big-data/hadoop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

HADOOP-4687 More moving around

Browse Source 
git-svn-id: https://svn.apache.org/repos/asf/hadoop/core/branches/HADOOP-4687/core@776175 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Owen O'Malley 2009-05-19 04:30:38 +00:00
parent 5128a9a453
commit c94ff0f240
42 changed files with 13948 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8971
CHANGES.txt Normal file
View File

File diff suppressed because it is too large Load Diff

244
LICENSE.txt Normal file
View File

@ -0,0 +1,244 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed 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.
APACHE HADOOP SUBCOMPONENTS:
The Apache Hadoop project contains subcomponents with separate copyright
notices and license terms. Your use of the source code for the these
subcomponents is subject to the terms and conditions of the following
licenses.
For the org.apache.hadoop.util.bloom.* classes:
/**
*
* Copyright (c) 2005, European Commission project OneLab under contract
* 034819 (http://www.one-lab.org)
* All rights reserved.
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
* - Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* - Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the distribution.
* - Neither the name of the University Catholique de Louvain - UCL
* nor the names of its contributors may be used to endorse or
* promote products derived from this software without specific prior
* written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/

2
NOTICE.txt Normal file
View File

@ -0,0 +1,2 @@
This product includes software developed by The Apache Software
Foundation (http://www.apache.org/).

31
README.txt Normal file
View File

@ -0,0 +1,31 @@
For the latest information about Hadoop, please visit our website at:
http://hadoop.apache.org/core/
and our wiki, at:
http://wiki.apache.org/hadoop/
This distribution includes cryptographic software. The country in
which you currently reside may have restrictions on the import,
possession, use, and/or re-export to another country, of
encryption software. BEFORE using any encryption software, please
check your country's laws, regulations and policies concerning the
import, possession, or use, and re-export of encryption software, to
see if this is permitted. See <http://www.wassenaar.org/> for more
information.
The U.S. Government Department of Commerce, Bureau of Industry and
Security (BIS), has classified this software as Export Commodity
Control Number (ECCN) 5D002.C.1, which includes information security
software using or performing cryptographic functions with asymmetric
algorithms. The form and manner of this Apache Software Foundation
distribution makes it eligible for export under the License Exception
ENC Technology Software Unrestricted (TSU) exception (see the BIS
Export Administration Regulations, Section 740.13) for both object
code and source code.
The following provides more details on the included cryptographic
software:
Hadoop Core uses the SSL libraries from the Jetty project written
by mortbay.org.

108
bin/hadoop Executable file
View File

@ -0,0 +1,108 @@
#!/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.
# This script runs the hadoop core commands.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
function print_usage(){
echo "Usage: hadoop [--config confdir] COMMAND"
echo " where COMMAND is one of:"
echo " fs run a generic filesystem user client"
echo " version print the version"
echo " jar <jar> run a jar file"
echo " distcp <srcurl> <desturl> copy file or directories recursively"
echo " archive -archiveName NAME <src>* <dest> create a hadoop archive"
echo " daemonlog get/set the log level for each daemon"
echo " or"
echo " CLASSNAME run the class named CLASSNAME"
echo ""
echo "Most commands print help when invoked w/o parameters."
}
if [ $# = 0 ]; then
print_usage
exit
fi
COMMAND=$1
case $COMMAND in
#hdfs commands
namenode|secondarynamenode|datanode|dfs|dfsadmin|fsck|balancer)
echo "DEPRECATED: Use of this script to execute hdfs command is deprecated."
echo "Instead use the hdfs command for it."
echo ""
#try to locate hdfs and if present, delegate to it.
if [ -f "${HADOOP_HDFS_HOME}"/bin/hdfs ]; then
exec "${HADOOP_HDFS_HOME}"/bin/hdfs $*
else
echo "HDFS not found."
exit
fi
;;
#mapred commands
mradmin|jobtracker|tasktracker|pipes|job|queue)
echo "DEPRECATED: Use of this script to execute mapred command is deprecated."
echo "Instead use the mapred command for it."
echo ""
#try to locate mapred and if present, delegate to it.
if [ -f "${HADOOP_MAPRED_HOME}"/bin/mapred ]; then
exec "${HADOOP_MAPRED_HOME}"/bin/mapred $*
else
echo "MAPRED not found."
exit
fi
;;
#core commands
*)
# the core commands
if [ "$COMMAND" = "fs" ] ; then
CLASS=org.apache.hadoop.fs.FsShell
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "version" ] ; then
CLASS=org.apache.hadoop.util.VersionInfo
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "jar" ] ; then
CLASS=org.apache.hadoop.util.RunJar
elif [ "$COMMAND" = "distcp" ] ; then
CLASS=org.apache.hadoop.tools.DistCp
CLASSPATH=${CLASSPATH}:${TOOL_PATH}
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "daemonlog" ] ; then
CLASS=org.apache.hadoop.log.LogLevel
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "archive" ] ; then
CLASS=org.apache.hadoop.tools.HadoopArchives
CLASSPATH=${CLASSPATH}:${TOOL_PATH}
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
else
CLASS=$COMMAND
fi
shift
if $cygwin; then
CLASSPATH=`cygpath -p -w "$CLASSPATH"`
fi
exec "$JAVA" $JAVA_HEAP_MAX $HADOOP_OPTS -classpath "$CLASSPATH" $CLASS "$@"
;;
esac

248
bin/hadoop-config.sh Normal file
View File

@ -0,0 +1,248 @@
# 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.
# included in all the hadoop scripts with source command
# should not be executable directly
# also should not be passed any arguments, since we need original $*
# resolve links - $0 may be a softlink
this="$0"
while [ -h "$this" ]; do
ls=`ls -ld "$this"`
link=`expr "$ls" : '.*-> \(.*\)$'`
if expr "$link" : '.*/.*' > /dev/null; then
this="$link"
else
this=`dirname "$this"`/"$link"
fi
done
# convert relative path to absolute path
bin=`dirname "$this"`
script=`basename "$this"`
bin=`cd "$bin"; pwd`
this="$bin/$script"
# the root of the Hadoop installation
#TODO: change the env variable when dir structure is changed
export HADOOP_HOME=`dirname "$this"`/..
export HADOOP_CORE_HOME="${HADOOP_HOME}"
#export HADOOP_HOME=`dirname "$this"`/../..
#export HADOOP_CORE_HOME="${HADOOP_CORE_HOME:-`dirname "$this"`/..}"
#check to see if the conf dir is given as an optional argument
if [ $# -gt 1 ]
then
if [ "--config" = "$1" ]
then
shift
confdir=$1
shift
HADOOP_CONF_DIR=$confdir
fi
fi
# Allow alternate conf dir location.
export HADOOP_CONF_DIR="${HADOOP_CONF_DIR:-$HADOOP_HOME/conf}"
#check to see it is specified whether to use the slaves or the
# masters file
if [ $# -gt 1 ]
then
if [ "--hosts" = "$1" ]
then
shift
slavesfile=$1
shift
export HADOOP_SLAVES="${HADOOP_CONF_DIR}/$slavesfile"
fi
fi
cygwin=false
case "`uname`" in
CYGWIN*) cygwin=true;;
esac
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
# some Java parameters
if [ "$JAVA_HOME" != "" ]; then
#echo "run java in $JAVA_HOME"
JAVA_HOME=$JAVA_HOME
fi
if [ "$JAVA_HOME" = "" ]; then
echo "Error: JAVA_HOME is not set."
exit 1
fi
JAVA=$JAVA_HOME/bin/java
JAVA_HEAP_MAX=-Xmx1000m
# check envvars which might override default args
if [ "$HADOOP_HEAPSIZE" != "" ]; then
#echo "run with heapsize $HADOOP_HEAPSIZE"
JAVA_HEAP_MAX="-Xmx""$HADOOP_HEAPSIZE""m"
#echo $JAVA_HEAP_MAX
fi
# CLASSPATH initially contains $HADOOP_CONF_DIR
CLASSPATH="${HADOOP_CONF_DIR}"
CLASSPATH=${CLASSPATH}:$JAVA_HOME/lib/tools.jar
# for developers, add Hadoop classes to CLASSPATH
if [ -d "$HADOOP_CORE_HOME/build/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_CORE_HOME/build/classes
fi
if [ -d "$HADOOP_CORE_HOME/build/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_CORE_HOME/build
fi
if [ -d "$HADOOP_CORE_HOME/build/test/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_CORE_HOME/build/test/classes
fi
if [ -d "$HADOOP_CORE_HOME/build/tools" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_CORE_HOME/build/tools
fi
# so that filenames w/ spaces are handled correctly in loops below
IFS=
# for releases, add core hadoop jar & webapps to CLASSPATH
if [ -d "$HADOOP_CORE_HOME/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_CORE_HOME
fi
for f in $HADOOP_CORE_HOME/hadoop-*-core.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# add libs to CLASSPATH
for f in $HADOOP_CORE_HOME/lib/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
if [ -d "$HADOOP_CORE_HOME/build/ivy/lib/Hadoop/common" ]; then
for f in $HADOOP_CORE_HOME/build/ivy/lib/Hadoop/common/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
fi
for f in $HADOOP_CORE_HOME/lib/jsp-2.1/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
for f in $HADOOP_CORE_HOME/hadoop-*-tools.jar; do
TOOL_PATH=${TOOL_PATH}:$f;
done
for f in $HADOOP_CORE_HOME/build/hadoop-*-tools.jar; do
TOOL_PATH=${TOOL_PATH}:$f;
done
# add user-specified CLASSPATH last
if [ "$HADOOP_CLASSPATH" != "" ]; then
CLASSPATH=${CLASSPATH}:${HADOOP_CLASSPATH}
fi
# default log directory & file
if [ "$HADOOP_LOG_DIR" = "" ]; then
HADOOP_LOG_DIR="$HADOOP_HOME/logs"
fi
if [ "$HADOOP_LOGFILE" = "" ]; then
HADOOP_LOGFILE='hadoop.log'
fi
# default policy file for service-level authorization
if [ "$HADOOP_POLICYFILE" = "" ]; then
HADOOP_POLICYFILE="hadoop-policy.xml"
fi
# restore ordinary behaviour
unset IFS
# cygwin path translation
if $cygwin; then
HADOOP_CORE_HOME=`cygpath -w "$HADOOP_CORE_HOME"`
HADOOP_LOG_DIR=`cygpath -w "$HADOOP_LOG_DIR"`
TOOL_PATH=`cygpath -p -w "$TOOL_PATH"`
fi
# setup 'java.library.path' for native-hadoop code if necessary
JAVA_LIBRARY_PATH=''
if [ -d "${HADOOP_CORE_HOME}/build/native" -o -d "${HADOOP_CORE_HOME}/lib/native" ]; then
JAVA_PLATFORM=`CLASSPATH=${CLASSPATH} ${JAVA} -Xmx32m org.apache.hadoop.util.PlatformName | sed -e "s/ /_/g"`
if [ -d "$HADOOP_CORE_HOME/build/native" ]; then
JAVA_LIBRARY_PATH=${HADOOP_CORE_HOME}/build/native/${JAVA_PLATFORM}/lib
fi
if [ -d "${HADOOP_CORE_HOME}/lib/native" ]; then
if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}:${HADOOP_CORE_HOME}/lib/native/${JAVA_PLATFORM}
else
JAVA_LIBRARY_PATH=${HADOOP_CORE_HOME}/lib/native/${JAVA_PLATFORM}
fi
fi
fi
# cygwin path translation
if $cygwin; then
JAVA_LIBRARY_PATH=`cygpath -p "$JAVA_LIBRARY_PATH"`
fi
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.dir=$HADOOP_LOG_DIR"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.file=$HADOOP_LOGFILE"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.home.dir=$HADOOP_CORE_HOME"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.id.str=$HADOOP_IDENT_STRING"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.root.logger=${HADOOP_ROOT_LOGGER:-INFO,console}"
if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
HADOOP_OPTS="$HADOOP_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH"
fi
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.policy.file=$HADOOP_POLICYFILE"
# put hdfs in classpath if present
if [ "$HADOOP_HDFS_HOME" = "" ]; then
if [ -d "${HADOOP_HOME}/hdfs" ]; then
HADOOP_HDFS_HOME=$HADOOP_HOME/hdfs
echo Found HDFS installed at $HADOOP_HDFS_HOME
fi
fi
if [ -d "${HADOOP_HDFS_HOME}" ]; then
for f in $HADOOP_HDFS_HOME/hadoop-*-hdfs.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# add libs to CLASSPATH
for f in $HADOOP_HDFS_HOME/lib/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
if [ -d "$HADOOP_HDFS_HOME/build/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HDFS_HOME/build/classes
fi
fi
# set mapred home if mapred is present
if [ "$HADOOP_MAPRED_HOME" = "" ]; then
if [ -d "${HADOOP_HOME}/mapred" ]; then
HADOOP_MAPRED_HOME=$HADOOP_HOME/mapred
echo Found MAPRED installed at $HADOOP_MAPRED_HOME
fi
fi
# TODO:remove this when dir structure is changed
export HADOOP_HDFS_HOME=$HADOOP_HOME
export HADOOP_MAPRED_HOME=$HADOOP_HOME

152
bin/hadoop-daemon.sh Executable file
View File

@ -0,0 +1,152 @@
#!/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.
# Runs a Hadoop command as a daemon.
#
# Environment Variables
#
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_HOME}/conf.
# HADOOP_LOG_DIR Where log files are stored. PWD by default.
# HADOOP_MASTER host:path where hadoop code should be rsync'd from
# HADOOP_PID_DIR The pid files are stored. /tmp by default.
# HADOOP_IDENT_STRING A string representing this instance of hadoop. $USER by default
# HADOOP_NICENESS The scheduling priority for daemons. Defaults to 0.
##
usage="Usage: hadoop-daemon.sh [--config <conf-dir>] [--hosts hostlistfile] [--script script] (start|stop) <hadoop-command> <args...>"
# if no args specified, show usage
if [ $# -le 1 ]; then
echo $usage
exit 1
fi
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# get arguments
#default value
hadoopScript="$HADOOP_HOME"/bin/hadoop
if [ "--script" = "$1" ]
then
shift
hadoopScript=$1
shift
fi
startStop=$1
shift
command=$1
shift
hadoop_rotate_log ()
{
log=$1;
num=5;
if [ -n "$2" ]; then
num=$2
fi
if [ -f "$log" ]; then # rotate logs
while [ $num -gt 1 ]; do
prev=`expr $num - 1`
[ -f "$log.$prev" ] && mv "$log.$prev" "$log.$num"
num=$prev
done
mv "$log" "$log.$num";
fi
}
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
# get log directory
if [ "$HADOOP_LOG_DIR" = "" ]; then
export HADOOP_LOG_DIR="$HADOOP_HOME/logs"
fi
mkdir -p "$HADOOP_LOG_DIR"
if [ "$HADOOP_PID_DIR" = "" ]; then
HADOOP_PID_DIR=/tmp
fi
if [ "$HADOOP_IDENT_STRING" = "" ]; then
export HADOOP_IDENT_STRING="$USER"
fi
# some variables
export HADOOP_LOGFILE=hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.log
export HADOOP_ROOT_LOGGER="INFO,DRFA"
log=$HADOOP_LOG_DIR/hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.out
pid=$HADOOP_PID_DIR/hadoop-$HADOOP_IDENT_STRING-$command.pid
# Set default scheduling priority
if [ "$HADOOP_NICENESS" = "" ]; then
export HADOOP_NICENESS=0
fi
case $startStop in
(start)
mkdir -p "$HADOOP_PID_DIR"
if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo $command running as process `cat $pid`. Stop it first.
exit 1
fi
fi
if [ "$HADOOP_MASTER" != "" ]; then
echo rsync from $HADOOP_MASTER
rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' $HADOOP_MASTER/ "$HADOOP_HOME"
fi
hadoop_rotate_log $log
echo starting $command, logging to $log
cd "$HADOOP_HOME"
nohup nice -n $HADOOP_NICENESS $hadoopScript --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null &
echo $! > $pid
sleep 1; head "$log"
;;
(stop)
if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo stopping $command
kill `cat $pid`
else
echo no $command to stop
fi
else
echo no $command to stop
fi
;;
(*)
echo $usage
exit 1
;;
esac

34
bin/hadoop-daemons.sh Executable file
View File

@ -0,0 +1,34 @@
#!/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.
# Run a Hadoop command on all slave hosts.
usage="Usage: hadoop-daemons.sh [--config confdir] [--hosts hostlistfile] [start|stop] command args..."
# if no args specified, show usage
if [ $# -le 1 ]; then
echo $usage
exit 1
fi
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. $bin/hadoop-config.sh
exec "$bin/slaves.sh" --config $HADOOP_CONF_DIR cd "$HADOOP_HOME" \; "$bin/hadoop-daemon.sh" --config $HADOOP_CONF_DIR "$@"

110
bin/hdfs Executable file
View File

@ -0,0 +1,110 @@
#!/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.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hdfs-config.sh
function print_usage(){
echo "Usage: hdfs [--config confdir] COMMAND"
echo " where COMMAND is one of:"
echo " namenode -format format the DFS filesystem"
echo " secondarynamenode run the DFS secondary namenode"
echo " namenode run the DFS namenode"
echo " datanode run a DFS datanode"
echo " dfsadmin run a DFS admin client"
echo " fsck run a DFS filesystem checking utility"
echo " balancer run a cluster balancing utility"
echo " jmxget get JMX exported values from NameNode or DataNode."
echo " oiv apply the offline fsimage viewer to an fsimage"
echo " Use -help to see options"
echo ""
echo "Most commands print help when invoked w/o parameters."
}
if [ $# = 0 ]; then
print_usage
exit
fi
COMMAND=$1
shift
if [ "$COMMAND" = "namenode" ] ; then
CLASS='org.apache.hadoop.hdfs.server.namenode.NameNode'
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_NAMENODE_OPTS"
elif [ "$COMMAND" = "secondarynamenode" ] ; then
CLASS='org.apache.hadoop.hdfs.server.namenode.SecondaryNameNode'
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_SECONDARYNAMENODE_OPTS"
elif [ "$COMMAND" = "datanode" ] ; then
CLASS='org.apache.hadoop.hdfs.server.datanode.DataNode'
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_DATANODE_OPTS"
elif [ "$COMMAND" = "dfs" ] ; then
CLASS=org.apache.hadoop.fs.FsShell
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "dfsadmin" ] ; then
CLASS=org.apache.hadoop.hdfs.tools.DFSAdmin
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "fsck" ] ; then
CLASS=org.apache.hadoop.hdfs.tools.DFSck
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "balancer" ] ; then
CLASS=org.apache.hadoop.hdfs.server.balancer.Balancer
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_BALANCER_OPTS"
elif [ "$COMMAND" = "jmxget" ] ; then
CLASS=org.apache.hadoop.hdfs.tools.JMXGet
elif [ "$COMMAND" = "oiv" ] ; then
CLASS=org.apache.hadoop.hdfs.tools.offlineImageViewer.OfflineImageViewer
else
echo $COMMAND - invalid command
print_usage
exit
fi
# for developers, add hdfs classes to CLASSPATH
if [ -d "$HADOOP_HDFS_HOME/build/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HDFS_HOME/build/classes
fi
if [ -d "$HADOOP_HDFS_HOME/build/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HDFS_HOME/build
fi
if [ -d "$HADOOP_HDFS_HOME/build/test/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HDFS_HOME/build/test/classes
fi
if [ -d "$HADOOP_HDFS_HOME/build/tools" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HDFS_HOME/build/tools
fi
# for releases, add core hdfs jar & webapps to CLASSPATH
if [ -d "$HADOOP_HDFS_HOME/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HDFS_HOME
fi
for f in $HADOOP_HDFS_HOME/hadoop-*-hdfs.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# add libs to CLASSPATH
for f in $HADOOP_HDFS_HOME/lib/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
if $cygwin; then
CLASSPATH=`cygpath -p -w "$CLASSPATH"`
fi
exec "$JAVA" $JAVA_HEAP_MAX $HADOOP_OPTS -classpath "$CLASSPATH" $CLASS "$@"

33
bin/hdfs-config.sh Normal file
View File

@ -0,0 +1,33 @@
#!/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.
# included in all the hdfs scripts with source command
# should not be executed directly
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
#TODO: change the env variable when directory structure is changed
export HADOOP_CORE_HOME="${HADOOP_CORE_HOME:-$bin/..}"
#export HADOOP_CORE_HOME="${HADOOP_CORE_HOME:-$bin/../../core}"
if [ -d "${HADOOP_CORE_HOME}" ]; then
. "$HADOOP_CORE_HOME"/bin/hadoop-config.sh
else
echo "Hadoop core not found."
exit
fi

100
bin/mapred Executable file
View File

@ -0,0 +1,100 @@
#!/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.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. $bin/mapred-config.sh
function print_usage(){
echo "Usage: mapred [--config confdir] COMMAND"
echo " where COMMAND is one of:"
echo " mradmin run a Map-Reduce admin client"
echo " jobtracker run the MapReduce job Tracker node"
echo " tasktracker run a MapReduce task Tracker node"
echo " pipes run a Pipes job"
echo " job manipulate MapReduce jobs"
echo " queue get information regarding JobQueues"
echo ""
echo "Most commands print help when invoked w/o parameters."
}
if [ $# = 0 ]; then
print_usage
exit
fi
COMMAND=$1
shift
if [ "$COMMAND" = "mradmin" ] ; then
CLASS=org.apache.hadoop.mapred.tools.MRAdmin
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "jobtracker" ] ; then
CLASS=org.apache.hadoop.mapred.JobTracker
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_JOBTRACKER_OPTS"
elif [ "$COMMAND" = "tasktracker" ] ; then
CLASS=org.apache.hadoop.mapred.TaskTracker
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_TASKTRACKER_OPTS"
elif [ "$COMMAND" = "job" ] ; then
CLASS=org.apache.hadoop.mapred.JobClient
elif [ "$COMMAND" = "queue" ] ; then
CLASS=org.apache.hadoop.mapred.JobQueueClient
elif [ "$COMMAND" = "pipes" ] ; then
CLASS=org.apache.hadoop.mapred.pipes.Submitter
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "sampler" ] ; then
CLASS=org.apache.hadoop.mapred.lib.InputSampler
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
else
echo $COMMAND - invalid command
print_usage
exit
fi
# for developers, add mapred classes to CLASSPATH
if [ -d "$HADOOP_MAPRED_HOME/build/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_MAPRED_HOME/build/classes
fi
if [ -d "$HADOOP_MAPRED_HOME/build/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_MAPRED_HOME/build
fi
if [ -d "$HADOOP_MAPRED_HOME/build/test/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_MAPRED_HOME/build/test/classes
fi
if [ -d "$HADOOP_MAPRED_HOME/build/tools" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_MAPRED_HOME/build/tools
fi
# for releases, add core mapred jar & webapps to CLASSPATH
if [ -d "$HADOOP_MAPRED_HOME/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_MAPRED_HOME
fi
for f in $HADOOP_MAPRED_HOME/hadoop-*-mapred.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# add libs to CLASSPATH
for f in $HADOOP_MAPRED_HOME/lib/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
if $cygwin; then
CLASSPATH=`cygpath -p -w "$CLASSPATH"`
fi
export CLASSPATH
exec "$JAVA" $JAVA_HEAP_MAX $HADOOP_OPTS $CLASS "$@"

33
bin/mapred-config.sh Normal file
View File

@ -0,0 +1,33 @@
#!/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.
# included in all the mapred scripts with source command
# should not be executed directly
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
#TODO: change the env variable when directory structure is changed
export HADOOP_CORE_HOME="${HADOOP_CORE_HOME:-$bin/..}"
#export HADOOP_CORE_HOME="${HADOOP_CORE_HOME:-$bin/../../core}"
if [ -d "${HADOOP_CORE_HOME}" ]; then
. "$HADOOP_CORE_HOME"/bin/hadoop-config.sh
else
echo "Hadoop core not found."
exit
fi

99
bin/rcc Executable file
View File

@ -0,0 +1,99 @@
#!/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.
# The Hadoop record compiler
#
# Environment Variables
#
# JAVA_HOME The java implementation to use. Overrides JAVA_HOME.
#
# HADOOP_OPTS Extra Java runtime options.
#
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_HOME}/conf.
#
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
# some Java parameters
if [ "$JAVA_HOME" != "" ]; then
#echo "run java in $JAVA_HOME"
JAVA_HOME=$JAVA_HOME
fi
if [ "$JAVA_HOME" = "" ]; then
echo "Error: JAVA_HOME is not set."
exit 1
fi
JAVA=$JAVA_HOME/bin/java
JAVA_HEAP_MAX=-Xmx1000m
# CLASSPATH initially contains $HADOOP_CONF_DIR
CLASSPATH="${HADOOP_CONF_DIR}"
CLASSPATH=${CLASSPATH}:$JAVA_HOME/lib/tools.jar
# for developers, add Hadoop classes to CLASSPATH
if [ -d "$HADOOP_HOME/build/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/classes
fi
if [ -d "$HADOOP_HOME/build/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build
fi
if [ -d "$HADOOP_HOME/build/test/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/test/classes
fi
# so that filenames w/ spaces are handled correctly in loops below
IFS=
# for releases, add core hadoop jar & webapps to CLASSPATH
if [ -d "$HADOOP_HOME/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME
fi
for f in $HADOOP_HOME/hadoop-*-core.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# add libs to CLASSPATH
for f in $HADOOP_HOME/lib/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
for f in $HADOOP_HOME/lib/jetty-ext/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# restore ordinary behaviour
unset IFS
CLASS='org.apache.hadoop.record.compiler.generated.Rcc'
# cygwin path translation
if expr `uname` : 'CYGWIN*' > /dev/null; then
CLASSPATH=`cygpath -p -w "$CLASSPATH"`
fi
# run it
exec "$JAVA" $HADOOP_OPTS -classpath "$CLASSPATH" $CLASS "$@"

68
bin/slaves.sh Executable file
View File

@ -0,0 +1,68 @@
#!/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.
# Run a shell command on all slave hosts.
#
# Environment Variables
#
# HADOOP_SLAVES File naming remote hosts.
# Default is ${HADOOP_CONF_DIR}/slaves.
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_HOME}/conf.
# HADOOP_SLAVE_SLEEP Seconds to sleep between spawning remote commands.
# HADOOP_SSH_OPTS Options passed to ssh when running remote commands.
##
usage="Usage: slaves.sh [--config confdir] command..."
# if no args specified, show usage
if [ $# -le 0 ]; then
echo $usage
exit 1
fi
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# If the slaves file is specified in the command line,
# then it takes precedence over the definition in
# hadoop-env.sh. Save it here.
HOSTLIST=$HADOOP_SLAVES
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
if [ "$HOSTLIST" = "" ]; then
if [ "$HADOOP_SLAVES" = "" ]; then
export HOSTLIST="${HADOOP_CONF_DIR}/slaves"
else
export HOSTLIST="${HADOOP_SLAVES}"
fi
fi
for slave in `cat "$HOSTLIST"|sed "s/#.*$//;/^$/d"`; do
ssh $HADOOP_SSH_OPTS $slave $"${@// /\\ }" \
2>&1 | sed "s/^/$slave: /" &
if [ "$HADOOP_SLAVE_SLEEP" != "" ]; then
sleep $HADOOP_SLAVE_SLEEP
fi
done
wait

36
bin/start-all.sh Executable file
View File

@ -0,0 +1,36 @@
#!/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.
# Start all hadoop daemons. Run this on master node.
echo "This script is Deprecated. Instead use start-dfs.sh and start-mapred.sh"
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# start hdfs daemons if hdfs is present
if [ -f "${HADOOP_HDFS_HOME}"/bin/start-dfs.sh ]; then
"${HADOOP_HDFS_HOME}"/bin/start-dfs.sh --config $HADOOP_CONF_DIR
fi
# start mapred daemons if mapred is present
if [ -f "${HADOOP_MAPRED_HOME}"/bin/start-mapred.sh ]; then
"${HADOOP_MAPRED_HOME}"/bin/start-mapred.sh --config $HADOOP_CONF_DIR
fi

25
bin/start-balancer.sh Executable file
View File

@ -0,0 +1,25 @@
#!/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.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hdfs-config.sh
# Start balancer daemon.
"$HADOOP_CORE_HOME"/bin/hadoop-daemon.sh --config $HADOOP_CONF_DIR --script "$bin"/hdfs start balancer $@

52
bin/start-dfs.sh Executable file
View File

@ -0,0 +1,52 @@
#!/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.
# Start hadoop dfs daemons.
# Optinally upgrade or rollback dfs state.
# Run this on master node.
usage="Usage: start-dfs.sh [-upgrade|-rollback]"
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hdfs-config.sh
# get arguments
if [ $# -ge 1 ]; then
nameStartOpt=$1
shift
case $nameStartOpt in
(-upgrade)
;;
(-rollback)
dataStartOpt=$nameStartOpt
;;
(*)
echo $usage
exit 1
;;
esac
fi
# start dfs daemons
# start namenode after datanodes, to minimize time namenode is up w/o data
# note: datanodes will log connection errors until namenode starts
"$HADOOP_CORE_HOME"/bin/hadoop-daemon.sh --config $HADOOP_CONF_DIR --script "$bin"/hdfs start namenode $nameStartOpt
"$HADOOP_CORE_HOME"/bin/hadoop-daemons.sh --config $HADOOP_CONF_DIR --script "$bin"/hdfs start datanode $dataStartOpt
"$HADOOP_CORE_HOME"/bin/hadoop-daemons.sh --config $HADOOP_CONF_DIR --hosts masters --script "$bin"/hdfs start secondarynamenode

29
bin/start-mapred.sh Executable file
View File

@ -0,0 +1,29 @@
#!/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.
# Start hadoop map reduce daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. $bin/mapred-config.sh
# start mapred daemons
# start jobtracker first to minimize connection errors at startup
"$HADOOP_CORE_HOME"/bin/hadoop-daemon.sh --config $HADOOP_CONF_DIR --script "$bin"/mapred start jobtracker
"$HADOOP_CORE_HOME"/bin/hadoop-daemons.sh --config $HADOOP_CONF_DIR --script "$bin"/mapred start tasktracker

37
bin/stop-all.sh Executable file
View File

@ -0,0 +1,37 @@
#!/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.
# Stop all hadoop daemons. Run this on master node.
echo "This script is Deprecated. Instead use stop-dfs.sh and stop-mapred.sh"
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# stop hdfs daemons if hdfs is present
if [ -f "${HADOOP_HDFS_HOME}"/bin/stop-dfs.sh ]; then
"${HADOOP_HDFS_HOME}"/bin/stop-dfs.sh --config $HADOOP_CONF_DIR
fi
# stop mapred daemons if mapred is present
if [ -f "${HADOOP_MAPRED_HOME}"/bin/stop-mapred.sh ]; then
"${HADOOP_MAPRED_HOME}"/bin/stop-mapred.sh --config $HADOOP_CONF_DIR
fi

26
bin/stop-balancer.sh Executable file
View File

@ -0,0 +1,26 @@
#!/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.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hdfs-config.sh
# Stop balancer daemon.
# Run this on the machine where the balancer is running
"$HADOOP_CORE_HOME"/bin/hadoop-daemon.sh --config $HADOOP_CONF_DIR --script "$bin"/hdfs stop balancer

28
bin/stop-dfs.sh Executable file
View File

@ -0,0 +1,28 @@
#!/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.
# Stop hadoop DFS daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hdfs-config.sh
"$HADOOP_CORE_HOME"/bin/hadoop-daemon.sh --config $HADOOP_CONF_DIR --script "$bin"/hdfs stop namenode
"$HADOOP_CORE_HOME"/bin/hadoop-daemons.sh --config $HADOOP_CONF_DIR --script "$bin"/hdfs stop datanode
"$HADOOP_CORE_HOME"/bin/hadoop-daemons.sh --config $HADOOP_CONF_DIR --hosts masters --script "$bin"/hdfs stop secondarynamenode

27
bin/stop-mapred.sh Executable file
View File

@ -0,0 +1,27 @@
#!/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.
# Stop hadoop map reduce daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. $bin/mapred-config.sh
"$HADOOP_CORE_HOME"/bin/hadoop-daemon.sh --config $HADOOP_CONF_DIR --script "$bin"/mapred stop jobtracker
"$HADOOP_CORE_HOME"/bin/hadoop-daemons.sh --config $HADOOP_CONF_DIR --script "$bin"/mapred stop tasktracker

2165
build.xml Normal file
View File

File diff suppressed because it is too large Load Diff

126
conf/capacity-scheduler.xml.template Normal file
View File

@ -0,0 +1,126 @@
<?xml version="1.0"?>
<!-- This is the configuration file for the resource manager in Hadoop. -->
<!-- You can configure various scheduling parameters related to queues. -->
<!-- The properties for a queue follow a naming convention,such as, -->
<!-- mapred.capacity-scheduler.queue.<queue-name>.property-name. -->
<configuration>
<property>
<name>mapred.capacity-scheduler.queue.default.capacity</name>
<value>100</value>
<description>Percentage of the number of slots in the cluster that are
to be available for jobs in this queue.
</description>
</property>
<property>
<name>mapred.capacity-scheduler.queue.default.supports-priority</name>
<value>false</value>
<description>If true, priorities of jobs will be taken into
account in scheduling decisions.
</description>
</property>
<property>
<name>mapred.capacity-scheduler.queue.default.minimum-user-limit-percent</name>
<value>100</value>
<description> Each queue enforces a limit on the percentage of resources
allocated to a user at any given time, if there is competition for them.
This user limit can vary between a minimum and maximum value. The former
depends on the number of users who have submitted jobs, and the latter is
set to this property value. For example, suppose the value of this
property is 25. If two users have submitted jobs to a queue, no single
user can use more than 50% of the queue resources. If a third user submits
a job, no single user can use more than 33% of the queue resources. With 4
or more users, no user can use more than 25% of the queue's resources. A
value of 100 implies no user limits are imposed.
</description>
</property>
<property>
<name>mapred.capacity-scheduler.queue.default.maximum-initialized-jobs-per-user</name>
<value>2</value>
<description>The maximum number of jobs to be pre-initialized for a user
of the job queue.
</description>
</property>
<!-- The default configuration settings for the capacity task scheduler -->
<!-- The default values would be applied to all the queues which don't have -->
<!-- the appropriate property for the particular queue -->
<property>
<name>mapred.capacity-scheduler.default-supports-priority</name>
<value>false</value>
<description>If true, priorities of jobs will be taken into
account in scheduling decisions by default in a job queue.
</description>
</property>
<property>
<name>mapred.capacity-scheduler.task.default-pmem-percentage-in-vmem</name>
<value>-1</value>
<description>A percentage (float) of the default VM limit for jobs
(mapred.task.default.maxvm). This is the default RAM task-limit
associated with a task. Unless overridden by a job's setting, this
number defines the RAM task-limit.
If this property is missing, or set to an invalid value, scheduling
based on physical memory, RAM, is disabled.
</description>
</property>
<property>
<name>mapred.capacity-scheduler.task.limit.maxpmem</name>
<value>-1</value>
<description>Configuration that provides an upper limit on the maximum
physical memory that can be specified by a job. The job configuration
mapred.task.maxpmem should be less than this value. If not, the job will
be rejected by the scheduler.
If it is set to -1, scheduler will not consider physical memory for
scheduling even if virtual memory based scheduling is enabled(by setting
valid values for both mapred.task.default.maxvmem and
mapred.task.limit.maxvmem).
</description>
</property>
<property>
<name>mapred.capacity-scheduler.default-minimum-user-limit-percent</name>
<value>100</value>
<description>The percentage of the resources limited to a particular user
for the job queue at any given point of time by default.
</description>
</property>
<property>
<name>mapred.capacity-scheduler.default-maximum-initialized-jobs-per-user</name>
<value>2</value>
<description>The maximum number of jobs to be pre-initialized for a user
of the job queue.
</description>
</property>
<!-- Capacity scheduler Job Initialization configuration parameters -->
<property>
<name>mapred.capacity-scheduler.init-poll-interval</name>
<value>5000</value>
<description>The amount of time in miliseconds which is used to poll
the job queues for jobs to initialize.
</description>
</property>
<property>
<name>mapred.capacity-scheduler.init-worker-threads</name>
<value>5</value>
<description>Number of worker threads which would be used by
Initialization poller to initialize jobs in a set of queue.
If number mentioned in property is equal to number of job queues
then a single thread would initialize jobs in a queue. If lesser
then a thread would get a set of queues assigned. If the number
is greater then number of threads would be equal to number of
job queues.
</description>
</property>
</configuration>

24
conf/configuration.xsl Normal file
View File

@ -0,0 +1,24 @@
<?xml version="1.0"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:output method="html"/>
<xsl:template match="configuration">
<html>
<body>
<table border="1">
<tr>
<td>name</td>
<td>value</td>
<td>description</td>
</tr>
<xsl:for-each select="property">
<tr>
<td><a name="{name}"><xsl:value-of select="name"/></a></td>
<td><xsl:value-of select="value"/></td>
<td><xsl:value-of select="description"/></td>
</tr>
</xsl:for-each>
</table>
</body>
</html>
</xsl:template>
</xsl:stylesheet>

8
conf/core-site.xml.template Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
</configuration>

54
conf/hadoop-env.sh.template Normal file
View File

@ -0,0 +1,54 @@
# Set Hadoop-specific environment variables here.
# The only required environment variable is JAVA_HOME. All others are
# optional. When running a distributed configuration it is best to
# set JAVA_HOME in this file, so that it is correctly defined on
# remote nodes.
# The java implementation to use. Required.
# export JAVA_HOME=/usr/lib/j2sdk1.5-sun
# Extra Java CLASSPATH elements. Optional.
# export HADOOP_CLASSPATH=
# The maximum amount of heap to use, in MB. Default is 1000.
# export HADOOP_HEAPSIZE=2000
# Extra Java runtime options. Empty by default.
# export HADOOP_OPTS=-server
# Command specific options appended to HADOOP_OPTS when specified
export HADOOP_NAMENODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_NAMENODE_OPTS"
export HADOOP_SECONDARYNAMENODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_SECONDARYNAMENODE_OPTS"
export HADOOP_DATANODE_OPTS="-Dcom.sun.management.jmxremote $HADOOP_DATANODE_OPTS"
export HADOOP_BALANCER_OPTS="-Dcom.sun.management.jmxremote $HADOOP_BALANCER_OPTS"
export HADOOP_JOBTRACKER_OPTS="-Dcom.sun.management.jmxremote $HADOOP_JOBTRACKER_OPTS"
# export HADOOP_TASKTRACKER_OPTS=
# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
# export HADOOP_CLIENT_OPTS
# Extra ssh options. Empty by default.
# export HADOOP_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HADOOP_CONF_DIR"
# Where log files are stored. $HADOOP_HOME/logs by default.
# export HADOOP_LOG_DIR=${HADOOP_HOME}/logs
# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.
# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves
# host:path where hadoop code should be rsync'd from. Unset by default.
# export HADOOP_MASTER=master:/home/$USER/src/hadoop
# Seconds to sleep between slave commands. Unset by default. This
# can be useful in large clusters, where, e.g., slave rsyncs can
# otherwise arrive faster than the master can service them.
# export HADOOP_SLAVE_SLEEP=0.1
# The directory where pid files are stored. /tmp by default.
# export HADOOP_PID_DIR=/var/hadoop/pids
# A string representing this instance of hadoop. $USER by default.
# export HADOOP_IDENT_STRING=$USER
# The scheduling priority for daemon processes. See 'man nice'.
# export HADOOP_NICENESS=10

53
conf/hadoop-metrics.properties Normal file
View File

@ -0,0 +1,53 @@
# Configuration of the "dfs" context for null
dfs.class=org.apache.hadoop.metrics.spi.NullContext
# Configuration of the "dfs" context for file
#dfs.class=org.apache.hadoop.metrics.file.FileContext
#dfs.period=10
#dfs.fileName=/tmp/dfsmetrics.log
# Configuration of the "dfs" context for ganglia
# dfs.class=org.apache.hadoop.metrics.ganglia.GangliaContext
# dfs.period=10
# dfs.servers=localhost:8649
# Configuration of the "mapred" context for null
mapred.class=org.apache.hadoop.metrics.spi.NullContext
# Configuration of the "mapred" context for file
#mapred.class=org.apache.hadoop.metrics.file.FileContext
#mapred.period=10
#mapred.fileName=/tmp/mrmetrics.log
# Configuration of the "mapred" context for ganglia
# mapred.class=org.apache.hadoop.metrics.ganglia.GangliaContext
# mapred.period=10
# mapred.servers=localhost:8649
# Configuration of the "jvm" context for null
jvm.class=org.apache.hadoop.metrics.spi.NullContext
# Configuration of the "jvm" context for file
#jvm.class=org.apache.hadoop.metrics.file.FileContext
#jvm.period=10
#jvm.fileName=/tmp/jvmmetrics.log
# Configuration of the "jvm" context for ganglia
# jvm.class=org.apache.hadoop.metrics.ganglia.GangliaContext
# jvm.period=10
# jvm.servers=localhost:8649
# Configuration of the "rpc" context for null
rpc.class=org.apache.hadoop.metrics.spi.NullContext
# Configuration of the "rpc" context for file
#rpc.class=org.apache.hadoop.metrics.file.FileContext
#rpc.period=10
#rpc.fileName=/tmp/rpcmetrics.log
# Configuration of the "rpc" context for ganglia
# rpc.class=org.apache.hadoop.metrics.ganglia.GangliaContext
# rpc.period=10
# rpc.servers=localhost:8649

97
conf/hadoop-policy.xml.template Normal file
View File

@ -0,0 +1,97 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>security.client.protocol.acl</name>
<value>*</value>
<description>ACL for ClientProtocol, which is used by user code
via the DistributedFileSystem.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.client.datanode.protocol.acl</name>
<value>*</value>
<description>ACL for ClientDatanodeProtocol, the client-to-datanode protocol
for block recovery.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.datanode.protocol.acl</name>
<value>*</value>
<description>ACL for DatanodeProtocol, which is used by datanodes to
communicate with the namenode.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.inter.datanode.protocol.acl</name>
<value>*</value>
<description>ACL for InterDatanodeProtocol, the inter-datanode protocol
for updating generation timestamp.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.namenode.protocol.acl</name>
<value>*</value>
<description>ACL for NamenodeProtocol, the protocol used by the secondary
namenode to communicate with the namenode.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.inter.tracker.protocol.acl</name>
<value>*</value>
<description>ACL for InterTrackerProtocol, used by the tasktrackers to
communicate with the jobtracker.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.job.submission.protocol.acl</name>
<value>*</value>
<description>ACL for JobSubmissionProtocol, used by job clients to
communciate with the jobtracker for job submission, querying job status etc.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.task.umbilical.protocol.acl</name>
<value>*</value>
<description>ACL for TaskUmbilicalProtocol, used by the map and reduce
tasks to communicate with the parent tasktracker.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
<property>
<name>security.refresh.policy.protocol.acl</name>
<value>*</value>
<description>ACL for RefreshAuthorizationPolicyProtocol, used by the
dfsadmin and mradmin commands to refresh the security policy in-effect.
The ACL is a comma-separated list of user and group names. The user and
group list is separated by a blank. For e.g. "alice,bob users,wheel".
A special value of "*" means all users are allowed.</description>
</property>
</configuration>

8
conf/hdfs-site.xml.template Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
</configuration>

94
conf/log4j.properties Normal file
View File

@ -0,0 +1,94 @@
# Define some default values that can be overridden by system properties
hadoop.root.logger=INFO,console
hadoop.log.dir=.
hadoop.log.file=hadoop.log
# Define the root logger to the system property "hadoop.root.logger".
log4j.rootLogger=${hadoop.root.logger}, EventCounter
# Logging Threshold
log4j.threshhold=ALL
#
# Daily Rolling File Appender
#
log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
# Rollver at midnight
log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
# 30-day backup
#log4j.appender.DRFA.MaxBackupIndex=30
log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
# Pattern format: Date LogLevel LoggerName LogMessage
log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
# Debugging Pattern format
#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
#
# console
# Add "console" to rootlogger above if you want to use this
#
log4j.appender.console=org.apache.log4j.ConsoleAppender
log4j.appender.console.target=System.err
log4j.appender.console.layout=org.apache.log4j.PatternLayout
log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
#
# TaskLog Appender
#
#Default values
hadoop.tasklog.taskid=null
hadoop.tasklog.noKeepSplits=4
hadoop.tasklog.totalLogFileSize=100
hadoop.tasklog.purgeLogSplits=true
hadoop.tasklog.logsRetainHours=12
log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
#
# Rolling File Appender
#
#log4j.appender.RFA=org.apache.log4j.RollingFileAppender
#log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
# Logfile size and and 30-day backups
#log4j.appender.RFA.MaxFileSize=1MB
#log4j.appender.RFA.MaxBackupIndex=30
#log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
#
# FSNamesystem Audit logging
# All audit events are logged at INFO level
#
log4j.logger.org.apache.hadoop.fs.FSNamesystem.audit=WARN
# Custom Logging levels
#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG
# Jets3t library
log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
#
# Event Counter Appender
# Sends counts of logging messages at different severity levels to Hadoop Metrics.
#
log4j.appender.EventCounter=org.apache.hadoop.metrics.jvm.EventCounter

31
conf/mapred-queue-acls.xml.template Normal file
View File

@ -0,0 +1,31 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- This is a template file for queue acls configuration properties -->
<configuration>
<property>
<name>mapred.queue.default.acl-submit-job</name>
<value>*</value>
<description> Comma separated list of user and group names that are allowed
to submit jobs to the 'default' queue. The user list and the group list
are separated by a blank. For e.g. alice,bob group1,group2.
If set to the special value '*', it means all users are allowed to
submit jobs.
</description>
</property>
<property>
<name>mapred.queue.default.acl-administer-jobs</name>
<value>*</value>
<description> Comma separated list of user and group names that are allowed
to delete jobs or modify job's priority for jobs not owned by the current
user in the 'default' queue. The user list and the group list
are separated by a blank. For e.g. alice,bob group1,group2.
If set to the special value '*', it means all users are allowed to do
this operation.
</description>
</property>
</configuration>

8
conf/mapred-site.xml.template Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
</configuration>

1
conf/masters.template Normal file
View File

@ -0,0 +1 @@
localhost

1
conf/slaves.template Normal file
View File

@ -0,0 +1 @@
localhost

57
conf/ssl-client.xml.example Normal file
View File

@ -0,0 +1,57 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>ssl.client.truststore.location</name>
<value></value>
<description>Truststore to be used by clients like distcp. Must be
specified.
</description>
</property>
<property>
<name>ssl.client.truststore.password</name>
<value></value>
<description>Optional. Default value is "".
</description>
</property>
<property>
<name>ssl.client.truststore.type</name>
<value>jks</value>
<description>Optional. Default value is "jks".
</description>
</property>
<property>
<name>ssl.client.keystore.location</name>
<value></value>
<description>Keystore to be used by clients like distcp. Must be
specified.
</description>
</property>
<property>
<name>ssl.client.keystore.password</name>
<value></value>
<description>Optional. Default value is "".
</description>
</property>
<property>
<name>ssl.client.keystore.keypassword</name>
<value></value>
<description>Optional. Default value is "".
</description>
</property>
<property>
<name>ssl.client.keystore.type</name>
<value>jks</value>
<description>Optional. Default value is "jks".
</description>
</property>
</configuration>

55
conf/ssl-server.xml.example Normal file
View File

@ -0,0 +1,55 @@
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>ssl.server.truststore.location</name>
<value></value>
<description>Truststore to be used by NN and DN. Must be specified.
</description>
</property>
<property>
<name>ssl.server.truststore.password</name>
<value></value>
<description>Optional. Default value is "".
</description>
</property>
<property>
<name>ssl.server.truststore.type</name>
<value>jks</value>
<description>Optional. Default value is "jks".
</description>
</property>
<property>
<name>ssl.server.keystore.location</name>
<value></value>
<description>Keystore to be used by NN and DN. Must be specified.
</description>
</property>
<property>
<name>ssl.server.keystore.password</name>
<value></value>
<description>Must be specified.
</description>
</property>
<property>
<name>ssl.server.keystore.keypassword</name>
<value></value>
<description>Must be specified.
</description>
</property>
<property>
<name>ssl.server.keystore.type</name>
<value>jks</value>
<description>Optional. Default value is "jks".
</description>
</property>
</configuration>

3
conf/taskcontroller.cfg Normal file
View File

@ -0,0 +1,3 @@
mapred.local.dir=#configured value of hadoop.tmp.dir it can be a list of paths comma seperated
hadoop.pid.dir=#configured HADOOP_PID_DIR
hadoop.indent.str=#configured HADOOP_IDENT_STR

264
ivy.xml Normal file
View File

@ -0,0 +1,264 @@
<?xml version="1.0" ?>
<!--
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.
-->
<ivy-module version="1.0">
<info organisation="org.apache.hadoop" module="${ant.project.name}" revision="${version}">
<license name="Apache 2.0"/>
<ivyauthor name="Apache Hadoop Team" url="http://hadoop.apache.org"/>
<description>
Hadoop Core
</description>
</info>
<configurations defaultconfmapping="default">
<!--these match the Maven configurations-->
<conf name="default" extends="master,runtime"/>
<conf name="master" description="contains the artifact but no dependencies"/>
<conf name="runtime" description="runtime but not the artifact"
extends="client,server,s3-server,kfs"/>
<conf name="mandatory" description="contains the critical dependencies"
extends="commons-logging,log4j"/>
<!--
These public configurations contain the core dependencies for running hadoop client or server.
The server is effectively a superset of the client.
-->
<conf name="client" description="client-side dependencies"
extends="mandatory,httpclient"/>
<conf name="server" description="server-side dependencies"
extends="client"/>
<conf name="s3-client" description="dependencies for working with S3/EC2 infrastructure"
extends="client"/>
<conf name="s3-server" description="dependencies for running on S3/EC2 infrastructure"
extends="s3-client,server"/>
<conf name="kfs" description="dependencies for KFS file system support"/>
<conf name="ftp" description="dependencies for workign with FTP filesytems"
extends="mandatory"/>
<conf name="jetty" description="Jetty provides the in-VM HTTP daemon" extends="commons-logging"/>
<!--Private configurations. -->
<conf name="common" visibility="private" extends="runtime,mandatory,httpclient,ftp,jetty"
description="common artifacts"/>
<conf name="javadoc" visibility="private" description="artiracts required while performing doc generation"
extends="common,mandatory,jetty,lucene"/>
<!--Testing pulls in everything-->
<conf name="test" extends="common,default,s3-server,kfs" visibility="private"
description="the classpath needed to run tests"/>
<conf name="releaseaudit" visibility="private"
description="Artifacts required for releaseaudit target"/>
<conf name="commons-logging" visibility="private"/>
<conf name="httpclient" visibility="private" extends="commons-logging"/>
<conf name="log4j" visibility="private"/>
<conf name="lucene" visibility="private"/>
<conf name="jdiff" visibility="private" extends="log4j,s3-client,jetty,server"/>
<conf name="checkstyle" visibility="private"/>
</configurations>
<publications>
<!--get the artifact from our module name-->
<artifact conf="master"/>
</publications>
<dependencies>
<!--used client side-->
<!-- <dependency org="commons-cli"
name="commons-cli"
rev="${commons-cli.version}"
conf="client->default"/> -->
<dependency org="checkstyle"
name="checkstyle"
rev="${checkstyle.version}"
conf="checkstyle->default"/>
<dependency org="jdiff"
name="jdiff"
rev="${jdiff.version}"
conf="jdiff->default"/>
<dependency org="xerces"
name="xerces"
rev="${xerces.version}"
conf="jdiff->default">
</dependency>
<dependency org="xmlenc"
name="xmlenc"
rev="${xmlenc.version}"
conf="server->default"/>
<!--Configuration: httpclient-->
<!--
commons-httpclient asks for too many files.
All it needs is commons-codec and commons-logging JARs
-->
<dependency org="commons-httpclient"
name="commons-httpclient"
rev="${commons-httpclient.version}"
conf="httpclient->master">
</dependency>
<dependency org="commons-codec"
name="commons-codec"
rev="${commons-codec.version}"
conf="httpclient->default"/>
<dependency org="commons-net"
name="commons-net"
rev="${commons-net.version}"
conf="ftp->default"/>
<!--Configuration: Jetty -->
<!-- <dependency org="javax.servlet"
name="servlet-api"
rev="${servlet-api.version}"
conf="jetty->master"/> -->
<dependency org="org.mortbay.jetty"
name="jetty"
rev="${jetty.version}"
conf="jetty->master"/>
<dependency org="org.mortbay.jetty"
name="jetty-util"
rev="${jetty-util.version}"
conf="jetty->master"/>
<dependency org="tomcat"
name="jasper-runtime"
rev="${jasper.version}"
conf="jetty->master"/>
<dependency org="tomcat"
name="jasper-compiler"
rev="${jasper.version}"
conf="jetty->master"/>
<dependency org="org.mortbay.jetty"
name="jsp-api-2.1"
rev="${jetty.version}"
conf="jetty->master"/>
<dependency org="org.mortbay.jetty"
name="jsp-2.1"
rev="${jetty.version}"
conf="jetty->master"/>
<dependency org="commons-el"
name="commons-el"
rev="${commons-el.version}"
conf="jetty->master"/>
<!--Configuration: commons-logging -->
<!--it is essential that only the master JAR of commons logging
is pulled in, as its dependencies are usually a mess, including things
like out of date servlet APIs, bits of Avalon, etc.
-->
<dependency org="commons-logging"
name="commons-logging"
rev="${commons-logging.version}"
conf="commons-logging->master"/>
<!--Configuration: commons-logging -->
<!--log4J is not optional until commons-logging.properties is stripped out of the JAR -->
<dependency org="log4j"
name="log4j"
rev="${log4j.version}"
conf="log4j->master"/>
<!--Configuration: s3-client -->
<!--there are two jets3t projects in the repository; this one goes up to 0.6 and
is assumed to be the live one-->
<dependency org="net.java.dev.jets3t"
name="jets3t"
rev="${jets3t.version}"
conf="s3-client->master"/>
<dependency org="commons-net"
name="commons-net"
rev="${commons-net.version}"
conf="s3-client->master"/>
<dependency org="org.mortbay.jetty"
name="servlet-api-2.5"
rev="${servlet-api-2.5.version}"
conf="s3-client->master"/>
<!--Configuration: kfs -->
<!-- This is not in the repository
<dependency org="org.kosmix"
name="kfs"
rev="${kfs.version}"
conf="kfs->default"/>-->
<!--Configuration: test -->
<!--artifacts needed for testing -->
<dependency org="junit"
name="junit"
rev="${junit.version}"
conf="common->default"/>
<dependency org="com.google.code.p.arat"
name="rat-lib"
rev="${rats-lib.version}"
conf="releaseaudit->default"/>
<dependency org="commons-lang"
name="commons-lang"
rev="${commons-lang.version}"
conf="releaseaudit->default"/>
<dependency org="commons-collections"
name="commons-collections"
rev="${commons-collections.version}"
conf="releaseaudit->default"/>
<!--<dependency org="hsqldb"
name="hsqldb"
rev="${hsqldb.version}"
conf="common->default"/>
<dependency org="lucene"
name="lucene"
rev="${lucene.version}"
conf="javadoc->default"/> -->
<dependency org="org.apache.lucene"
name="lucene-core"
rev="${lucene-core.version}"
conf="javadoc->default"/>
<dependency org="commons-logging"
name="commons-logging-api"
rev="${commons-logging-api.version}"
conf="common->default"/>
<dependency org="org.slf4j"
name="slf4j-api"
rev="${slf4j-api.version}"
conf="common->master"/>
<dependency org="org.eclipse.jdt"
name="core"
rev="${core.version}"
conf="common->master"/>
<dependency org="oro"
name="oro"
rev="${oro.version}"
conf="common->default"/>
<dependency org="org.slf4j"
name="slf4j-log4j12"
rev="${slf4j-log4j12.version}"
conf="common->master">
</dependency>
</dependencies>
</ivy-module>

257
ivy/hadoop-core.pom Normal file
View File

@ -0,0 +1,257 @@
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<!--
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.
-->
<modelVersion>4.0.0</modelVersion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<packaging>jar</packaging>
<version>${hadoop.version}</version>
<description>
Hadoop is the distributed computing framework of Apache; hadoop-core contains
the filesystem, job tracker and map/reduce modules
</description>
<licenses>
<license>
<name>Apache License, Version 2.0</name>
<url>http://apache.org/licenses/LICENSE-2.0</url>
</license>
</licenses>
<dependencies>
<!-- always include commons-logging and log4J -->
<dependency>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
<version>${commons-logging.version}</version>
<exclusions>
<exclusion>
<groupId>avalon-framework</groupId>
<artifactId>avalon-framework</artifactId>
</exclusion>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
<exclusion>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
</exclusion>
<exclusion>
<groupId>logkit</groupId>
<artifactId>logkit</artifactId>
</exclusion>
<exclusion>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>${log4j.version}</version>
<scope>optional</scope>
<exclusions>
<exclusion>
<groupId>javax.mail</groupId>
<artifactId>mail</artifactId>
</exclusion>
<exclusion>
<groupId>javax.jms</groupId>
<artifactId>jms</artifactId>
</exclusion>
<exclusion>
<groupId>com.sun.jdmk</groupId>
<artifactId>jmxtools</artifactId>
</exclusion>
<exclusion>
<groupId>com.sun.jmx</groupId>
<artifactId>jmxri</artifactId>
</exclusion>
</exclusions>
</dependency>
<!--SLF4J is a JAR-based dependency; this POM binds it to log4J-->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>${slf4j-api.version}</version>
<scope>optional</scope>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>${slf4j-log4j12.version}</version>
<scope>optional</scope>
<exclusions>
<exclusion>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
</exclusion>
</exclusions>
</dependency>
<!--Httpclient and its components are optional-->
<dependency>
<groupId>commons-httpclient</groupId>
<artifactId>commons-httpclient</artifactId>
<version>3.1</version>
<scope>optional</scope>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</exclusion>
<exclusion>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
<version>1.3</version>
<scope>optional</scope>
</dependency>
<!--CLI is needed to scan the command line, but only the 1.0 branch is released -->
<dependency>
<groupId>commons-cli</groupId>
<artifactId>commons-cli</artifactId>
<version>2.0-20070823</version>
<scope>optional</scope>
</dependency>
<!-- this is used for the ftp:// filesystem-->
<dependency>
<groupId>commons-net</groupId>
<artifactId>commons-net</artifactId>
<version>1.4.1</version>
<scope>optional</scope>
</dependency>
<!-- Jetty is used to serve up the application. It is marked as optional because
clients do not need it. All server-side deployments will need
all of these files.-->
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
<version>${servlet-api.version}</version>
<scope>optional</scope>
</dependency>
<dependency>
<groupId>jetty</groupId>
<artifactId>org.mortbay.jetty</artifactId>
<version>${jetty.version}</version>
<scope>optional</scope>
</dependency>
<!--JSP support -->
<dependency>
<groupId>org.mortbay.jetty</groupId>
<artifactId>jsp-2.1</artifactId>
<version>${jetty.version}</version>
<scope>optional</scope>
</dependency>
<dependency>
<groupId>org.mortbay.jetty</groupId>
<artifactId>jsp-api-2.1</artifactId>
<version>${jetty.version}</version>
<scope>optional</scope>
</dependency>
<dependency>
<groupId>commons-el</groupId>
<artifactId>commons-el</artifactId>
<version>${commons-el.version}</version>
<scope>optional</scope>
</dependency>
<!--JSPC assistance-->
<dependency>
<groupId>org.eclipse.jdt</groupId>
<artifactId>core</artifactId>
<version>${core.version}</version>
<scope>optional</scope>
</dependency>
<dependency>
<groupId>org.apache.ant</groupId>
<artifactId>ant</artifactId>
<version>${apacheant.version}</version>
<scope>optional</scope>
</dependency>
<!-- JetS3t is a client library for S3.
-It is only needed if you want to work with S3 filesystems
-It pulls in commons-logging 1.1.1 and does not exclude all the cruft that comes with it.
By excluding it we stay in control of versions and dependencies
-->
<dependency>
<groupId>net.java.dev.jets3t</groupId>
<artifactId>jets3t</artifactId>
<version>${jets3t.version}</version>
<scope>optional</scope>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</exclusion>
<exclusion>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
</exclusion>
</exclusions>
</dependency>
<!--Kosmos filesystem
http://kosmosfs.sourceforge.net/
This is not in the central repository
-->
<!--
<dependency>
<groupId>org.kosmix</groupId>
<artifactId>kfs</artifactId>
<version>0.1</version>
<scope>optional</scope>
</dependency>
-->
<!--
http://xmlenc.sourceforge.net/
"The xmlenc library is a fast stream-based XML output library for Java."
-->
<dependency>
<groupId>xmlenc</groupId>
<artifactId>xmlenc</artifactId>
<version>0.52</version>
<scope>optional</scope>
</dependency>
</dependencies>
</project>

81
ivy/ivysettings.xml Normal file
View File

@ -0,0 +1,81 @@
<ivysettings>
<!--
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.
-->
<!--
see http://www.jayasoft.org/ivy/doc/configuration
-->
<!-- you can override this property to use mirrors
http://repo1.maven.org/maven2/
http://mirrors.dotsrc.org/maven2
http://ftp.ggi-project.org/pub/packages/maven2
http://mirrors.sunsite.dk/maven2
http://public.planetmirror.com/pub/maven2
http://ibiblio.lsu.edu/main/pub/packages/maven2
http://www.ibiblio.net/pub/packages/maven2
-->
<property name="repo.maven.org"
value="http://repo1.maven.org/maven2/"
override="false"/>
<property name="snapshot.apache.org"
value="http://people.apache.org/repo/m2-snapshot-repository/"
override="false"/>
<property name="maven2.pattern"
value="[organisation]/[module]/[revision]/[module]-[revision]"/>
<property name="maven2.pattern.ext"
value="${maven2.pattern}.[ext]"/>
<!-- pull in the local repository -->
<include url="${ivy.default.conf.dir}/ivyconf-local.xml"/>
<settings defaultResolver="default"/>
<resolvers>
<ibiblio name="maven2"
root="${repo.maven.org}"
pattern="${maven2.pattern.ext}"
m2compatible="true"
/>
<ibiblio name="apache-snapshot"
root="${snapshot.apache.org}"
pattern="${maven2.pattern.ext}"
m2compatible="true"
/>
<chain name="default" dual="true">
<resolver ref="local"/>
<resolver ref="maven2"/>
</chain>
<chain name="internal">
<resolver ref="local"/>
</chain>
<chain name="external">
<resolver ref="maven2"/>
</chain>
<chain name="external-and-snapshots">
<resolver ref="maven2"/>
<resolver ref="apache-snapshot"/>
</chain>
</resolvers>
<modules>
<!--
This forces a requirement for other hadoop-artifacts to be built locally
rather than look for them online.
-->
<module organisation="org.apache.hadoop" name=".*" resolver="internal"/>
<!--until commons cli is external, we need to pull it in from the snapshot repository -if present -->
<module organisation="org.apache.commons" name=".*" resolver="external-and-snapshots"/>
</modules>
</ivysettings>

68
ivy/libraries.properties Normal file
View File

@ -0,0 +1,68 @@
# Licensed 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.
#This properties file lists the versions of the various artifacts used by hadoop and components.
#It drives ivy and the generation of a maven POM
#These are the versions of our dependencies (in alphabetical order)
apacheant.version=1.7.0
checkstyle.version=4.2
commons-cli.version=2.0-SNAPSHOT
commons-codec.version=1.3
commons-collections.version=3.1
commons-httpclient.version=3.0.1
commons-lang.version=2.4
commons-logging.version=1.0.4
commons-logging-api.version=1.0.4
commons-el.version=1.0
commons-fileupload.version=1.2
commons-io.version=1.4
commons-net.version=1.4.1
core.version=3.1.1
coreplugin.version=1.3.2
hsqldb.version=1.8.0.10
#ivy.version=2.0.0-beta2
ivy.version=2.0.0-rc2
jasper.version=5.5.12
#not able to figureout the version of jsp & jsp-api version to get it resolved throught ivy
# but still declared here as we are going to have a local copy from the lib folder
jsp.version=2.1
jsp-api.version=5.5.12
jets3t.version=0.6.1
jetty.version=6.1.14
jetty-util.version=6.1.14
junit.version=4.5
jdiff.version=1.0.9
json.version=1.0
kfs.version=0.1
log4j.version=1.2.15
lucene-core.version=2.3.1
oro.version=2.0.8
rats-lib.version=0.5.1
servlet.version=4.0.6
servlet-api-2.5.version=6.1.14
servlet-api.version=2.5
slf4j-api.version=1.4.3
slf4j-log4j12.version=1.4.3
xmlenc.version=0.52
xerces.version=1.4.4