[CI] Use precise terminology for image components

.github/workflows/jvm_tests.yml

@@ -247,10 +247,10 @@ jobs:
       matrix:
         variant:
           - name: cpu
-            container_id: xgb-ci.jvm
+            image_repo: xgb-ci.jvm
             artifact_from: build-test-jvm-packages
           - name: gpu
-            container_id: xgb-ci.jvm_gpu_build
+            image_repo: xgb-ci.jvm_gpu_build
             artifact_from: build-jvm-gpu
         scala_version: ['2.12', '2.13']
     steps:
@@ -272,4 +272,4 @@ jobs:
       - name: Deploy JVM packages to S3
         run: |
           bash ops/pipeline/deploy-jvm-packages.sh ${{ matrix.variant.name }} \
-            ${{ matrix.variant.container_id }} ${{ matrix.scala_version }}
+            ${{ matrix.variant.image_repo }} ${{ matrix.scala_version }}

.github/workflows/main.yml

@@ -220,22 +220,22 @@ jobs:
       matrix:
         include:
           - description: single-gpu
-            container: xgb-ci.gpu
+            image_repo: xgb-ci.gpu
             suite: gpu
             runner: linux-amd64-gpu
             artifact_from: build-cuda
           - description: multiple-gpu
-            container: xgb-ci.gpu
+            image_repo: xgb-ci.gpu
             suite: mgpu
             runner: linux-amd64-mgpu
             artifact_from: build-cuda
           - description: cpu-amd64
-            container: xgb-ci.cpu
+            image_repo: xgb-ci.cpu
             suite: cpu
             runner: linux-amd64-cpu
             artifact_from: build-cuda
           - description: cpu-arm64
-            container: xgb-ci.aarch64
+            image_repo: xgb-ci.aarch64
             suite: cpu-arm64
             runner: linux-arm64-cpu
             artifact_from: build-cpu-arm64
@@ -257,4 +257,4 @@ jobs:
           mv -v wheelhouse/xgboost .
           chmod +x ./xgboost
       - name: Run Python tests, ${{ matrix.description }}
-        run: bash ops/pipeline/test-python-wheel.sh ${{ matrix.suite }} ${{ matrix.container }}
+        run: bash ops/pipeline/test-python-wheel.sh ${{ matrix.suite }} ${{ matrix.image_repo }}

doc/contrib/ci.rst

@@ -44,16 +44,17 @@ To make changes to the CI container, carry out the following steps:
 4. Submit a pull request to `dmlc/xgboost-devops <https://github.com/dmlc/xgboost-devops>`_ with
    the proposed changes to the Dockerfile. Make note of the pull request number. Example: ``#204``
 5. Clone `dmlc/xgboost <https://github.com/dmlc/xgboost>`_ and update all references to the
-   old container to point to the new container. More specifically, all Docker tags of format
-   ``492475357299.dkr.ecr.us-west-2.amazonaws.com/[container_id]:main`` should have the last
-   component replaced with ``PR-#``, where ``#`` is the pull request number. For the example above,
+   old container to point to the new container. More specifically, all container image URIs of form
+   ``492475357299.dkr.ecr.us-west-2.amazonaws.com/[image_repo]:main`` should have its image tag
+   (last component) replaced with ``PR-#``, where ``#`` is the pull request number.
+   For the example above,
    we'd replace ``492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main`` with
    ``492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:PR-204``.
 6. Now submit a pull request to `dmlc/xgboost <https://github.com/dmlc/xgboost>`_. The CI will
    run tests using the new container. Verify that all tests pass.
 7. Merge the pull request in ``dmlc/xgboost-devops``. Wait until the CI completes on the ``main`` branch.
-8. Go back to the the pull request for ``dmlc/xgboost`` and change the container references back
-   to ``:main``.
+8. Go back to the the pull request for ``dmlc/xgboost`` and revise all the container references to use
+   the old tag ``:main``.
 9. Merge the pull request in ``dmlc/xgboost``.
 
 .. _build_run_docker_locally:
@@ -83,11 +84,12 @@ and invoke ``containers/docker_build.sh`` as follows:
   # For local testing, set them to "main"
   export GITHUB_SHA="main"
   export BRANCH_NAME="main"
-  bash containers/docker_build.sh CONTAINER_ID
+  bash containers/docker_build.sh IMAGE_REPO
 
-where ``CONTAINER_ID`` identifies for the container. The wrapper script will look up the YAML file
-``containers/ci_container.yml``. For example, when ``CONTAINER_ID`` is set to ``xgb-ci.gpu``,
-the script will use the corresponding entry from ``containers/ci_container.yml``:
+where ``IMAGE_REPO`` is the name of the container image. The wrapper script will look up the
+YAML file ``containers/ci_container.yml``. For example, when ``IMAGE_REPO`` is set to
+``xgb-ci.gpu``, the script will use the corresponding entry from
+``containers/ci_container.yml``:
 
 .. code-block:: yaml
 
@@ -113,10 +115,11 @@ the build arguments are:
 
 The build arguments provide inputs to the ``ARG`` instructions in the Dockerfile.
 
-When ``containers/docker_build.sh`` completes, you will have access to the container with tag
-``492475357299.dkr.ecr.us-west-2.amazonaws.com/[container_id]:main``. The prefix
-``492475357299.dkr.ecr.us-west-2.amazonaws.com/`` was added so that the container could
-later be uploaded to AWS Elastic Container Registry (ECR), a private Docker registry.
+When ``containers/docker_build.sh`` completes, you will have access to the container with the
+(fully qualified) URI ``492475357299.dkr.ecr.us-west-2.amazonaws.com/[image_repo]:main``.
+The prefix ``492475357299.dkr.ecr.us-west-2.amazonaws.com/`` was added so that
+the container could later be uploaded to AWS Elastic Container Registry (ECR),
+a private Docker registry.
 
 -----------------------------------------
 To run commands within a Docker container
@@ -126,7 +129,7 @@ Invoke ``ops/docker_run.py`` from the main ``dmlc/xgboost`` repo as follows:
 .. code-block:: bash
 
   python3 ops/docker_run.py \
-    --container-tag 492475357299.dkr.ecr.us-west-2.amazonaws.com/[container_id]:main \
+    --image-uri 492475357299.dkr.ecr.us-west-2.amazonaws.com/[image_repo]:[image_tag] \
     [--use-gpus] \
     -- "command to run inside the container"
 
@@ -138,12 +141,12 @@ For example:
 
   # Run without GPU
   python3 ops/docker_run.py \
-    --container-tag 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.cpu:main \
+    --image-uri 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.cpu:main \
     -- bash ops/pipeline/build-cpu-impl.sh cpu
 
   # Run with NVIDIA GPU
   python3 ops/docker_run.py \
-    --container-tag 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
+    --image-uri 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
     --use-gpus \
     -- bash ops/pipeline/test-python-wheel-impl.sh gpu
 
@@ -154,7 +157,7 @@ Optionally, you can specify ``--run-args`` to pass extra arguments to ``docker r
   # Allocate extra space in /dev/shm to enable NCCL
   # Also run the container with elevated privileges
   python3 ops/docker_run.py \
-    --container-tag 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
+    --image-uri 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
     --use-gpus \
     --run-args='--shm-size=4g --privileged' \
     -- bash ops/pipeline/test-python-wheel-impl.sh gpu
@@ -171,7 +174,7 @@ Examples: useful tasks for local development
 
     export DOCKER_REGISTRY=492475357299.dkr.ecr.us-west-2.amazonaws.com
     python3 ops/docker_run.py \
-      --container-tag ${DOCKER_REGISTRY}/xgb-ci.gpu_build_rockylinux8:main \
+      --image-uri ${DOCKER_REGISTRY}/xgb-ci.gpu_build_rockylinux8:main \
       -- ops/pipeline/build-cuda-impl.sh
 
 * Run Python tests
@@ -180,7 +183,7 @@ Examples: useful tasks for local development
 
     export DOCKER_REGISTRY=492475357299.dkr.ecr.us-west-2.amazonaws.com
     python3 ops/docker_run.py \
-      --container-tag ${DOCKER_REGISTRY}/xgb-ci.cpu:main \
+      --image-uri ${DOCKER_REGISTRY}/xgb-ci.cpu:main \
       -- ops/pipeline/test-python-wheel-impl.sh cpu
 
 * Run Python tests with GPU algorithm
@@ -189,7 +192,7 @@ Examples: useful tasks for local development
 
     export DOCKER_REGISTRY=492475357299.dkr.ecr.us-west-2.amazonaws.com
     python3 ops/docker_run.py \
-      --container-tag ${DOCKER_REGISTRY}/xgb-ci.gpu:main \
+      --image-uri ${DOCKER_REGISTRY}/xgb-ci.gpu:main \
       --use-gpus \
       -- ops/pipeline/test-python-wheel-impl.sh gpu
 
@@ -199,7 +202,7 @@ Examples: useful tasks for local development
 
     export DOCKER_REGISTRY=492475357299.dkr.ecr.us-west-2.amazonaws.com
     python3 ops/docker_run.py \
-      --container-tag ${DOCKER_REGISTRY}/xgb-ci.gpu:main \
+      --image-uri ${DOCKER_REGISTRY}/xgb-ci.gpu:main \
       --use-gpus \
       --run-args='--shm-size=4g' \
       -- ops/pipeline/test-python-wheel-impl.sh mgpu
@@ -212,7 +215,7 @@ Examples: useful tasks for local development
     export DOCKER_REGISTRY=492475357299.dkr.ecr.us-west-2.amazonaws.com
     export SCALA_VERSION=2.12  # Specify Scala version (2.12 or 2.13)
     python3 ops/docker_run.py \
-      --container-tag ${DOCKER_REGISTRY}/xgb-ci.jvm:main \
+      --image-uri ${DOCKER_REGISTRY}/xgb-ci.jvm:main \
       --run-args "-e SCALA_VERSION" \
       -- ops/pipeline/build-test-jvm-packages-impl.sh
 
@@ -224,7 +227,7 @@ Examples: useful tasks for local development
     export SCALA_VERSION=2.12  # Specify Scala version (2.12 or 2.13)
     export USE_CUDA=1
     python3 ops/docker_run.py \
-      --container-tag ${DOCKER_REGISTRY}/xgb-ci.jvm_gpu_build:main \
+      --image-uri ${DOCKER_REGISTRY}/xgb-ci.jvm_gpu_build:main \
       --use-gpus \
       --run-args "-e SCALA_VERSION -e USE_CUDA --shm-size=4g" \
       -- ops/pipeline/build-test-jvm-packages-impl.sh
@@ -456,7 +459,7 @@ For example, when you run ``bash containers/docker_build.sh xgb-ci.gpu``, the lo
 
   # docker_build.sh calls docker_build.py...
   python3 containers/docker_build.py --container-def gpu \
-    --container-tag 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
+    --image-uri 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
     --build-arg CUDA_VERSION_ARG=12.4.1 --build-arg NCCL_VERSION_ARG=2.23.4-1 \
     --build-arg RAPIDS_VERSION_ARG=24.10
 
@@ -480,14 +483,14 @@ Here is an example with ``docker_run.py``:
 
   # Run without GPU
   python3 ops/docker_run.py \
-    --container-tag 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.cpu:main \
+    --image-uri 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.cpu:main \
     -- bash ops/pipeline/build-cpu-impl.sh cpu
 
   # Run with NVIDIA GPU
   # Allocate extra space in /dev/shm to enable NCCL
   # Also run the container with elevated privileges
   python3 ops/docker_run.py \
-    --container-tag 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
+    --image-uri 492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main \
     --use-gpus \
     --run-args='--shm-size=4g --privileged' \
     -- bash ops/pipeline/test-python-wheel-impl.sh gpu

ops/docker_run.py

@@ -53,7 +53,7 @@ def fancy_print_cli_args(*, cli_args: list[str]) -> None:
 
 def docker_run(
     *,
-    container_tag: str,
+    image_uri: str,
     command_args: list[str],
     use_gpus: bool,
     workdir: pathlib.Path,
@@ -71,7 +71,7 @@ def docker_run(
         itertools.chain.from_iterable([["-e", f"{k}={v}"] for k, v in user_ids.items()])
     )
     docker_run_cli_args.extend(extra_args)
-    docker_run_cli_args.append(container_tag)
+    docker_run_cli_args.append(image_uri)
     docker_run_cli_args.extend(command_args)
 
     cli_args = ["docker", "run"] + docker_run_cli_args
@@ -90,7 +90,7 @@ def main(*, args: argparse.Namespace) -> None:
         run_args.append("-it")
 
     docker_run(
-        container_tag=args.container_tag,
+        image_uri=args.image_uri,
         command_args=args.command_args,
         use_gpus=args.use_gpus,
         workdir=args.workdir,
@@ -102,18 +102,18 @@ def main(*, args: argparse.Namespace) -> None:
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(
         usage=(
-            f"{sys.argv[0]} --container-tag CONTAINER_TAG [--use-gpus] [--interactive] "
+            f"{sys.argv[0]} --image-uri IMAGE_URI [--use-gpus] [--interactive] "
             "[--workdir WORKDIR] [--run-args RUN_ARGS] -- COMMAND_ARG "
             "[COMMAND_ARG ...]"
         ),
         description="Run tasks inside a Docker container",
     )
     parser.add_argument(
-        "--container-tag",
+        "--image-uri",
         type=str,
         required=True,
         help=(
-            "Container tag to identify the container, e.g. "
+            "Fully qualified image URI to identify the container, e.g. "
             "492475357299.dkr.ecr.us-west-2.amazonaws.com/xgb-ci.gpu:main"
         ),
     )

ops/pipeline/build-cpu-arm64.sh

@@ -13,17 +13,17 @@ source ops/pipeline/classify-git-branch.sh
 source ops/pipeline/get-docker-registry-details.sh
 
 WHEEL_TAG=manylinux_2_28_aarch64
-CONTAINER_TAG=${DOCKER_REGISTRY_URL}/xgb-ci.aarch64:main
+IMAGE_URI=${DOCKER_REGISTRY_URL}/xgb-ci.aarch64:main
 
 echo "--- Build CPU code targeting ARM64"
 set -x
 python3 ops/docker_run.py \
-  --container-tag ${CONTAINER_TAG} \
+  --image-uri ${IMAGE_URI} \
   -- ops/pipeline/build-cpu-arm64-impl.sh
 
 echo "--- Audit binary wheel to ensure it's compliant with ${WHEEL_TAG} standard"
 python3 ops/docker_run.py \
-  --container-tag ${CONTAINER_TAG} \
+  --image-uri ${IMAGE_URI} \
   -- auditwheel repair --only-plat \
   --plat ${WHEEL_TAG} python-package/dist/*.whl
 python3 -m wheel tags --python-tag py3 --abi-tag none --platform ${WHEEL_TAG} --remove \

ops/pipeline/build-cpu.sh

@@ -6,7 +6,7 @@ set -euo pipefail
 source ops/pipeline/classify-git-branch.sh
 source ops/pipeline/get-docker-registry-details.sh
 
-CONTAINER_TAG=${DOCKER_REGISTRY_URL}/xgb-ci.cpu:main
+IMAGE_URI=${DOCKER_REGISTRY_URL}/xgb-ci.cpu:main
 
 echo "--- Build CPU code"
 set -x
@@ -24,13 +24,13 @@ export UBSAN_OPTIONS='print_stacktrace=1:log_path=ubsan_error.log'
 # Work around https://github.com/google/sanitizers/issues/1614
 sudo sysctl vm.mmap_rnd_bits=28
 python3 ops/docker_run.py \
-  --container-tag ${CONTAINER_TAG} \
+  --image-uri ${IMAGE_URI} \
   --run-args '-e ASAN_SYMBOLIZER_PATH -e ASAN_OPTIONS -e UBSAN_OPTIONS
     --cap-add SYS_PTRACE' \
   -- bash ops/pipeline/build-cpu-impl.sh cpu-sanitizer
 
 # Test without sanitizer
 rm -rf build/
 python3 ops/docker_run.py \
-  --container-tag ${CONTAINER_TAG} \
+  --image-uri ${IMAGE_URI} \
   -- bash ops/pipeline/build-cpu-impl.sh cpu

ops/pipeline/build-cuda.sh

@@ -11,10 +11,10 @@ fi
 
 if [[ "$#" -lt 2 ]]
 then
-  echo "Usage: $0 [container_id] {enable-rmm,disable-rmm}"
+  echo "Usage: $0 [image_repo] {enable-rmm,disable-rmm}"
   exit 2
 fi
-container_id="$1"
+image_repo="$1"
 rmm_flag="$2"
 
 # Validate RMM flag
@@ -35,8 +35,8 @@ source ops/pipeline/classify-git-branch.sh
 source ops/pipeline/get-docker-registry-details.sh
 
 WHEEL_TAG=manylinux_2_28_x86_64
-BUILD_CONTAINER_TAG="${DOCKER_REGISTRY_URL}/${container_id}:main"
-MANYLINUX_CONTAINER_TAG="${DOCKER_REGISTRY_URL}/xgb-ci.${WHEEL_TAG}:main"
+BUILD_IMAGE_URI="${DOCKER_REGISTRY_URL}/${image_repo}:main"
+MANYLINUX_IMAGE_URI="${DOCKER_REGISTRY_URL}/xgb-ci.${WHEEL_TAG}:main"
 
 echo "--- Build with CUDA"
 
@@ -57,13 +57,13 @@ fi
 set -x
 
 python3 ops/docker_run.py \
-  --container-tag ${BUILD_CONTAINER_TAG} \
+  --image-uri ${BUILD_IMAGE_URI} \
   --run-args='-e BUILD_ONLY_SM75 -e USE_RMM' \
   -- ops/pipeline/build-cuda-impl.sh
 
 echo "--- Audit binary wheel to ensure it's compliant with ${WHEEL_TAG} standard"
 python3 ops/docker_run.py \
-  --container-tag ${MANYLINUX_CONTAINER_TAG} \
+  --image-uri ${MANYLINUX_IMAGE_URI} \
   -- auditwheel repair --only-plat \
   --plat ${WHEEL_TAG} python-package/dist/*.whl
 python3 -m wheel tags --python-tag py3 --abi-tag none --platform ${WHEEL_TAG} --remove \

ops/pipeline/build-gpu-rpkg.sh

@@ -11,12 +11,12 @@ fi
 source ops/pipeline/classify-git-branch.sh
 source ops/pipeline/get-docker-registry-details.sh
 
-CONTAINER_TAG=${DOCKER_REGISTRY_URL}/xgb-ci.gpu_build_r_rockylinux8:main
+IMAGE_URI=${DOCKER_REGISTRY_URL}/xgb-ci.gpu_build_r_rockylinux8:main
 
 echo "--- Build XGBoost R package with CUDA"
 set -x
 python3 ops/docker_run.py \
-  --container-tag ${CONTAINER_TAG} \
+  --image-uri ${IMAGE_URI} \
   -- ops/pipeline/build-gpu-rpkg-impl.sh \
   ${GITHUB_SHA}
 

ops/pipeline/build-jvm-doc.sh

@@ -19,10 +19,10 @@ fi
 
 source ops/pipeline/get-docker-registry-details.sh
 
-CONTAINER_TAG=${DOCKER_REGISTRY_URL}/xgb-ci.jvm_gpu_build:main
+IMAGE_URI=${DOCKER_REGISTRY_URL}/xgb-ci.jvm_gpu_build:main
 
 echo "--- Build JVM packages doc"
 set -x
 python3 ops/docker_run.py \
-  --container-tag ${CONTAINER_TAG} \
+  --image-uri ${IMAGE_URI} \
   -- ops/pipeline/build-jvm-doc-impl.sh ${BRANCH_NAME}

ops/pipeline/build-jvm-gpu.sh

@@ -6,7 +6,7 @@ set -euo pipefail
 source ops/pipeline/classify-git-branch.sh
 source ops/pipeline/get-docker-registry-details.sh
 
-CONTAINER_TAG=${DOCKER_REGISTRY_URL}/xgb-ci.jvm_gpu_build:main
+IMAGE_URI=${DOCKER_REGISTRY_URL}/xgb-ci.jvm_gpu_build:main
 
 echo "--- Build libxgboost4j.so with CUDA"
 
@@ -32,5 +32,5 @@ mkdir -p build-gpu/
 # TODO(hcho3): Remove this once new CUDA version ships with CCCL 2.6.0+
 git clone https://github.com/NVIDIA/cccl.git -b v2.6.1 --quiet --depth 1
 python3 ops/docker_run.py \
-  --container-tag ${CONTAINER_TAG} \
+  --image-uri ${IMAGE_URI} \
   -- bash -c "${COMMAND}"