[mvapich-discuss] Problem building mvapich2-1.7

Jonathan Perkins perkinjo at cse.ohio-state.edu
Tue Oct 11 13:59:10 EDT 2011


Thanks for the typescript.  I've taken a quick look through the logs
and I see that its not actually the mvapich2 rpm that is failing but
the mpitests rpm.  The other interesting thing to note is that the rpm
builds fine but its only at installation time.

If the QLogic script is simply using rpm -Uvh or yum localinstall -y
at this point then the problem could be related to the post install
step of the mpitests rpm.  Other than that guess I'm not sure what is
going on.   I'm going to see if I can reproduce this on one of our
systems and take a quick look if I can.

==========================================================

Installing test programs 3.2 for MVAPICH2 MPI 1.7...

Preparing packages for installation...

mpitests_mvapich2_gcc-3.2-923

Build Errors:

make[2]: *** [INSTALL_LIBSO] Error 1

make[4]: [clean-postamble] Error 1 (ignored)



FAILED Build, errors detected

On Tue, Oct 11, 2011 at 1:29 PM, Mike Heinz <michael.heinz at qlogic.com> wrote:
> Okay - I can confirm that I get this problem when building straight from the OFED source RPM, but -->not<-- when building from the  MVAPICH2 tarball I just downloaded from OSU.
>
> The only "special" thing here is I used the script we provide our users to specify the options for the rpm build.
>
> Machine settings are:
>
> [root at ifs002 MPI]# uname -a
> Linux ifs002.dev.silverstorm.com 2.6.32-131.0.15.el6.x86_64 #1 SMP Tue May 10 15:42:40 EDT 2011 x86_64 x86_64 x86_64 GNU/Linux
> [root at ifs002 MPI]# cat /etc/redhat-release
> Red Hat Enterprise Linux Server release 6.1 (Santiago)
> [root at ifs002 MPI]#  gcc --version
> gcc (GCC) 4.4.5 20110214 (Red Hat 4.4.5-6)
> Copyright (C) 2010 Free Software Foundation, Inc.
> This is free software; see the source for copying conditions.  There is NO
> warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
>
> Configure options were:
>
> ./configure --prefix=/usr/mpi/gcc/mvapich2-1.7 --with-rdma=gen2 --with-ib-include=/usr/include --with-ib-libpath=/usr/lib64 --enable-shared CC=gcc CXX=g++ F77=gfortran FC=gfortran
>
> I've attached a typescript capture of the build process.
>
> -----Original Message-----
> From: mvapich-discuss-bounces at cse.ohio-state.edu [mailto:mvapich-discuss-bounces at cse.ohio-state.edu] On Behalf Of Mike Heinz
> Sent: Tuesday, October 11, 2011 12:50 PM
> To: Jonathan Perkins; mvapich-discuss at cse.ohio-state.edu
> Cc: Todd Rimmer
> Subject: RE: [mvapich-discuss] Problem building mvapich2-1.7
>
> Jonathan,
>
> The error came up in the middle of a build of the QLogic IFS bundle (which is OFED plus additional stuff) so I'm working my way through doing a standalone build from the tarball of mvapich2-1.7 to see if I get the same result. I'm building on RHEL6.1.
>
> If the standalone build completes with the same error, I'll pass you the logs but since you obviously haven't encountered this issue, I won't bother you if it turns out that the problem is in our build process.
>
> -----Original Message-----
> From: Jonathan Perkins [mailto:perkinjo at cse.ohio-state.edu]
> Sent: Tuesday, October 11, 2011 12:46 PM
> To: Mike Heinz
> Cc: mvapich-discuss at cse.ohio-state.edu
> Subject: Re: [mvapich-discuss] Problem building mvapich2-1.7
>
> Hello Mike,
> Can you send me the full logs related to this build.  I would like to see the rpmbuild command line used during this build.  Can you also tell me which linux distribution that you're using to build this as well as any other oddities that you may believe could be applicable in reproducing this failure?  Thanks.
>
> On Tue, Oct 11, 2011 at 12:16 PM, Mike Heinz <michael.heinz at qlogic.com> wrote:
>> When building the version of mvapich2 shipped with OFED 1.5.4-rc1, I'm getting the following error message:
>>
>> /bin/sh ../libtool --finish /usr/mpi/gcc/mvapich2-1.7/lib/trace_rlog
>> libtool: finish: invalid argument `/usr/mpi/gcc/mvapich2-1.7/lib/trace_rlog'
>> make[2]: *** [INSTALL_LIBSO] Error 1
>>
>> Any ideas what might be causing this?
>>
>>
>> This message and any attached documents contain information from QLogic Corporation or its wholly-owned subsidiaries that may be confidential. If you are not the intended recipient, you may not read, copy, distribute, or use this information. If you have received this transmission in error, please notify the sender immediately by reply e-mail and then delete this message.
>>
>>
>> _______________________________________________
>> mvapich-discuss mailing list
>> mvapich-discuss at cse.ohio-state.edu
>> http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss
>>
>>
>
>
>
> --
> Jonathan Perkins
> http://www.cse.ohio-state.edu/~perkinjo
>
>
> This message and any attached documents contain information from QLogic Corporation or its wholly-owned subsidiaries that may be confidential. If you are not the intended recipient, you may not read, copy, distribute, or use this information. If you have received this transmission in error, please notify the sender immediately by reply e-mail and then delete this message.
>
>
> _______________________________________________
> mvapich-discuss mailing list
> mvapich-discuss at cse.ohio-state.edu
> http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss
>
>
> This message and any attached documents contain information from QLogic Corporation or its wholly-owned subsidiaries that may be confidential. If you are not the intended recipient, you may not read, copy, distribute, or use this information. If you have received this transmission in error, please notify the sender immediately by reply e-mail and then delete this message.
>



-- 
Jonathan Perkins
http://www.cse.ohio-state.edu/~perkinjo



More information about the mvapich-discuss mailing list