user
+        if args.pai_host is not None:
+            config[args.ts]['paiConfig']['host'] = args.pai_host
+        if args.pai_token is not None:
+            config[args.ts]['paiConfig']['token'] = args.pai_token
+        if args.nni_docker_image is not None:
+            config[args.ts]['trial']['image'] = args.nni_docker_image
+        if args.nniManagerNFSMountPath is not None:
+            config[args.ts]['trial']['nniManagerNFSMountPath'] = args.nni_manager_nfs_mount_path
+        if args.containerNFSMountPath is not None:
+            config[args.ts]['trial']['containerNFSMountPath'] = args.container_nfs_mount_path
+        if args.paiStoragePlugin is not None:
+            config[args.ts]['trial']['paiStoragePlugin'] = args.pai_storage_plugin
+        if args.vc is not None:
+            config[args.ts]['trial']['virtualCluster'] = args.vc
     elif args.ts == 'kubeflow':
         if args.nfs_server is not None:
             config[args.ts]['kubeflowConfig']['nfs']['server'] = args.nfs_server
@@ -94,6 +111,10 @@ def convert_command():
     parser.add_argument("--data_dir", type=str)
     parser.add_argument("--output_dir", type=str)
     parser.add_argument("--vc", type=str)
+    parser.add_argument("--pai_token", type=str)
+    parser.add_argument("--pai_storage_plugin", type=str)
+    parser.add_argument("--nni_manager_nfs_mount_path", type=str)
+    parser.add_argument("--container_nfs_mount_path", type=str)
     # args for kubeflow and frameworkController
     parser.add_argument("--nfs_server", type=str)
     parser.add_argument("--nfs_path", type=str)

test/pipelines-it-pai.yml

@@ -51,9 +51,9 @@ jobs:
 
       echo "TEST_IMG:$TEST_IMG"
       cd test
-      python3 generate_ts_config.py --ts pai --pai_host $(pai_host) --pai_user $(pai_user) --pai_pwd $(pai_pwd) --vc $(pai_virtual_cluster) \
-      --nni_docker_image $TEST_IMG --data_dir $(data_dir) --output_dir $(output_dir) --nni_manager_ip $(nni_manager_ip)
+      python3 generate_ts_config.py --ts pai --pai_host $(pai_host) --pai_user $(pai_user) --nni_docker_image $TEST_IMG --pai_storage_plugin $(pai_storage_plugin)\
+       --pai_token $(pai_token) --nni_manager_nfs_mount_path $(nni_manager_nfs_mount_path) --container_nfs_mount_path $(container_nfs_mount_path) --nni_manager_ip $(nni_manager_ip)
 
-      PATH=$HOME/.local/bin:$PATH python3 config_test.py --ts pai
+      PATH=$HOME/.local/bin:$PATH python3 config_test.py --ts pai --exclude multi_phase
       PATH=$HOME/.local/bin:$PATH python3 metrics_test.py
     displayName: 'integration test'

test/pipelines-it-paiYarn.yml

@@ -0,0 +1,59 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+jobs:
+- job: 'integration_test_paiYarn'
+  timeoutInMinutes: 0
+
+  steps:
+  - script: python3 -m pip install --upgrade pip setuptools --user
+    displayName: 'Install python tools'
+
+  - script: |
+      cd deployment/pypi
+      echo 'building prerelease package...'
+      make build
+      ls $(Build.SourcesDirectory)/deployment/pypi/dist/
+    condition: eq( variables['build_docker_img'], 'true' )
+    displayName: 'build nni bdsit_wheel'
+
+  - script: |
+      source install.sh
+    displayName: 'Install nni toolkit via source code'
+
+  - script: |
+      sudo apt-get install swig -y
+      PATH=$HOME/.local/bin:$PATH nnictl package install --name=SMAC
+      PATH=$HOME/.local/bin:$PATH nnictl package install --name=BOHB
+    displayName: 'Install dependencies for integration tests in PAI mode'
+
+  - script: |
+      set -e
+      if [ $(build_docker_img) = 'true' ]
+      then
+        cd deployment/pypi
+        docker login -u $(docker_hub_user) -p $(docker_hub_pwd)
+        echo 'updating docker file for installing nni from local...'
+        # update Dockerfile to install NNI in docker image from whl file built in last step
+        sed -ie 's/RUN python3 -m pip --no-cache-dir install nni/COPY .\/dist\/* .\nRUN python3 -m pip install nni-*.whl/' ../docker/Dockerfile
+        cat ../docker/Dockerfile
+        export IMG_TAG=`date -u +%y%m%d%H%M`
+
+        echo 'build and upload docker image'
+        docker build -f ../docker/Dockerfile -t $(test_docker_img_name):$IMG_TAG .
+        docker push $(test_docker_img_name):$IMG_TAG
+
+        export TEST_IMG=$(test_docker_img_name):$IMG_TAG
+        cd ../../
+      else
+        export TEST_IMG=$(existing_docker_img)
+      fi
+
+      echo "TEST_IMG:$TEST_IMG"
+      cd test
+      python3 generate_ts_config.py --ts paiYarn --pai_host $(pai_host) --pai_user $(pai_user) --pai_pwd $(pai_pwd) --vc $(pai_virtual_cluster) \
+      --nni_docker_image $TEST_IMG --data_dir $(data_dir) --output_dir $(output_dir) --nni_manager_ip $(nni_manager_ip)
+
+      PATH=$HOME/.local/bin:$PATH python3 config_test.py --ts paiYarn
+      PATH=$HOME/.local/bin:$PATH python3 metrics_test.py
+    displayName: 'integration test'

test/training_service.yml

@@ -52,7 +52,7 @@ frameworkcontroller:
 
 local:
   trainingServicePlatform: local
-pai:
+paiYarn:
   nniManagerIp:
   maxExecDuration: 15m
   paiYarnConfig:
@@ -68,6 +68,21 @@ pai:
     memoryMB: 8192
     outputDir:
     virtualCluster:
+pai:
+  nniManagerIp:
+  maxExecDuration: 15m
+  paiConfig:
+    host:
+    userName:
+  trainingServicePlatform: pai
+  trial:
+    gpuNum: 1
+    cpuNum: 1
+    image:
+    memoryMB: 8192
+    nniManagerNFSMountPath: 
+    containerNFSMountPath: 
+    paiStoragePlugin: 
 remote:
   machineList:
   - ip: