14174abd42
During aggregation in Python worker, if the memory usage is above spark.executor.memory, it will do disk spilling aggregation. It will split the aggregation into multiple stage, in each stage, it will partition the aggregated data by hash and dump them into disks. After all the data are aggregated, it will merge all the stages together (partition by partition). Author: Davies Liu <davies.liu@gmail.com> Closes #1460 from davies/spill and squashes the following commits: cad91bf [Davies Liu] call gc.collect() after data.clear() to release memory as much as possible. 37d71f7 [Davies Liu] balance the partitions 902f036 [Davies Liu] add shuffle.py into run-tests dcf03a9 [Davies Liu] fix memory_info() of psutil 67e6eba [Davies Liu] comment for MAX_TOTAL_PARTITIONS f6bd5d6 [Davies Liu] rollback next_limit() again, the performance difference is huge: e74b785 [Davies Liu] fix code style and change next_limit to memory_limit 400be01 [Davies Liu] address all the comments 6178844 [Davies Liu] refactor and improve docs fdd0a49 [Davies Liu] add long doc string for ExternalMerger 1a97ce4 [Davies Liu] limit used memory and size of objects in partitionBy() e6cc7f9 [Davies Liu] Merge branch 'master' into spill 3652583 [Davies Liu] address comments e78a0a0 [Davies Liu] fix style 24cec6a [Davies Liu] get local directory by SPARK_LOCAL_DIR 57ee7ef [Davies Liu] update docs 286aaff [Davies Liu] let spilled aggregation in Python configurable e9a40f6 [Davies Liu] recursive merger 6edbd1f [Davies Liu] Hash based disk spilling aggregation
82 lines
2.6 KiB
Bash
Executable file
82 lines
2.6 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
|
|
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
|
|
# Figure out where the Spark framework is installed
|
|
FWDIR="$(cd `dirname $0`; cd ../; pwd)"
|
|
|
|
# CD into the python directory to find things on the right path
|
|
cd "$FWDIR/python"
|
|
|
|
FAILED=0
|
|
|
|
rm -f unit-tests.log
|
|
|
|
# Remove the metastore and warehouse directory created by the HiveContext tests in SparkSQL
|
|
rm -rf metastore warehouse
|
|
|
|
function run_test() {
|
|
echo "Running test: $1"
|
|
SPARK_TESTING=1 $FWDIR/bin/pyspark $1 2>&1 | tee -a > unit-tests.log
|
|
FAILED=$((PIPESTATUS[0]||$FAILED))
|
|
|
|
# Fail and exit on the first test failure.
|
|
if [[ $FAILED != 0 ]]; then
|
|
cat unit-tests.log | grep -v "^[0-9][0-9]*" # filter all lines starting with a number.
|
|
echo -en "\033[31m" # Red
|
|
echo "Had test failures; see logs."
|
|
echo -en "\033[0m" # No color
|
|
exit -1
|
|
fi
|
|
}
|
|
|
|
echo "Running PySpark tests. Output is in python/unit-tests.log."
|
|
|
|
run_test "pyspark/rdd.py"
|
|
run_test "pyspark/context.py"
|
|
run_test "pyspark/conf.py"
|
|
if [ -n "$_RUN_SQL_TESTS" ]; then
|
|
run_test "pyspark/sql.py"
|
|
fi
|
|
# These tests are included in the module-level docs, and so must
|
|
# be handled on a higher level rather than within the python file.
|
|
export PYSPARK_DOC_TEST=1
|
|
run_test "pyspark/broadcast.py"
|
|
run_test "pyspark/accumulators.py"
|
|
run_test "pyspark/serializers.py"
|
|
unset PYSPARK_DOC_TEST
|
|
run_test "pyspark/shuffle.py"
|
|
run_test "pyspark/tests.py"
|
|
run_test "pyspark/mllib/_common.py"
|
|
run_test "pyspark/mllib/classification.py"
|
|
run_test "pyspark/mllib/clustering.py"
|
|
run_test "pyspark/mllib/linalg.py"
|
|
run_test "pyspark/mllib/recommendation.py"
|
|
run_test "pyspark/mllib/regression.py"
|
|
run_test "pyspark/mllib/tests.py"
|
|
|
|
if [[ $FAILED == 0 ]]; then
|
|
echo -en "\033[32m" # Green
|
|
echo "Tests passed."
|
|
echo -en "\033[0m" # No color
|
|
fi
|
|
|
|
# TODO: in the long-run, it would be nice to use a test runner like `nose`.
|
|
# The doctest fixtures are the current barrier to doing this.
|