[v1.x] Fix nightly CD for python docker image releases

cd/Jenkinsfile_cd_pipeline

@@ -47,41 +47,29 @@ pipeline {
           cd_utils = load('cd/Jenkinsfile_utils.groovy')
 
           // Update release job state in Jenkins
-          cd_utils.update_release_job_state()
+          cd_utils.update_release_job_state(params.CD_RELEASE_JOB_NAME)
         }
       }
     }
 
     stage("MXNet Release") {
       steps {
         script {
-          cd_utils.error_checked_parallel([
-
-            "Static libmxnet based release": {
-              stage("Build") {
-                cd_utils.trigger_release_job("Build static libmxnet", "mxnet_lib/static", params.MXNET_VARIANTS)    
-              }
-              stage("Releases") {
-                cd_utils.error_checked_parallel([
-                  "PyPI Release": {
-                    echo "Building PyPI Release"
-                    cd_utils.trigger_release_job("Release PyPI Packages", "python/pypi", params.MXNET_VARIANTS)
-                  },
-                  "Python Docker Release": {
-                    echo "Building Python Docker Release"
-                    cd_utils.trigger_release_job("Release Python Docker Images", "python/docker", params.MXNET_VARIANTS)
-                  }
-                ])
-              }
-            },
-
-            "Dynamic libmxnet based release": {
-              stage("Build") {
-                cd_utils.trigger_release_job("Build dynamic libmxnet", "mxnet_lib/dynamic", params.MXNET_VARIANTS)    
+          stage("Build libmxnet") {
+            cd_utils.trigger_release_job(params.CD_RELEASE_JOB_NAME, "Build libmxnet", "mxnet_lib", params.MXNET_VARIANTS)
+          }
+          stage("Releases") {
+            cd_utils.error_checked_parallel([
+              "PyPI Release": {
+                echo "Building PyPI Release"
+                cd_utils.trigger_release_job(params.CD_RELEASE_JOB_NAME, "Release PyPI Packages", "python/pypi", params.MXNET_VARIANTS)
+              },
+              "Python Docker Release": {
+                echo "Building Python Docker Release"
+                cd_utils.trigger_release_job(params.CD_RELEASE_JOB_NAME, "Release Python Docker Images", "python/docker", params.MXNET_VARIANTS)
               }
-            }
-
-          ])
+            ])
+          }
         }
       }
     }

cd/Jenkinsfile_release_job

@@ -42,7 +42,7 @@ pipeline {
     // Using string instead of choice parameter to keep the changes to the parameters minimal to avoid
     // any disruption caused by different COMMIT_ID values chaning the job parameter configuration on
     // Jenkins.
-    string(defaultValue: "mxnet_lib/static", description: "Pipeline to build", name: "RELEASE_JOB_TYPE")
+    string(defaultValue: "mxnet_lib", description: "Pipeline to build", name: "RELEASE_JOB_TYPE")
     string(defaultValue: "cpu,native,cu100,cu101,cu102,cu110,cu112", description: "Comma separated list of variants", name: "MXNET_VARIANTS")
     booleanParam(defaultValue: false, description: 'Whether this is a release build or not', name: "RELEASE_BUILD")
   }
@@ -74,7 +74,7 @@ pipeline {
             |Release Build: ${params.RELEASE_BUILD}
             |Commit Id: ${env.GIT_COMMIT}
             |Branch: ${env.GIT_BRANCH}
-            |Variants: ${env.MXNET_VARIANTS}""".stripMargin()
+            |Variants: ${params.MXNET_VARIANTS}""".stripMargin()
           }
         }
       }
@@ -90,8 +90,7 @@ pipeline {
 
           // Add new job types here
           def valid_job_types = [
-            "mxnet_lib/static",
-            "mxnet_lib/dynamic",
+            "mxnet_lib",
             "python/pypi",
             "python/docker"
           ]

cd/Jenkinsfile_utils.groovy

@@ -19,16 +19,16 @@
 
 // Triggers a downstream jenkins job responsible for building, testing
 // and publishing all the variants for a particular 'job_type'.
-// The 'job_type' should be the name of the directory that contains the 
-// 'Jenkins_pipeline.groovy' file and has the pipeline definition for the 
+// The 'job_type' should be the name of the directory that contains the
+// 'Jenkins_pipeline.groovy' file and has the pipeline definition for the
 // artifact (docker image, binary, pypi or maven package, etc.) that should
 // be published.
 
 STATE_UPDATE="State Update"
 
-def trigger_release_job(job_name, job_type, mxnet_variants) {
+def trigger_release_job(cd_release_job, job_name, job_type, mxnet_variants) {
   def run = build(
-    job: env.CD_RELEASE_JOB_NAME, 
+    job: cd_release_job,
     parameters: [
       string(name: "RELEASE_JOB_NAME", value: "${job_name}"),
       string(name: "RELEASE_JOB_TYPE", value: "${job_type}"),
@@ -49,7 +49,7 @@ def trigger_release_job(job_name, job_type, mxnet_variants) {
   // continue with the pipeline and try to post as many releases as possible
   // but mark it as unstable
   if (result == "UNSTABLE" || result == "ABORTED") {
-    currentBuild.result = "UNSTABLE" 
+    currentBuild.result = "UNSTABLE"
   }
 
   // Throw an exception on failure, because this would mean the whole
@@ -65,12 +65,12 @@ def trigger_release_job(job_name, job_type, mxnet_variants) {
 // the configuration of the release job in jenkins
 // to the configuration of release job as defined in the
 // Jenkinsfile _release_job for env.GIT_COMMIT revision
-def update_release_job_state() {
+def update_release_job_state(cd_release_job) {
   build(
-    job: env.CD_RELEASE_JOB_NAME, 
+    job: cd_release_job,
     parameters: [
       string(name: "RELEASE_JOB_TYPE", value: STATE_UPDATE),
-  
+
       // Should be set to the current git commit
       string(name: "COMMIT_ID", value: "${env.GIT_COMMIT}")
     ])
@@ -103,7 +103,7 @@ def wrap_variant_pipeline_fn(variant_pipeline, total_num_pipelines) {
 // The outcome of the execution of each parallel step will affect
 // the result (SUCCESS, FAILURE, ABORTED, UNSTABLE) of the overall job.
 // If all steps fail or are aborted, the job will be set to failed.
-// If some steps fail or are aborted, the job will be set to unstable. 
+// If some steps fail or are aborted, the job will be set to unstable.
 def error_checked_parallel(variant_pipelines) {
   pipelines = variant_pipelines.inject([:]) { mp, key, value ->
     mp << ["${key}": wrap_variant_pipeline_fn(value, variant_pipelines.size())]
@@ -179,7 +179,7 @@ def restore_dynamic_libmxnet(variant) {
 // NOTE: Be mindful of the expected time that a step should take. If it will take a long time,
 // and it can be done in a CPU node, do it in a CPU node. We should avoid using GPU instances unless
 // we *have* to.
-// However, if it is only packaging libmxnet and that doesn't take long. Then, the pipeline can 
+// However, if it is only packaging libmxnet and that doesn't take long. Then, the pipeline can
 // just run on a single node. As is done bellow.
 // For examples of multi-node CD pipelines, see the the binary_release/static and binary_release/dynamic
 // pipeline.

cd/README.md

@@ -60,7 +60,7 @@ The [release job](Jenkinsfile_release_job) takes five parameters:
  * **RELEASE\_JOB\_TYPE**: Defines the release pipeline you want to execute.
  * **COMMIT_ID**: The commit id to build
 
-The release job executes, in parallel, the release pipeline for each of the variants (**MXNET_VARIANTS**) for the job type (**RELEASE\_JOB\_TYPE**). The job type the path to a directory (relative to the `cd` directory) that includes a `Jenkins_pipeline.groovy` file ([e.g.](mxnet_lib/static/Jenkins_pipeline.groovy)).
+The release job executes, in parallel, the release pipeline for each of the variants (**MXNET_VARIANTS**) for the job type (**RELEASE\_JOB\_TYPE**). The job type the path to a directory (relative to the `cd` directory) that includes a `Jenkins_pipeline.groovy` file ([e.g.](mxnet_lib/Jenkins_pipeline.groovy)).
 
 NOTE: The **COMMIT_ID** is a little tricky and we must be very careful with it. It is necessary to ensure that the same commit is built through out the pipeline, but at the same time, it has the potential to change the current state of the release job configuration - specifically the parameter configuration. Any changes to this configuration will require a "dry-run" of the release job to ensure Jenkins has the current (master) version. This is acceptable as there will be few changes to the parameter configuration for the job, if any at all. But, it's something to keep in mind.
 
@@ -192,4 +192,4 @@ def test(mxnet_variant) {
 
 Examples:
 
-Both the [statically linked libmxnet](mxnet_lib/static/Jenkins_pipeline.groovy) and [dynamically linked libmxnet](mxnet_lib/dynamic/Jenkins_pipeline.groovy) pipelines have long running compilation and testing stages that **do not** require specialized/expensive hardware (e.g. GPUs). Therefore, as much as possible, it is important to run each stage in on its own node, and design the pipeline to spend the least amount of time possible on expensive hardware. E.g. for GPU builds, only run GPU tests on GPU instances, all other stages can be executed on CPU nodes.
+The [libmxnet](mxnet_lib/Jenkins_pipeline.groovy) pipeline has long running compilation and testing stages that **do not** require specialized/expensive hardware (e.g. GPUs). Therefore, as much as possible, it is important to run each stage in on its own node, and design the pipeline to spend the least amount of time possible on expensive hardware. E.g. for GPU builds, only run GPU tests on GPU instances, all other stages can be executed on CPU nodes.

cd/python/docker/Dockerfile

@@ -23,15 +23,14 @@
 ARG BASE_IMAGE
 FROM ${BASE_IMAGE}
 
-RUN apt-get update || true
-RUN apt-get install -y software-properties-common
-RUN add-apt-repository -y ppa:deadsnakes/ppa
-RUN apt-get update || true
-RUN apt-get install -y python3.7-dev python3.7-distutils virtualenv wget
-RUN ln -sf /usr/bin/python3.7 /usr/local/bin/python3
-
-RUN wget -nv https://bootstrap.pypa.io/get-pip.py
-RUN python3 get-pip.py
+RUN apt-get update && \
+    apt-get install -y software-properties-common && \
+    add-apt-repository -y ppa:deadsnakes/ppa && \
+    apt-get update && \
+    apt-get install -y python3.7-dev python3.7-distutils virtualenv wget && \
+    ln -sf /usr/bin/python3.7 /usr/local/bin/python3 && \
+    wget -nv https://bootstrap.pypa.io/get-pip.py && \
+    python3 get-pip.py
 
 ARG MXNET_COMMIT_ID
 ENV MXNET_COMMIT_ID=${MXNET_COMMIT_ID}

cd/python/docker/Dockerfile.test

@@ -23,9 +23,6 @@
 ARG BASE_IMAGE
 FROM ${BASE_IMAGE}
 
-# Install test dependencies
-RUN pip install nose
-
 ARG USER_ID=1001
 ARG GROUP_ID=1001
 

cd/python/docker/python_images.sh

@@ -23,7 +23,7 @@
 
 set -xe
 
-usage="Usage: python_images.sh <build|test|publish> MXNET-VARIANT"
+usage="Usage: python_images.sh <build|test|push> MXNET-VARIANT"
 
 command=${1:?$usage}
 mxnet_variant=${2:?$usage}
@@ -39,8 +39,8 @@ image_name="${repository}:${main_tag}"
 
 resources_path='cd/python/docker'
 
-if [ ! -z "${RELEASE_DOCKERHUB_REPOSITORY}" ]; then
-    image_name="${RELEASE_DOCKERHUB_REPOSITORY}/${image_name}"
+if [ ! -z "${RELEASE_PUBLIC_ECR_REPOSITORY}" ]; then
+    image_name="${RELEASE_PUBLIC_ECR_REPOSITORY}/${image_name}"
 fi
 
 build() {
@@ -57,26 +57,24 @@ test() {
 
     # Ensure the correct context root is passed in when building - Dockerfile.test expects ci directory
     docker build -t "${test_image_name}" --build-arg USER_ID=`id -u` --build-arg GROUP_ID=`id -g` --build-arg BASE_IMAGE="${image_name}" -f ${resources_path}/Dockerfile.test ./ci
-    ./ci/safe_docker_run.py ${runtime_param} --cap-add "SYS_PTRACE" -u `id -u`:`id -g` -v `pwd`:/work/mxnet "${test_image_name}" ${resources_path}/test_python_image.sh "${mxnet_variant}"
 }
 
 push() {
-    if [ -z "${RELEASE_DOCKERHUB_REPOSITORY}" ]; then
-        echo "Cannot publish image without RELEASE_DOCKERHUB_REPOSITORY environment variable being set."
+    if [ -z "${RELEASE_PUBLIC_ECR_REPOSITORY}" ]; then
+        echo "Cannot publish image without RELEASE_PUBLIC_ECR_REPOSITORY environment variable being set."
         exit 1
     fi
 
-    # The secret name env var is set in the Jenkins configuration
-    # Manage Jenkins -> Configure System
-    ./${ci_utils}/docker_login.py --secret-name "${RELEASE_DOCKERHUB_SECRET_NAME}"
+    # Retrieve an authentication token and authenticate Docker client to registry
+    aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/w6z5f7h2
 
     # Push image
     docker push "${image_name}"
 
     # Iterate over remaining tags, if any
     for ((i=1;i<${#docker_tags[@]};i++)); do
         local docker_tag="${docker_tags[${i}]}"
-        local latest_image_name="${RELEASE_DOCKERHUB_REPOSITORY}/${repository}:${docker_tag}_py3"
+        local latest_image_name="${RELEASE_PUBLIC_ECR_REPOSITORY}/${repository}:${docker_tag}_py3"
 
         docker tag "${image_name}" "${latest_image_name}"
         docker push "${latest_image_name}"

cd/utils/docker_tag.sh

@@ -21,7 +21,7 @@
 
 mxnet_variant=${1:?"Please specify the mxnet variant as the first parameter"}
 is_release=${RELEASE_BUILD:-false}
-version=${VERSION:-nightly}
+version=${VERSION:-nightly_v1.x}
 
 # The docker tags will be in the form <version>_<hardware>(_mkl)
 # Eg. nightly_cpu, 1.4.0_cpu_mkl, nightly_gpu_cu80_mkl, etc.

cd/utils/mxnet_base_image.sh

@@ -22,25 +22,25 @@ mxnet_variant=${1:?"Please specify the mxnet variant as the first parameter"}
 
 case ${mxnet_variant} in
     cu100*)
-    echo "nvidia/cuda:10.0-cudnn7-runtime-ubuntu16.04"
+    echo "nvidia/cuda:10.0-cudnn7-runtime-ubuntu18.04"
     ;;
     cu101*)
-    echo "nvidia/cuda:10.1-cudnn7-runtime-ubuntu16.04"
+    echo "nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04"
     ;;
     cu102*)
-    echo "nvidia/cuda:10.2-cudnn7-runtime-ubuntu16.04"
+    echo "nvidia/cuda:10.2-cudnn7-runtime-ubuntu18.04"
     ;;
     cu110*)
-    echo "nvidia/cuda:11.0-cudnn8-runtime-ubuntu16.04"
+    echo "nvidia/cuda:11.0-cudnn8-runtime-ubuntu18.04"
     ;;
     cu112*)
-    echo "nvidia/cuda:11.2.1-cudnn8-runtime-ubuntu16.04"
+    echo "nvidia/cuda:11.2.1-cudnn8-runtime-ubuntu18.04"
     ;;
     cpu)
-    echo "ubuntu:16.04"
+    echo "ubuntu:18.04"
     ;;
     native)
-    echo "ubuntu:16.04"
+    echo "ubuntu:18.04"
     ;;
     *)
     echo "Error: Unrecognized mxnet-variant: '${mxnet_variant}'"