Return-Path: X-Original-To: apmail-hbase-issues-archive@www.apache.org Delivered-To: apmail-hbase-issues-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 79E9118B00 for ; Thu, 17 Dec 2015 02:40:48 +0000 (UTC) Received: (qmail 22293 invoked by uid 500); 17 Dec 2015 02:40:47 -0000 Delivered-To: apmail-hbase-issues-archive@hbase.apache.org Received: (qmail 22103 invoked by uid 500); 17 Dec 2015 02:40:47 -0000 Mailing-List: contact issues-help@hbase.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Delivered-To: mailing list issues@hbase.apache.org Received: (qmail 21914 invoked by uid 99); 17 Dec 2015 02:40:47 -0000 Received: from arcas.apache.org (HELO arcas) (140.211.11.28) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 17 Dec 2015 02:40:47 +0000 Received: from arcas.apache.org (localhost [127.0.0.1]) by arcas (Postfix) with ESMTP id DAB842C1F76 for ; Thu, 17 Dec 2015 02:40:46 +0000 (UTC) Date: Thu, 17 Dec 2015 02:40:46 +0000 (UTC) From: "Jingcheng Du (JIRA)" To: issues@hbase.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Commented] (HBASE-14460) [Perf Regression] Merge of MVCC and SequenceId (HBASE-HBASE-8763) slowed Increments, CheckAndPuts, batch operations 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/HBASE-14460?page=3Dcom.atlassia= n.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=3D150= 61361#comment-15061361 ]=20 Jingcheng Du commented on HBASE-14460: -------------------------------------- [~stack], I got your and [~eclark]'s ideas. It tries to use write lock to g= uarantee there is not earlier entries on this row. Does it impact if the wal sync is included in the write lock (During the te= st, it uses WAL_SKIP, right?)? What if users enable the wal, would it be mu= ch worse? Please advise. > [Perf Regression] Merge of MVCC and SequenceId (HBASE-HBASE-8763) slowed = Increments, CheckAndPuts, batch operations > -------------------------------------------------------------------------= ------------------------------------------ > > Key: HBASE-14460 > URL: https://issues.apache.org/jira/browse/HBASE-14460 > Project: HBase > Issue Type: Bug > Components: Performance > Reporter: stack > Assignee: stack > Priority: Critical > Attachments: 0.94.test.patch, 0.98.test.patch, 1.0.80.flamegraph-= 7932.svg, 14460.txt, 98.80.flamegraph-11428.svg, HBASE-14460-discussion.pat= ch, client.test.patch, flamegraph-13120.svg.master.singlecell.svg, flamegra= ph-26636.094.100.svg, flamegraph-28066.098.singlecell.svg, flamegraph-28767= .098.100.svg, flamegraph-31647.master.100.svg, flamegraph-9466.094.singlece= ll.svg, hack.flamegraph-16593.svg, hack.uncommitted.patch, m.test.patch, re= gion_lock.png, testincrement.094.patch, testincrement.098.patch, testincrem= ent.master.patch > > > As reported by =E9=88=B4=E6=9C=A8=E4=BF=8A=E8=A3=95 up on the mailing lis= t -- see "Performance degradation between CDH5.3.1(HBase0.98.6) and CDH5.4.= 5(HBase1.0.0)" -- our unification of sequenceid and MVCC slows Increments (= and other ops) as the mvcc needs to 'catch up' to our current point before = we can read the last Increment value that we need to update. > We can say that our Increment is just done wrong, we should just be writi= ng Increments and summing on read, but checkAndPut as well as batching oper= ations have the same issue. Fix. -- This message was sent by Atlassian JIRA (v6.3.4#6332)