From 853cc0466811c310486fff6042d7b76ab3b78947 Mon Sep 17 00:00:00 2001 From: Akira Ajisaka Date: Sat, 28 Mar 2015 03:35:03 +0900 Subject: [PATCH] MAPREDUCE-5762. Port MAPREDUCE-3223 (Remove MRv1 config from mapred-default.xml) to branch-2. (aajisaka) --- hadoop-mapreduce-project/CHANGES.txt | 3 + .../src/main/resources/mapred-default.xml | 478 +----------------- 2 files changed, 20 insertions(+), 461 deletions(-) diff --git a/hadoop-mapreduce-project/CHANGES.txt b/hadoop-mapreduce-project/CHANGES.txt index 37eaf7b37a7..d0dfd5fb34c 100644 --- a/hadoop-mapreduce-project/CHANGES.txt +++ b/hadoop-mapreduce-project/CHANGES.txt @@ -42,6 +42,9 @@ Release 2.8.0 - UNRELEASED CompletedJob#loadFullHistoryData for code optimization. (zxu via rkanter) + MAPREDUCE-5762. Port MAPREDUCE-3223 (Remove MRv1 config from + mapred-default.xml) to branch-2. (aajisaka) + OPTIMIZATIONS BUG FIXES 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 b093f35a25b..f57ddd67dd9 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 @@ -23,47 +23,6 @@ - - mapreduce.jobtracker.jobhistory.location - - If job tracker is static the history files are stored - in this single well known place. If No value is set here, by default, - it is in the local file system at ${hadoop.log.dir}/history. - - - - - mapreduce.jobtracker.jobhistory.task.numberprogresssplits - 12 - Every task attempt progresses from 0.0 to 1.0 [unless - it fails or is killed]. We record, for each task attempt, certain - statistics over each twelfth of the progress range. You can change - the number of intervals we divide the entire range of progress into - by setting this property. Higher values give more precision to the - recorded data, but costs more memory in the job tracker at runtime. - Each increment in this attribute costs 16 bytes per running task. - - - - - mapreduce.job.userhistorylocation - - User can specify a location to store the history files of - a particular job. If nothing is specified, the logs are stored in - output directory. The files are stored in "_logs/history/" in the directory. - User can stop logging by giving the value "none". - - - - - mapreduce.jobtracker.jobhistory.completed.location - - The completed job history files are stored at this single well - known location. If nothing is specified, the files are stored at - ${mapreduce.jobtracker.jobhistory.location}/done. - - - mapreduce.job.committer.setup.cleanup.needed true @@ -98,15 +57,6 @@ set to less than .5 - - mapreduce.jobtracker.address - local - The host and port that the MapReduce job tracker runs - at. If "local", then jobs are run in-process as a single map - and reduce task. - - - mapreduce.local.clientfactory.class.name org.apache.hadoop.mapred.LocalClientFactory @@ -114,139 +64,11 @@ creating local job runner client - - mapreduce.jobtracker.http.address - 0.0.0.0:50030 - - The job tracker http server address and port the server will listen on. - If the port is 0 then the server will start on a free port. - - - - - mapreduce.jobtracker.handler.count - 10 - - The number of server threads for the JobTracker. This should be roughly - 4% of the number of tasktracker nodes. - - - - - mapreduce.tasktracker.report.address - 127.0.0.1:0 - The interface and port that task tracker server listens on. - Since it is only connected to by the tasks, it uses the local interface. - EXPERT ONLY. Should only be changed if your host does not have the loopback - interface. - - - - mapreduce.cluster.local.dir - ${hadoop.tmp.dir}/mapred/local - The local directory where MapReduce stores intermediate - data files. May be a comma-separated list of - directories on different devices in order to spread disk i/o. - Directories that do not exist are ignored. - - - - - mapreduce.jobtracker.system.dir - ${hadoop.tmp.dir}/mapred/system - The directory where MapReduce stores control files. - - - - - mapreduce.jobtracker.staging.root.dir - ${hadoop.tmp.dir}/mapred/staging - The root of the staging area for users' job files - In practice, this should be the directory where users' home - directories are located (usually /user) - - - - - mapreduce.cluster.temp.dir - ${hadoop.tmp.dir}/mapred/temp - A shared directory for temporary files. - - - - - mapreduce.tasktracker.local.dir.minspacestart - 0 - If the space in mapreduce.cluster.local.dir drops under this, - do not ask for more tasks. - Value in bytes. - - - - - mapreduce.tasktracker.local.dir.minspacekill - 0 - If the space in mapreduce.cluster.local.dir drops under this, - do not ask more tasks until all the current ones have finished and - cleaned up. Also, to save the rest of the tasks we have running, - kill one of them, to clean up some space. Start with the reduce tasks, - then go with the ones that have finished the least. - Value in bytes. - - - - - mapreduce.jobtracker.expire.trackers.interval - 600000 - Expert: The time-interval, in miliseconds, after which - a tasktracker is declared 'lost' if it doesn't send heartbeats. - - - - - mapreduce.tasktracker.instrumentation - org.apache.hadoop.mapred.TaskTrackerMetricsInst - Expert: The instrumentation class to associate with each TaskTracker. - - - - - mapreduce.tasktracker.resourcecalculatorplugin - - - Name of the class whose instance will be used to query resource information - on the tasktracker. - - The class must be an instance of - org.apache.hadoop.util.ResourceCalculatorPlugin. If the value is null, the - tasktracker attempts to use a class appropriate to the platform. - Currently, the only platform supported is Linux. - - - - - mapreduce.tasktracker.taskmemorymanager.monitoringinterval - 5000 - The interval, in milliseconds, for which the tasktracker waits - between two cycles of monitoring its tasks' memory usage. Used only if - tasks' memory management is enabled via mapred.tasktracker.tasks.maxmemory. - - - - - mapreduce.tasktracker.tasks.sleeptimebeforesigkill - 5000 - The time, in milliseconds, the tasktracker waits for sending a - SIGKILL to a task, after it has been sent a SIGTERM. This is currently - not used on WINDOWS where tasks are just sent a SIGTERM. - - - mapreduce.job.maps 2 The default number of map tasks per job. - Ignored when mapreduce.jobtracker.address is "local". + Ignored when mapreduce.framework.name is "local". @@ -256,34 +78,10 @@ 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 still be executed in a single wave. - Ignored when mapreduce.jobtracker.address is "local". + Ignored when mapreduce.framework.name is "local". - - mapreduce.jobtracker.restart.recover - false - "true" to enable (job) recovery upon restart, - "false" to start afresh - - - - - mapreduce.jobtracker.jobhistory.block.size - 3145728 - The block size of the job history file. Since the job recovery - uses job history, its important to dump job history to disk as - soon as possible. Note that this is an expert level parameter. - The default value is set to 3 MB. - - - - - mapreduce.jobtracker.taskscheduler - org.apache.hadoop.mapred.JobQueueTaskScheduler - The class responsible for scheduling the tasks. - - mapreduce.job.running.map.limit 0 @@ -322,20 +120,12 @@ mapreduce.job.split.metainfo.maxsize 10000000 The maximum permissible size of the split metainfo file. - The JobTracker won't attempt to read split metainfo files bigger than - the configured value. + The MapReduce ApplicationMaster won't attempt to read submitted split metainfo + files bigger than this configured value. No limits if set to -1. - - mapreduce.jobtracker.taskscheduler.maxrunningtasks.perjob - - The maximum number of running tasks for a job before - it gets preempted. No limits if undefined. - - - mapreduce.map.maxattempts 4 @@ -395,7 +185,7 @@ mapreduce.reduce.shuffle.connect.timeout 180000 Expert: The maximum amount of time (in milli seconds) reduce - task spends in trying to connect to a tasktracker for getting map output. + task spends in trying to connect to a remote node for getting map output. @@ -432,22 +222,6 @@ - - mapreduce.tasktracker.map.tasks.maximum - 2 - The maximum number of map tasks that will be run - simultaneously by a task tracker. - - - - - mapreduce.tasktracker.reduce.tasks.maximum - 2 - The maximum number of reduce tasks that will be run - simultaneously by a task tracker. - - - mapreduce.map.memory.mb 1024 @@ -480,36 +254,6 @@ - - mapreduce.jobtracker.retiredjobs.cache.size - 1000 - The number of retired job status to keep in the cache. - - - - - mapreduce.tasktracker.outofband.heartbeat - false - Expert: Set this to true to let the tasktracker send an - out-of-band heartbeat on task-completion for better latency. - - - - - mapreduce.jobtracker.jobhistory.lru.cache.size - 5 - The number of job history files loaded in memory. The jobs are - loaded when they are first accessed. The cache is cleared based on LRU. - - - - - mapreduce.jobtracker.instrumentation - org.apache.hadoop.mapred.JobTrackerMetricsInst - Expert: The instrumentation class to associate with each JobTracker. - - - mapred.child.java.opts -Xmx200m @@ -806,14 +550,6 @@ - - mapreduce.job.jvm.numtasks - 1 - How many tasks to run per jvm. If set to -1, there is - no limit. - - - mapreduce.job.ubertask.enable false @@ -884,13 +620,6 @@ - - mapreduce.jobtracker.maxtasks.perjob - -1 - The maximum number of tasks for a single job. - A value of -1 indicates that there is no maximum. - - mapreduce.input.lineinputformat.linespermap 1 @@ -898,6 +627,7 @@ to include in each split. + mapreduce.client.submit.file.replication 10 @@ -906,41 +636,6 @@ - - - mapreduce.tasktracker.dns.interface - default - The name of the Network Interface from which a task - tracker should report its IP address. - - - - - mapreduce.tasktracker.dns.nameserver - default - The host name or IP address of the name server (DNS) - which a TaskTracker should use to determine the host name used by - the JobTracker for communication and display purposes. - - - - - mapreduce.tasktracker.http.threads - 40 - The number of worker threads that for the http server. This is - used for map output fetching - - - - - mapreduce.tasktracker.http.address - 0.0.0.0:50060 - - The task tracker http server address and port. - If the port is 0 then the server will start on a free port. - - - mapreduce.task.files.preserve.failedtasks false @@ -1073,54 +768,10 @@ - - mapreduce.job.userlog.retain.hours - 24 - The maximum time, in hours, for which the user-logs are to be - retained after the job completion. - - - - - mapreduce.jobtracker.hosts.filename - - Names a file that contains the list of nodes that may - connect to the jobtracker. If the value is empty, all hosts are - permitted. - - - - mapreduce.jobtracker.hosts.exclude.filename - - Names a file that contains the list of hosts that - should be excluded by the jobtracker. If the value is empty, no - hosts are excluded. - - - - mapreduce.jobtracker.heartbeats.in.second - 100 - Expert: Approximate number of heart-beats that could arrive - at JobTracker in a second. Assuming each RPC can be processed - in 10msec, the default value is made 100 RPCs in a second. - - - - - mapreduce.jobtracker.tasktracker.maxblacklists - 4 - The number of blacklists for a taskTracker by various jobs - after which the task tracker could be blacklisted across - all jobs. The tracker will be given a tasks later - (after a day). The tracker will become a healthy - tracker after a restart. - - - mapreduce.job.maxtaskfailures.per.tracker 3 - The number of task-failures on a tasktracker of a given job + The number of task-failures on a node manager of a given job after which new tasks of that job aren't assigned to it. It MUST be less than mapreduce.map.maxattempts and mapreduce.reduce.maxattempts otherwise the failed task will @@ -1142,8 +793,8 @@ mapreduce.client.completion.pollinterval 5000 The interval (in milliseconds) between which the JobClient - polls the JobTracker for updates about job status. You may want to set this - to a lower value to make tests run faster on a single node system. Adjusting + polls the MapReduce ApplicationMaster for updates about job status. You may want to + set this to a lower value to make tests run faster on a single node system. Adjusting this value in production may lead to unwanted client-server traffic. @@ -1158,32 +809,6 @@ - - mapreduce.jobtracker.persist.jobstatus.active - true - Indicates if persistency of job status information is - active or not. - - - - - mapreduce.jobtracker.persist.jobstatus.hours - 1 - The number of hours job status information is persisted in DFS. - The job status information will be available after it drops of the memory - queue and between jobtracker restarts. With a zero value the job status - information is not persisted at all in DFS. - - - - - mapreduce.jobtracker.persist.jobstatus.dir - /jobtracker/jobsInfo - The directory where the job status information is persisted - in a file system to be available after it drops of the memory queue and - between jobtracker restarts. - - mapreduce.task.profile @@ -1241,8 +866,8 @@ The number of Task attempts AFTER which skip mode will be kicked off. When skip mode is kicked off, the tasks reports the range of records which it will process - next, to the TaskTracker. So that on failures, TT knows which - ones are possibly the bad records. On further executions, + next, to the MR ApplicationMaster. So that on failures, the MR AM + knows which ones are possibly the bad records. On further executions, those are skipped. @@ -1325,15 +950,6 @@ - - mapreduce.jobtracker.taskcache.levels - 2 - This is the max level of the task cache. For example, if - the level is 2, the tasks cached are at the host level and at the rack - level. - - - mapreduce.job.queuename default @@ -1359,13 +975,13 @@ Specifies whether ACLs should be checked for authorization of users for doing various queue and job level operations. ACLs are disabled by default. If enabled, access control checks are made by - JobTracker and TaskTracker when requests are made by users for queue + MapReduce ApplicationMaster when requests are made by users for queue operations like submit job to a queue and kill a job in the queue and job operations like viewing the job-details (See mapreduce.job.acl-view-job) or for modifying the job (See mapreduce.job.acl-modify-job) using Map/Reduce APIs, RPCs or via the console and web user interfaces. - For enabling this flag(mapreduce.cluster.acls.enabled), this is to be set - to true in mapred-site.xml on JobTracker node and on all TaskTracker nodes. + For enabling this flag, set to true in mapred-site.xml file of all + MapReduce clients (MR job submitting nodes). @@ -1418,8 +1034,8 @@ o job-level counters o task-level counters o tasks' diagnostic information - o task-logs displayed on the TaskTracker web-UI and - o job.xml showed by the JobTracker's web-UI + o task-logs displayed on the HistoryServer's web-UI and + o job.xml showed by the HistoryServer's web-UI Every other piece of information of jobs is still accessible by any other user, for e.g., JobStatus, JobProfile, list of jobs in the queue, etc. @@ -1436,14 +1052,6 @@ - - mapreduce.tasktracker.indexcache.mb - 10 - The maximum memory that a task tracker allows for the - index cache that is used when serving map outputs to reducers. - - - mapreduce.job.token.tracking.ids.enabled false @@ -1465,7 +1073,7 @@ mapreduce.task.merge.progress.records 10000 The number of records to process during merge before - sending a progress notification to the TaskTracker. + sending a progress notification to the MR ApplicationMaster. @@ -1493,22 +1101,6 @@ - - mapreduce.tasktracker.taskcontroller - org.apache.hadoop.mapred.DefaultTaskController - TaskController which is used to launch and manage task execution - - - - - mapreduce.tasktracker.group - - Expert: Group to which TaskTracker belongs. If - LinuxTaskController is configured via mapreduce.tasktracker.taskcontroller, - the group owner of the task-controller binary should be same as this group. - - - mapreduce.shuffle.port 13562 @@ -1528,42 +1120,6 @@ - - - - mapreduce.tasktracker.healthchecker.script.path - - Absolute path to the script which is - periodicallyrun by the node health monitoring service to determine if - the node is healthy or not. If the value of this key is empty or the - file does not exist in the location configured here, the node health - monitoring service is not started. - - - - mapreduce.tasktracker.healthchecker.interval - 60000 - Frequency of the node health script to be run, - in milliseconds - - - - mapreduce.tasktracker.healthchecker.script.timeout - 600000 - Time after node health script should be killed if - unresponsive and considered that the script has failed. - - - - mapreduce.tasktracker.healthchecker.script.args - - List of arguments which are to be passed to - node health script when it is being launched comma seperated. - - - - -