Posts by AMDave
| log in |
|
1)
Message boards :
Number crunching :
WUProp (nci) client using 48% CPU in Linux kernel 3.11.0
(Message 1823)
Posted 8 Nov 2013 by AMDave WUProp (nci) client using 48% CPU in Linux kernel 3.11.0 Observation: after upgrading to kernel 3.11.0 I observed the Data Collection version 4 4.11 continuously using 48% CPU on 2 cores of a 6 core CPU and 50% of 1 core on a 4 core CPU. It does not behave like this on the 2 core CPUs I have never seen this before, so I assume that it has something to do with the changes in linux kernel 3.11. Suspend and resume returns to the same state. Detach & re-attach returns to the same state. It is consistently not (nci) any more with Kernel 3.11 removing WUProp from these machines immediately |
|
2)
Message boards :
Number crunching :
3.3.27 estimates way off
(Message 637)
Posted 6 Oct 2011 by AMDave Looks like my estimates are coming down again. They exceeded 90 hours this morning, but now are back down to around 34 hours. |
|
3)
Message boards :
Number crunching :
3.3.27 estimates way off
(Message 636)
Posted 5 Oct 2011 by AMDave Hi Dirk. You are correct that the WUProp project sends only one work unit per client at a time. It is possible that the estimate baseline was reset when the latest client app was released on 29 Sept. http://wuprop.boinc-af.org/apps.php The original WUProp work units ran for much longer than the current length. On the AMD Users forum you also observe that the estimate is getting longer. I can confirm that I see the same thing on my clients also. That behaviour is a puzzle. There could be some other reason that the Admin may share with us? |