Return-Path: Delivered-To: apmail-cassandra-user-archive@www.apache.org Received: (qmail 76689 invoked from network); 7 Jul 2010 06:29:15 -0000 Received: from unknown (HELO mail.apache.org) (140.211.11.3) by 140.211.11.9 with SMTP; 7 Jul 2010 06:29:15 -0000 Received: (qmail 34130 invoked by uid 500); 7 Jul 2010 06:29:14 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 33964 invoked by uid 500); 7 Jul 2010 06:29:11 -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 33954 invoked by uid 99); 7 Jul 2010 06:29:10 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 07 Jul 2010 06:29:10 +0000 X-ASF-Spam-Status: No, hits=2.0 required=10.0 tests=MIME_QP_LONG_LINE,RCVD_IN_BL_SPAMCOP_NET,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (nike.apache.org: local policy) Received: from [88.198.48.29] (HELO eaerendil.duergner.eu) (88.198.48.29) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 07 Jul 2010 06:29:02 +0000 Received: from [10.170.160.129] (unknown [89.204.137.65]) by eaerendil.duergner.eu (Postfix) with ESMTPSA id AC6BB64578 for ; Wed, 7 Jul 2010 08:28:11 +0200 (CEST) References: In-Reply-To: Mime-Version: 1.0 (iPhone Mail 8A293) Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=us-ascii Message-Id: Cc: "user@cassandra.apache.org" X-Mailer: iPhone Mail (8A293) From: =?utf-8?Q?Michael_D=C3=BCrgner?= Subject: Re: EC2 small instance config? Date: Wed, 7 Jul 2010 08:27:38 +0200 To: "user@cassandra.apache.org" X-Virus-Checked: Checked by ClamAV on apache.org Have you done some testing with small nodes already? Because from what we sa= w trying to run IO bound services on small instances is, that their IO perfo= rmance is really bad compared to other instance types as you can read in sev= eral blogs. Would be interesting to hear, if a Cassandra cluster can handle that. Sent from my iPhone On 07.07.2010, at 07:30, Andrew Rollins wrote: > Anyone using Amazon EC2 small instances for a production cluster under rea= sonably high loads (perhaps hundreds or low thousands ops/sec)? >=20 > I'm looking for an example storage-conf.xml file to use as a guide. If you= 've done one and would be willing to share, please let me know. >=20 > I'm willing to bet a few people think running a few small nodes in a clust= er is a bad idea and that maybe I should just use one or two large instances= , but it should be doable for the throughput I'm targeting. Using smalls als= o provides a better spread of data (more smaller nodes equals more cuts of t= he data, which means less data to move after node failure). >=20 > - Andrew