From user-return-34553-apmail-cassandra-user-archive=cassandra.apache.org@cassandra.apache.org Mon Jun 10 22:13:41 2013 Return-Path: X-Original-To: apmail-cassandra-user-archive@www.apache.org Delivered-To: apmail-cassandra-user-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id C138010BBD for ; Mon, 10 Jun 2013 22:13:41 +0000 (UTC) Received: (qmail 75593 invoked by uid 500); 10 Jun 2013 22:13:39 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 75516 invoked by uid 500); 10 Jun 2013 22:13:39 -0000 Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@cassandra.apache.org Delivered-To: mailing list user@cassandra.apache.org Received: (qmail 75508 invoked by uid 99); 10 Jun 2013 22:13:39 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 10 Jun 2013 22:13:39 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: local policy) Received: from [98.139.213.147] (HELO nm10-vm0.bullet.mail.bf1.yahoo.com) (98.139.213.147) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 10 Jun 2013 22:13:33 +0000 Received: from [98.139.215.140] by nm10.bullet.mail.bf1.yahoo.com with NNFMP; 10 Jun 2013 22:13:11 -0000 Received: from [98.139.212.192] by tm11.bullet.mail.bf1.yahoo.com with NNFMP; 10 Jun 2013 22:13:11 -0000 Received: from [127.0.0.1] by omp1001.mail.bf1.yahoo.com with NNFMP; 10 Jun 2013 22:13:11 -0000 X-Yahoo-Newman-Property: ymail-3 X-Yahoo-Newman-Id: 936981.68465.bm@omp1001.mail.bf1.yahoo.com Received: (qmail 97412 invoked by uid 60001); 10 Jun 2013 22:13:11 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1370902391; bh=7fh3+V7bvRMJEq87ILMccHql0+nTy8AV22v0UEYTYxM=; h=X-YMail-OSG:Received:X-Rocket-MIMEInfo:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type; b=FvFw4WK3p88RfcFgTWsi4rd47sSUji9KfAql8seRdlGK77Wz7ZU5c1TuRnk0jDXzFHe7UPxgUSdZTtxflmEROuwJmTf0gZK1blKT6qreW+P70UJwZwK9DkbUenpqTqHlGUNV/xnmoFdF2JIEJz0LNXSuP3YLeCCG63Z9bs1Bh38= DomainKey-Signature:a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:X-Rocket-MIMEInfo:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type; b=n8qRUq9K10u1SGHD0OBv/T4iIj0NKwF4aeDjaYmsNU0Oy9xQlhoqy/kYQ83DctjR8yap5sAaI41mytxaWQ6cVxFtN7NXAdT6/pwfGmJzQ1/d08sBae8wj9jlEK2mcEltyvr/x2glR+mzgITS/hnsR8VW2eqxeRwYQwbbzoG6WFM=; X-YMail-OSG: EFONxfAVM1mQx_KTNBD5zrd2XmjqQJYyy_S_qbzPrXj9bR7 E0fswcRA7B8DzxWkhb4OVkor._inuUbSwye1GCyq2h1ToPd_YZyF81MuihpS PuuEOKVL_leFuLVDPPZ3ibindDHvRNDLUYx5PnBmoTuKrhr6JRuBK9sSTt_h yjekzaBsnw0l8Y4dglLmeGziwd2UllvUbNLnTsw.Q5DtCUzIm6uBplBQFgmx hvCsCeHRA.DfLtbe3PGRLrV3qOOPXz1yWs9VIOyLHIre2EfINz7l1rq30hfN 0nTbyi57IZ_H1Ps3wrrCEdgc73RPiK8chWwnqBKkmpdnExseyT4jYUSU2uJJ qVc5Yjppp8ejbOBzuKnkSYsVfmjHYy_9wf0h41nw2z951wUvATUFBzDe_CZc mDhicYBGa18j_44MaiMrxWZPtmXqmUzCqziwVj0EXw53ZHPfnmPdUciyf2t9 NeD5MB1LBRq6QsC9LIp5xLGIunb0s4H2RY84PNGftR4.A6_uc2WYWh1wVbTe 1nJw4_IWWXC3KT8O.O4kHKw.UxE3vQn8u56KJHrPwMKvxAiq9QlBJ7gpX31B 4tlsQTAblo45C9.dIVEoZXfquPvYzcbXgIDKwQ7J1mWgxOF_TiS1s.yMoYiY LxgIkAZbe7154hCsvXL3PlCHURE7PQ6Ckr4FNUB51CDQNe0LZwMKVdA-- Received: from [198.95.226.40] by web162006.mail.bf1.yahoo.com via HTTP; Mon, 10 Jun 2013 15:13:11 PDT X-Rocket-MIMEInfo: 002.001,VGhhbmsgeW91IEVkd2FyZC4KCkkgc3VzcGVjdCB0aGF0IG5vZGV0b29sIGNsZWFudXAgaXMgSU8gaW50ZW5zaXZlLiBTbyBydW5uaW5nIG5vZGV0b29sIGNsZWFudXAgY29uY3VycmVudGx5IG9uIHRoZSBlbnRpcmUgY2x1c3RlciBtYXkgaGF2ZSBhIHNpZ25pZmljYW50bHkgaW1wYWN0IHRoZSBJTyDCoHBlcmZvcm1hbmNlIG9mIGFwcGxpY2F0aW9ucy4KCkFwYXJ0IGZyb20gdGhpcywgZG8geW91IHNlZSBhbnkgb3RoZXIgaW1wbGljYXRpb25zIG9uIHJ1bm5pbmcgdGhlIG5vZGV0b29sIGNsZWFudXAgY29uY3UBMAEBAQE- X-Mailer: YahooMailWebService/0.8.146.552 References: <1372322D3525455AA2CEAEC5E159FEB4@gmail.com> <6A747AD830B9440EA4669ACC8072599A@gmail.com> <1370898000.27157.YahooMailNeo@web162005.mail.bf1.yahoo.com> Message-ID: <1370902391.96634.YahooMailNeo@web162006.mail.bf1.yahoo.com> Date: Mon, 10 Jun 2013 15:13:11 -0700 (PDT) From: Emalayan Vairavanathan Reply-To: Emalayan Vairavanathan Subject: Re: [Cassandra] Expanding a Cassandra cluster To: "user@cassandra.apache.org" In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="1229592896-1333041356-1370902391=:96634" X-Virus-Checked: Checked by ClamAV on apache.org --1229592896-1333041356-1370902391=:96634 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Thank you Edward.=0A=0AI suspect that nodetool cleanup is IO intensive. So = running nodetool cleanup concurrently on the entire cluster may have a sign= ificantly impact the IO =A0performance of applications.=0A=0AApart from thi= s, do you see any other implications on running the nodetool cleanup concur= rently on the entire cluster ?=0A=0AThank you=0AEmalayan=0A=0A=0A__________= ______________________=0A From: Edward Capriolo =0AT= o: "user@cassandra.apache.org" ; Emalayan Vairav= anathan =0ASent: Monday, 10 June 2013 2:53 PM=0ASubj= ect: Re: [Cassandra] Expanding a Cassandra cluster=0A =0A=0A=0AYou eventual= ly should run cleanup to remove data no longer needed on the node. However = it does not need to be run quickly after a join. You can run it when you ge= t around to it. I would run it on a few nodes at a time until they are all = cleaned up.=0A=0A=0A=0A=0AOn Mon, Jun 10, 2013 at 5:00 PM, Emalayan Vairava= nathan wrote:=0A=0AHi All,=0A>=0A>=0A>Datastax manua= l suggests that during a Cassandra cluster expansion, an administrator has = to run nodetool cleanup on each of the previously existing Cassandra nodes = to remove the keys that are no longer belonging to those nodes. Further the= manual says that thenodetool cleanup =A0task should be run sequentially on= the existing Cassandra nodes.=0A>=0A>=0A>Reference:=A0http://www.datastax.= com/docs/1.2/operations/add_replace_nodes#adding-capacity=0A>=0A>=0A>Here i= s my problem: I have a very large Cassandra cluster with 100s of nodes and = running nodetool cleanup=A0sequentially will take a long time to finish.=A0= =0A>=0A>=0A>=A0Questions: a) So can someone tell me =A0about the implicatio= ns of running the nodetool cleanup concurrently on the entire cluster ?=0A>= =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0b) Will Cassandra automatically take= care of removing obsolete keys in future ?=0A>=0A>=0A>=0A>=0A>Thank youEma= layan=A0 --1229592896-1333041356-1370902391=:96634 Content-Type: text/html; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable
Thank you = Edward.

= I suspect that nodetool cleanup is IO intensive. So running nodetool cleanu= p concurrently on the entire cluster may have a significantly impact the IO=  performance of applications.

Apart from this, do you see any other implica= tions on running the nodetool cleanup concurrently on the entire cluster ?<= /span>

Thank yo= u
Emalayan


From: Edward Capriolo <edlinuxguru@gmail.com>
To: "user@cassandra.apache.org" <user@cassandr= a.apache.org>; Emalayan Vairavanathan <svemalayan@yahoo.com>
= Sent: Monday, 10 June 2013= 2:53 PM
Subject: Re: = [Cassandra] Expanding a Cassandra cluster

You eventua= lly should run cleanup to remove data no longer needed on the node. However= it does not need to be run quickly after a join. You can run it when you g= et around to it. I would run it on a few nodes at a time until they are all= cleaned up.
=0A


On Mon, Jun 10, 2013 at 5:00 PM, Emal= ayan Vairavanathan <svemalayan@yahoo.com> wrote:
=0A
Hi All,

=0ADatastax manual suggests that during a Cassandra cluster expansio= n, an administrator has to run nodetool c= leanup on each of the previously existing Cassandra nodes to remove = the keys that are no longer belonging to those nodes. Further the manual sa= ys that the nodetool cleanup  task should be run sequentially on the existing Cassandra nodes.
=0A<= div style=3D"font-style:normal;font-size:16px;background-color:transparent;= ">
=0A
Here is my problem: I have a very l= arge Cassandra cluster with 100s of nodes and running nodetool cleanup sequentially will take a long tim= e to finish. 
=0A

=0A Questions: a) So can so= meone tell me  about the implications of running the nodetool cleanup concurrently on the entire cluster= ?
=0A                 = ;  b) Will Cassandra automatically take care of removing obsolete keys= in future ?
=0A

=0AThank you
Emalayan 
=0A



=
--1229592896-1333041356-1370902391=:96634--