This is an automated email from the git hooks/post-receive script. It was generated because a ref change was pushed to the repository containing the project "MPICH primary repository". The branch, master has been updated via 73e3211228c525b08221fbfcb161f88878f8cd24 (commit) from 4309ba574293e7bdf2ec03224e4afa948a1e6fd9 (commit) Those revisions listed above that are new to this repository have not appeared on any other notification email; so we list those revisions in full, below. - Log ----------------------------------------------------------------- http://git.mpich.org/mpich.git/commitdiff/73e3211228c525b08221fbfcb161f88878... commit 73e3211228c525b08221fbfcb161f88878f8cd24 Author: Ken Raffenetti <[email protected]> Date: Thu Apr 16 14:10:40 2015 -0500 portals4: fix anysource_matched 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: Antonio J. Pena <[email protected]> diff --git a/src/mpid/ch3/channels/nemesis/netmod/portals4/ptl_recv.c b/src/mpid/ch3/channels/nemesis/netmod/portals4/ptl_recv.c index ec6d90a..f732751 100644 --- a/src/mpid/ch3/channels/nemesis/netmod/portals4/ptl_recv.c +++ b/src/mpid/ch3/channels/nemesis/netmod/portals4/ptl_recv.c @@ -22,7 +22,10 @@ static void dequeue_req(const ptl_event_t *e) REQ_PTL(rreq)->put_me = PTL_INVALID_HANDLE; found = MPIDI_CH3U_Recvq_DP(rreq); - MPIU_Assert(found); + /* an MPI_ANY_SOURCE request may have been previously removed from the + CH3 queue by an FDP (find and dequeue posted) operation */ + if (rreq->dev.match.parts.rank != MPI_ANY_SOURCE) + MPIU_Assert(found); rreq->status.MPI_ERROR = MPI_SUCCESS; rreq->status.MPI_SOURCE = NPTL_MATCH_GET_RANK(e->match_bits); @@ -597,15 +600,12 @@ static int cancel_recv(MPID_Request *rreq, int *cancelled) /* An invalid handle indicates the operation has been completed and the matching list entry unlinked. At that point, the operation cannot be cancelled. */ - if (REQ_PTL(rreq)->put_me != PTL_INVALID_HANDLE) { - ptl_err = PtlMEUnlink(REQ_PTL(rreq)->put_me); - if (ptl_err == PTL_OK) - *cancelled = TRUE; - /* FIXME: if we properly invalidate matching list entry handles, we should be - able to ensure an unlink operation results in either PTL_OK or PTL_IN_USE. - Anything else would be an error. For now, though, we assume anything but PTL_OK - is uncancelable and return. */ - } + if (REQ_PTL(rreq)->put_me == PTL_INVALID_HANDLE) + goto fn_exit; + + ptl_err = PtlMEUnlink(REQ_PTL(rreq)->put_me); + if (ptl_err == PTL_OK) + *cancelled = TRUE; fn_exit: MPIDI_FUNC_EXIT(MPID_STATE_CANCEL_RECV); @@ -635,7 +635,7 @@ int MPID_nem_ptl_anysource_matched(MPID_Request *rreq) fn_exit: MPIDI_FUNC_EXIT(MPID_STATE_MPID_NEM_PTL_ANYSOURCE_MATCHED); - return MPI_SUCCESS; + return !cancelled; fn_fail: goto fn_exit; } diff --git a/test/mpi/threads/pt2pt/testlist b/test/mpi/threads/pt2pt/testlist index 08e25a4..b6ab43e 100644 --- a/test/mpi/threads/pt2pt/testlist +++ b/test/mpi/threads/pt2pt/testlist @@ -1,6 +1,6 @@ threads 2 timeLimit=600 threaded_sr 2 -alltoall 4 xfail=ticket2199 +alltoall 4 sendselfth 1 multisend 2 multisend2 5 ----------------------------------------------------------------------- Summary of changes: .../channels/nemesis/netmod/portals4/ptl_recv.c | 22 ++++++++++---------- test/mpi/threads/pt2pt/testlist | 2 +- 2 files changed, 12 insertions(+), 12 deletions(-) hooks/post-receive -- MPICH primary repository