From mapreduce-issues-return-91553-archive-asf-public=cust-asf.ponee.io@hadoop.apache.org Tue Apr 17 15:24:05 2018 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by mx-eu-01.ponee.io (Postfix) with SMTP id EE4DC180789 for ; Tue, 17 Apr 2018 15:24:04 +0200 (CEST) Received: (qmail 35182 invoked by uid 500); 17 Apr 2018 13:24:03 -0000 Mailing-List: contact mapreduce-issues-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Delivered-To: mailing list mapreduce-issues@hadoop.apache.org Received: (qmail 35043 invoked by uid 99); 17 Apr 2018 13:24:03 -0000 Received: from pnap-us-west-generic-nat.apache.org (HELO spamd1-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 17 Apr 2018 13:24:03 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd1-us-west.apache.org (ASF Mail Server at spamd1-us-west.apache.org) with ESMTP id 437BDC73ED for ; Tue, 17 Apr 2018 13:24:03 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd1-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: -109.501 X-Spam-Level: X-Spam-Status: No, score=-109.501 tagged_above=-999 required=6.31 tests=[ENV_AND_HDR_SPF_MATCH=-0.5, KAM_ASCII_DIVIDERS=0.8, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, USER_IN_DEF_SPF_WL=-7.5, USER_IN_WHITELIST=-100] autolearn=disabled Received: from mx1-lw-eu.apache.org ([10.40.0.8]) by localhost (spamd1-us-west.apache.org [10.40.0.7]) (amavisd-new, port 10024) with ESMTP id Wo0IaAXx12nL for ; Tue, 17 Apr 2018 13:24:02 +0000 (UTC) Received: from mailrelay1-us-west.apache.org (mailrelay1-us-west.apache.org [209.188.14.139]) by mx1-lw-eu.apache.org (ASF Mail Server at mx1-lw-eu.apache.org) with ESMTP id D2B125FC13 for ; Tue, 17 Apr 2018 13:24:01 +0000 (UTC) Received: from jira-lw-us.apache.org (unknown [207.244.88.139]) by mailrelay1-us-west.apache.org (ASF Mail Server at mailrelay1-us-west.apache.org) with ESMTP id CCD31E0CB4 for ; Tue, 17 Apr 2018 13:24:00 +0000 (UTC) Received: from jira-lw-us.apache.org (localhost [127.0.0.1]) by jira-lw-us.apache.org (ASF Mail Server at jira-lw-us.apache.org) with ESMTP id 39C1D241C8 for ; Tue, 17 Apr 2018 13:24:00 +0000 (UTC) Date: Tue, 17 Apr 2018 13:24:00 +0000 (UTC) From: "Jason Lowe (JIRA)" To: mapreduce-issues@hadoop.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Updated] (MAPREDUCE-7081) Default speculator won't speculate the last several submitted reduced task if the total task num is large MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394 [ https://issues.apache.org/jira/browse/MAPREDUCE-7081?page=3Dcom.atla= ssian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jason Lowe updated MAPREDUCE-7081: ---------------------------------- Summary: Default speculator won't speculate the last several submitted = reduced task if the total task num is large (was: Default speculator won't= sepculate the last several submitted reduced task if the total task num is= large) > Default speculator won't speculate the last several submitted reduced tas= k if the total task num is large > -------------------------------------------------------------------------= -------------------------------- > > Key: MAPREDUCE-7081 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-7081 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mrv2 > Affects Versions: 2.9.0, 2.7.5 > Reporter: Zhizhen Hou > Priority: Major > > DefaultSpeculator speculates a task one time.=C2=A0 By default, the numbe= r of speculators is max(max(10, 0.01 * tasks.size), 0.1 * running tasks). > I=C2=A0 set mapreduce.job.reduce.slowstart.completedmaps =3D 1 to start r= educe after all the map tasks are finished. The cluster has 1000 vcores, an= d the Job has 5000 reduce jobs. At first, 1000 reduces tasks can run simult= aneously, number of speculators can speculator at most is 0.1 * 1000 =3D 10= 0 tasks. Reduce tasks with less data can over shortly, and speculator will = speculator a task per second by default. The task be speculated execution m= ay be because the more data to be processed. It will speculator=C2=A0 100 t= asks within 100 seconds. When 4900 reduces is over, If a reduce is executed= with a lot of=C2=A0 data be processed and is put on a slow machine. The sp= eculate opportunity is running out, it will not be speculated. It can incre= ase the execution time of job significantly. > In short, it may waste the speculate opportunity at first only because th= e execution time of=C2=A0 reduce with less data to be processed as average = time. At=C2=A0 end of job, there is no speculate opportunity available, esp= ecially last several running tasks, judged the number of the running tasks = .=C2=A0=C2=A0 > In my opinion, the number of running tasks should not determine the numbe= r of speculate opportunity .The number of tasks be speculated can be judged= by square of finished task percent. Take an example, if ninety percent of= =C2=A0 the task is finished, only 0.9*0.9 =3D 0.81 speculate opportunity ca= n be used. It will leave enough opportunity for latter tasks. -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: mapreduce-issues-unsubscribe@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-help@hadoop.apache.org