[CI] Upload nightly builds to S3 (#4976)

* Do not store built artifacts in the Jenkins master

* Add wheel renaming script

* Upload wheels to S3 bucket

* Use env.GIT_COMMIT

* Capture git hash correctly

* Add missing import in Jenkinsfile

* Address reviewer's comments

* Put artifacts for pull requests in separate directory

* No wildcard expansion in Windows CMD

Jenkinsfile

@@ -6,6 +6,11 @@
 // Command to run command inside a docker container
 dockerRun = 'tests/ci_build/ci_build.sh'
 
+import groovy.transform.Field
+
+@Field
+def commit_id   // necessary to pass a variable from one stage to another
+
 pipeline {
   // Each stage specify its own agent
   agent none
@@ -31,6 +36,7 @@ pipeline {
       steps {
         script {
           checkoutSrcs()
+          commit_id = "${GIT_COMMIT}"
         }
         stash name: 'srcs'
         milestone ordinal: 1
@@ -158,7 +164,6 @@ def Doxygen() {
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/doxygen.sh ${BRANCH_NAME}
     """
-    archiveArtifacts artifacts: "build/${BRANCH_NAME}.tar.bz2", allowEmptyArchive: true
     echo 'Uploading doc...'
     s3Upload file: "build/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "doxygen/${BRANCH_NAME}.tar.bz2"
     deleteDir()
@@ -213,12 +218,14 @@ def BuildCUDA(args) {
     sh """
     ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_via_cmake.sh -DUSE_CUDA=ON -DUSE_NCCL=ON -DOPEN_MP:BOOL=ON
     ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
+    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python3 tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux1_x86_64
     """
     // Stash wheel for CUDA 9.0 target
     if (args.cuda_version == '9.0') {
       echo 'Stashing Python wheel...'
       stash name: 'xgboost_whl_cuda9', includes: 'python-package/dist/*.whl'
-      archiveArtifacts artifacts: "python-package/dist/*.whl", allowEmptyArchive: true
+      path = ("${BRANCH_NAME}" == 'master') ? '/' : "${BRANCH_NAME}/"
+      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
       echo 'Stashing C++ test executable (testxgboost)...'
       stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost'
     }
@@ -252,7 +259,6 @@ def BuildJVMDoc() {
     sh """
     ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_doc.sh ${BRANCH_NAME}
     """
-    archiveArtifacts artifacts: "jvm-packages/${BRANCH_NAME}.tar.bz2", allowEmptyArchive: true
     echo 'Uploading doc...'
     s3Upload file: "jvm-packages/${BRANCH_NAME}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${BRANCH_NAME}.tar.bz2"
     deleteDir()

Jenkinsfile-win64

@@ -3,6 +3,11 @@
 
 /* Jenkins pipeline for Windows AMD64 target */
 
+import groovy.transform.Field
+
+@Field
+def commit_id   // necessary to pass a variable from one stage to another
+
 pipeline {
   agent none
   // Build stages
@@ -12,6 +17,7 @@ pipeline {
       steps {
         script {
           checkoutSrcs()
+          commit_id = "${GIT_COMMIT}"
         }
         stash name: 'srcs'
         milestone ordinal: 1
@@ -76,7 +82,7 @@ def BuildWin64() {
     """
     bat """
     cd python-package
-    conda activate && python setup.py bdist_wheel --universal
+    conda activate && python setup.py bdist_wheel --universal && for /R %%i in (dist\\*.whl) DO python ../tests/ci_build/rename_whl.py "%%i" ${commit_id} win_amd64
     """
     echo "Insert vcomp140.dll (OpenMP runtime) into the wheel..."
     bat """
@@ -86,7 +92,8 @@ def BuildWin64() {
     """
     echo 'Stashing Python wheel...'
     stash name: 'xgboost_whl', includes: 'python-package/dist/*.whl'
-    archiveArtifacts artifacts: "python-package/dist/*.whl", allowEmptyArchive: true
+    path = ("${BRANCH_NAME}" == 'master') ? '/' : "${BRANCH_NAME}/"
+    s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
     echo 'Stashing C++ test executable (testxgboost)...'
     stash name: 'xgboost_cpp_tests', includes: 'build/testxgboost.exe'
     deleteDir()

doc/build.rst

@@ -15,6 +15,7 @@ Installation Guide
 
   * The binary wheel will support GPU algorithms (`gpu_hist`) on machines with NVIDIA GPUs. Please note that **training with multiple GPUs is only supported for Linux platform**. See :doc:`gpu/index`.
   * Currently, we provide binary wheels for 64-bit Linux and Windows.
+  * Nightly builds are available. You can now run *pip install https://s3-us-west-2.amazonaws.com/xgboost-nightly-builds/xgboost-[version]+[commit hash]-py2.py3-none-manylinux1_x86_64.whl* to install the nightly build with the given commit hash. See `this page <https://s3-us-west-2.amazonaws.com/xgboost-nightly-builds/list.html>`_ to see the list of all nightly builds.
 
 ****************************
 Building XGBoost from source

tests/ci_build/rename_whl.py

@@ -0,0 +1,37 @@
+import sys
+import os
+from contextlib import contextmanager
+
+@contextmanager
+def cd(path):
+    path = os.path.normpath(path)
+    cwd = os.getcwd()
+    os.chdir(path)
+    print("cd " + path)
+    try:
+        yield path
+    finally:
+        os.chdir(cwd)
+
+if len(sys.argv) != 4:
+    print('Usage: {} [wheel to rename] [commit id] [platform tag]'.format(sys.argv[0]))
+    sys.exit(1)
+
+whl_path = sys.argv[1]
+commit_id = sys.argv[2]
+platform_tag = sys.argv[3]
+
+assert platform_tag in ['manylinux1_x86_64', 'win_amd64']
+
+dirname, basename = os.path.dirname(whl_path), os.path.basename(whl_path)
+
+with cd(dirname):
+    tokens = basename.split('-')
+    assert len(tokens) == 5
+    keywords = {'pkg_name': tokens[0],
+                'version': tokens[1],
+                'commit_id': commit_id,
+                'platform_tag': platform_tag}
+    new_name = '{pkg_name}-{version}+{commit_id}-py2.py3-none-{platform_tag}.whl'.format(**keywords)
+    print('Renaming {} to {}...'.format(basename, new_name))
+    os.rename(basename, new_name)