[mpich-discuss] Core dump in parse_args

[kumar.tarun at siemens.com]

Thanks for that.

Regards
Tarun

From: Raffenetti, Ken <raffenet at anl.gov>
Sent: Monday, September 18, 2023 2:44 PM
To: discuss at mpich.org; Thakur, Rajeev <thakur at anl.gov>
Cc: Kumar, Tarun (DI SW ICS DVT RD QSCE) <kumar.tarun at siemens.com>
Subject: Re: [mpich-discuss] Core dump in parse_args

Hi Tarun,

We did find that there is a hardcoded limit of ~1000 command line arguments. If you want a temporary workaround, you can increase the value of this define in the MPICH source to something larger:

#define HYD_NUM_TMP_STRINGS 1000

I created https://github.com/pmodels/mpich/issues/6681 to track progress on a more robust fix.

Ken

From: "Raffenetti, Ken via discuss" <discuss at mpich.org<mailto:discuss at mpich.org>>
Reply-To: "discuss at mpich.org<mailto:discuss at mpich.org>" <discuss at mpich.org<mailto:discuss at mpich.org>>
Date: Monday, September 18, 2023 at 4:23 PM
To: "discuss at mpich.org<mailto:discuss at mpich.org>" <discuss at mpich.org<mailto:discuss at mpich.org>>, "Thakur, Rajeev" <thakur at anl.gov<mailto:thakur at anl.gov>>
Cc: "Raffenetti, Ken" <raffenet at anl.gov<mailto:raffenet at anl.gov>>, "kumar.tarun at siemens.com<mailto:kumar.tarun at siemens.com>" <kumar.tarun at siemens.com<mailto:kumar.tarun at siemens.com>>
Subject: Re: [mpich-discuss] Core dump in parse_args

I'm not aware of a hard-coded limit, but I am able to reproduce a segfault reliably by passing 1000 arguments a toy executable. Will update with more info when we have it.

Ken

From: "kumar.tarun--- via discuss" <discuss at mpich.org<mailto:discuss at mpich.org>>
Reply-To: "discuss at mpich.org<mailto:discuss at mpich.org>" <discuss at mpich.org<mailto:discuss at mpich.org>>
Date: Friday, September 15, 2023 at 4:57 PM
To: "Thakur, Rajeev" <thakur at anl.gov<mailto:thakur at anl.gov>>, "discuss at mpich.org<mailto:discuss at mpich.org>" <discuss at mpich.org<mailto:discuss at mpich.org>>
Cc: "kumar.tarun at siemens.com<mailto:kumar.tarun at siemens.com>" <kumar.tarun at siemens.com<mailto:kumar.tarun at siemens.com>>
Subject: Re: [mpich-discuss] Core dump in parse_args

Thanks Rajeev for your reply.
I don't have the exact number as of now. It's definitely more than 1000. Is there a hard coded limit?

Regards
Tarun

From: Thakur, Rajeev <thakur at anl.gov<mailto:thakur at anl.gov>>
Sent: Friday, September 15, 2023 2:40 PM
To: discuss at mpich.org<mailto:discuss at mpich.org>
Cc: Kumar, Tarun (DI SW ICS DVT RD QSCE) <kumar.tarun at siemens.com<mailto:kumar.tarun at siemens.com>>
Subject: Re: [mpich-discuss] Core dump in parse_args

How many arguments?

Rajeev

From: "kumar.tarun--- via discuss" <discuss at mpich.org<mailto:discuss at mpich.org>>
Reply-To: "discuss at mpich.org<mailto:discuss at mpich.org>" <discuss at mpich.org<mailto:discuss at mpich.org>>
Date: Friday, September 15, 2023 at 4:22 PM
To: "discuss at mpich.org<mailto:discuss at mpich.org>" <discuss at mpich.org<mailto:discuss at mpich.org>>
Cc: "kumar.tarun at siemens.com<mailto:kumar.tarun at siemens.com>" <kumar.tarun at siemens.com<mailto:kumar.tarun at siemens.com>>
Subject: [mpich-discuss] Core dump in parse_args

Hi,
     I recently encountered this crash where mpiexec when executed from a bash script and with a large number of arguments crashes. The core dump is as follows:

#0  0x0000000000408ec3 in parse_args ()
#1  0x0000000000409f26 in HYD_uii_mpx_get_parameters ()
#2  0x000000000040397a in main ()

If I reduce the number of arguments then I don't see the crash. Is it a known issue?

Regards
Tarun

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20230918/9ec71f17/attachment.html>