#! /usr/bin/perl
################################################################################
#
# Usage: checkpoint_script
#
# This script is invoked by pbs_mom to checkpoint a job.
#
################################################################################
use strict;
use Sys::Syslog;
# Log levels:
# 0 = none -- no logging
# 1 = fail -- log only failures
# 2 = info -- log invocations
# 3 = debug -- log all subcommands
my $logLevel = 3;
logPrint(2, "Invoked: $0 " . join(' ', @ARGV) . "\n");
my ($sessionId, $jobId, $userId, $signalNum, $checkpointDir, $checkpointName);
my $usage =
"Usage: $0 \n";
# Note that depth is not used in this script but could control a limit to the number of checkpoint
# image files that are preserved on the disk.
#
# Note also that a request was made to identify whether this script was invoked by the job's
# owner or by a system administrator. While this information is known to pbs_server, it
# is not propagated to pbs_mom and thus it is not possible to pass this to the script.
# Therefore, a workaround is to invoke qmgr and attempt to set a trivial variable.
# This will fail if the invoker is not a manager.
if (@ARGV == 7)
{
($sessionId, $jobId, $userId, $checkpointDir, $checkpointName, $signalNum ) =
@ARGV;
}
else { logDie(1, $usage); }
# Change to the checkpoint directory where we want the checkpoint to be created
chdir $checkpointDir
or logDie(1, "Unable to cd to checkpoint dir ($checkpointDir): $!\n")
if $logLevel;
my $cmd = "cr_checkpoint";
$cmd .= " --signal $signalNum" if $signalNum;
$cmd .= " --tree $sessionId";
$cmd .= " --file $checkpointName";
my $output = `$cmd 2>&1`;
my $rc = $? >> 8;
logDie(1, "Subcommand ($cmd) failed with rc=$rc:\n$output")
if $rc && $logLevel >= 1;
logPrint(3, "Subcommand ($cmd) yielded rc=$rc:\n$output")
if $logLevel >= 3;
exit 0;
################################################################################
# logPrint($message)
# Write a message (to syslog) and die
################################################################################
sub logPrint
{
my ($level, $message) = @_;
my @severity = ('none', 'warning', 'info', 'debug');
return if $level > $logLevel;
openlog('checkpoint_script', '', 'user');
syslog($severity[$level], $message);
closelog();
}
################################################################################
# logDie($message)
# Write a message (to syslog) and die
################################################################################
sub logDie
{
my ($level, $message) = @_;
logPrint($level, $message);
die($message);
}