Return-Path: X-Original-To: apmail-cloudstack-users-archive@www.apache.org Delivered-To: apmail-cloudstack-users-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 0D40510850 for ; Thu, 4 Jul 2013 16:26:08 +0000 (UTC) Received: (qmail 27293 invoked by uid 500); 4 Jul 2013 16:26:07 -0000 Delivered-To: apmail-cloudstack-users-archive@cloudstack.apache.org Received: (qmail 27031 invoked by uid 500); 4 Jul 2013 16:26:06 -0000 Mailing-List: contact users-help@cloudstack.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: users@cloudstack.apache.org Delivered-To: mailing list users@cloudstack.apache.org Received: (qmail 27021 invoked by uid 99); 4 Jul 2013 16:26:05 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 04 Jul 2013 16:26:05 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_LOW,SPF_NEUTRAL X-Spam-Check-By: apache.org Received-SPF: error (nike.apache.org: encountered temporary error during SPF processing of domain of cgeiger@it1solutions.com) Received: from [216.32.180.187] (HELO co1outboundpool.messaging.microsoft.com) (216.32.180.187) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 04 Jul 2013 16:25:59 +0000 Received: from mail207-co1-R.bigfish.com (10.243.78.230) by CO1EHSOBE012.bigfish.com (10.243.66.75) with Microsoft SMTP Server id 14.1.225.22; Thu, 4 Jul 2013 16:25:17 +0000 Received: from mail207-co1 (localhost [127.0.0.1]) by mail207-co1-R.bigfish.com (Postfix) with ESMTP id 802FC30034B; Thu, 4 Jul 2013 16:25:17 +0000 (UTC) X-Forefront-Antispam-Report: CIP:173.227.255.201;KIP:(null);UIP:(null);IPV:NLI;H:exchange.itonesolutions.com;RD:exchange.itonesolutions.com;EFVD:NLI X-SpamScore: -3 X-BigFish: VPS-3(zzbb2dI98dI9371Ic85dh1432Izz1f42h1ee6h1de0h1fdah2073h1202h1e76h1d1ah1d2ah1fc6hzz18c673h8275bh8275dhz2ei2a8h668h839hbe3hd24hf0ah10d2h1288h12a5h12bdh137ah1441h14ddh1537h153bh162dh1631h1758h18deh18e1h1946h19b5h1b0ah1bceh1d0ch1d2eh1d3fh1dfeh1dffh1e1dh1155h) Received-SPF: neutral (mail207-co1: 173.227.255.201 is neither permitted nor denied by domain of it1solutions.com) client-ip=173.227.255.201; envelope-from=cgeiger@it1solutions.com; helo=exchange.itonesolutions.com ;olutions.com ; Received: from mail207-co1 (localhost.localdomain [127.0.0.1]) by mail207-co1 (MessageSwitch) id 1372955114150590_5272; Thu, 4 Jul 2013 16:25:14 +0000 (UTC) Received: from CO1EHSMHS015.bigfish.com (unknown [10.243.78.252]) by mail207-co1.bigfish.com (Postfix) with ESMTP id 22C57DC0049; Thu, 4 Jul 2013 16:25:14 +0000 (UTC) Received: from exchange.itonesolutions.com (173.227.255.201) by CO1EHSMHS015.bigfish.com (10.243.66.25) with Microsoft SMTP Server (TLS) id 14.1.225.23; Thu, 4 Jul 2013 16:25:13 +0000 Received: from EXCHANGE.itonesolutions.com ([fe80::c98e:c9dc:d61c:74ea]) by exchange.itonesolutions.com ([fe80::c98e:c9dc:d61c:74ea%15]) with mapi id 14.03.0123.003; Thu, 4 Jul 2013 12:26:06 -0400 From: Conrad Geiger To: "users@cloudstack.apache.org" , "aemneina@gmail.com" Subject: Re: How many vms per primary storage can offer best performance? Thread-Topic: How many vms per primary storage can offer best performance? Thread-Index: AQHOeLHmq37iWb9nEUimKZHi//t7xJlUwNQA///0Jf8= Date: Thu, 4 Jul 2013 16:26:05 +0000 Message-ID: <52bf5f553h0krdaq2s3jubnl.1372954788225@email.android.com> References: , In-Reply-To: Reply-To: Conrad Geiger Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: Content-Type: multipart/alternative; boundary="_000_52bf5f553h0krdaq2s3jubnl1372954788225emailandroidcom_" MIME-Version: 1.0 X-OriginatorOrg: it1solutions.com X-Virus-Checked: Checked by ClamAV on apache.org --_000_52bf5f553h0krdaq2s3jubnl1372954788225emailandroidcom_ Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable I would also say that 8 spindles for 15-20 VMs is low. You are going to ru= n out of iops. Sent from my Verizon Wireless 4G LTE Smartphone -------- Original message -------- From: Ahmad Emneina Date: 07/04/2013 9:10 AM (GMT-05:00) To: Cloudstack users mailing list Subject: Re: How many vms per primary storage can offer best performance? I would google NFS tuning and atomically test changes. Changes vary from the kernel level up through the switches (sizing frames) as well as introducing bonding. YMMV here NFS tuning is a huge part trial and error. On Thu, Jul 4, 2013 at 5:26 AM, WXR <1485739420@qq.com> wrote: > I use NFS share as primary storage,the NFS share is on a 8 SATA HDDs > RAID10 volume. > The network link is gigabit ethernet.The switch is dell powerconnect. > > When I just create 15-20 vm instances and start them(not run any software > on them),I find the disk IO performance of the vm is very low. > If a file copy job on a pc needs 10 minutes , the same job on the vm need= s > 20minutes. > > I don't know if it is normal,and I want to know the correct configuration > of the primary storage,I need your suggests with enough experience. --_000_52bf5f553h0krdaq2s3jubnl1372954788225emailandroidcom_--