<table cellspacing="0" cellpadding="0" border="0" ><tr><td valign="top" style="font: inherit;">Hi,<br><br>I configureed my PVFS2.7.1 server on my IBM thinkpad laptop, which works under ubuntu8.10 and so does the client. Now I use pio-bench to take simple stride PVFS I/O trace and it works fine, the thing is I must set the number of process to 1 when I running mpiexec, if I set the number of process more than 1 it fails and tips like below:<br><br>gxwangdi@WANGDI:~/Desktop/pio-bench$ sudo mpiexec -n 1 ./pio-bench<br>[sudo] password for gxwangdi: <br>File under test: /mnt/pvfs2/ftpaccess<br>Number of Processes: 1<br>Sync: off<br>Averaging: Off<br>the nested strided pattern needs to be run with an even amount of processes<br>gxwangdi@WANGDI:~/Desktop/pio-bench$ sudo mpiexec -n 4 ./pio-bench<br>Fatal error in MPI_Barrier: Other MPI error, error stack:<br>MPI_Barrier(406)..........................: MPI_Barrier(MPI_COMM_WORLD)
failed<br>MPIR_Barrier(77)..........................: <br>MPIC_Sendrecv(126)........................: <br>MPIC_Wait(270)............................: <br>MPIDI_CH3i_Progress_wait(215).............: an error occurred while handling an event returned by MPIDU_Sock_Wait()<br>MPIDI_CH3I_Progress_handle_sock_event(420): <br>MPIDU_Socki_handle_read(637)..............: connection failure (set=0,sock=1,errno=104:Connection reset by peer)[cli_0]: aborting job:<br>Fatal error in MPI_Barrier: Other MPI error, error stack:<br>MPI_Barrier(406)..........................: MPI_Barrier(MPI_COMM_WORLD) failed<br>MPIR_Barrier(77)..........................: <br>MPIC_Sendrecv(126)........................: <br>MPIC_Wait(270)............................: <br>MPIDI_CH3i_Progress_wait(215).............: an error occurred while handling an event returned by MPIDU_Sock_Wait()<br>MPIDI_CH3I_Progress_handle_sock_event(420): <br>MPIDU_Socki_handle_readFatal error in MPI_Bcast: Other
MPI error, error stack:<br>MPI_Bcast(786)............................: MPI_Bcast(buf=0x1fd6ca78, count=20, MPI_BYTE, root=0, MPI_COMM_WORLD) failed<br>MPIR_Bcast(198)...........................: <br>MPIC_Recv(81).............................: <br>MPIC_Wait(270)............................: <br>MPIDI_CH3i_Progress_wait(215).............: an error occurred while handling an event returned by MPIDU_Sock_Wait()<br>MPIDI_CH3I_Progress_handle_sock_event(456): <br>adjust_iov(973)...........................: ch3|sock|immedread 0x1e5a0d60 0x1f329978 0x1f3258d0<br>MPIDU_Sock_readv(455).....................: the supplied buffer contains invalid memory (set=0,sock=1,errno=14:Bad address)[cli_1]: aborting job:<br>Fatal error in MPI_Bcast: Other MPI error, error stack:<br>MPI_Bcast(786)............................: MPI_Bcast(buf=0x1fd6ca78, count=20, MPI_BYTE, root=0, MPI_COMM_WORLD) failed<br>MPIR_Bcast(198)...........................:
<br>MPIC_Recv(81).............................: <br>MPIC_Wait(270)............................(637)..............: connection failure (set=0,sock=1,errno=104:Connection reset by peer)<br>: <br>MPIDI_CH3i_Progress_wait(215).............: an error occurred while handling an event returned by MPIDU_Sock_Wait()<br>MPIDI_CH3I_Progress_handle_sock_event(456): <br>adjust_iov(973)...........................: ch3|sock|immedread 0x1e5a0d60 0x1f329978 0x1f3258d0<br>MPIDU_Sock_readv(455).....................: the supplied buffer contains invalid memory (set=0,sock=1,errno=14:Bad address)<br>Fatal error in MPI_Bcast: Other MPI error, error stack:<br>MPI_Bcast(786)............................: MPI_Bcast(buf=0x1fd6ca78, count=20, MPI_BYTE, root=0, MPI_COMM_WORLD) failed<br>MPIR_Bcast(198)...........................: <br>MPIC_Recv(81).............................: <br>MPIC_Wait(270)............................: <br>MPIDI_CH3i_Progress_wait(215).............: an error
occurred while handling an event returned by MPIDU_Sock_Wait()<br>MPIDI_CH3I_Progress_handle_sock_event(456): <br>adjust_iov(973)...........................: ch3|sock|immedread 0x1e5a0d60 0x1eb9f978 0x1eb9b8d0<br>MPIDU_Sock_readv(455).....................: the supplied buffer contains invalid memory (set=0,sock=1,errno=14:Bad address)[cli_2]: aborting job:<br>Fatal error in MPI_Bcast: Other MPI error, error stack:<br>MPI_Bcast(786)............................: MPI_Bcast(buf=0x1fd6ca78, count=20, MPI_BYTE, root=0, MPI_COMM_WORLD) failed<br>MPIR_Bcast(198)...........................: <br>MPIC_Recv(81).............................: <br>MPIC_Wait(270)............................: <br>MPIDI_CH3i_Progress_wait(215).............: an error occurred while handling an event returned by MPIDU_Sock_Wait()<br>MPIDI_CH3I_Progress_handle_sock_event(456): <br>adjust_iov(973)...........................: ch3|sock|immedread 0x1e5a0d60 0x1eb9f978
0x1eb9b8d0<br>MPIDU_Sock_readv(455).....................: the supplied buffer contains invalid memory (set=0,sock=1,errno=14:Bad address)<br>rank 1 in job 9 WANGDI_59039 caused collective abort of all ranks<br> exit status of rank 1: return code 1 <br>rank 0 in job 9 WANGDI_59039 caused collective abort of all ranks<br> exit status of rank 0: return code 1 <br>gxwangdi@WANGDI:~/Desktop/pio-bench$ sudo mpiexec -n 4 hostname<br>WANGDI<br>WANGDI<br>WANGDI<br>WANGDI<br><br>The MPI works fine as I have verified it using hostname command. My pio-bench.conf is like below:<br><br> Testfile "/mnt/pvfs2/ftpaccess"<br>#TestFile "/home/gxwangdi/Desktop/ftpaccess"<br><br>OutputToFile "/home/gxwangdi/Desktop/pio-bench/results/result"<br><br><ap_module><br> ModuleName "Nested Strided (read)"<br> ModuleReps 3<br> ModuleSettleTime
5<br></ap_module><br><br><ap_module><br> ModuleName "Nested Strided (write)"<br> ModuleReps 3<br> ModuleSettleTime 5<br></ap_module><br><br><ap_module><br> ModuleName "Nested Strided (read-modify-write)"<br> ModuleReps 3<br> ModuleSettleTime 5<br></ap_module><br><br><ap_module><br> ModuleName "Nested Strided (re-read)"<br> ModuleReps 3<br> ModuleSettleTime 5<br></ap_module><br><br><ap_module><br> ModuleName "Nested Strided (re-write)"<br> ModuleReps 3<br> ModuleSettleTime 5<br></ap_module><br><br>As I can not find the system log file for pio-bench somewhere in the directory, I do not understand what the problem is.<br><br>Appreciate your responses.<br></td></tr></table><br>
<hr size=1><a href="http://cn.rd.yahoo.com/mail_cn/tagline/card/*http://card.mail.cn.yahoo.com/"> 好玩贺卡等你发，邮箱贺卡全新上线！</a>