Return-Path: X-Original-To: archive-asf-public-internal@cust-asf2.ponee.io Delivered-To: archive-asf-public-internal@cust-asf2.ponee.io Received: from cust-asf.ponee.io (cust-asf.ponee.io [163.172.22.183]) by cust-asf2.ponee.io (Postfix) with ESMTP id 6F64A200B8A for ; Fri, 9 Sep 2016 12:32:22 +0200 (CEST) Received: by cust-asf.ponee.io (Postfix) id 6DF6E160AB6; Fri, 9 Sep 2016 10:32:22 +0000 (UTC) Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by cust-asf.ponee.io (Postfix) with SMTP id B7C2B160AC2 for ; Fri, 9 Sep 2016 12:32:21 +0200 (CEST) Received: (qmail 9752 invoked by uid 500); 9 Sep 2016 10:32:20 -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 9670 invoked by uid 99); 9 Sep 2016 10:32:20 -0000 Received: from arcas.apache.org (HELO arcas) (140.211.11.28) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 09 Sep 2016 10:32:20 +0000 Received: from arcas.apache.org (localhost [127.0.0.1]) by arcas (Postfix) with ESMTP id A052B2C1B7B for ; Fri, 9 Sep 2016 10:32:20 +0000 (UTC) Date: Fri, 9 Sep 2016 10:32:20 +0000 (UTC) From: "binlijin (JIRA)" To: issues@hbase.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Comment Edited] (HBASE-16594) ROW_INDEX_V2 DBE MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394 archived-at: Fri, 09 Sep 2016 10:32:22 -0000 [ https://issues.apache.org/jira/browse/HBASE-16594?page=3Dcom.atlassia= n.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=3D154= 76744#comment-15476744 ]=20 binlijin edited comment on HBASE-16594 at 9/9/16 10:31 AM: ----------------------------------------------------------- The performance on a single regionserver is : BlockSize=EF=BC=9D8K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 4/42=EF=BC=89 37k BlockSize=EF=BC=9D16K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 3/41=EF=BC=89 41k BlockSize=EF=BC=9D32K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 3/45=EF=BC=89 43k BlockSize=EF=BC=9D64K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 3/46=EF=BC=89 36k BlockSize=EF=BC=9D32k DATA_BLOCK_ENCODING =3D> 'Row_Index_V1' =EF=BC=88CPU = 4/45=EF=BC=89 45k BlockSize=EF=BC=9D32k DATA_BLOCK_ENCODING =3D> 'Row_Index_V2' =EF=BC=88CPU = 4/48=EF=BC=89 64k =EF=BC=88CPU 4/42=EF=BC=89 which mean System CPU 4%=EF=BC=8CUser CPU 42%. was (Author: aoxiang): The performance on a single regionserver is : BlockSize=EF=BC=9D8K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 4/42=EF=BC=89 37k BlockSize=EF=BC=9D16K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 3/41=EF=BC=89 41k BlockSize=EF=BC=9D32K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 3/45=EF=BC=89 43k BlockSize=EF=BC=9D64K DATA_BLOCK_ENCODING =3D> 'NONE' =EF=BC=88CPU = 3/46=EF=BC=89 36k BlockSize=EF=BC=9D32k DATA_BLOCK_ENCODING =3D> 'Row_Index_V1' =EF=BC=88CPU = 4/45=EF=BC=89 45k BlockSize=EF=BC=9D32k DATA_BLOCK_ENCODING =3D> 'Row_Index_V2' =EF=BC=88CPU = 4/48=EF=BC=89 64k > ROW_INDEX_V2 DBE > ---------------- > > Key: HBASE-16594 > URL: https://issues.apache.org/jira/browse/HBASE-16594 > Project: HBase > Issue Type: Sub-task > Components: Performance > Reporter: binlijin > Fix For: 2.0.0, 1.4.0 > > Attachments: HBASE-16594-master_v1.patch > > > See HBASE-16213, ROW_INDEX_V1 DataBlockEncoding. > ROW_INDEX_V1 is the first version which have no storage optimization,=20 > ROW_INDEX_V2 do storage optimization: store every row only once, store co= lumn family only once in a HFileBlock. > ROW_INDEX_V1 is :=20 > /**=20 > * Store cells following every row's start offset, so we can binary searc= h to a row's cells.=20 > *=20 > * Format:=20 > * flat cells=20 > * integer: number of rows=20 > * integer: row0's offset=20 > * integer: row1's offset=20 > * ....=20 > * integer: dataSize=20 > *=20 > */ > ROW_INDEX_V2 is : > * row1 qualifier timestamp type value tag > * qualifier timestamp type value tag > * qualifier timestamp type value tag > * row2 qualifier timestamp type value tag > * row3 qualifier timestamp type value tag > * qualifier timestamp type value tag > * ....=20 > * integer: number of rows=20 > * integer: row0's offset=20 > * integer: row1's offset=20 > * ....=20 > * column family > * integer: dataSize=20 -- This message was sent by Atlassian JIRA (v6.3.4#6332)