Return-Path: X-Original-To: apmail-cassandra-commits-archive@www.apache.org Delivered-To: apmail-cassandra-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 39903F902 for ; Fri, 12 Dec 2014 16:40:14 +0000 (UTC) Received: (qmail 60032 invoked by uid 500); 12 Dec 2014 16:40:14 -0000 Delivered-To: apmail-cassandra-commits-archive@cassandra.apache.org Received: (qmail 59992 invoked by uid 500); 12 Dec 2014 16:40:14 -0000 Mailing-List: contact commits-help@cassandra.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@cassandra.apache.org Delivered-To: mailing list commits@cassandra.apache.org Received: (qmail 59980 invoked by uid 99); 12 Dec 2014 16:40:13 -0000 Received: from arcas.apache.org (HELO arcas.apache.org) (140.211.11.28) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 12 Dec 2014 16:40:13 +0000 Date: Fri, 12 Dec 2014 16:40:13 +0000 (UTC) From: "Yuki Morishita (JIRA)" To: commits@cassandra.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Updated] (CASSANDRA-8193) Multi-DC parallel snapshot repair 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/CASSANDRA-8193?page=3Dcom.atla= ssian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yuki Morishita updated CASSANDRA-8193: -------------------------------------- Attachment: 8193-followup.txt Patch to change API not to use RepairParallelism. Instead, methods take int= value that matches RepairParallelism ordinal. > Multi-DC parallel snapshot repair > --------------------------------- > > Key: CASSANDRA-8193 > URL: https://issues.apache.org/jira/browse/CASSANDRA-8193 > Project: Cassandra > Issue Type: Improvement > Reporter: Jimmy M=C3=A5rdell > Assignee: Jimmy M=C3=A5rdell > Priority: Minor > Fix For: 2.0.12, 2.1.3 > > Attachments: 8193-followup.txt, cassandra-2.0-8193-1.txt, cassand= ra-2.0-8193-2.txt > > > The current behaviour of snapshot repair is to let one node at a time cal= culate a merkle tree. This is to ensure only one node at a time is doing th= e expensive calculation. The drawback is that it takes even longer time to = do the merkle tree calculation. > In a multi-DC setup, I think it would make more sense to have one node in= each DC calculate the merkle tree at the same time. This would yield a sig= nificant improvement when you have many data centers. > I'm not sure how relevant this is in 2.1, but I don't see us upgrading to= 2.1 any time soon. Unless there is an obvious drawback that I'm missing, I= 'd like to implement this in the 2.0 branch. -- This message was sent by Atlassian JIRA (v6.3.4#6332)