diff options
author | Josh Rosen <joshrosen@databricks.com> | 2015-06-29 21:32:40 -0700 |
---|---|---|
committer | Davies Liu <davies@databricks.com> | 2015-06-29 21:32:40 -0700 |
commit | 7bbbe380c52419cd580d1c99c10131184e4ad440 (patch) | |
tree | 7a80e1faf633627b77a21917cf3abfd994bfdbcd /dev | |
parent | f9b6bf2f83d9dad273aa36d65d0560d35b941cc2 (diff) | |
download | spark-7bbbe380c52419cd580d1c99c10131184e4ad440.tar.gz spark-7bbbe380c52419cd580d1c99c10131184e4ad440.tar.bz2 spark-7bbbe380c52419cd580d1c99c10131184e4ad440.zip |
[SPARK-5161] Parallelize Python test execution
This commit parallelizes the Python unit test execution, significantly reducing Jenkins build times. Parallelism is now configurable by passing the `-p` or `--parallelism` flags to either `dev/run-tests` or `python/run-tests` (the default parallelism is 4, but I've successfully tested with higher parallelism).
To avoid flakiness, I've disabled the Spark Web UI for the Python tests, similar to what we've done for the JVM tests.
Author: Josh Rosen <joshrosen@databricks.com>
Closes #7031 from JoshRosen/parallelize-python-tests and squashes the following commits:
feb3763 [Josh Rosen] Re-enable other tests
f87ea81 [Josh Rosen] Only log output from failed tests
d4ded73 [Josh Rosen] Logging improvements
a2717e1 [Josh Rosen] Make parallelism configurable via dev/run-tests
1bacf1b [Josh Rosen] Merge remote-tracking branch 'origin/master' into parallelize-python-tests
110cd9d [Josh Rosen] Fix universal_newlines for Python 3
cd13db8 [Josh Rosen] Also log python_implementation
9e31127 [Josh Rosen] Log Python --version output for each executable.
a2b9094 [Josh Rosen] Bump up parallelism.
5552380 [Josh Rosen] Python 3 fix
866b5b9 [Josh Rosen] Fix lazy logging warnings in Prospector checks
87cb988 [Josh Rosen] Skip MLLib tests for PyPy
8309bfe [Josh Rosen] Temporarily disable parallelism to debug a failure
9129027 [Josh Rosen] Disable Spark UI in Python tests
037b686 [Josh Rosen] Temporarily disable JVM tests so we can test Python speedup in Jenkins.
af4cef4 [Josh Rosen] Initial attempt at parallelizing Python test execution
Diffstat (limited to 'dev')
-rwxr-xr-x | dev/run-tests | 2 | ||||
-rwxr-xr-x | dev/run-tests.py | 24 | ||||
-rw-r--r-- | dev/sparktestsupport/shellutils.py | 1 |
3 files changed, 24 insertions, 3 deletions
diff --git a/dev/run-tests b/dev/run-tests index a00d9f0c27..257d1e8d50 100755 --- a/dev/run-tests +++ b/dev/run-tests @@ -20,4 +20,4 @@ FWDIR="$(cd "`dirname $0`"/..; pwd)" cd "$FWDIR" -exec python -u ./dev/run-tests.py +exec python -u ./dev/run-tests.py "$@" diff --git a/dev/run-tests.py b/dev/run-tests.py index e5c897b94d..4596e07014 100755 --- a/dev/run-tests.py +++ b/dev/run-tests.py @@ -19,6 +19,7 @@ from __future__ import print_function import itertools +from optparse import OptionParser import os import re import sys @@ -360,12 +361,13 @@ def run_scala_tests(build_tool, hadoop_version, test_modules): run_scala_tests_sbt(test_modules, test_profiles) -def run_python_tests(test_modules): +def run_python_tests(test_modules, parallelism): set_title_and_block("Running PySpark tests", "BLOCK_PYSPARK_UNIT_TESTS") command = [os.path.join(SPARK_HOME, "python", "run-tests")] if test_modules != [modules.root]: command.append("--modules=%s" % ','.join(m.name for m in test_modules)) + command.append("--parallelism=%i" % parallelism) run_cmd(command) @@ -379,7 +381,25 @@ def run_sparkr_tests(): print("Ignoring SparkR tests as R was not found in PATH") +def parse_opts(): + parser = OptionParser( + prog="run-tests" + ) + parser.add_option( + "-p", "--parallelism", type="int", default=4, + help="The number of suites to test in parallel (default %default)" + ) + + (opts, args) = parser.parse_args() + if args: + parser.error("Unsupported arguments: %s" % ' '.join(args)) + if opts.parallelism < 1: + parser.error("Parallelism cannot be less than 1") + return opts + + def main(): + opts = parse_opts() # Ensure the user home directory (HOME) is valid and is an absolute directory if not USER_HOME or not os.path.isabs(USER_HOME): print("[error] Cannot determine your home directory as an absolute path;", @@ -461,7 +481,7 @@ def main(): modules_with_python_tests = [m for m in test_modules if m.python_test_goals] if modules_with_python_tests: - run_python_tests(modules_with_python_tests) + run_python_tests(modules_with_python_tests, opts.parallelism) if any(m.should_run_r_tests for m in test_modules): run_sparkr_tests() diff --git a/dev/sparktestsupport/shellutils.py b/dev/sparktestsupport/shellutils.py index ad9b0cc89e..12bd0bf3a4 100644 --- a/dev/sparktestsupport/shellutils.py +++ b/dev/sparktestsupport/shellutils.py @@ -15,6 +15,7 @@ # limitations under the License. # +from __future__ import print_function import os import shutil import subprocess |