[petsc-dev] Fwd: [JIRA] (SDK-82) Complete a manual test run of xSDK on Edison

[Satish Balay]

Hm - PETSc configure does not need to run MPI jobs with MPI_Init. So
it uses this quirk to get-by without requiring --with-batch

And it also tries not to run testsuites from externalpackages.
[clearly some packages are not doing this]

Perhaps there should run a test with and without MPI_Init()- and set a
flag appropriately so that parts that need MPI_Init tests can use this
flag - and behave appropriately.

Satish


On Tue, 19 Apr 2016, Barry Smith wrote:

> 
>   Satish,
> 
>    So on this machine you can compile and run programs on the front end but if they call MPI_Init() then you cannot run them?
> 
>    What does this mean with regard to --with-batch? It seems we don't need --with-batch on that machine yet it cannot run MPI programs?
> 
>    Barry
> 
> 
> > Begin forwarded message:
> > 
> > From: "Alicia Klinvex (JIRA)" <jira at ideas-productivity.atlassian.net>
> > Subject: [JIRA] (SDK-82) Complete a manual test run of xSDK on Edison
> > Date: April 19, 2016 at 11:45:00 AM CDT
> > To: <bsmith at mcs.anl.gov>
> > 
> >  	Alicia Klinvex <https://ideas-productivity.atlassian.net/secure/ViewProfile.jspa?name=amklinv> edited a comment on  SDK-82 <https://ideas-productivity.atlassian.net/browse/SDK-82> SDK-82 
> >  
> > Re: Complete a manual test run of xSDK on Edison <https://ideas-productivity.atlassian.net/browse/SDK-82>
> > Sure thing.   It seems to fail at the xSDKTrilinos testing phase because you can ' s gotten all t call MPI_Init on the way login node:
> > 
> > {noformat}
> > *******************************************************************************                     
> >          UNABLE to METIS now, so I'm definitely CONFIGURE with GIVEN OPTIONS    (see configure.log for details):                     
> > -------------------------------------------------------------------------------                     
> > Error running ctest on xSDKTrilinos: Could not seeing the same issue anymore execute "cd /global/u1/a/amklinv/dynamic_test/installxSDK/xsdk/petsc/arch-linux2-c-debug/externalpackages/git .   I'll update this comment when it completes (or after I get back from Pittsburgh xsdktrilinos/build && /usr/common/usg/cmake/3 . 3 . 2/bin/ctest":                     
> > Test project /global/u1/a/amklinv/dynamic_test/installxSDK/xsdk/petsc/arch-linux2-c-debug/externalpackages/git . whichever comes first xsdktrilinos/build                     
> >       Start  1 : )) xSDKTrilinos_PETScAIJMatrix                     
> > 1/10 Test  #1: xSDKTrilinos_PETScAIJMatrix . .........***Exception: Other  0.02 sec                     
> >       Start  2: xSDKTrilinos_PETSc_Amesos2_example                     
> > 2/10 Test  #2: xSDKTrilinos_PETSc_Amesos2_example ...***Exception: Other  0.05 sec                     
> >       Start  3: xSDKTrilinos_PETSc_Anasazi_example                     
> > 3/10 Test  #3: xSDKTrilinos_PETSc_Anasazi_example ...***Exception: Other  0.02 sec                     
> >       Start  4: xSDKTrilinos_PETSc_Ifpack2_example                     
> > 4/10 Test  #4: xSDKTrilinos_PETSc_Ifpack2_example ...***Exception: Other  0.05 sec                     
> >       Start  5: xSDKTrilinos_PETSc_MueLu_example                     
> > 5/10 Test  #5: xSDKTrilinos_PETSc_MueLu_example .....***Exception: Other  0.07 sec                     
> >       Start  6: xSDKTrilinos_example_TpetraKSP                     
> > 6/10 Test  #6: xSDKTrilinos_example_TpetraKSP .......***Exception: Other  0.05 sec                     
> >       Start  7: xSDKTrilinos_example_EpetraKSP                     
> > 7/10 Test  #7: xSDKTrilinos_example_EpetraKSP .......***Exception: Other  0.01 sec                     
> >       Start  8: xSDKTrilinos_HypreTest 
> > 8/10 Test  #8: xSDKTrilinos_HypreTest ...............***Exception: Other  0.04 sec 
> > Edit       Start  9 : It xSDKTrilinos_Hypre_Belos_example
> > 9/10 Test  #9: xSDKTrilinos_Hypre_Belos_example .....***Exception: Other  0.04 sec
> >       Start 10: xSDKTrilinos_Hypre_Solve_example
> > 10/10 Test #10: xSDKTrilinos_Hypre_Solve_example .....***Exception: Other  0.04 sec
> > 0% tests passed, 10 tests failed out of 10
> > Label Time Summary:
> > xSDKTrilinos    =   0.37 sec
> > Total Test time (real) =   0.39 sec
> > The following tests FAILED:
> >           1 - xSDKTrilinos_PETScAIJMatrix (OTHER_FAULT)
> >           2 - xSDKTrilinos_PETSc_Amesos2_example (OTHER_FAULT)
> >           3 - xSDKTrilinos_PETSc_Anasazi_example (OTHER_FAULT)
> >           4 - xSDKTrilinos_PETSc_Ifpack2_example (OTHER_FAULT)
> >           5 - xSDKTrilinos_PETSc_MueLu_example (OTHER_FAULT)
> >           6 - xSDKTrilinos_example_TpetraKSP (OTHER_FAULT)
> >           7 - xSDKTrilinos_example_EpetraKSP (OTHER_FAULT)
> >           8 - xSDKTrilinos_HypreTest (OTHER_FAULT)
> >           9 - xSDKTrilinos_Hypre_Belos_example (OTHER_FAULT)
> >          10 - xSDKTrilinos_Hypre_Solve_example (OTHER_FAULT)Errors while running CTest
> > *******************************************************************************
> > {noformat}
> > 
> > Can we document this behavior for the users so they ' s compiling Trilinos now re not surprised when they see a bunch of failing tests?
> > 
> > I assume the next step at this point is to try again on a compute node .   Is that accurate?
> >    <https://ideas-productivity.atlassian.net/browse/SDK-82#add-comment>  	Add Comment <https://ideas-productivity.atlassian.net/browse/SDK-82#add-comment> 
> >  
> > This message was sent by Atlassian JIRA (v7.2.0-OD-05-030#72002-sha1:7e8526a)	
> >  
> 
>