<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
Sven,
<div class=""><br class="">
</div>
<div class="">It’s been a while since I tried that, but the last time I tried to limit the impact of a restripe by only running it on a few NSD server nodes it made things worse. Everybody was as slowed down as they would’ve been if I’d thrown every last NSD
server we have at it and they were slowed down for longer, since using fewer NSD servers meant the restripe ran longer.</div>
<div class=""><br class="">
</div>
<div class="">What we do is always kick off restripes on a Friday afternoon, throw every NSD server we have at them, and let them run over the weekend. Interactive use is lower then and people don’t notice or care if their batch jobs run longer.</div>
<div class=""><br class="">
</div>
<div class="">Of course, this is all just my experiences. YMMV...</div>
<div class=""><br class="">
</div>
<div class="">Kevin</div>
<div class=""><br class="">
<div>
<blockquote type="cite" class="">
<div class="">On Jul 1, 2015, at 9:21 AM, Sven Oehme <<a href="mailto:oehmes@us.ibm.com" class="">oehmes@us.ibm.com</a>> wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<div class="">
<p class="">Daniel,<br class="">
<br class="">
as you know, we can't discuss future / confidential items on a mailing list. <br class="">
what i presented as an outlook to future releases hasn't changed from a technical standpoint, we just can't share a release date until we announce it official.<br class="">
there are multiple ways today to limit the impact on restripe and other tasks, the best way to do this is to run the task ( using -N) on a node (or very small number of nodes) that has no performance critical role. while this is not perfect, it should limit
the impact significantly. .<br class="">
<br class="">
sven<br class="">
<br class="">
------------------------------------------<br class="">
Sven Oehme <br class="">
Scalable Storage Research <br class="">
email: <a href="mailto:oehmes@us.ibm.com" class="">oehmes@us.ibm.com</a> <br class="">
Phone: +1 (408) 824-8904 <br class="">
IBM Almaden Research Lab <br class="">
------------------------------------------<br class="">
<br class="">
<span id="cid:1__=07BBF4E6DFDDF49C8f9e8a93df938690918c07B@"><graycol.gif></span><font color="#424282" class="">Daniel Vogel ---07/01/2015 03:29:11 AM---Hi Years ago, IBM made some plan to do a implementation "QoS for mmrestripefs, mmdeldisk...". If a "</font><br class="">
<br class="">
<font size="2" color="#5F5F5F" class="">From: </font><font size="2" class="">Daniel Vogel <<a href="mailto:Daniel.Vogel@abcsystems.ch" class="">Daniel.Vogel@abcsystems.ch</a>></font><br class="">
<font size="2" color="#5F5F5F" class="">To: </font><font size="2" class="">"'<a href="mailto:gpfsug-discuss@gpfsug.org" class="">gpfsug-discuss@gpfsug.org</a>'" <<a href="mailto:gpfsug-discuss@gpfsug.org" class="">gpfsug-discuss@gpfsug.org</a>></font><br class="">
<font size="2" color="#5F5F5F" class="">Date: </font><font size="2" class="">07/01/2015 03:29 AM</font><br class="">
<font size="2" color="#5F5F5F" class="">Subject: </font><font size="2" class="">[gpfsug-discuss] GPFS 4.1.1 without QoS for mmrestripefs?</font><br class="">
<font size="2" color="#5F5F5F" class="">Sent by: </font><font size="2" class=""><a href="mailto:gpfsug-discuss-bounces@gpfsug.org" class="">gpfsug-discuss-bounces@gpfsug.org</a></font><br class="">
</p>
<hr width="100%" size="2" align="left" noshade="" style="color:#8091A5; " class="">
<br class="">
<br class="">
<br class="">
<font face="Calibri" class="">Hi</font><br class="">
<font face="Calibri" class=""></font><br class="">
<font face="Calibri" class="">Years ago, IBM made some plan to do a implementation “QoS for mmrestripefs, mmdeldisk…”. If a “mmfsrestripe” is running, very poor performance for NFS access.</font><br class="">
<font face="Calibri" class="">I opened a PMR to ask for QoS in version 4.1.1 (Spectrum Scale).</font><br class="">
<font face="Calibri" class=""></font><br class="">
<font face="Calibri" class="">PMR 61309,113,848:</font><br class="">
<i class=""><font face="Arial" class="">I discussed the question of QOS with the development team. These
<br class="">
command changes that were noticed are not meant to be used as GA code<br class="">
which is why they are not documented. I cannot provide any further <br class="">
information from the support perspective. </font></i><font face="Arial" class=""><br class="">
</font><br class="">
<font face="Calibri" class=""></font><br class="">
<font face="Calibri" class="">Anybody knows about QoS? The last hope was at “GPFS Workshop Stuttgart März 2015” with Sven Oehme as speaker.</font><br class="">
<font face="Calibri" class=""></font><br class="">
<font face="Calibri" class="">Daniel Vogel</font><br class="">
<font face="Calibri" class="">IT Consultant</font><br class="">
<font face="Calibri" class=""></font><br class="">
<b class=""><font face="Calibri" class="">ABC SYSTEMS AG</font></b><br class="">
<font face="Calibri" class="">Hauptsitz Zürich</font><br class="">
<font face="Calibri" class="">Rütistrasse 28</font><br class="">
<font face="Calibri" class="">CH - 8952 Schlieren</font><br class="">
<font face="Calibri" class="">T +41 43 433 6 433</font><br class="">
<font face="Calibri" class="">D +41 43 433 6 467</font><br class="">
<font face="Calibri" class=""><a href="http://www.abcsystems.ch/" class="">http://www.abcsystems.ch</a></font><br class="">
<font face="Calibri" class=""></font><br class="">
<b class=""><i class=""><font color="#1F497D" face="Calibri" class="">ABC - A</font></i></b><i class=""><font color="#1F497D" face="Calibri" class="">lways
</font></i><b class=""><i class=""><font color="#1F497D" face="Calibri" class="">B</font></i></b><i class=""><font color="#1F497D" face="Calibri" class="">etter
</font></i><b class=""><i class=""><font color="#1F497D" face="Calibri" class="">C</font></i></b><i class=""><font color="#1F497D" face="Calibri" class="">oncepts.
</font></i><b class=""><i class=""><font color="#1F497D" face="Calibri" class="">A</font></i></b><i class=""><font color="#1F497D" face="Calibri" class="">pproved
</font></i><b class=""><i class=""><font color="#1F497D" face="Calibri" class="">B</font></i></b><i class=""><font color="#1F497D" face="Calibri" class="">y
</font></i><b class=""><i class=""><font color="#1F497D" face="Calibri" class="">C</font></i></b><i class=""><font color="#1F497D" face="Calibri" class="">ustomers since 1981.</font></i><br class="">
<font face="Calibri" class=""></font><tt class="">_______________________________________________<br class="">
gpfsug-discuss mailing list<br class="">
gpfsug-discuss at <a href="http://gpfsug.org" class="">gpfsug.org</a><br class="">
</tt><tt class=""><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss" class="">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a></tt><tt class=""><br class="">
</tt><br class="">
<br class="">
<br class="">
</div>
_______________________________________________<br class="">
gpfsug-discuss mailing list<br class="">
gpfsug-discuss at <a href="http://gpfsug.org" class="">gpfsug.org</a><br class="">
<a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss" class="">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a><br class="">
</div>
</blockquote>
</div>
<br class="">
<div class="">
<div class="">—</div>
<div class="">Kevin Buterbaugh - Senior System Administrator</div>
<div class="">Vanderbilt University - Advanced Computing Center for Research and Education</div>
<div class=""><a href="mailto:Kevin.Buterbaugh@vanderbilt.edu" class="">Kevin.Buterbaugh@vanderbilt.edu</a> - (615)875-9633</div>
<div class=""><br class="">
</div>
<br class="Apple-interchange-newline">
</div>
<br class="">
</div>
</body>
</html>