/orcd/pool/004/jahn/centos7/MITgcm_gfortran-mpi/verification/aim.5l_cs/run ../../../tools/tst_2+2 -mpi All -command "mpirun -n 6 -hostfile /tmp/machinefile.54697 ./mitgcmuv" cmdEXE='mpirun -n 6 -hostfile /tmp/machinefile.54697 ./mitgcmuv' from previous run STDOUT.0000, lastPick=' 69130 ckptA' ; iter='69130' ; sufx='ckptA' prepare parameter file 'data.tst' : prepare file 'data.tst' : done diff data.tst data 43,46c43,44 < nIter0=69130, < nTimeSteps=4, < # nIter0=69120, < # nTimeSteps=10, --- > nIter0=69120, > nTimeSteps=10, 54c52 < # pChkptFreq=2592000., --- > pChkptFreq=2592000., link back: temp_tst/pickup*.ckptA* rename ckptA -> 0000069130 for all: pickup pickup_land rnp_loc: pickup.ckptA pickup.0000069130 rnp_loc: pickup_land.ckptA pickup_land.0000069130 start-end iter: 69130 , 69132 , 69134 sufix: '0000069130' '0000069132' '0000069134' cmdEXE=mpirun -n 6 -hostfile /tmp/machinefile.54697 ./mitgcmuv ==> START RUN 2 x 2 it STOP NORMAL END STOP NORMAL END STOP NORMAL END STOP NORMAL END Note: The following floating-point exceptions are signalling: IEEE_UNDERFLOW_FLAG STOP NORMAL END STOP NORMAL END ==> END RUN 2 x 2 it listP= pickup pickup_land rnp_loc: pickup.ckptA pickup.0000069134 rnp_loc: pickup_land.ckptA pickup_land.0000069134 move_outp: res_2it ==> START RUN 1iA STOP NORMAL END STOP NORMAL END STOP NORMAL END STOP NORMAL END Note: The following floating-point exceptions are signalling: IEEE_UNDERFLOW_FLAG STOP NORMAL END STOP NORMAL END ==> END RUN 1iA rnp_loc: pickup.ckptA pickup.0000069132 rnp_loc: pickup_land.ckptA pickup_land.0000069132 move_outp: res_1iA ==> START RUN 1iB STOP ABNORMAL END: S/R MDS_READ_FIELD STOP ABNORMAL END: S/R MDS_READ_FIELD STOP ABNORMAL END: S/R MDS_READ_FIELD mlx5: node669: got completion with error: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000006 00000000 00000000 00000000 00000000 00008813 08003776 005016d2 [node669:mpi_rank_1][handle_cqe] Send desc error in msg to 5, wc_opcode=0 [node669:mpi_rank_1][handle_cqe] Msg from 5: wc.status=10, wc.wr_id=0x33b6dc0, wc.opcode=0, vbuf->phead->type=0 = MPIDI_CH3_PKT_EAGER_SEND [node669:mpi_rank_1][handle_cqe] src/mpid/ch3/channels/mrail/src/gen2/ibv_channel_manager.c:548: [] Got completion with error 10, vendor code=0x88, dest rank=5 : No such file or directory (2) ==> RUN 1iB STOP without writing pickup => exit