Index  | Recent Threads  | Unanswered Threads  | Who's Active  | Guidelines  | Search
 

Quick Go »
No member browsing this thread
Thread Status: Active
Total posts in this thread: 31
Posts: 31   Pages: 4   [ Previous Page | 1 2 3 4 | Next Page ]
[ Jump to Last Post ]
Post new Thread
Author
Previous Thread This topic has been viewed 7687 times and has 30 replies Next Thread
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

skgiven,
I think I was wrong... I'm about to check it once again, but it seems that after restart the tasks return about two dozens of valid results and then begin to crash. The same is happening with version 6.10.58.

SekeRob,
As for MySQL, I just stopped it on this server. Actually, it was one of the reasons why I deployed boinc there — I just wanted the server to do something :)
[Jun 2, 2011 5:11:44 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

Suggest to run, after another boot, a mix of HCC/HCMD2/C4CW and see if this postpones the error development.

Don't know if there are other members who run 16 core machines (real or hyperthreaded cores incl.?) with C4CW only, presumably on 64 bit and the success rate.

Let us know.
[Jun 2, 2011 5:50:11 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

I do run a mix of c4cw, Clean energy and Cure for cancer tasks. Sorry for not mentioning that before. The other projects work fine. Besides, the server works for climateprediction.net, but they have no tasks now.

The server has two quad-core CPUs with hyperthreading.

I've joined SIMAP today. Can't find results stats on their web site, but I hope there'll be enough info in the logs to find out if their WUs complete correctly.
[Jun 2, 2011 6:20:17 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

SIMAP has a http://boincsimap.org/boincsimap/batchmonitor.php and on the Your Account there is somewhat down the link to Tasks view.

Top will show the science app that's running where the suffix indicates if it's a 32 or 64 bit version. The initial download also shows the version/bit size, for example:

1764 boincsimap 02-06-2011 08:48 Started download of simap_5.12_windows_x86_64.exe


--//--
[Jun 2, 2011 6:50:05 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Crystal Pellet
Veteran Cruncher
Joined: May 21, 2008
Post Count: 1403
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

I've joined SIMAP today. Can't find results stats on their web site, but I hope there'll be enough info in the logs to find out if their WUs complete correctly.

It looks fine and you're running: BOINCSIMAP simap application 5.10 x86_64-pc-linux-gnu

Your valid SIMAP's: http://boincsimap.org/boincsimap/results.php?...;show_names=0&state=3
Your pending SIMAP's waiting for wingmen: http://boincsimap.org/boincsimap/results.php?...;show_names=0&state=2
[Jun 2, 2011 7:49:28 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

I've downgraded boinc-client back to 6.10.17. Thus far, 31 BOINCSIMAP tasks were validated. I think we can safely assume that SIMAP works fine. Reattaching WCG again.
[Jun 2, 2011 1:16:17 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

Most curious, I've put a note out to the techs asking to look in. SIMAP is not the lightest of computations, certainly it causes me quad CPU to always warm up a tad more.

[ot]Your 2 sig-site links are interesting, self very much newbie still on Linux... no doubt your English is excellent.[/ot]
[Jun 2, 2011 4:11:00 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

Still the same. C4CW remains the only task that regularly returns errors. After restart, some tasks complete successfully, but soon they begin to segfault.

I tried to debug the tasks using 'strace' tool, but the results looked more like I was debugging the controlling task of boinc-client then the calculation itself. Is there a way to debug the WUs? Or to increase logging level for them?

SekeRob, glad you liked these two blogs :). Unfortunately, I had little time to update them in the last months.
----------------------------------------
[Edit 1 times, last edit by Former Member at Jun 4, 2011 3:37:20 PM]
[Jun 4, 2011 12:49:22 PM]   Link   Report threatening or abusive post: please login first  Go to top 
sk..
Master Cruncher
http://s17.rimg.info/ccb5d62bd3e856cc0d1df9b0ee2f7f6a.gif
Joined: Mar 22, 2007
Post Count: 2324
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

Did you try just running C4CW (no other task types), to eliminate the possibility that other tasks are causing this (holding onto memory space, or using memory area assigned to another thread, for example)? You would need to do a restart after present tasks complete to rule out any interference by existing tasks or other tasks that have already run.
[Jun 4, 2011 1:41:42 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Repeating errors on 64-bit server

No, I didn't. Will try, thank you. It'll take time, as usual :)
----------------------------------------
[Edit 1 times, last edit by Former Member at Jun 4, 2011 3:42:41 PM]
[Jun 4, 2011 3:37:59 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Posts: 31   Pages: 4   [ Previous Page | 1 2 3 4 | Next Page ]
[ Jump to Last Post ]
Post new Thread