From bee542817dd1cf525229aa903ca34d21b284f1ec Mon Sep 17 00:00:00 2001 From: Akira Ajisaka Date: Wed, 30 Dec 2015 01:03:12 +0900 Subject: [PATCH] MAPREDUCE-6584. Remove trailing whitespaces from mapred-default.xml. (aajisaka) --- hadoop-mapreduce-project/CHANGES.txt | 3 + .../src/main/resources/mapred-default.xml | 162 +++++++++--------- 2 files changed, 84 insertions(+), 81 deletions(-) diff --git a/hadoop-mapreduce-project/CHANGES.txt b/hadoop-mapreduce-project/CHANGES.txt index b55fa0d9ff..689cd1b9df 100644 --- a/hadoop-mapreduce-project/CHANGES.txt +++ b/hadoop-mapreduce-project/CHANGES.txt @@ -457,6 +457,9 @@ Release 2.8.0 - UNRELEASED MAPREDUCE-6574. MR AM should print host of failed tasks. (Mohammad Shahid Khan via wangda) + MAPREDUCE-6584. Remove trailing whitespaces from mapred-default.xml. + (aajisaka) + OPTIMIZATIONS MAPREDUCE-6376. Add avro binary support for jhist files (Ray Chiang via diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml index 6ece048aa4..962584c3e3 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml @@ -27,7 +27,7 @@ mapreduce.job.committer.setup.cleanup.needed true true, if job needs job-setup and job-cleanup. - false, otherwise + false, otherwise @@ -42,7 +42,7 @@ mapreduce.task.io.sort.mb 100 - The total amount of buffer memory to use while sorting + The total amount of buffer memory to use while sorting files, in megabytes. By default, gives each merge stream 1MB, which should minimize seeks. @@ -69,7 +69,7 @@ mapreduce.job.reduces 1 The default number of reduce tasks per job. Typically set to 99% - of the cluster's reduce capacity, so that if a node fails the reduces can + of the cluster's reduce capacity, so that if a node fails the reduces can still be executed in a single wave. Ignored when mapreduce.framework.name is "local". @@ -115,7 +115,7 @@ mapreduce.job.max.split.locations 10 - The max number of block locations to store for each split for + The max number of block locations to store for each split for locality calculation. @@ -123,7 +123,7 @@ mapreduce.job.split.metainfo.maxsize 10000000 - The maximum permissible size of the split metainfo file. + The maximum permissible size of the split metainfo file. The MapReduce ApplicationMaster won't attempt to read submitted split metainfo files bigger than this configured value. No limits if set to -1. @@ -157,7 +157,7 @@ mapreduce.reduce.shuffle.fetch.retry.interval-ms 1000 - Time of interval that fetcher retry to fetch again when some + Time of interval that fetcher retry to fetch again when some non-fatal failure happens because of some events like NM restart. @@ -165,7 +165,7 @@ mapreduce.reduce.shuffle.fetch.retry.timeout-ms 30000 - Timeout value for fetcher to retry to fetch again when some + Timeout value for fetcher to retry to fetch again when some non-fatal failure happens because of some events like NM restart. @@ -266,15 +266,15 @@ mapred.child.java.opts Java opts for the task processes. - The following symbol, if present, will be interpolated: @taskid@ is replaced + The following symbol, if present, will be interpolated: @taskid@ is replaced by current TaskID. Any other occurrences of '@' will go unchanged. For example, to enable verbose gc logging to a file named for the taskid in /tmp and to set the heap maximum to be a gigabyte, pass a 'value' of: -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc - + Usage of -Djava.library.path can cause programs to no longer function if - hadoop native libraries are used. These values should instead be set as part - of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and + hadoop native libraries are used. These values should instead be set as part + of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and mapreduce.reduce.env config settings. If -Xmx is not set, it is inferred from mapreduce.{map|reduce}.memory.mb and @@ -339,12 +339,12 @@ mapreduce.admin.user.env - Expert: Additional execution environment entries for + Expert: Additional execution environment entries for map and reduce task processes. This is not an additive property. You must preserve the original value if you want your map and - reduce tasks to have access to native libraries (compression, etc). - When this value is empty, the command to set execution - envrionment will be OS dependent: + reduce tasks to have access to native libraries (compression, etc). + When this value is empty, the command to set execution + envrionment will be OS dependent: For linux, use LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native. For windows, use PATH = %PATH%;%HADOOP_COMMON_HOME%\\bin. @@ -389,7 +389,7 @@ mapreduce.reduce.merge.inmem.threshold 1000 - The threshold, in terms of the number of files + The threshold, in terms of the number of files for the in-memory merge process. When we accumulate threshold number of files we initiate the in-memory merge and spill to disk. A value of 0 or less than 0 indicates we want to DON'T have any threshold and instead depend only on @@ -468,12 +468,12 @@ mapreduce.shuffle.transferTo.allowed - This option can enable/disable using nio transferTo method in - the shuffle phase. NIO transferTo does not perform well on windows in the - shuffle phase. Thus, with this configuration property it is possible to - disable it, in which case custom transfer method will be used. Recommended - value is false when running Hadoop on Windows. For Linux, it is recommended - to set it to true. If nothing is set then the default value is false for + This option can enable/disable using nio transferTo method in + the shuffle phase. NIO transferTo does not perform well on windows in the + shuffle phase. Thus, with this configuration property it is possible to + disable it, in which case custom transfer method will be used. Recommended + value is false when running Hadoop on Windows. For Linux, it is recommended + to set it to true. If nothing is set then the default value is false for Windows, and true for Linux. @@ -481,8 +481,8 @@ mapreduce.shuffle.transfer.buffer.size 131072 - This property is used only if - mapreduce.shuffle.transferTo.allowed is set to false. In that case, + This property is used only if + mapreduce.shuffle.transferTo.allowed is set to false. In that case, this property defines the size of the buffer used in the buffer copy code for the shuffle phase. The size of this buffer determines the size of the IO requests. @@ -500,14 +500,14 @@ mapreduce.map.speculative true - If true, then multiple instances of some map tasks + If true, then multiple instances of some map tasks may be executed in parallel. mapreduce.reduce.speculative true - If true, then multiple instances of some reduce tasks + If true, then multiple instances of some reduce tasks may be executed in parallel. @@ -555,7 +555,7 @@ of the collectors in turn. The first to successfully initialize will be used. - + mapreduce.job.speculative.slowtaskthreshold 1.0 @@ -654,14 +654,14 @@ mapreduce.task.files.preserve.failedtasks false - Should the files for failed tasks be kept. This should only be + Should the files for failed tasks be kept. This should only be used on jobs that are failing, because the storage is never reclaimed. It also prevents the map outputs from being erased from the reduce directory as they are consumed. -