This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Home Products Support Community News


[Xen-API] Howto do a benchmark of VHD with/whthout local caching over NF

To: xen-api <xen-api@xxxxxxxxxxxxxxxxxxx>
Subject: [Xen-API] Howto do a benchmark of VHD with/whthout local caching over NFS?
From: Marco Sinhoreli <msinhore@xxxxxxxxx>
Date: Mon, 14 Mar 2011 13:52:43 -0300
Delivery-date: Mon, 14 Mar 2011 10:05:46 -0700
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:date:message-id:subject:from:to :content-type; bh=c4H3fPSXIXtK7NP+fTNBNdvHSX3PW3Jaon8iQKcoWi4=; b=E44wxL7No32rFmMvVnqi6fjmen7tAi9TLIFL2rFhGY77TaDl0awHm2bPlPrLw6LqKS wZUJ3d4d44n4jL86tL/IWsSFxGm7AayPw2V7OLDrZf+vsePEMayqTJeXprZ4+7UyQQLx NBVPD2cNVohTyM2VT5yFOwBuXR9nAmiubZR8Y=
Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:content-type; b=GnXBluy8eESdzXt3jhrX25bw4apHY46ErL65Ly7/nZsBXjiQNaOfy94/rxUm6lAAi9 Lock3NNOd1pQTYlAO2NQfp+SfmD4RlbfbRB/kdKxZsbNmPnoHR8hRrWf+xp6jyeyLOh4 nyflNYVeWcwx+LL4RBMW7ruFlcljrpxx+1fx8=
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-api-request@lists.xensource.com?subject=help>
List-id: Discussion of API issues surrounding Xen <xen-api.lists.xensource.com>
List-post: <mailto:xen-api@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-api>, <mailto:xen-api-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-api>, <mailto:xen-api-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-api-bounces@xxxxxxxxxxxxxxxxxxx
Hi all:

I'm trying to make a VM filesystem benchmark of XCP 1.0 using NFS with
local caching enabled and disabled. I'm using iozone.
My infrastructure is configured as above:

Storage: NetAPP - NFSv3 - 4x gbit ethernet aggregated with Jumbo Frame enabled.
All switches have 10 gbit/s port link and have Jumbo frame enabled in all ports
Servers: blade HP with 10 gbit ethernet - Nehalem processors model
L5640 (2 x 6 cores with Hyper-Threading) - 24GB RAM

The problem: I've 8 gbit/s to write and I think the host is making
cache. It's unfeasible my tests. The iozone is running over a CentOS
5.4 64bit.


Marco Sinhoreli

xen-api mailing list

<Prev in Thread] Current Thread [Next in Thread>