<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"><!-- P {margin-top:0;margin-bottom:0;} --></style>
</head>
<body dir="ltr">
<div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Arial,Helvetica,sans-serif;" dir="ltr">
<p><br>
</p>
Hi,
<div><br>
</div>
<div>Thank for your answer.</div>
<div><br>
</div>
<div><span style="font-size: 13.333333015441895px;">> 1) Do you mean 1,000 human users, or 1,000 machines doing NFS/CIFS mounts?</span><br style="font-size: 13.333333015441895px;">
<div>True, here the list:</div>
<div>- 800 users that have 1 workstation through 1Gb/s ethernet and will use NFS/CIFS</div>
<div>- 200 users that have 2 workstation through 1Gb/s ethernet, few have 10Gb/s ethernet and will use NFS/CIFS</div>
<div><br>
</div>
<span style="font-size: 13.333333015441895px;">> 2) How many of the users are likely to be active at the same time? 1,000</span><br style="font-size: 13.333333015441895px;">
<span style="font-size: 13.333333015441895px;">> users, each of whom are active an hour a week is entirely different from</span><br style="font-size: 13.333333015441895px;">
<span style="font-size: 13.333333015441895px;">> 200 users that are each active 140 hours a week.</span><br style="font-size: 13.333333015441895px;">
True again, around 200 users will actively use GPFS through NFS/CIFS during night and day, but we cannot control if people will use 2 workstations or more :(</div>
<div>We will have peak during day with an average of 700 'workstations'<br>
<br style="font-size: 13.333333015441895px;">
<span style="font-size: 13.333333015441895px;">> 3) What SLA/performance target are they expecting? If they want</span><br style="font-size: 13.333333015441895px;">
<span style="font-size: 13.333333015441895px;">> large 1TB I/O and 100MB/sec is acceptable, that's different than if they</span><br style="font-size: 13.333333015441895px;">
<span style="font-size: 13.333333015441895px;">> have a business need to go at 1.2GB/sec....</span></div>
<div>We just want to provide at normal throughput through an 1GB/s network. Users are aware of such situation and will mainly use HPC cluster for high speed and heavy computation. </div>
<div>But they would like to do 'light' computation on their desktop.</div>
<div>The main topic here is to sustain 'normal' throughput for all users during peak.</div>
<div><br>
</div>
<div>Thank for your help.</div>
<div> <br>
<div style="color: rgb(0, 0, 0);">
<div>
<hr tabindex="-1" style="display:inline-block; width:98%">
<div id="x_divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" color="#000000" style="font-size:11pt"><b>From:</b> valdis.kletnieks@vt.edu <valdis.kletnieks@vt.edu><br>
<b>Sent:</b> Saturday, April 22, 2017 6:30 AM<br>
<b>To:</b> gpfsug main discussion list<br>
<b>Subject:</b> Re: [gpfsug-discuss] Protocol node recommendations</font>
<div> </div>
</div>
</div>
<font size="2"><span style="font-size:10pt;">
<div class="PlainText">On Thu, 20 Apr 2017 12:27:13 -0000, Frank Tower said:<br>
<br>
> - some will do large I/O (e.g: store 1TB files)<br>
> - some will read/write more than 10k files in a raw<br>
> - other will do only sequential read<br>
<br>
> But I wondering if some people have recommendations regarding hardware sizing<br>
> and software tuning for such situation ?<br>
<br>
The three most critical pieces of info are missing here:<br>
<br>
1) Do you mean 1,000 human users, or 1,000 machines doing NFS/CIFS mounts?<br>
<br>
2) How many of the users are likely to be active at the same time? 1,000<br>
users, each of whom are active an hour a week is entirely different from<br>
200 users that are each active 140 hours a week.<br>
<br>
3) What SLA/performance target are they expecting? If they want<br>
large 1TB I/O and 100MB/sec is acceptable, that's different than if they<br>
have a business need to go at 1.2GB/sec....<br>
</div>
</span></font></div>
</div>
</div>
</body>
</html>