| Re: [ptp-user] IBM LoadLeveler (Eclipse Iuno RC3 Build id: 20120606-2254) |
|
On Wednesday, June 20, 2012 11:03:20 Greg Watson wrote: > The monitoring is not working because LL 5.1 changed the default output from > the llstatus command from 'machine' to 'cluster'. We should have a fix for > this in 6.0.1. In the mean time, you can edit the file > '.eclipsesettings/rms/LL/da_nodes_info_LML.pl' and change the line > 'open(IN," $cmd -l |");' to 'open(IN," $cmd -L machine -l |");'.
Greg,
I guess, you meant the .eclipsesettings on the remote $HOME ?
I did the change as follows. di69job@login03:~/.eclipsesettings/rms/LL> pwd /home/hpc/pr63vu/di69job/.eclipsesettings/rms/LL di69job@login03:~/.eclipsesettings/rms/LL> grep open da_nodes_info_LML.pl open(IN," $cmd -L machine -l |"); open(OUT,"> $filename") || die "cannot open file $filename";
Then I restarted eclipse, opened the monitoring view, and switched on monitoring for remote connection "SuperMUC".
This caused my eclipse to hang. The eclipse screen froze, the process eclipse took more CPU load than a single core (typically CPU1 100%, CPU2 38%). I had to kill eclipse (signal terminate), which put the CPU-load back to normal and made the fan of my TP go quiet again.
Could it be that the perl script is overwhelmed by the number of machines ?
I executed the following command to test on the amount of output lines to be scanned by perl. di69job@login03:~/.eclipsesettings/rms/LL> /usr/bin/llstatus -L machine -l \ | wc 706948 2451395 23667162
Could that pose a problem ?
At least the llstatus command returns OK on the command line.
--
Mit freundlichen Grüßen / Kind regards
Dr. Christoph Pospiech High Performance & Parallel Computing Phone: +49-351 86269826 Mobile: +49-171-765 5871 E-Mail: christoph.pospiech@xxxxxxxxxx ------------------------------------------------------------------------------------------------------------------------------------------- IBM Deutschland GmbH / Vorsitzender des Aufsichtsrats: Martin Jetter Geschäftsführung: Martina Koederitz (Vorsitzende), Reinhard Reschke, Dieter Scholz, Gregor Pillen, Joachim Heel, Christian Noll Sitz der Gesellschaft: Ehningen / Registergericht: Amtsgericht Stuttgart, HRB 14562 / WEEE-Reg.-Nr. DE 99369940
|