[Users] Benchmarking

[Khamesra, Bhavesh]

Hi Ian, The segfault was mentioned in the error file, you can find the complete error in it (Attached here).


It's possible that the segfault is not in Cactus

Yes, I completely agree. The error does not refer to any Cactus file and hence I wasn't sure what is the cause of it.


Thanks,

.............................

Bhavesh Khamesra

Graduate Student

Centre of Relativistic Astrophysics

Georgia Institute of Technology

________________________________
From: Ian Hinder <ian.hinder at aei.mpg.de>
Sent: Saturday, May 6, 2017 3:58:46 AM
To: Khamesra, Bhavesh
Cc: Erik Schnetter; Einstein Toolkit Users
Subject: Re: [Users] Benchmarking


On 5 May 2017, at 20:38, Khamesra, Bhavesh <bhaveshkhamesra at gatech.edu<mailto:bhaveshkhamesra at gatech.edu>> wrote:

Hi Ian, No I do not find any backtrace files in the output directory.

How do you know that there is a segfault? Can you post the error message?  It's possible that the segfault is not in Cactus - e.g. it could be from mpirun or some other part of the system.  If Cactus aborts with a segfault, and the run is using Carpet as the driver (i.e. the Carpet thorn is active in the parameter file), then it should write a backtrace file.



.............................
Bhavesh Khamesra
Graduate Student
Centre of Relativistic Astrophysics
Georgia Institute of Technology
________________________________
From: Ian Hinder <ian.hinder at aei.mpg.de<mailto:ian.hinder at aei.mpg.de>>
Sent: Friday, May 5, 2017 1:13:38 PM
To: Khamesra, Bhavesh
Cc: Erik Schnetter; Einstein Toolkit Users
Subject: Re: [Users] Benchmarking


On 5 May 2017, at 18:43, Khamesra, Bhavesh <bhaveshkhamesra at gatech.edu<mailto:bhaveshkhamesra at gatech.edu>> wrote:

I have heard of such a segfault before. I assume it is caused by using too many processes or too many threads for a particular resolution. I have not yet reproduced it, and I don't know what causes it. It would be helpful if you could produce a stack backtrace or similar. On the other hand, if this segfault only appears for very inefficient configurations, then there is no urgent need to debug this, as people won't be interested in using such configurations anyway.
I do not think that it is caused by using too many processors. I tried it with varying number of cores from 68 (insufficient) to 204 but get the same error. Also, I am getting this error with all my BBH parameter files I have tried, so its kind of important. Is there a way to produce backtrace file using simfactory?

Carpet should write a backtrace file into the output directory if there is a segfault.  Do you see backtrace files in

sim/output-0000/sim/backtrace.*.txt

?

--
Ian Hinder
http://members.aei.mpg.de/ianhin

--
Ian Hinder
http://members.aei.mpg.de/ianhin

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.einsteintoolkit.org/pipermail/users/attachments/20170506/c0fb901a/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Benchmarking_ETK_GW150914_KNL.err
Type: application/octet-stream
Size: 25582 bytes
Desc: Benchmarking_ETK_GW150914_KNL.err
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20170506/c0fb901a/attachment-0001.obj