[SPARK-25957][K8S] Make building alternate language binding docker im…

…ages optional ## What changes were proposed in this pull request? bin/docker-image-tool.sh tries to build all docker images (JVM, PySpark and SparkR) by default. But not all spark distributions are built with SparkR and hence this script will fail on such distros. With this change, we make building alternate language binding docker images (PySpark and SparkR) optional. User has to specify dockerfile for those language bindings using -p and -R flags accordingly, to build the binding docker images. ## How was this patch tested? Tested following scenarios. *bin/docker-image-tool.sh -r <repo> -t <tag> build* --> Builds only JVM docker image (default behavior) *bin/docker-image-tool.sh -r <repo> -t <tag> -p kubernetes/dockerfiles/spark/bindings/python/Dockerfile build* --> Builds both JVM and PySpark docker images *bin/docker-image-tool.sh -r <repo> -t <tag> -p kubernetes/dockerfiles/spark/bindings/python/Dockerfile -R kubernetes/dockerfiles/spark/bindings/R/Dockerfile build* --> Builds JVM, PySpark and SparkR docker images. Author: Nagaram Prasad Addepally <ram@cloudera.com> Closes apache#23053 from ramaddepally/SPARK-25957.
jkleckner · Aug 23, 2020 · d0f9561 · d0f9561
1 parent e5bef51
commit d0f9561
Show file tree

Hide file tree

Showing 3 changed files with 88 additions and 26 deletions.
diff --git a/bin/docker-image-tool.sh b/bin/docker-image-tool.sh
@@ -41,6 +41,18 @@ function image_ref {
   echo "$image"
 }
 
+function docker_push {
+  local image_name="$1"
+  if [ ! -z $(docker images -q "$(image_ref ${image_name})") ]; then
+    docker push "$(image_ref ${image_name})"
+    if [ $? -ne 0 ]; then
+      error "Failed to push $image_name Docker image."
+    fi
+  else
+    echo "$(image_ref ${image_name}) image not found. Skipping push for this image."
+  fi
+}
+
 function build {
   local BUILD_ARGS
   local IMG_PATH
@@ -72,26 +84,36 @@ function build {
     base_img=$(image_ref spark)
   )
   local BASEDOCKERFILE=${BASEDOCKERFILE:-"$IMG_PATH/spark/Dockerfile"}
-  local PYDOCKERFILE=${PYDOCKERFILE:-"$IMG_PATH/spark/bindings/python/Dockerfile"}
-  local RDOCKERFILE=${RDOCKERFILE:-"$IMG_PATH/spark/bindings/R/Dockerfile"}
+  local PYDOCKERFILE=${PYDOCKERFILE:-false}
+  local RDOCKERFILE=${RDOCKERFILE:-false}
 
   docker build $NOCACHEARG "${BUILD_ARGS[@]}" \
     -t $(image_ref spark) \
     -f "$BASEDOCKERFILE" .
 
-  docker build $NOCACHEARG "${BINDING_BUILD_ARGS[@]}" \
-    -t $(image_ref spark-py) \
-    -f "$PYDOCKERFILE" .
+  if [ "${PYDOCKERFILE}" != "false" ]; then
+    docker build $NOCACHEARG "${BINDING_BUILD_ARGS[@]}" \
+      -t $(image_ref spark-py) \
+      -f "$PYDOCKERFILE" .
+      if [ $? -ne 0 ]; then
+        error "Failed to build PySpark Docker image, please refer to Docker build output for details."
+      fi
+  fi
 
-  docker build $NOCACHEARG "${BINDING_BUILD_ARGS[@]}" \
-    -t $(image_ref spark-r) \
-    -f "$RDOCKERFILE" .
+  if [ "${RDOCKERFILE}" != "false" ]; then
+    docker build $NOCACHEARG "${BINDING_BUILD_ARGS[@]}" \
+      -t $(image_ref spark-r) \
+      -f "$RDOCKERFILE" .
+    if [ $? -ne 0 ]; then
+      error "Failed to build SparkR Docker image, please refer to Docker build output for details."
+    fi
+  fi
 }
 
 function push {
-  docker push "$(image_ref spark)"
-  docker push "$(image_ref spark-py)"
-  docker push "$(image_ref spark-r)"
+  docker_push "spark"
+  docker_push "spark-py"
+  docker_push "spark-r"
 }
 
 function usage {
@@ -106,8 +128,10 @@ Commands:
 
 Options:
   -f file               Dockerfile to build for JVM based Jobs. By default builds the Dockerfile shipped with Spark.
-  -p file               Dockerfile to build for PySpark Jobs. Builds Python dependencies and ships with Spark.
-  -R file               Dockerfile to build for SparkR Jobs. Builds R dependencies and ships with Spark.
+  -p file               (Optional) Dockerfile to build for PySpark Jobs. Builds Python dependencies and ships with Spark.
+                        Skips building PySpark docker image if not specified.
+  -R file               (Optional) Dockerfile to build for SparkR Jobs. Builds R dependencies and ships with Spark.
+                        Skips building SparkR docker image if not specified.
   -r repo               Repository address.
   -t tag                Tag to apply to the built image, or to identify the image to be pushed.
   -m                    Use minikube's Docker daemon.
@@ -127,6 +151,9 @@ Examples:
   - Build image in minikube with tag "testing"
     $0 -m -t testing build
 
+  - Build PySpark docker image
+    $0 -r docker.io/myrepo -t v2.3.0 -p kubernetes/dockerfiles/spark/bindings/python/Dockerfile build
+
   - Build and push image with tag "v2.3.0" to docker.io/myrepo
     $0 -r docker.io/myrepo -t v2.3.0 build
     $0 -r docker.io/myrepo -t v2.3.0 push

diff --git a/docs/running-on-kubernetes.md b/docs/running-on-kubernetes.md
@@ -87,6 +87,18 @@ $ ./bin/docker-image-tool.sh -r <repo> -t my-tag build
 $ ./bin/docker-image-tool.sh -r <repo> -t my-tag push
 ```
 
+By default `bin/docker-image-tool.sh` builds docker image for running JVM jobs. You need to opt-in to build additional 
+language binding docker images.
+
+Example usage is
+```bash
+# To build additional PySpark docker image
+$ ./bin/docker-image-tool.sh -r <repo> -t my-tag -p ./kubernetes/dockerfiles/spark/bindings/python/Dockerfile build
+
+# To build additional SparkR docker image
+$ ./bin/docker-image-tool.sh -r <repo> -t my-tag -R ./kubernetes/dockerfiles/spark/bindings/R/Dockerfile build
+```
+
 ## Cluster Mode
 
 To launch Spark Pi in cluster mode,

diff --git a/resource-managers/kubernetes/integration-tests/scripts/setup-integration-test-env.sh b/resource-managers/kubernetes/integration-tests/scripts/setup-integration-test-env.sh
@@ -71,19 +71,42 @@ if [[ $IMAGE_TAG == "N/A" ]];
 then
   IMAGE_TAG=$(uuidgen);
   cd $UNPACKED_SPARK_TGZ
-  if [[ $DEPLOY_MODE == cloud ]] ;
-  then
-    $UNPACKED_SPARK_TGZ/bin/docker-image-tool.sh -r $IMAGE_REPO -t $IMAGE_TAG build
-    if  [[ $IMAGE_REPO == gcr.io* ]] ;
-    then
-      gcloud docker -- push $IMAGE_REPO/spark:$IMAGE_TAG
-    else
-      $UNPACKED_SPARK_TGZ/bin/docker-image-tool.sh -r $IMAGE_REPO -t $IMAGE_TAG push
-    fi
-  else
-    # -m option for minikube.
-    $UNPACKED_SPARK_TGZ/bin/docker-image-tool.sh -m -r $IMAGE_REPO -t $IMAGE_TAG build
-  fi
+
+  # Build PySpark image
+  LANGUAGE_BINDING_BUILD_ARGS="-p $UNPACKED_SPARK_TGZ/kubernetes/dockerfiles/spark/bindings/python/Dockerfile"
+
+  # Build SparkR image
+  LANGUAGE_BINDING_BUILD_ARGS="$LANGUAGE_BINDING_BUILD_ARGS -R $UNPACKED_SPARK_TGZ/kubernetes/dockerfiles/spark/bindings/R/Dockerfile"
+
+  case $DEPLOY_MODE in
+    cloud)
+      # Build images
+      $UNPACKED_SPARK_TGZ/bin/docker-image-tool.sh -r $IMAGE_REPO -t $IMAGE_TAG $LANGUAGE_BINDING_BUILD_ARGS build
+
+      # Push images appropriately
+      if [[ $IMAGE_REPO == gcr.io* ]] ;
+      then
+        gcloud docker -- push $IMAGE_REPO/spark:$IMAGE_TAG
+      else
+        $UNPACKED_SPARK_TGZ/bin/docker-image-tool.sh -r $IMAGE_REPO -t $IMAGE_TAG push
+      fi
+      ;;
+
+    docker-for-desktop)
+       # Only need to build as this will place it in our local Docker repo which is all
+       # we need for Docker for Desktop to work so no need to also push
+       $UNPACKED_SPARK_TGZ/bin/docker-image-tool.sh -r $IMAGE_REPO -t $IMAGE_TAG $LANGUAGE_BINDING_BUILD_ARGS build
+       ;;
+
+    minikube)
+       # Only need to build and if we do this with the -m option for minikube we will
+       # build the images directly using the minikube Docker daemon so no need to push
+       $UNPACKED_SPARK_TGZ/bin/docker-image-tool.sh -m -r $IMAGE_REPO -t $IMAGE_TAG $LANGUAGE_BINDING_BUILD_ARGS build
+       ;;
+    *)
+       echo "Unrecognized deploy mode $DEPLOY_MODE" && exit 1
+       ;;
+  esac
   cd -
 fi