From user-return-35544-apmail-cassandra-user-archive=cassandra.apache.org@cassandra.apache.org Wed Jul 24 15:16:52 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 4D7E5107F1 for ; Wed, 24 Jul 2013 15:16:52 +0000 (UTC) Received: (qmail 88245 invoked by uid 500); 24 Jul 2013 15:16:49 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 88218 invoked by uid 500); 24 Jul 2013 15:16:48 -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 88210 invoked by uid 99); 24 Jul 2013 15:16:48 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 24 Jul 2013 15:16:48 +0000 X-ASF-Spam-Status: No, hits=1.5 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_LOW,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: domain of a.e.cobley@dundee.ac.uk designates 213.199.154.206 as permitted sender) Received: from [213.199.154.206] (HELO am1outboundpool.messaging.microsoft.com) (213.199.154.206) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 24 Jul 2013 15:16:44 +0000 Received: from mail31-am1-R.bigfish.com (10.3.201.238) by AM1EHSOBE014.bigfish.com (10.3.207.136) with Microsoft SMTP Server id 14.1.225.22; Wed, 24 Jul 2013 15:16:21 +0000 Received: from mail31-am1 (localhost [127.0.0.1]) by mail31-am1-R.bigfish.com (Postfix) with ESMTP id 139362A0248 for ; Wed, 24 Jul 2013 15:16:21 +0000 (UTC) X-Forefront-Antispam-Report: CIP:157.56.249.53;KIP:(null);UIP:(null);IPV:NLI;H:AMSPRD0411HT005.eurprd04.prod.outlook.com;RD:none;EFVD:NLI X-SpamScore: 0 X-BigFish: PS0(zz98dIc85fhzz1f42h208ch1ee6h1de0h1d18h1fdah2073h1202h1e76h1d1ah1d2ah1fc6hz31iz1de098h17326ah18c673h1de097h1de096h8275bhz2fh2a8h668h839hd25he5bhf0ah1288h12a5h12bdh137ah1441h1504h1537h153bh162dh1631h1758h18e1h1946h19b5h1ad9h1b0ah1bceh1d0ch1d2eh1d3fh1dfeh1dffh1e1dh1155h) Received-SPF: pass (mail31-am1: domain of dundee.ac.uk designates 157.56.249.53 as permitted sender) client-ip=157.56.249.53; envelope-from=a.e.cobley@dundee.ac.uk; helo=AMSPRD0411HT005.eurprd04.prod.outlook.com ;.outlook.com ; Received: from mail31-am1 (localhost.localdomain [127.0.0.1]) by mail31-am1 (MessageSwitch) id 1374678979334512_27634; Wed, 24 Jul 2013 15:16:19 +0000 (UTC) Received: from AM1EHSMHS009.bigfish.com (unknown [10.3.201.227]) by mail31-am1.bigfish.com (Postfix) with ESMTP id 4A95D340047 for ; Wed, 24 Jul 2013 15:16:19 +0000 (UTC) Received: from AMSPRD0411HT005.eurprd04.prod.outlook.com (157.56.249.53) by AM1EHSMHS009.bigfish.com (10.3.207.109) with Microsoft SMTP Server (TLS) id 14.16.227.3; Wed, 24 Jul 2013 15:16:18 +0000 Received: from AMSPRD0411MB437.eurprd04.prod.outlook.com ([169.254.4.178]) by AMSPRD0411HT005.eurprd04.prod.outlook.com ([10.255.62.168]) with mapi id 14.16.0329.000; Wed, 24 Jul 2013 15:16:18 +0000 From: Andrew Cobley To: "" Subject: Re: Cassandra and RAIDs Thread-Topic: Cassandra and RAIDs Thread-Index: AQHOiHtr2orbNHH9XU612leNeqfAgplz8IyA Date: Wed, 24 Jul 2013 15:16:17 +0000 Message-ID: <9163598F-8720-4934-A84D-558B07D1FA88@dundee.ac.uk> References: In-Reply-To: Accept-Language: en-GB, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: Content-Type: multipart/alternative; boundary="_000_9163598F87204934A84D558B07D1FA88dundeeacuk_" MIME-Version: 1.0 X-OriginatorOrg: dundee.ac.uk X-FOPE-CONNECTOR: Id%0$Dn%*$RO%0$TLS%0$FQDN%$TlsDn% X-Virus-Checked: Checked by ClamAV on apache.org --_000_9163598F87204934A84D558B07D1FA88dundeeacuk_ Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable From: http://www.datastax.com/docs/1.2/cluster_architecture/cluster_planning * RAID on data disks: It is generally not necessary to use RAID for the= following reasons: * Data is replicated across the cluster based on the replication factor= you've chosen. * Starting in version 1.2, Cassandra includes takes care of disk manage= ment with the JBOD (Just a bunch of disks) support feature. Because Cassand= ra properly reacts to a disk failure, based on your availability/consistenc= y requirements, either by stopping the affected node or by blacklisting the= failed drive, this allows you to deploy Cassandra nodes with large disk ar= rays without the overhead of RAID 10. * RAID on the commit log disk: Generally RAID is not needed for the com= mit log disk. Replication adequately prevents data loss. If you need the ex= tra redundancy, use RAID 1. Andy On 24 Jul 2013, at 15:36, Jan Algermissen > wrote: Hi, second question: is it recommended to set up Cassandra using 'RAID-ed' disks for per-node re= liability or do people usually just rely on having the multiple nodes anywa= y - why bother with replicated disks? Jan The University of Dundee is a registered Scottish Charity, No: SC015096 --_000_9163598F87204934A84D558B07D1FA88dundeeacuk_ Content-Type: text/html; charset="us-ascii" Content-ID: Content-Transfer-Encoding: quoted-printable From:


  • RAID on data disks: It is generally not= necessary to use RAID for the following reasons:

    • Data is replicated across the cluster based on the replication factor y= ou've chosen.
    • Starting in version 1.2, Cassandra includes takes care of disk man= agement with the JBOD (Just a bunch of disks) support feature. Because Cass= andra properly reacts to a disk failure, based on your availability/consist= ency requirements, either by stopping the affected node or by blacklisting the failed drive, this allows you to = deploy Cassandra nodes with large disk arrays without the overhead of RAID = 10.
  • RAID on the commit log disk: Generally = RAID is not needed for the commit log disk. Replication adequately prevents= data loss. If you need the extra redundancy, use RAID 1.



    Andy

    On 24 Jul 2013, at 15:36, Jan Algermissen <jan.algermissen@nordsc.com> wrote:

    Hi,

    second question:

    is it recommended to set up Cassandra using 'RAID-ed' disks for per-node re= liability or do people usually just rely on having the multiple nodes anywa= y - why bother with replicated disks?

    Jan


  • The University of Dundee is a registered Sco= ttish Charity, No: SC015096 --_000_9163598F87204934A84D558B07D1FA88dundeeacuk_--