dadca7da88
This merge adds Checkpoint/Restart support to Open MPI. The initial frameworks and components support a LAM/MPI-like implementation. This commit follows the risk assessment presented to the Open MPI core development group on Feb. 22, 2007. This commit closes trac:158 More details to follow. This commit was SVN r14051. The following SVN revisions from the original message are invalid or inconsistent and therefore were not cross-referenced: r13912 The following Trac tickets were found above: Ticket 158 --> https://svn.open-mpi.org/trac/ompi/ticket/158
130 строки
3.6 KiB
Groff
130 строки
3.6 KiB
Groff
.\"
|
|
.\" Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
|
|
.\" University Research and Technology
|
|
.\" Corporation. All rights reserved.
|
|
.\"
|
|
.\" Man page for OPAL's opal-restart command
|
|
.\"
|
|
.\" .TH name section center-footer left-footer center-header
|
|
.TH OPAL-RESTART 1 "March 2007" "Open PAL" "OPEN PAL COMMANDS"
|
|
.\" **************************
|
|
.\" Name Section
|
|
.\" **************************
|
|
.SH NAME
|
|
.
|
|
opal-restart \- Restart a previously checkpointed sequential process using the
|
|
Open PAL Checkpoint/Restart Service (CRS)
|
|
.
|
|
.P
|
|
\fBNote\fR: This should only be used by the user if the application being
|
|
restarted is an OPAL-only application. If it is an Open RTE or Open MPI
|
|
program their respective tools should be used.
|
|
.
|
|
.\" **************************
|
|
.\" Synopsis Section
|
|
.\" **************************
|
|
.SH SYNOPSIS
|
|
.
|
|
.B opal-restart
|
|
.R [ options ]
|
|
.B <SNAPSHOT HANDLE>
|
|
.
|
|
.\" **************************
|
|
.\" Options Section
|
|
.\" **************************
|
|
.SH Options
|
|
.
|
|
\fIopal-restart\fR will attempt to restart a previously checkpointed squential
|
|
process from the snapshot handle reference returned by \fIopal_checkpoint\fP.
|
|
.
|
|
.TP 10
|
|
.B <SNAPSHOT HANDLE>
|
|
The snapshot handle reference returned by \fIopal_checkpoint\fP, used to
|
|
restart the process. This is required to be the last argument to this command.
|
|
.
|
|
.
|
|
.TP
|
|
.B -h | --help
|
|
Display help for this command
|
|
.
|
|
.
|
|
.TP
|
|
.B --fork
|
|
Fork off a new process, which is the restarted process. By default, the
|
|
restarted process will replace \fIopal-restart\fR process.
|
|
.
|
|
.
|
|
.TP
|
|
.B -w | --where
|
|
The location of the local snapshot reference.
|
|
.
|
|
.
|
|
.TP
|
|
.B -s | --self
|
|
Restart this process using the \fIself\fR CRS component. This component is a
|
|
special case, all other CRS components are automaticly detected.
|
|
.
|
|
.
|
|
.TP
|
|
.B -v | --verbose
|
|
Enable verbose output for debugging.
|
|
.
|
|
.
|
|
.TP
|
|
.B -gmca | --gmca \fR<key> <value>\fP
|
|
Pass global MCA parameters that are applicable to all contexts. \fI<key>\fP is
|
|
the parameter name; \fI<value>\fP is the parameter value.
|
|
.
|
|
.
|
|
.TP
|
|
.B -mca | --mca <key> <value>
|
|
Send arguments to various MCA modules.
|
|
.
|
|
.
|
|
.\" **************************
|
|
.\" Description Section
|
|
.\" **************************
|
|
.SH DESCRIPTION
|
|
.
|
|
.PP
|
|
\fIopal-restart\fR can be invoked multiple, non-overlapping times. This
|
|
allows the user to restart a previously running sequential
|
|
process. See opal_crs(7) for more information about the CRS framework and
|
|
components.
|
|
.
|
|
.PP
|
|
When using the \fIself\fR CRS component, the \fB<FILENAME>\fR argument is
|
|
replaced by the name of the program to be restarted followed by any arguments
|
|
that need to be passed to the program. For example, if under normal execution
|
|
we would start our program "foo" as:
|
|
|
|
\fBshell$\fP setenv OMPI_MCA_crs=self
|
|
\fBshell$\fP setenv OMPI_MCA_crs_self_prefix=my_callback_prefix
|
|
\fBshell$\fP ./foo arg1 arg2
|
|
|
|
To restart this process, we may only need to call:
|
|
|
|
\fBshell$\fP opal-restart --self
|
|
-mca crs_self_prefix my_callback_prefix \\
|
|
./foo arg1 arg2
|
|
|
|
This will cause the "my_callback_prefix-restart" function to be called as soon
|
|
as the program "foo" calls \fIOPAL_INIT\fP. You do not have to call your
|
|
program with the same argument set as before. There for we could have just as
|
|
correctly called:
|
|
|
|
\fBshell$\fP opal-restart --self \\
|
|
-mca crs_self_prefix my_callback_prefix \\
|
|
./foo arg3
|
|
|
|
This depends upon the behavior of the program "foo".
|
|
.
|
|
.
|
|
.\" **************************
|
|
.\" See Also Section
|
|
.\" **************************
|
|
.
|
|
.SH SEE ALSO
|
|
opal-checkpoint(1), opal_crs(7)
|
|
.\", orte_crs(7), ompi_crs(7)
|