1. daos@daos.groups.io

Re: daos_test failing with Infiniband

Oganezov, Alexander A
 

Hi Peter,

 

I saw something similar a while ago when our mpi-based applications ended up compiling against ‘bad’ version of MPI, or more specifically MPI that links bad UCX (ucx provides libucs). There appears to be a bug in some UCX versions causing this segfault (e.g. https://github.com/open-mpi/ompi/issues/6789)

 

One thing to try is to see which MPIs you have installed and compile against different one from what you are using.

 

“module avail”  will provide you list of installed mpi packages

You can use then “module load <package>” and after that recompile daos via

scons -c ; scons -c install;  scons MPI_PKG=any -j 12 install

 

Let me know if this helps any.

 

Thanks,

~~Alex.

 

From: daos@daos.groups.io <daos@daos.groups.io> On Behalf Of Lombardi, Johann
Sent: Tuesday, December 15, 2020 12:00 AM
To: daos@daos.groups.io
Subject: Re: [daos] daos_test failing with Infiniband

 

I see, then maybe libucs is somehow used under the hood. Are you using the MOFED stack?

Maybe you could try to reduce FI_UNIVERSE_SIZE to 512 (i.e. export FI_UNIVERSE_SIZE=512).

 

Cheers,

Johann

 

From: <daos@daos.groups.io> on behalf of Peter <magpiesaresoawesome@...>
Reply-To: "daos@daos.groups.io" <daos@daos.groups.io>
Date: Tuesday 15 December 2020 at 08:36
To: "daos@daos.groups.io" <daos@daos.groups.io>
Subject: Re: [daos] daos_test failing with Infiniband

 

I have specified ofi+verbs;ofi_rxm

What should I look into to get libfabric to load a supported library?

Thank you for your reply. 

---------------------------------------------------------------------
Intel Corporation SAS (French simplified joint stock company)
Registered headquarters: "Les Montalets"- 2, rue de Paris,
92196 Meudon Cedex, France
Registration Number:  302 456 199 R.C.S. NANTERRE
Capital: 4,572,000 Euros

This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.
Join daos@daos.groups.io to automatically receive all group messages.
More
Home Messages Hashtags Subgroups About Features Pricing Updates Terms Help Twitter