<html><body><p><font size="2">Hi,</font><br><br><font size="2">when it comes to clusters of this size then 150 nodes per collector rule of thumb is a good way to start. So 3-4 collector nodes should be OK for your setup. </font><br><font size="2">The GUI(s) can also be installed on those nodes as well.</font><br><font size="2">Collector nodes mainly need a good amount of RAM as all 'current' incoming sensor data is kept there.</font><br><font size="2">Local disk is typically not stressed heavily, plain HDD or simple onboard RAID is sufficient, plan for 20-50 GB disc space on each node.</font><br><font size="2">For network no special requirements are needed, default should be whatever is used in the cluster anyway.</font><br><br><font size="2" face="Arial">Mit freundlichen Grüßen / Kind regards</font><p><b><font face="Arial">Norbert Schuld</font></b><br><br><font size="1" color="#999999" face="Arial">IBM Deutschland Research & Development GmbH / Vorsitzender des Aufsichtsrats: Martina Koederitz /Geschäftsführung: Dirk Wittkopp <br>Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB 243294 </font><br><br><img width="16" height="16" src="cid:1__=8FBB0837DFBBC1058f9e8a93df938690918c8FB@" border="0" alt="Inactive hide details for David Johnson ---31/05/2018 20:22:02---We are planning to bring up the new ZIMon tools on our 450+ no"><font size="2" color="#424282">David Johnson ---31/05/2018 20:22:02---We are planning to bring up the new ZIMon tools on our 450+ node cluster, and need to purchase new n</font><br><br><font size="2" color="#5F5F5F">From: </font><font size="2">David Johnson <david_johnson@brown.edu></font><br><font size="2" color="#5F5F5F">To: </font><font size="2">gpfsug main discussion list <gpfsug-discuss@spectrumscale.org></font><br><font size="2" color="#5F5F5F">Date: </font><font size="2">31/05/2018 20:22</font><br><font size="2" color="#5F5F5F">Subject: </font><font size="2">[gpfsug-discuss] recommendations for gpfs 5.x GUI and perf/health monitoring collector nodes</font><br><font size="2" color="#5F5F5F">Sent by: </font><font size="2">gpfsug-discuss-bounces@spectrumscale.org</font><br><hr width="100%" size="2" align="left" noshade style="color:#8091A5; "><br><br><br><tt><font size="2">We are planning to bring up the new ZIMon tools on our 450+ node cluster, and need to purchase new<br>nodes to run the collector federation and GUI function on. What would you choose as a platform for this?<br> — memory size?<br> — local disk space — SSD? shared?<br> — net attach — 10Gig? 25Gig? IB?<br> — CPU horse power — single or dual socket?<br>I think I remember somebody in Cambridge UG meeting saying 150 nodes per collector as a rule of thumb, so<br>we’re guessing a federation of 4 nodes would do it. Does this include the GUI host(s) or are those separate?<br>Finally, we’re still using client/server based licensing model, do these nodes count as clients?<br><br>Thanks,<br> — ddj<br>Dave Johnson<br>Brown University<br>_______________________________________________<br>gpfsug-discuss mailing list<br>gpfsug-discuss at spectrumscale.org<br></font></tt><tt><font size="2"><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a></font></tt><tt><font size="2"><br><br></font></tt><br><BR>
</body></html>