[
https://issues.apache.org/jira/browse/MAPREDUCE-6806?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Tianyin Xu updated MAPREDUCE-6806:
----------------------------------
Status: Patch Available (was: Open)
> Trim configuration values in gridmix/DistributedCacheEmulator.java
> ------------------------------------------------------------------
>
> Key: MAPREDUCE-6806
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-6806
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: contrib/gridmix
> Affects Versions: 3.0.0-alpha1
> Reporter: Tianyin Xu
> Priority: Minor
> Attachments: MAPREDUCE-6806.0000.patch
>
>
> The current implementation of {{DistributedCacheEmulator.java}} in
> {{gridmix}} does not follow the practice of trimming configuration values.
> This leads to errors if users set values containing space or newline.
> see the previous commits as reference (just list a few):
> HADOOP-6578. Configuration should trim whitespace around a lot of value types
> HADOOP-6534. Trim whitespace from directory lists initializing
> Patch is available against trunk
> HDFS-9708. FSNamesystem.initAuditLoggers() doesn't trim classnames
> HDFS-2799. Trim fs.checkpoint.dir values.
> YARN-3395. FairScheduler: Trim whitespaces when using username for queuename.
> YARN-2869. CapacityScheduler should trim sub queue names when parse
> configuration.
> Patch is available against trunk (tested):
> {code:title=DistributedCacheEmulator.java|borderStyle=solid}
> index 72027c1..eb12723 100644
> ---
> a/hadoop-tools/hadoop-gridmix/src/main/java/org/apache/hadoop/mapred/gridmix/DistributedCacheEmulator.java
> +++
> b/hadoop-tools/hadoop-gridmix/src/main/java/org/apache/hadoop/mapred/gridmix/DistributedCacheEmulator.java
> @@ -315,14 +315,14 @@ void updateHDFSDistCacheFilesList(JobStory jobdesc)
> throws IOException {
> // paths, to be used by this simulated job.
> JobConf jobConf = jobdesc.getJobConf();
> - String[] files = jobConf.getStrings(MRJobConfig.CACHE_FILES);
> + String[] files = jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILES);
> if (files != null) {
> - String[] fileSizes = jobConf.getStrings(MRJobConfig.CACHE_FILES_SIZES);
> + String[] fileSizes =
> jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILES_SIZES);
> String[] visibilities =
> - jobConf.getStrings(MRJobConfig.CACHE_FILE_VISIBILITIES);
> + jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILE_VISIBILITIES);
> String[] timeStamps =
> - jobConf.getStrings(MRJobConfig.CACHE_FILE_TIMESTAMPS);
> + jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILE_TIMESTAMPS);
> FileSystem fs = FileSystem.get(conf);
> String user = jobConf.getUser();
> @@ -495,7 +495,7 @@ void configureDistCacheFiles(Configuration conf, JobConf
> jobConf)
> throws IOException {
> if (shouldEmulateDistCacheLoad()) {
> - String[] files = jobConf.getStrings(MRJobConfig.CACHE_FILES);
> + String[] files = jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILES);
> if (files != null) {
> // hdfs based distributed cache files to be configured for simulated
> job
> List<String> cacheFiles = new ArrayList<String>();
> @@ -504,10 +504,10 @@ void configureDistCacheFiles(Configuration conf,
> JobConf jobConf)
> List<String> localCacheFiles = new ArrayList<String>();
> String[] visibilities =
> - jobConf.getStrings(MRJobConfig.CACHE_FILE_VISIBILITIES);
> + jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILE_VISIBILITIES);
> String[] timeStamps =
> - jobConf.getStrings(MRJobConfig.CACHE_FILE_TIMESTAMPS);
> - String[] fileSizes =
> jobConf.getStrings(MRJobConfig.CACHE_FILES_SIZES);
> + jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILE_TIMESTAMPS);
> + String[] fileSizes =
> jobConf.getTrimmedStrings(MRJobConfig.CACHE_FILES_SIZES);
> String user = jobConf.getUser();
> for (int i = 0; i < files.length; i++) {
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
