1. 10 Apr, 2015 7 commits
    • Kenneth Raffenetti's avatar
      portals4: tuning · daf29e33
      Kenneth Raffenetti authored
      
      
      Changes the value of various static limits in the Portals4 netmod, based
      on experimentation results and suggestions from collaborators.
      
      1. Bump most ni_limits from 32K to 64K. These limits relate closely to
         queue depth. We can reasonably expect to support a queue depth
         of 64K.
      
      2. Limit issued origin events to 500. This translates to sending ~250
         operations to Portals at a time, which over IB is roughly the
         saturation point. TODO: turn this into a CVAR.
      
      3. Limit per target issued operations to 50. This will give the target a
         better chance to process events without being overwhelmed by a single
         process. TODO: turn this into a CVAR, also.
      
      4. Allocate more buffer space for incoming control messages. Observed
         results, especially with larger messages, showed that more buffer space
         cuts down on flow-control events.
      Signed-off-by: default avatarAntonio J. Pena <apenya@mcs.anl.gov>
      daf29e33
    • Kenneth Raffenetti's avatar
      portals4: revert [722d85a4] and [d459c025] · 2f97f429
      Kenneth Raffenetti authored
      The 2 commits being reverted introduced a "safe" PtlMEAppend function
      that would call MPID_nem_ptl_poll to process some events in case there
      was no space to append the match list entry. However the poll function
      is not reentrant safe, which could lead to ordering problems.
      
      The increased list entry limit from [c6c0d6f6
      
      ] should prevent PTL_NO_SPACE
      errors from happening, except in the extreme case. If we still find we are
      hitting this error, a proper fix can be done in the Rportals layer.
      Signed-off-by: default avatarAntonio J. Pena <apenya@mcs.anl.gov>
      2f97f429
    • Charles J Archer's avatar
    • Pavan Balaji's avatar
      Update .gitignore. · 5addea2c
      Pavan Balaji authored and Kenneth Raffenetti's avatar Kenneth Raffenetti committed
      
      Signed-off-by: Kenneth Raffenetti's avatarKen Raffenetti <raffenet@mcs.anl.gov>
      5addea2c
    • Pavan Balaji's avatar
      Simplify the bcast test. · e01a20b6
      Pavan Balaji authored and Kenneth Raffenetti's avatar Kenneth Raffenetti committed
      
      
      The current number of combinations we are checking are too many,
      causing the test to take too long on some platforms.  This patch
      simplifies the test, so we build two versions of the test.  In the
      first version, we run only on COMM_WORLD but go through all datatypes.
      In the second version, we run on all communicators, but go through
      only a small subset of datatypes.
      Signed-off-by: Kenneth Raffenetti's avatarKen Raffenetti <raffenet@mcs.anl.gov>
      e01a20b6
    • Pavan Balaji's avatar
      Cosmetic changes to the bcast2 test. · be82b6a7
      Pavan Balaji authored and Kenneth Raffenetti's avatar Kenneth Raffenetti committed
      
      
      1. Renamed bcast2 to bcast.
      
      2. White-space cleanup for bcast.c
      Signed-off-by: Kenneth Raffenetti's avatarKen Raffenetti <raffenet@mcs.anl.gov>
      be82b6a7
    • Pavan Balaji's avatar
      Get rid of bcast3.c · e7eab9df
      Pavan Balaji authored and Kenneth Raffenetti's avatar Kenneth Raffenetti committed
      
      
      This test is exactly the same as bcast2.  Originally these two tests
      were different, but over time they have become essentially the same.
      There's no point testing the same thing twice.
      Signed-off-by: Kenneth Raffenetti's avatarKen Raffenetti <raffenet@mcs.anl.gov>
      e7eab9df
  2. 09 Apr, 2015 1 commit
  3. 08 Apr, 2015 2 commits
  4. 07 Apr, 2015 14 commits
  5. 06 Apr, 2015 1 commit
  6. 03 Apr, 2015 10 commits
  7. 02 Apr, 2015 2 commits
  8. 01 Apr, 2015 1 commit
  9. 31 Mar, 2015 2 commits