107 lines
3.5 KiB
Perl
107 lines
3.5 KiB
Perl
#! /usr/bin/perl
|
|
# @configure_input@
|
|
################################################################################
|
|
#
|
|
# Usage: checkpoint_script <session_id> <job_id> <user_id> <group_id> <checkpoint_dir> <checkpoint_name> <signal_num> <checkpoint_depth>
|
|
#
|
|
# This script is invoked by pbs_mom to checkpoint a job.
|
|
# Errors are logged to syslog
|
|
#
|
|
################################################################################
|
|
use strict;
|
|
use Sys::Syslog;
|
|
|
|
# configure should assign a value to blcr_bindir
|
|
# blcr_bindir, if non-empty, is appended to path
|
|
my $blcr_bindir="@BLCR_BINDIR@";
|
|
|
|
# Customize the following script variables
|
|
# Customize the PATH to include location of blcr cr_checkpoint command
|
|
$ENV{PATH} .= ":$blcr_bindir" if $blcr_bindir;
|
|
my $logLevel = 3; # 0 = none, 1 = fail, 2 = info, 3 = debug
|
|
|
|
logPrint(2, "Invoked: $0 " . join(' ', @ARGV) . "\n");
|
|
|
|
my ($sessionId, $jobId, $userId, $groupId, $signalNum, $checkpointDir, $checkpointName, $checkpointDepth);
|
|
my $usage =
|
|
"Usage: $0 <session_id> <job_id> <user_id> <group_id> <checkpoint_dir> <checkpoint_name> <signal_num> <checkpoint_depth>\n";
|
|
|
|
# Note that depth is not used in this script but could control a limit to the
|
|
# number of checkpoint image files that are preserved on the disk.
|
|
#
|
|
# Note also that a request was made to identify whether this script was invoked
|
|
# by the job's owner or by a system administrator. While this information is
|
|
# known to pbs_server, it is not propagated to pbs_mom and thus it is not
|
|
# possible to pass this to the script. Therefore, a workaround is to invoke
|
|
# qmgr and attempt to set a trivial variable. This will fail if the invoker is
|
|
# not a manager.
|
|
|
|
if (@ARGV == 8)
|
|
{
|
|
($sessionId, $jobId, $userId, $groupId, $checkpointDir, $checkpointName, $signalNum, $checkpointDepth) = @ARGV;
|
|
}
|
|
else { logDie(1, $usage); }
|
|
|
|
# Drop privileges to the job owner
|
|
my $gid = getgrnam($groupId);
|
|
logDie(1, "Unable to resolve group id ($groupId)\n") unless defined $gid;
|
|
$( = $gid;
|
|
$) = $gid;
|
|
logDie(1, "Unable to set gid: $gid") unless $gid == $(;
|
|
my $uid = getpwnam($userId);
|
|
logDie(1, "Unable to resolve user id ($userId)\n") unless defined $uid;
|
|
$< = $uid;
|
|
$> = $uid;
|
|
logDie(1, "Unable to set uid: $uid") unless $uid == $<;
|
|
|
|
# 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;
|
|
|
|
# Build blcr checkpoint command
|
|
my $cmd = "cr_checkpoint";
|
|
$cmd .= " --signal $signalNum" if $signalNum;
|
|
$cmd .= " --tree $sessionId";
|
|
$cmd .= " --file $checkpointName";
|
|
my $output = `$cmd 2>&1`;
|
|
my $rc = $? >> 8;
|
|
if ($rc)
|
|
{
|
|
logPrint(1, "Subcommand ($cmd) failed with rc=$rc:\n$output") if $logLevel >= 1;
|
|
}
|
|
else
|
|
{
|
|
logPrint(3, "Subcommand ($cmd) yielded rc=$rc:\n$output") if $logLevel >= 3;
|
|
}
|
|
exit $rc;
|
|
|
|
################################################################################
|
|
# logPrint($message)
|
|
# Write a message (to syslog) and die
|
|
################################################################################
|
|
sub logPrint
|
|
{
|
|
my ($level, $message) = @_;
|
|
my @severity = ('none', 'warning', 'info', 'debug');
|
|
|
|
return if $logLevel < $level;
|
|
|
|
openlog('checkpoint_script', '', 'user');
|
|
syslog($severity[$level], $message);
|
|
closelog();
|
|
}
|
|
|
|
################################################################################
|
|
# logDie($message)
|
|
# Write a message (to syslog) and die
|
|
################################################################################
|
|
sub logDie
|
|
{
|
|
my ($level, $message) = @_;
|
|
|
|
logPrint($level, $message);
|
|
die($message);
|
|
}
|
|
|