1. 29 May, 2015 1 commit
  2. 28 May, 2015 1 commit
  3. 22 May, 2015 2 commits
  4. 11 May, 2015 1 commit
  5. 05 May, 2015 1 commit
    • Kenneth Raffenetti's avatar
      tsuite: explicitly add -lpthread when used in tests · 60482cc2
      Kenneth Raffenetti authored
      
      
      For tests that call pthread routines, add an explicit dependency.
      This was not an issue previously, because either the compile wrappers
      always added -lpthread, or the linker discovered the pthread symbols
      via an interlibrary dependency on libmpi. However on FreeBSD 10, the
      interlibrary dependency resolution appears more strict. Applications
      must specify any libraries directly used, thus this fix.
      Signed-off-by: default avatarHalim Amer <aamer@anl.gov>
      60482cc2
  6. 30 Apr, 2015 2 commits
  7. 29 Apr, 2015 1 commit
  8. 28 Apr, 2015 1 commit
  9. 24 Apr, 2015 2 commits
  10. 21 Apr, 2015 2 commits
  11. 20 Apr, 2015 1 commit
    • Min Si's avatar
      A workaround for FreeBSD pthread mallc/free bug. · 8f6b3cbb
      Min Si authored
      
      
      On FreeBSD, test threads/pt2pt/multisend4 sometimes reports the segfault
      error when calling free function. This error only happens when the
      buffer size is equal to 4M bytes and every thread performs malloc/free
      for multiple times. This bug can be reproduced by using simple memcpy
      without MPI communication, thus it is considered not as a MPI bug but a
      bug of the thread-safe memory allocation on FreeBSD. A workaround of
      this bug is to move malloc-free outside the loop to avoid frequent
      malloc-free calls. This patch added it.
      Signed-off-by: default avatarHuiwei Lu <huiweilu@mcs.anl.gov>
      8f6b3cbb
  12. 17 Apr, 2015 1 commit
    • Kenneth Raffenetti's avatar
      portals4: fix anysource_matched · 73e32112
      Kenneth Raffenetti authored
      
      
      This fix, along with a pending patch to the Portal4 reference implementation,
      should make anysource_matched a more reliable operation for multithreaded apps. We
      were seeing a race condition where an ME would unlink successfully, but an
      event matching it would still arrive in the queue. CH3 can now reliably search
      the netmod queue for matched MPI_ANY_SOURCE requests.
      
      The reason that we no longer assert that an MPI_ANY_SOURCE request was removed
      from the CH3 queue is that FDP (find and dequeue posted) operations will remove
      the request from the queue, if it is known to be already matched by the netmod,
      even if it has not yet completed.
      
      Fixes #2199
      Signed-off-by: default avatarAntonio J. Pena <apenya@mcs.anl.gov>
      73e32112
  13. 16 Apr, 2015 2 commits
  14. 15 Apr, 2015 1 commit
    • Pavan Balaji's avatar
      Increase bcast_full time limit. · 04060d1d
      Pavan Balaji authored
      We increased the number of cases the bcast test was running in
      [e01a20b6].  This is causing it to timeout on some platforms, where
      the test now seems to take close to 3 minutes.  This increased timeout
      should be sufficient on those platforms.
      
      No reviewer.
      04060d1d
  15. 11 Apr, 2015 1 commit
  16. 10 Apr, 2015 4 commits
  17. 08 Apr, 2015 1 commit
  18. 07 Apr, 2015 2 commits
    • Antonio J. Pena's avatar
      Fix win_shared_create* tests · 05fe55b2
      Antonio J. Pena authored
      
      
      The tests were modifying local buffers without locking them after window
      creation, causing potential race conditions. I've moved the buffer
      initialization to be performed before the global window is created.
      
      These tests were failing due to incorrect results in Jenkins whith async
      enabled.
      Signed-off-by: default avatarXin Zhao <xinzhao3@illinois.edu>
      05fe55b2
    • Antonio J. Pena's avatar
      Fix unsafe datatype release in several RMA tests · b47d95f7
      Antonio J. Pena authored
      
      
      The datatypes shouldn't be released until we make sure that there
      are no more remote operations using that datatype. I've changed several
      tests to release the datatype after a barrier. To avoid introducing
      a barrier in every iteration, and aiming to stress out a little more,
      I've restructured the tests so that the datatypes are not created and
      freed every iteration.
      
      This was causing intermittent segfaults mainly with async enabled.
      Signed-off-by: default avatarXin Zhao <xinzhao3@illinois.edu>
      b47d95f7
  19. 27 Mar, 2015 2 commits
  20. 20 Mar, 2015 2 commits
    • Pavan Balaji's avatar
      Reduce the number of processes in the commcreatep test. · cc663e76
      Pavan Balaji authored
      
      
      This test is run with 64 processes.  On platforms that do not schedule
      that many processes well (such as FreeBSD), this can slow down the
      test a lot and cause timeouts.
      Signed-off-by: Rob Latham's avatarRob Latham <robl@mcs.anl.gov>
      cc663e76
    • Wesley Bland's avatar
      Extend timeouts for putfence1/getfence1 · 5c060dfd
      Wesley Bland authored
      These tests take a longer time on OSX due to the poor performance of
      malloc/calloc on OSX platforms. The extended timeout gives them a chance
      to complete.
      
      This could be better fixed in the future by only allocating the memory
      for the window once instead of over and over (~5000 times).
      
      No reviewer
      5c060dfd
  21. 13 Mar, 2015 1 commit
  22. 10 Mar, 2015 1 commit
  23. 09 Mar, 2015 2 commits
  24. 06 Mar, 2015 1 commit
  25. 05 Mar, 2015 3 commits
  26. 04 Mar, 2015 1 commit