Validate Docker version in CI. (#26496)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26496

It is a BAD BAD idea to deploy Docker versions which are not deployed
(per ossci-job-dsl) because those versions will get GC'ed after two
weeks.  At the moment, there is no verification that your Docker version
is deployed.  This adds an Azure job to check this.

Signed-off-by: Edward Z. Yang <ezyang@fb.com>

Test Plan: Imported from OSS

Differential Revision: D17575100

Pulled By: ezyang

fbshipit-source-id: 8df2331c6e6899c585bc2917b55e8955908b0e4a

.circleci/validate-docker-version.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+
+import urllib.request
+import re
+
+import cimodel.data.pytorch_build_definitions as pytorch_build_definitions
+import cimodel.data.caffe2_build_definitions as caffe2_build_definitions
+
+RE_VERSION = re.compile(r'allDeployedVersions = "([0-9,]+)"')
+
+URL_TEMPLATE = (
+    "https://raw.githubusercontent.com/pytorch/ossci-job-dsl/"
+    "master/src/main/groovy/ossci/{}/DockerVersion.groovy"
+)
+
+def check_version(job, expected_version):
+    url = URL_TEMPLATE.format(job)
+    with urllib.request.urlopen(url) as f:
+        contents = f.read().decode('utf-8')
+        m = RE_VERSION.search(contents)
+        if not m:
+            raise RuntimeError(
+                "Unbelievable! I could not find the variable allDeployedVersions in "
+                "{}; did the organization of ossci-job-dsl change?\n\nFull contents:\n{}"
+                .format(url, contents)
+            )
+        valid_versions = [int(v) for v in m.group(1).split(',')]
+        if expected_version not in valid_versions:
+            raise RuntimeError(
+                "We configured {} to use Docker version {}; but this "
+                "version is not deployed in {}.  Non-deployed versions will be "
+                "garbage collected two weeks after they are created.  DO NOT LAND "
+                "THIS TO MASTER without also updating ossci-job-dsl with this version."
+                "\n\nDeployed versions: {}"
+                .format(job, expected_version, url, m.group(1))
+            )
+
+def validate_docker_version():
+    check_version('pytorch', pytorch_build_definitions.DOCKER_IMAGE_VERSION)
+    check_version('caffe2', caffe2_build_definitions.DOCKER_IMAGE_VERSION)
+
+
+if __name__ == "__main__":
+    validate_docker_version()

azure-pipelines.yml

@@ -13,6 +13,16 @@ jobs:
   - script: pip install -r requirements.txt
   - script: cd .circleci && ./ensure-consistency.py
 
+- job: validate_docker_version
+  displayName: "Ensure Docker version is correctly deployed"
+  pool:
+    vmImage: 'Ubuntu 16.04'
+  steps:
+  - task: UsePythonVersion@0
+    inputs:
+      versionSpec: "3.7"
+  - script: .circleci/validate-docker-version.py
+
 - job: shellcheck_jenkins
   displayName: "Shellcheck Jenkins scripts"
   pool: