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 704F7188CF for ; Fri, 17 Jul 2015 21:08:57 +0000 (UTC) Received: (qmail 192 invoked by uid 500); 17 Jul 2015 21:08:54 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 148 invoked by uid 500); 17 Jul 2015 21:08:54 -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 138 invoked by uid 99); 17 Jul 2015 21:08:54 -0000 Received: from Unknown (HELO spamd3-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 17 Jul 2015 21:08:54 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd3-us-west.apache.org (ASF Mail Server at spamd3-us-west.apache.org) with ESMTP id E62FF185FD7 for ; Fri, 17 Jul 2015 21:08:53 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd3-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: 2.979 X-Spam-Level: ** X-Spam-Status: No, score=2.979 tagged_above=-999 required=6.31 tests=[HTML_MESSAGE=3, RCVD_IN_MSPIKE_H3=-0.01, RCVD_IN_MSPIKE_WL=-0.01, SPF_PASS=-0.001] autolearn=disabled Received: from mx1-us-east.apache.org ([10.40.0.8]) by localhost (spamd3-us-west.apache.org [10.40.0.10]) (amavisd-new, port 10024) with ESMTP id 7hFDDTU9x18A for ; Fri, 17 Jul 2015 21:08:53 +0000 (UTC) Received: from mail-la0-f47.google.com (mail-la0-f47.google.com [209.85.215.47]) by mx1-us-east.apache.org (ASF Mail Server at mx1-us-east.apache.org) with ESMTPS id C254842AA9 for ; Fri, 17 Jul 2015 21:08:52 +0000 (UTC) Received: by lahh5 with SMTP id h5so67618894lah.2 for ; Fri, 17 Jul 2015 14:08:45 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:from:date:message-id:subject:to :content-type; bh=8mfHcFEUloItUMNje2QkDZvd3phsL0Xx/YO7zf52/Uc=; b=iZrPEGkZt/HCJR839zXX1Rq4bIoLEc81qIrOXQjbllDq9DZe+vzhJTTq6//B96e6a9 agB+jAPEXEKBCYQhIDHZcZgNL+rWC4+rUrjwCwix5KNOJ2IYcjlwAeaglRN9gWg+9zT2 kvoJ8VDLYvvakXxPF3IuREIOBcsoT8XbulkQqlIrfq8h3OFucoF7lAh3CPyfPK+uG47t h+fUX3wj3GqTXId+dXGOJPazJXvLCEwriLApXbaHPMZUQKYoH2C1iSDaeFWAbiTh4URL EzLPNLhcyZzTE36nITkcriv0WdJjtl8D3ci3sTnsqgFF1qXJwMt6DhHOHYZ+FcblkO6Y 9fJQ== X-Gm-Message-State: ALoCoQmDlGZj7nwYdVBgK27asTBQSSsAt8wQESTlefWug5HP9zQogZZVBvk+5KGPIeb0wk6Bm930 X-Received: by 10.152.19.8 with SMTP id a8mr16229397lae.121.1437167325903; Fri, 17 Jul 2015 14:08:45 -0700 (PDT) MIME-Version: 1.0 Received: by 10.25.83.72 with HTTP; Fri, 17 Jul 2015 14:08:26 -0700 (PDT) From: Soerian Lieve Date: Fri, 17 Jul 2015 14:08:26 -0700 Message-ID: Subject: Unbalanced disk load To: user@cassandra.apache.org Content-Type: multipart/alternative; boundary=089e01493b94f1985d051b189765 --089e01493b94f1985d051b189765 Content-Type: text/plain; charset=UTF-8 Hi, I am currently benchmarking Cassandra with three machines, and on each machine I am seeing an unbalanced distribution of data among the data directories (1 per disk). I am concerned that this affects my write performance, is there anything that I can make the distribution be more even? Would raid0 be my best option? Details: 3 machines, each have 24 cores, 64GB of RAM, 7 SSDs of 500GB each. Commitlog is on a separate disk, cassandra.yaml configured according to Datastax' guide on cassandra.yaml. Total size of data is about 2TB, 14B records, all unique. Replication factor of 1. Thanks, Soerian --089e01493b94f1985d051b189765 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable
Hi,

I am currently benchmarking Cassand= ra with three machines, and on each machine I am seeing an unbalanced distr= ibution of data among the data directories (1 per disk).=C2=A0
I = am concerned that this affects my write performance, is there anything that= I can make the distribution be more even? Would raid0 be my best option?

Details:
3 machines, each have 24 cores, = 64GB of RAM, 7 SSDs of 500GB each.=C2=A0
Commitlog is on a separa= te disk, cassandra.yaml configured according to Datastax' guide on cass= andra.yaml.
Total size of data is about 2TB, 14B records, all= unique. Replication factor of 1.

Thanks,
Soerian
--089e01493b94f1985d051b189765--