在 2010年12月23日下午5:35，孟宪军 <xjun.meng@gmail.com>写道：

My main question is:

after I finished the checkpoint operation against a simple task which ran on tow machines, I can only restart it on one machine. if I ran the following command to force the ompi-restart to run the program on two machines:

ompi-restart -hostfile ./machine_names ompi_global_snapshot_XXX.ckpt
(the machine_names include two host names)

the output is:
--------------------------------------------------------------------------
Error: Unable to obtain the proper restart command to restart from the
checkpoint file (opal_snapshot_1.ckpt). Returned -1.

--------------------------------------------------------------------------
[jx-mpi-fcr048:04116] [ 0] /lib64/tls/libpthread.so.0 [0x302b80c420]
[jx-mpi-fcr048:04116] [ 1] /lib64/tls/libc.so.6(__libc_free+0x25) [0x302af68b85]
[jx-mpi-fcr048:04116] [ 2] /home/hpc_meng/openmpi/lib/libopen-pal.so.0(opal_argv_free+0x41) [0x2a9557de31]
[jx-mpi-fcr048:04116] [ 3] /home/hpc_meng/openmpi/lib/libopen-pal.so.0(opal_event_fini+0x27) [0x2a95573ac7]
[jx-mpi-fcr048:04116] [ 4] /home/hpc_meng/openmpi/lib/libopen-pal.so.0(opal_finalize+0x2f) [0x2a95568a0f]
[jx-mpi-fcr048:04116] [ 5] opal-restart [0x401888]
[jx-mpi-fcr048:04116] [ 6] /lib64/tls/libc.so.6(__libc_start_main+0xdb) [0x302af1c4bb]
[jx-mpi-fcr048:04116] [ 7] opal-restart [0x40147a]
[jx-mpi-fcr048:04116] *** End of error message ***
--------------------------------------------------------------------------
mpirun noticed that process rank 1 with PID 4116 on node jx-mpi-fcr048.jx.baidu.com exited on signal 11 (Segmentation fault).
--------------------------------------------------------------------------

My global_snapshot_meta.data is:

# Seq: 0
# Timestamp: Thu Dec 23 16:39:46 2010
# Process: 1680080897.0
# OPAL CRS Component: blcr
# Snapshot Reference: opal_snapshot_0.ckpt
# Snapshot Location: /home/work/checkpoint/ompi_global_snapshot_22817.ckpt/0
# Process: 1680080897.1
# OPAL CRS Component: blcr
# Snapshot Reference: opal_snapshot_1.ckpt
# Snapshot Location: /home/work/checkpoint/ompi_global_snapshot_22817.ckpt/0
# Timestamp: Thu Dec 23 16:39:47 2010
# Finished Seq: 0

Does anabody know why?

Thanks
Xianjun Meng

2010/12/23 孟宪军 <xjun.meng@gmail.com>

Dear all,

I had to try the checkpoint/restart function of Openmpi recently, and after several failure and checking lots of the docement, I am still very confused about how to config the checkpoint/restart function. Can anybody give me a $HOME/.openmpi/mca-params.conf script and introduce me what parameters I should specified when i install the openmpi?

BTW, I want to install the openmpi1.5.1 and blcr 0.8.0.

Thanks
Xianjun Meng