Problem with Riesel Base Short on Dual-Xeon
log in

Advanced search

Message boards : Number crunching : Problem with Riesel Base Short on Dual-Xeon

Author Message
Roadranner
Send message
Joined: 10 Dec 14
Posts: 7
Credit: 12,742,176
RAC: 0
Message 1655 - Posted: 14 Jul 2015, 5:06:24 UTC

When I run Riesel Base Short on all (31) cores I get computation errors (output file missing). Also other subprojects then run into computation errors.
I limited cores to 5, but that's a suboptimal solution.

Profile rebirther
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 2 Jan 13
Posts: 7255
Credit: 42,729,227
RAC: 4
Message 1656 - Posted: 14 Jul 2015, 16:34:46 UTC - in response to Message 1655.

When I run Riesel Base Short on all (31) cores I get computation errors (output file missing). Also other subprojects then run into computation errors.
I limited cores to 5, but that's a suboptimal solution.


I can see only "finish file present too long". All the writings to disk with 31 cores is too slow and BOINC is killing the app after the 10s limit. At the moment its the main problem on the project. Perhaps someone can take a look into the wrapper code and find a better solution to get rid of this error.

Dr Who Fan
Avatar
Send message
Joined: 30 Nov 14
Posts: 31
Credit: 21,994,765
RAC: 206
Message 1657 - Posted: 14 Jul 2015, 18:16:02 UTC - in response to Message 1656.

This problem sounds a bit similar to what they have been discussing over at SETI and Milkyway in the Number Crunching forums. SETI is down for it's usual weekly maintenance but I found the topic at Milkyway.

Richard Haselgrove posted this at Milkyway > Message 63799 in Message boards : Number crunching : What is the cause of these 'validate errors' <

"After intensive work with Keith Myers and others (mainly in the SETI message board thread Stderr Truncations), I think I've finally traced and recorded the full life-cycle of these little beasties.

The easiest starting point is the debris left behind."

____________

Profile rebirther
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 2 Jan 13
Posts: 7255
Credit: 42,729,227
RAC: 4
Message 1658 - Posted: 14 Jul 2015, 19:16:52 UTC - in response to Message 1657.
Last modified: 14 Jul 2015, 19:18:41 UTC

There is also a fix out but I dont know if its related to this error.

http://boinc.berkeley.edu/gitweb/?p=boinc-v2.git;a=commit;h=f2d690029c6dab9d586a9ba1a2e0af03dc7f3c70

Update:

The new boinc client 7.6.6 has this fix included


Post to thread

Message boards : Number crunching : Problem with Riesel Base Short on Dual-Xeon


Main page · Your account · Message boards


Copyright © 2014-2024 BOINC Confederation / rebirther