run on aws batch

.github/workflow_scripts/pytest_check.sh

@@ -0,0 +1,5 @@
+cd ../..
+
+set -ex
+
+python3 -m pytest test_main.py -v

.github/workflows/bk_ci_githubhost.yml

@@ -0,0 +1,30 @@
+name: continuous_integration
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+    - name: Install dependencies
+      run: |
+        python -m venv venv
+        source venv/bin/activate
+        pip install pytest
+        pip install -r requirements.txt
+      env:
+        CI: true
+    - name: Run tests
+      run: |
+        source venv/bin/activate
+        python -m pytest test_main.py -v

.github/workflows/continuous_integration.yml

@@ -6,25 +6,39 @@ on:
       - main
   pull_request:
 
+# All test scripts split in individual .sh files and moved to .github/workflow scripts
+env:
+  COMMAND-PYTEST: bash ./pytest_check.sh
+
+
 jobs:
-  test:
+  pytest_check:
+    if: ${{ github.event.label.name != 'draft' }}
     runs-on: ubuntu-latest
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v2
-    - name: Set up Python
-      uses: actions/setup-python@v2
+    - name: Configure AWS Credentials
+      uses: aws-actions/configure-aws-credentials@v1
+      with:
+        role-to-assume: arn:aws:iam::801250864718:role/github-oidc-role
+        aws-region: us-west-2
+    - name: Checkout repository
+      uses: actions/checkout@v3
+    - name: Set up Python 3.x
+      uses: actions/setup-python@v4
       with:
-        python-version: '3.9'
+        python-version: '3.x'
     - name: Install dependencies
+      shell: bash
       run: |
-        python -m venv venv
-        source venv/bin/activate
-        pip install pytest
-        pip install -r requirements.txt
-      env:
-        CI: true
-    - name: Run tests
+        python3 -m pip install --upgrade pip
+        python3 -m pip install pytest
+        pip3 install boto3
+    - name: Submit Job
+      shell: bash
       run: |
-        source venv/bin/activate
-        python -m pytest test_main.py -v
+        echo "Start submitting job - Check"  
+        python3 ./submitJob.py --job-type CI-CPU --name hello_DGL-pytest-check-'${{ github.ref }}' \
+                               --command "${{ env.COMMAND-PYTEST }}" \
+                               --remote https://github.com/'${{ github.repository }}' \
+                               --source-ref '${{ github.ref }}' \
+                               --wait

submitJob.py

@@ -0,0 +1,148 @@
+# script to submit jobs to AWS Batch, queues and definitions are already existing and set up 
+import argparse
+import random
+import re
+import sys
+import time
+from datetime import datetime
+
+import boto3
+from botocore.compat import total_seconds
+from botocore.config import Config
+
+
+job_type_info = {
+    'CI-CPU': {
+        'job_definition': 'hello_dgl',
+        'job_queue': 'hello_dgl',
+    },
+}
+
+parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+parser.add_argument('--profile', help='profile name of aws account.', type=str,
+                    default=None)
+parser.add_argument('--region', help='Default region when creating new connections', type=str,
+                    default='us-west-2')
+parser.add_argument('--name', help='name of the job', type=str, default='dummy')
+parser.add_argument('--job-type', help='type of job to submit.', type=str,
+                    choices=job_type_info.keys(), default='CI-CPU')
+parser.add_argument('--command', help='command to run', type=str,
+                    default='git rev-parse HEAD | tee stdout.log')
+parser.add_argument('--wait', help='block wait until the job completes. '
+                    'Non-zero exit code if job fails.', action='store_true')
+parser.add_argument('--timeout', help='job timeout in seconds', default=10800, type=int)
+
+parser.add_argument('--source-ref',
+                    help='ref in hello_DGL main github. e.g. master, refs/pull/500/head',
+                    type=str, default='main')
+parser.add_argument('--remote',
+                    help='git repo address. https://github.com/dglai/hello_dgl.git',
+                    type=str, default="https://github.com/dglai/hello_dgl.git")
+
+args = parser.parse_args()
+
+
+session = boto3.Session(profile_name=args.profile, region_name=args.region)
+config = Config(
+    retries = dict(
+        max_attempts = 5
+    )
+)
+
+batch, cloudwatch = [session.client(service_name=sn, config=config) for sn in ['batch', 'logs']]
+
+def printLogs(logGroupName, logStreamName, startTime):
+    kwargs = {'logGroupName': logGroupName,
+              'logStreamName': logStreamName,
+              'startTime': startTime,
+              'startFromHead': True}
+
+    lastTimestamp = startTime - 1
+    while True:
+        logEvents = cloudwatch.get_log_events(**kwargs)
+
+        for event in logEvents['events']:
+            lastTimestamp = event['timestamp']
+            timestamp = datetime.utcfromtimestamp(lastTimestamp / 1000.0).isoformat()
+            print('[{}] {}'.format((timestamp + '.000')[:23] + 'Z', event['message']))
+
+        nextToken = logEvents['nextForwardToken']
+        if nextToken and kwargs.get('nextToken') != nextToken:
+            kwargs['nextToken'] = nextToken
+        else:
+            break
+    return lastTimestamp
+
+
+def nowInMillis():
+    endTime = int(total_seconds(datetime.utcnow() - datetime(1970, 1, 1))) * 1000
+    return endTime
+
+
+def main():
+    spin = ['-', '/', '|', '\\', '-', '/', '|', '\\']
+    logGroupName = '/aws/batch/job' # This is the group where aws batch logs are stored in Cloudwatch
+
+    jobName = re.sub('[^A-Za-z0-9_\-]', '', args.name)[:128]  # Enforce AWS Batch jobName rules
+    jobType = args.job_type
+    jobQueue = job_type_info[jobType]['job_queue']
+    jobDefinition = job_type_info[jobType]['job_definition']
+    wait = args.wait
+
+    # Printing actions parameters
+    print("GitHub SourceRef: ", args.source_ref)
+    print("GitHub Remote: ", args.remote)
+
+    parameters = {
+        'COMMAND': f"\"{args.command}\"",  # wrap command with double quotation mark, so that batch can treat it as a single command
+        'SOURCE_REF': args.source_ref,
+        'REMOTE': args.remote,
+    }
+    kwargs = dict(
+        jobName=jobName,
+        jobQueue=jobQueue,
+        jobDefinition=jobDefinition,
+        parameters=parameters,
+    )
+    if args.timeout is not None:
+        kwargs['timeout'] = {'attemptDurationSeconds': args.timeout}
+    submitJobResponse = batch.submit_job(**kwargs)
+
+    jobId = submitJobResponse['jobId']
+    print('Submitted job [{} - {}] to the job queue [{}]'.format(jobName, jobId, jobQueue))
+
+    spinner = 0
+    running = False
+    status_set = set()
+    startTime = 0
+    logStreamName = None
+    while wait:
+        time.sleep(10)  # Wait for 10 seconds to fetch job data from batch service
+        describeJobsResponse = batch.describe_jobs(jobs=[jobId])
+        status = describeJobsResponse['jobs'][0]['status']
+        if status == 'SUCCEEDED' or status == 'FAILED':
+            if logStreamName:
+                startTime = printLogs(logGroupName, logStreamName, startTime) + 1
+            print('=' * 80)
+            print('Job [{} - {}] {}'.format(jobName, jobId, status))
+            sys.exit(status == 'FAILED')
+
+        elif status == 'RUNNING':
+            logStreamName = describeJobsResponse['jobs'][0]['container']['logStreamName']
+            if not running:
+                running = True
+                print('\rJob [{}, {}] is RUNNING.'.format(jobName, jobId))
+                if logStreamName:
+                    print('Output [{}]:\n {}'.format(logStreamName, '=' * 80))
+            if logStreamName:
+                startTime = printLogs(logGroupName, logStreamName, startTime) + 1
+        elif status not in status_set:
+            status_set.add(status)
+            print('\rJob [%s - %s] is %-9s... %s' % (jobName, jobId, status, spin[spinner % len(spin)]),)
+            sys.stdout.flush()
+            spinner += 1
+
+
+if __name__ == '__main__':
+    main()