Posts by Mumps [MM]

1) Message boards : News : GPU app - beta version for linux nvidia (Message 2234)
Posted 24 Mar 2019 by Mumps [MM]
Post:
Would it be possible for the Server Status page to separate the CPU/GPU WU counts out? So we can tell if there are GPU WU's available?
2) Message boards : Number crunching : Underutilized CPU (Message 1218)
Posted 7 Jan 2015 by Mumps [MM]
Post:
Yup. Bounded definitely looks a lot better. Thanks again for the tweak Eric!
3) Message boards : Number crunching : Underutilized CPU (Message 1211)
Posted 27 Dec 2014 by Mumps [MM]
Post:
OK, I've finished up all my older Bounded. I'll re-enable Bounded and watch a few systems. Thank Eric!
4) Message boards : Number crunching : Underutilized CPU (Message 1198)
Posted 18 Dec 2014 by Mumps [MM]
Post:
Sounds like you've got it. Looking at some of the systems still running Bounded, the sar activity shows 99-100% disk activity with 6+ running. 92% on an 8 core system running 4 Bounded. Those running UnBounded or other projects (even VM based ones) report negligible disk activity. So, I think I'll simply limit to one, maybe two Bounded at a time with an app_config.xml and let Unbounded consume the rest. :)
5) Message boards : Number crunching : Underutilized CPU (Message 1194)
Posted 17 Dec 2014 by Mumps [MM]
Post:
I've been having problems with my Linux hosts running Bounded recently. After digging in to it a bit this evening, it seems to be related to Multi-tasking and something the WU's are sharing causing the individual tasks to block, waiting for something one of the other WU's is locking. On my 8-32 core boxes, I've had a pile of WU's where they sit there idling with a Run State of "D" (Uninterruptable wait, probably IO) and the group of WU's together will only add up to a single full core worth of CPU utilization. If I abort half of them, the remaining ones that are running double their actual CPU utilization, but still leave tons of idle cores. For now, I'm going to limit the systems to only running a single WU at a time, but I wonder what could be the cause of this behavior so I can get back to running full out. :) I've ended up cancelling lots of WU's that have run for *days* and the stats report significantly less CPU time consumed than Wall time. Here's one example:

http://numberfields.asu.edu/NumberFields/workunit.php?wuid=9092322

I'm also going to try switching to the Unbounded to see if this affects both Linux apps.
6) Message boards : Number crunching : This computer has reached a limit on tasks in progress (10) (Message 204)
Posted 16 Sep 2011 by Mumps [MM]
Post:
If it's of concern to have other hosts, with fewer cores, having 24 jobs waiting, it's fine to leave the setting lower. I was more thinking about getting it to just match the number of Procs a given host has. I noticed many of my 4 thread boxes now had 16 tasks, so there's going to be many more waiting on other hosts out there. And I recall you not wanting to waste much effort in case some of the WU's end up being numbers that get factored elsewhere and represent work no longer needed.

As I mentioned, BOINC is good at allowing you to share resources with other projects. So it's not a big deal to me if I spend a couple cores on something else. :-)
7) Message boards : Number crunching : This computer has reached a limit on tasks in progress (10) (Message 198)
Posted 14 Sep 2011 by Mumps [MM]
Post:
Thanks. You may not have noticed, but some of my hosts actually have 24 cores. 8-)
8) Message boards : Number crunching : This computer has reached a limit on tasks in progress (10) (Message 194)
Posted 13 Sep 2011 by Mumps [MM]
Post:
Hmmm. I guess I should have my hosts with more than 10 cores doing something else to keep them busy. :)

Unless the admin is interested in setting the limit to at least match the number of CPU's a host happens to have.





Main page · Your account · Message boards


Copyright © 2024 Arizona State University