[Myrinet] Cannot use totatalview debuger with mpich-gm.
??????? ?????? ??????????? <[email protected]>
| Newsgroups | gmane.network.myrinet.general |
|---|---|
| Organization | Kvant |
| Message-ID | <[email protected]> |
Hi!
My program is aborted then I try to run it under totalview. Here goes the log
of debug session:
[maximh@M257E:~/testinteract]$ /common/mpich/bin/mpirun.ch_gm --gm-np 8 --gm-f gmpilist -tv
/home/maximh/testinteract/intertest
/usr/bin/totalviewcli
TVROOT = /common/toolworks/totalview.5.0.0-1
exectarget = /common/toolworks/totalview.5.0.0-1/linux-alpha/bin/tv5climain
Linux Alpha TotalView 5.0.0-1
Copyright 1999-2001 by Etnus, LLC. ALL RIGHTS RESERVED.
Copyright 1999 by Etnus, Inc.
Copyright 1996-1998 by Dolphin Interconnect Solutions, Inc.
Copyright 1989-1996 by BBN Inc.
Mapping 16196 bytes of ELF string data from '/home/maximh/testinteract/intertest'...done
Digesting 1021 ELF symbols from '/home/maximh/testinteract/intertest'...done
Skimming 9852 bytes of DWARF '.debug_info' symbols from '/home/maximh/testinteract/intertest'...done
Indexing 600 bytes of DWARF '.debug_frame' symbols from '/home/maximh/testinteract/intertest'...done
Digesting 4177 ECOFF external symbols...done
Digesting 307 ECOFF local symbols...done
Loading dynamic symbols for /home/maximh/testinteract/intertest
Mapping 53450 bytes of ELF string data from '/lib/libc.so.6.1'...done
Digesting 9661 ELF symbols from '/lib/libc.so.6.1'...done
Digesting 2790 ECOFF external symbols...done
Digesting 269212 ECOFF local symbols...done
Library /lib/libc.so.6.1 is loaded at 0x2000011e000
Mapping 7380 bytes of ELF string data from '/usr/lib/libots.so'...done
Digesting 1056 ELF symbols from '/usr/lib/libots.so'...done
Digesting 98 ECOFF external symbols...done
Digesting 1030 ECOFF local symbols...done
Library /usr/lib/libots.so is loaded at 0x20000354000
Mapping 5768 bytes of ELF string data from '/lib/ld-linux.so.2'...done
Digesting 1234 ELF symbols from '/lib/ld-linux.so.2'...done
Digesting 269 ECOFF external symbols...done
Digesting 18624 ECOFF local symbols...done
Library /lib/ld-linux.so.2 is loaded at 0x20000000000
Thread 1.1 has appeared
Process 1 has exited
{ Here I made quite a long pause (about 30 sec). I didn't entered any TotalView
command (like dstep, dcont ..) and after that period of time i've got the following
messages. When they appears, debugging is not possible anymore.
NOTE: If I execute dcont command right after the debugging session start
everything is Ok and debugging works fine }
d1.<> WARNING: libgm/gm_send.c:176:???():userland:
send failed: target port was closed
_gm_sent: gmID=336 'M258E' msg_cnt=1 send failed to complete (see kernel log for details)WARNING:
libgm/gm_send.c:176:???():userland:
send failed: target port was closed
_gm_sent: gmID=336 'M258E' msg_cnt=1 send failed to complete (see kernel log for details)WARNING:
libgm/gm_send.c:176:???():userland:
WARNING: libgm/gm_send.c:176:???():userland:
send failed: target port was closed
send failed: target port was closed
_gm_sent: gmID=337 'M259E' msg_cnt=1 send failed to complete (see kernel log for details)_gm_sent: gmID=337 'M259E'
msg_cnt=1 send failed to complete (see kernel log for details)WARNING: libgm/gm_send.c:176:???():userland:
send failed: target port was closed
WARNING: libgm/gm_send.c:176:???():userland:
send failed: target port was closed
_gm_sent: gmID=338 'M260E' msg_cnt=1 send failed to complete (see kernel log for details)_gm_sent: gmID=338 'M260E'
msg_cnt=1 send failed to complete (see kernel log for details)
d1.<>
d1.<> interacttest:Node noini[0/0] Receive SIGINT signal 2
{ Here I pressed Ctrl-C. }
Anyone has some ideas ?
Kirill