I haven't reviewed the code, but can confirm that it fixes the issue for me.
Thanks --Nysal On Thu, Feb 18, 2016 at 9:26 AM, Gilles Gouaillardet <gil...@rist.or.jp> wrote: > Folks, > > i made https://github.com/open-mpi/ompi/pull/1376 to fix this issue > > note it also revert the changes previously introduced in > ompi/runtime/ompi_mpi_init.c > > Cheers, > > Gilles > > > On 2/18/2016 8:37 AM, Gilles Gouaillardet wrote: > >> Jeff, >> >> this commit only fixes MPI_Init() and not the openib btl. >> >> As Ralph pointed previously, there is still an abstraction violation in >> MPI_Init() and it is now "under control" >> as it was before. >> >> Regarding this issue (opal_memory_linux_malloc_set_alignment), i will >> extend the memory mca since >> yet an other abstraction violation does not seem necessary here. >> >> Cheers, >> >> Gilles >> >> On 2/18/2016 7:17 AM, Jeff Squyres (jsquyres) wrote: >> >>> Nysal -- >>> >>> FWIW, I'm unable to replicate the error on master. >>> >>> Did this commit not fix it for you? >>> >>> >>> https://github.com/open-mpi/ompi/commit/7de01b347cd13544439b4eae86607a535c32489c >>> >>> If it didn't, then we might as well revert that commit and PR 1351 until >>> it's fixed properly. >>> >>> >>> -----Original Message----- >>> From: Ralph Castain <r...@open-mpi.org> >>> Reply: Open MPI Developers <de...@open-mpi.org> >>> Date: February 17, 2016 at 3:29:32 PM >>> To: Open MPI Developers <de...@open-mpi.org> >>> Subject: Re: [OMPI devel] Trunk is broken >>> >>> Probably should - looks like this may take more thought and probably >>>> will be handled in >>>> discussions next week >>>> >>>>> On Feb 17, 2016, at 11:26 AM, Howard Pritchard wrote: >>>>> >>>>> Hi Folks, >>>>> >>>>> Should we revert PR 1351 till there is a fix? >>>>> >>>>> Howard >>>>> >>>>> >>>>> 2016-02-17 11:34 GMT-07:00 Ralph Castain >: >>>>> FWIW: I wouldn’t have seen that because I don’t have IB on my system. >>>>> >>>>> On Feb 17, 2016, at 10:11 AM, Nysal Jan K A > >>>>>> >>>>> wrote: >>>> >>>>> So this seems to be still broken. >>>>>> >>>>>> mca_btl_openib.so: undefined symbol: >>>>>> opal_memory_linux_malloc_set_alignment >>>>>> >>>>>> I built with "--with-memory-manager=none" >>>>>> >>>>>> Regards >>>>>> --Nysal >>>>>> >>>>>> On Tue, Feb 16, 2016 at 10:19 AM, Ralph Castain > >>>>>> >>>>> wrote: >>>> >>>>> It is very easy to reproduce - configure with: >>>>>> enable_mem_debug=no >>>>>> enable_mem_profile=no >>>>>> enable_memchecker=no >>>>>> with_memory_manager=no >>>>>> >>>>>> I’m not sure which of those is required. However, your assertion is >>>>>> incorrect. The >>>>>> >>>>> person who introduced the original violation went to great lengths to >>>> ensure it didn’t >>>> create a problem if the referenced component was not built. I’m not >>>> saying it was a good >>>> thing to do, but we spent a lot of time discussing it and figuring out >>>> how to do it without >>>> causing the problem. >>>> >>>>> So whatever was done missed those precautions and introduced this >>>>>> symbol regardless >>>>>> >>>>> of the configuration. >>>> >>>>> >>>>>> On Feb 15, 2016, at 8:39 PM, Gilles Gouaillardet > >>>>>>> >>>>>> wrote: >>>> >>>>> Ralph, >>>>>>> >>>>>>> this is being discussed at >>>>>>> https://github.com/open-mpi/ompi/pull/1351 >>>>>>> >>>>>>> btw, how do you get this warning ? i do not see it. >>>>>>> fwiw, the abstraction violation was kind of already here, so i am >>>>>>> surprised it pops >>>>>>> >>>>>> up now only >>>> >>>>> Cheers, >>>>>>> >>>>>>> Gilles >>>>>>> >>>>>>> On 2/16/2016 1:17 PM, Ralph Castain wrote: >>>>>>> >>>>>>>> Looks like someone broke the master build on Linux: >>>>>>>> >>>>>>>> ../../../ompi/.libs/libmpi.so: undefined reference to >>>>>>>> `opal_memory_linux_malloc_init_hook' >>>>>>>> >>>>>>>> >>>>>>>> I suspect it was a hard-coded reference to some component’s >>>>>>>> variable? >>>>>>>> Ralph >>>>>>>> >>>>>>>> >>>>>>>> >>>>>>>> _______________________________________________ >>>>>>>> devel mailing list >>>>>>>> de...@open-mpi.org >>>>>>>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>>>>>>> Link to this post: >>>>>>>> http://www.open-mpi.org/community/lists/devel/2016/02/18598.php >>>>>>>> >>>>>>> _______________________________________________ >>>>>>> devel mailing list >>>>>>> de...@open-mpi.org >>>>>>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>>>>>> Link to this post: >>>>>>> http://www.open-mpi.org/community/lists/devel/2016/02/18599.php >>>>>>> >>>>>> _______________________________________________ >>>>>> devel mailing list >>>>>> de...@open-mpi.org >>>>>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>>>>> Link to this post: >>>>>> http://www.open-mpi.org/community/lists/devel/2016/02/18600.php >>>>>> _______________________________________________ >>>>>> devel mailing list >>>>>> de...@open-mpi.org >>>>>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>>>>> Link to this post: >>>>>> http://www.open-mpi.org/community/lists/devel/2016/02/18601.php >>>>>> >>>>> _______________________________________________ >>>>> devel mailing list >>>>> de...@open-mpi.org >>>>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>>>> Link to this post: >>>>> http://www.open-mpi.org/community/lists/devel/2016/02/18602.php >>>>> _______________________________________________ >>>>> devel mailing list >>>>> de...@open-mpi.org >>>>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>>>> Link to this post: >>>>> http://www.open-mpi.org/community/lists/devel/2016/02/18603.php >>>>> >>>> _______________________________________________ >>>> devel mailing list >>>> de...@open-mpi.org >>>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>>> Link to this post: >>>> http://www.open-mpi.org/community/lists/devel/2016/02/18604.php >>>> >>> -- >>> Jeff Squyres >>> jsquy...@cisco.com >>> For corporate legal information go to: >>> http://www.cisco.com/web/about/doing_business/legal/cri/ >>> _______________________________________________ >>> devel mailing list >>> de...@open-mpi.org >>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >>> Link to this post: >>> http://www.open-mpi.org/community/lists/devel/2016/02/18605.php >>> >> >> _______________________________________________ >> devel mailing list >> de...@open-mpi.org >> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel >> Link to this post: >> http://www.open-mpi.org/community/lists/devel/2016/02/18606.php >> > > _______________________________________________ > devel mailing list > de...@open-mpi.org > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel > Link to this post: > http://www.open-mpi.org/community/lists/devel/2016/02/18607.php
