druid/integration-tests/script/copy_resources_template.sh

85 lines
4.3 KiB
Bash
Raw Normal View History

#!/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.
echo "Copying integration test resources."
Fixes and tests related to the Indexer process. (#10631) * Fixes and tests related to the Indexer process. Three bugs fixed: 1) Indexers would not announce themselves as segment servers if they did not have storage locations defined. This used to work, but was broken in #9971. Fixed this by adding an "isSegmentServer" method to ServerType and updating SegmentLoadDropHandler to always announce if this method returns true. 2) Certain batch task types were written in a way that assumed "isReady" would be called before "run", which is not guaranteed. In particular, they relied on it in order to initialize "taskLockHelper". Fixed this by updating AbstractBatchIndexTask to ensure "isReady" is called before "run" for these tasks. 3) UnifiedIndexerAppenderatorsManager did not properly handle complex datasources. Introduced DataSourceAnalysis in order to fix this. Test changes: 1) Add a new "docker-compose.cli-indexer.yml" config that spins up an Indexer instead of a MiddleManager. 2) Introduce a "USE_INDEXER" environment variable that determines if docker-compose will start up an Indexer or a MiddleManager. 3) Duplicate all the jdk8 tests and run them in both MiddleManager and Indexer mode. 4) Various adjustments to encourage fail-fast errors in the Docker build scripts. 5) Various adjustments to speed up integration tests and reduce memory usage. 6) Add another Mac-specific approach to determining a machine's own IP. This was useful on my development machine. 7) Update segment-count check in ITCompactionTaskTest to eliminate a race condition (it was looking for 6 segments, which only exist together briefly, until the older 4 are marked unused). Javadoc updates: 1) AbstractBatchIndexTask: Added javadocs to determineLockGranularityXXX that make it clear when taskLockHelper will be initialized as a side effect. (Related to the second bug above.) 2) Task: Clarified that "isReady" is not guaranteed to be called before "run". It was already implied, but now it's explicit. 3) ZkCoordinator: Clarified deprecation message. 4) DataSegmentServerAnnouncer: Clarified deprecation message. * Fix stop_cluster script. * Fix sanity check in script. * Fix hashbang lines. * Test and doc adjustments. * Additional tests, and adjustments for tests. * Split ITs back out. * Revert change to druid_coordinator_period_indexingPeriod. * Set Indexer capacity to match MM. * Bump up Historical memory. * Bump down coordinator, overlord memory. * Bump up Broker memory.
2020-12-08 19:02:26 -05:00
set -e
# setup client keystore
./docker/tls/generate-client-certs-and-keystores.sh
rm -rf docker/client_tls
cp -r client_tls docker/client_tls
# install druid jars
rm -rf $SHARED_DIR/docker
mkdir -p $SHARED_DIR
cp -R docker $SHARED_DIR/docker
pushd ../
rm -rf distribution/target/apache-druid-$DRUID_VERSION-integration-test-bin
# using parallel build here may not yield significant speedups
mvn -B -Pskip-static-checks,skip-tests -Dweb.console.skip=true install -Pintegration-test
mv distribution/target/apache-druid-$DRUID_VERSION-integration-test-bin/bin $SHARED_DIR/docker/bin
mv distribution/target/apache-druid-$DRUID_VERSION-integration-test-bin/lib $SHARED_DIR/docker/lib
mv distribution/target/apache-druid-$DRUID_VERSION-integration-test-bin/extensions $SHARED_DIR/docker/extensions
popd
# Make directoriess if they dont exist
mkdir -p $SHARED_DIR/hadoop_xml
mkdir -p $SHARED_DIR/hadoop-dependencies
mkdir -p $SHARED_DIR/logs
mkdir -p $SHARED_DIR/tasklogs
mkdir -p $SHARED_DIR/docker/credentials
# install logging config
cp src/main/resources/log4j2.xml $SHARED_DIR/docker/lib/log4j2.xml
# Extensions for testing are pulled while creating a binary.
# See the 'integration-test' profile in $ROOT/distribution/pom.xml.
# Pull Hadoop dependency if needed
if [ -n "$DRUID_INTEGRATION_TEST_START_HADOOP_DOCKER" ] && [ "$DRUID_INTEGRATION_TEST_START_HADOOP_DOCKER" == true ]
then
# HdfsStorageDruidModule loads all implementations of org.apache.hadoop.fs.FileSystem using an extension class loader.
# This requires for all FileSystem implementations to be installed in druid-hdfs-storage.
DRUID_HDFS_EXT=$SHARED_DIR/docker/extensions/druid-hdfs-storage
HADOOP_AWS_DIR=$SHARED_DIR/hadoop-dependencies/hadoop-aws/${hadoop.compile.version}
HADOOP_GCS_DIR=$SHARED_DIR/hadoop-dependencies/hadoop-gcs/${hadoop.compile.version}
HADOOP_AZURE_DIR=$SHARED_DIR/hadoop-dependencies/hadoop-azure/${hadoop.compile.version}
mkdir -p $DRUID_HDFS_EXT
mkdir -p $HADOOP_GCS_DIR
## We put same version in both commands but as we have an if, correct code path will always be executed as this is generated script.
## <TODO> Remove if
"$SHARED_DIR/docker/bin/run-java" -cp "$SHARED_DIR/docker/lib/*" -Ddruid.extensions.hadoopDependenciesDir="$SHARED_DIR/hadoop-dependencies" org.apache.druid.cli.Main tools pull-deps -h org.apache.hadoop:hadoop-client-api:${hadoop.compile.version} -h org.apache.hadoop:hadoop-client-runtime:${hadoop.compile.version} -h org.apache.hadoop:hadoop-aws:${hadoop.compile.version} -h org.apache.hadoop:hadoop-azure:${hadoop.compile.version}
curl https://storage.googleapis.com/hadoop-lib/gcs/gcs-connector-hadoop3-latest.jar --output $HADOOP_GCS_DIR/gcs-connector-hadoop3-latest.jar
cp $HADOOP_GCS_DIR/gcs-connector-hadoop3-latest.jar $DRUID_HDFS_EXT
cp $HADOOP_AWS_DIR/hadoop-aws-${hadoop.compile.version}.jar $DRUID_HDFS_EXT
cp $HADOOP_AZURE_DIR/hadoop-azure-${hadoop.compile.version}.jar $DRUID_HDFS_EXT
fi
# one of the integration tests needs the wikiticker sample data
mkdir -p $SHARED_DIR/wikiticker-it
cp ../examples/quickstart/tutorial/wikiticker-2015-09-12-sampled.json.gz $SHARED_DIR/wikiticker-it/wikiticker-2015-09-12-sampled.json.gz
cp docker/wiki-simple-lookup.json $SHARED_DIR/wikiticker-it/wiki-simple-lookup.json
cp docker/test-data/wikipedia.desc $SHARED_DIR/wikiticker-it/wikipedia.desc
# copy other files if needed
if [ -n "$DRUID_INTEGRATION_TEST_RESOURCE_FILE_DIR_PATH" ]
then
cp -a $DRUID_INTEGRATION_TEST_RESOURCE_FILE_DIR_PATH/. $SHARED_DIR/docker/credentials/
fi