<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><html>
<head>
<meta name="Generator" content="Zarafa WebAccess v7.1.7-42779">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>RE: [Gluster-users] Build disk tiering offer with GlusterFS</title>
<style type="text/css">
body
{
font-family: Arial, Verdana, Sans-Serif ! important;
font-size: 12px;
padding: 5px 5px 5px 5px;
margin: 0px;
border-style: none;
background-color: #ffffff;
}
p, ul, li
{
margin-top: 0px;
margin-bottom: 0px;
}
</style>
</head>
<body>
<p>Calors,</p><p> </p><p>Thank for your answer.</p><p> </p><p>The GlusterFS will be presented using NFS through a 10g network to a farm of KVM servers managed by Cloudstack.</p><p>I need space (1T hdd) and redundancy (GlusterFS) and want to have two disk offer (standard and faster)</p><p> </p><p>hug<br /> </p><blockquote style="border-left: 2px solid #325FBA; padding-left: 5px;margin-left:5px;">-----Message initial-----<br /><strong>De:</strong>        Carlos Capriotti <capriotti.carlos@gmail.com><br /><strong>Envoyé:</strong>        mar. 25-03-2014 19:10<br /><strong>Sujet:</strong>        Re: [Gluster-users] Build disk tiering offer with GlusterFS<br /><strong>À:</strong>        Hugues Lepesant <hugues@lepesant.com>; <br /><strong>Cc:</strong>        gluster-users@gluster.org; <br /><style type="text/css">body { font-family: monospace; }</style> <div dir="ltr">Hugues:<div> </div><div>I tend to agree with you with your disk setting for system. I have that myself and it is rock solid, and lightning fast. </div><div> </div><div>For your 11 x 1 To (tera octets, uh ? The French way), I'd tend to agree, because these 7.2 Krpm disks feel a bit slow, but for the 11x600 GB 15 Krpm... I think that will be a waste of diskspace. That is my IMPRESSION anyway, based on my similar 10x300 GB 10K rpm (PE2900 with PERC 5/i). This setting can peak 800 MBytes/second, and my worst reading with it are around 400 MBytes/s.</div> <div> </div><div>So, you can easily saturate regular network cards, in theory (1 Gbps), or at least, have a very decent data stream with 10 Gbps.</div><div> </div><div>My suggestion: install a quick test system with very basic tools on your 146 GB raid1 volume, just to be quick and do NOT include the data raid volumes.</div> <div> </div><div>Next, make performance tests with each variation, RAID 5, RAID6 (if you have it), and RAID50, with both disk sets.</div><div> </div><div>Well, supposing of course you have the the hardware available, which sounds you have.</div> <div> </div><div>KR, </div><div> </div><div>Carlos</div></div><div><br /><br /><div>On Tue, Mar 25, 2014 at 4:30 PM, Hugues Lepesant <span dir="ltr"><<a title="This external link will open in a new window" target="_blank" onclick="parent.webclient.openWindow(this, 'createmail', 'index.php?load=dialog&task=createmail_standard&to=hugues@lepesant.com'); return false;" href="mailto:hugues@lepesant.com">hugues@lepesant.com</a>></span> wrote:<br /> <blockquote style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> <div><p>Hi all,</p><p> </p><p>I can have Dell PowerEdge server with 3 groups of RAID drive.</p><p> </p><p>1st : 2x146Go in RAID1 for the system</p><p>2nd : 11x1To 7.2K RPM in RAID50 (with one spare)</p><p>3rd : 11x600Go 15K RPM in RAID50 (with one spare)</p> <p> </p><p>Can I make a kind of tiering with two gluster volumes, one for each speed of disk, and shared (by NFS) them on two IP address ?</p><p> </p><p>Regards,</p><p>Hugues</p><p> </p></div> <br />_______________________________________________<br /> Gluster-users mailing list<br /> <a title="This external link will open in a new window" target="_blank" onclick="parent.webclient.openWindow(this, 'createmail', 'index.php?load=dialog&task=createmail_standard&to=Gluster-users@gluster.org'); return false;" href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br /> <a title="This external link will open in a new window" target="_blank" href="http://supercolony.gluster.org/mailman/listinfo/gluster-users">http://supercolony.gluster.org/mailman/listinfo/gluster-users</a><br /></blockquote></div></div> </blockquote>
</body>
</html>