mirror of
https://github.com/apache/impala.git
synced 2026-01-05 21:00:54 -05:00
7e76e92bef
All logs, test results and SQL files generated during data loading and testing are now consolidated under a single new directory $IMPALA_HOME/logs. The goal is to simplify archiving in Jenkins runs and debugging. The new structure is as follows: $IMPALA_HOME/logs/cluster - logs of Hadoop components and Impala $IMPALA_HOME/logs/data_loading - logs and SQL files produced in data loading $IMPALA_HOME/logs/fe_tests - logs and test output of Frontend unit tests $IMPALA_HOME/logs/be_tests - logs and test output of Backend unit tests $IMPALA_HOME/logs/ee_tests - logs and test output of end-to-end tests $IMPALA_HOME/logs/custom_cluster_tests - logs and test output of custom cluster tests I tested this change with a full data load which was successful. Change-Id: Ief1f58f3320ec39d31b3c6bc6ef87f58ff7dfdfa Reviewed-on: http://gerrit.cloudera.org:8080/2456 Reviewed-by: Alex Behm <alex.behm@cloudera.com> Tested-by: Internal Jenkins
65 lines
1.9 KiB
Bash
Executable File
65 lines
1.9 KiB
Bash
Executable File
#!/bin/bash
|
|
# Copyright (c) 2012 Cloudera, Inc. All rights reserved.
|
|
|
|
set -euo pipefail
|
|
trap 'echo Error in $0 at line $LINENO: $(cd "'$PWD'" && awk "NR == $LINENO" $0)' ERR
|
|
|
|
. ${IMPALA_HOME}/bin/set-pythonpath.sh
|
|
|
|
HIVE_SERVER_PORT=10000
|
|
export HIVE_SERVER2_THRIFT_PORT=11050
|
|
HIVE_METASTORE_PORT=9083
|
|
LOGDIR=${IMPALA_CLUSTER_LOGS_DIR}/hive
|
|
HIVES2_TRANSPORT="plain_sasl"
|
|
METASTORE_TRANSPORT="buffered"
|
|
ONLY_METASTORE=0
|
|
|
|
CLUSTER_BIN=${IMPALA_HOME}/testdata/bin
|
|
|
|
if ${CLUSTER_DIR}/admin is_kerberized; then
|
|
# Making a kerberized cluster... set some more environment variables.
|
|
. ${MINIKDC_ENV}
|
|
|
|
HIVES2_TRANSPORT="kerberos"
|
|
# The metastore isn't kerberized yet:
|
|
# METASTORE_TRANSPORT="kerberos"
|
|
fi
|
|
|
|
mkdir -p ${LOGDIR}
|
|
|
|
while [ -n "$*" ]
|
|
do
|
|
case $1 in
|
|
-only_metastore)
|
|
ONLY_METASTORE=1
|
|
;;
|
|
-help|-h|*)
|
|
echo "run-hive-server.sh : Starts the hive server and the metastore."
|
|
echo "[-metastore_only] : Only starts the hive metastore."
|
|
exit 1;
|
|
;;
|
|
esac
|
|
shift;
|
|
done
|
|
|
|
# TODO: We should have a retry loop for every service we start.
|
|
# Kill for a clean start.
|
|
${CLUSTER_BIN}/kill-hive-server.sh &> /dev/null
|
|
|
|
# Starts a Hive Metastore Server on the specified port.
|
|
HADOOP_CLIENT_OPTS=-Xmx2024m hive --service metastore -p $HIVE_METASTORE_PORT \
|
|
> ${LOGDIR}/hive-metastore.out 2>&1 &
|
|
|
|
# Wait for the Metastore to come up because HiveServer2 relies on it being live.
|
|
${CLUSTER_BIN}/wait-for-metastore.py --transport=${METASTORE_TRANSPORT}
|
|
|
|
if [ ${ONLY_METASTORE} -eq 0 ]; then
|
|
# Starts a HiveServer2 instance on the port specified by the HIVE_SERVER2_THRIFT_PORT
|
|
# environment variable.
|
|
hive --service hiveserver2 > ${LOGDIR}/hive-server2.out 2>&1 &
|
|
|
|
# Wait for the HiveServer2 service to come up because callers of this script
|
|
# may rely on it being available.
|
|
${CLUSTER_BIN}/wait-for-hiveserver2.py --transport=${HIVES2_TRANSPORT}
|
|
fi
|