Computation Errors

Message boards : Number crunching : Computation Errors
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Spectrum
Avatar

Send message
Joined: 14 Jun 99
Posts: 468
Credit: 53,129,336
RAC: 0
Australia
Message 1032904 - Posted: 11 Sep 2010, 14:08:20 UTC

Hi all, one of my hosts seems to be getting a lot of errors in the last few hours since the servers came back online Host ID: 879910 I have another three WU's that are yet to report and I noticed the run time is identical when they exit at 01:51:44 I am running AK's optimised app and they are non Cuda WU's, anyone having similar problems?
One of them link below

EXIT STATUS -177 (0xffffffffffffff4f)

http://setiathome.berkeley.edu/result.php?resultid=1698440392
ID: 1032904 · Report as offensive
Profile Questor Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 3 Sep 04
Posts: 471
Credit: 230,506,401
RAC: 157
United Kingdom
Message 1032911 - Posted: 11 Sep 2010, 14:28:06 UTC - in response to Message 1032904.  

Hi all, one of my hosts seems to be getting a lot of errors in the last few hours since the servers came back online Host ID: 879910 I have another three WU's that are yet to report and I noticed the run time is identical when they exit at 01:51:44 I am running AK's optimised app and they are non Cuda WU's, anyone having similar problems?
One of them link below

EXIT STATUS -177 (0xffffffffffffff4f)

http://setiathome.berkeley.edu/result.php?resultid=1698440392


There are a few threads with explanations as to the cause of these errors but as a quick fix you can download the new Reschedule tool by Fred which has an option to fix the problem. (The -177 happens when a task exits because it has reached a maximum timeout value)

New Reschedule tool

John.
GPU Users Group



ID: 1032911 · Report as offensive
Profile perryjay
Volunteer tester
Avatar

Send message
Joined: 20 Aug 02
Posts: 3377
Credit: 20,676,751
RAC: 0
United States
Message 1032912 - Posted: 11 Sep 2010, 14:28:36 UTC - in response to Message 1032904.  
Last modified: 11 Sep 2010, 14:29:47 UTC

-177 error is exceeded time allotted. In other words the tasks are taking longer than it was thought they would. The easiest way to cure this is to get EFmer's new reschedule tool. There are other ways and I'm sure others will chime in but the tool seems to be the best to me.


Edit: Thanks John, I didn't have the link.


PROUD MEMBER OF Team Starfire World BOINC
ID: 1032912 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 446,358
RAC: 0
Germany
Message 1032913 - Posted: 11 Sep 2010, 14:29:29 UTC - in response to Message 1032904.  
Last modified: 11 Sep 2010, 14:30:19 UTC

Error -177 stands for "Maximum elapsed time exceeded", so it's not surprising that they all had the same run time.

You could try a forum search (top left corner) for "-177" (without quotation marks).

Gruß,
Gundolf
[edit]Wow, three at a time![/edit]
Computer sind nicht alles im Leben. (Kleiner Scherz)

SETI@home classic workunits 3,758
SETI@home classic CPU time 66,520 hours
ID: 1032913 · Report as offensive
Profile Spectrum
Avatar

Send message
Joined: 14 Jun 99
Posts: 468
Credit: 53,129,336
RAC: 0
Australia
Message 1032921 - Posted: 11 Sep 2010, 15:05:50 UTC
Last modified: 11 Sep 2010, 15:06:58 UTC

Thanks guys, I will try the reschedule app, I have been using the old one to get rid of vlars but it sounds like there is a new kid on the block.
ID: 1032921 · Report as offensive
Profile Spectrum
Avatar

Send message
Joined: 14 Jun 99
Posts: 468
Credit: 53,129,336
RAC: 0
Australia
Message 1032935 - Posted: 11 Sep 2010, 15:45:12 UTC

Hi again, just a question re rescheduler, I thought it was for when the Cuda app gets the vlar's so they are sent to the cpu, my errors are on the cpu work units not the cuda, they keep on climbing in time to completion and wind up with the error, am I missing something?
ID: 1032935 · Report as offensive
Profile perryjay
Volunteer tester
Avatar

Send message
Joined: 20 Aug 02
Posts: 3377
Credit: 20,676,751
RAC: 0
United States
Message 1032943 - Posted: 11 Sep 2010, 16:06:43 UTC - in response to Message 1032935.  

Nope, not missing anything. They are probably old work sent back out again. The rescheduler will change the flops bound or whatever it's called so that it will judge the time correctly on both CPU and GPU work. Lots of improvements in this new rescheduler.


PROUD MEMBER OF Team Starfire World BOINC
ID: 1032943 · Report as offensive

Message boards : Number crunching : Computation Errors


 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.