Here's what you need:
- perl interpreter in /usr/bin/perl
- nagios' utils.pm in /usr/local/nagios/libexec/
- perl module Time::HiRes (cpan; install Time::HiRes)
- sudo in /usr/bin/
- MegaCli in /opt/MegaRAID/MegaCli/MegaCli64
#!/usr/bin/perl -wT
#
# CHECK DELL/MegaRAID DISK ARRAYS ON LINUX
# $Id: check_dellperc 142 2008-03-17 22:25:46Z thiago $
#
BEGIN {
$ENV{'PATH'} = '/usr/bin';
$ENV{'ENV'} = '';
$ENV{'BASH_ENV'} = '';
$ENV{'IFS'} = ' ' if ( defined($ENV{'IFS'}) ) ;
}
use strict;
use lib "/usr/local/nagios/libexec";
use utils qw($TIMEOUT %ERRORS &print_revision &support &usage);
use Getopt::Long;
use Time::HiRes qw ( tv_interval gettimeofday );
use vars qw($opt_h $help $opt_V $version);
use vars qw($PROGNAME $SUDO $MEGACLI);
$PROGNAME = "check_dellperc";
$SUDO = "/usr/bin/sudo";
$MEGACLI = "/opt/MegaRAID/MegaCli/MegaCli64";
my $t_start = [gettimeofday];
Getopt::Long::Configure('bundling');
GetOptions
("V" => \$opt_V, "version" => \$opt_V,
"h" => \$opt_h, "help" => \$opt_h,
);
if ( $opt_V ) { print_revision($PROGNAME, '$Id: check_dellperc 142 2008-03-17 22:25:46Z thiago $');
exit $ERRORS{'OK'};
} elsif ( $opt_h ) {
print_help();
exit $ERRORS{'OK'};
}
my $TIMEOUT = $utils::TIMEOUT;
my $start_time = time();
# TODO: add timeout option#if ( $opt_t && $opt_t =~ /^([0-9]+)$/ ) {
# $TIMEOUT = $1;
#}
# Check state of Logical Devices
my $status = "PERC OK";
my $perfdata = "";
my $errors = $ERRORS{'OK'};
my $vd = "";
my $vds = "";
open(MROUT, "$SUDO $MEGACLI -LDInfo -Lall -aALL -NoLog|");
if (!<MROUT>) {
print("Can't run $MEGACLI\n");
exit $ERRORS{'UNKNOWN'};
}
while (<MROUT>) {
my $line = $_;
chomp($line);
if ($line =~ /^Virtual Disk: (\d+)/) {
$vd = $1;
next;
}
if ($vd =~ /^[0-9]+$/) {
if ($line =~ /^State: (\w+)/) {
$vds = $1; #TODO: verbose print("State for VD #$vd is $vds\n");
$perfdata = $perfdata." VD$vd=$vds";
if ($vds !~ /^Optimal$/) {
$errors = $ERRORS{'CRITICAL'};
$status = "RAID ERROR";
#TODO: verbose print("Error found: $status. Skipping remaining Virtual Drive tests.\n");
last;
} else {
$vd = ""; $vds = "";
}
}
}
}
close(MROUT);
# Check state of Physical Drives
my $count_type;my $pd = "";
my $pds = "";
open(MROUT, "$SUDO $MEGACLI -PDList -aALL -NoLog|");
if (!<MROUT>) {
print("Can't run $MEGACLI\n");
exit $ERRORS{'UNKNOWN'};
}
while (<MROUT>) {
my $line = $_;
chomp($line);
if ($line =~ /^Device Id: (\d+)/) {
$pd = $1;
next;
}
if ($pd =~ /^[0-9]+$/) {
if ($line =~ /^(Media Error|Other Error|Predictive Failure) Count: (\w+)/) {
$count_type = $1;
$pds = $2; #TODO: verbose print("$count_type count for device id #$pd is $pds\n");
$perfdata = $perfdata." PD$pd=$count_type;$pds";
if ($pds != 0) {
if ($errors == $ERRORS{'OK'}) {
$status = "DISK ERROR";
$errors = $ERRORS{'WARNING'};
}
}
}
}
}
close(MROUT);
# Got here OK
#
my $t_end = [gettimeofday];
print "$status| time=" . (tv_interval $t_start, $t_end) . "$perfdata\n";
exit $errors;
sub print_usage
{
print "Usage: $PROGNAME\n";
}
sub print_help
{
print_revision($PROGNAME, '$Revision: 142 $ ');
print "Copyright (C) 2007 Westfield Ltd\n\n";
print "Check Dell/MegaRaid Disk Array plugin for Nagios\n\n";
print_usage();
print <<USAGE
-V, --version
Print program version information
-h, --help
This help screen
Example:
$PROGNAME
USAGE
;
}
After installing the script above and changing the paths to match your system, edit your sudoers file (sudo /usr/sbin/visudo) and comment the following line:
# Defaults requiretty
If you are doing NRPE checks, the line above will prevent the script from running sudo because there is no TTY associated with it. There is probably a way around it that doesn't involve disabling this security feature - if you find out please tell me.
While in the sudoers file, also add the following two lines:
nagios ALL=(ALL) NOPASSWD: /opt/MegaRAID/MegaCli/MegaCli64 -PDList -aALL -NoLog
nagios ALL=(ALL) NOPASSWD: /opt/MegaRAID/MegaCli/MegaCli64 -LDInfo -Lall -aALL –NoLog
If you run NRPE with a user different than "nagios", change the lines above to match it.
That is it, basically. Before adding it to your NRPE checks, give it a try:
PERC OK| time=0.189185 VD0=Optimal VD1=Optimal PD0=Media Error;0 PD0=Other Error;0 PD0=Predictive Failure;0 PD1=Media Error;0 PD1=Other Error;0 PD1=Predictive Failure;0 PD2=Media Error;0 PD2=Other Error;0 PD2=Predictive Failure;0 PD3=Media Error;0 PD3=Other Error;0 PD3=Predictive Failure;0 PD4=Media Error;0 PD4=Other Error;0 PD4=Predictive Failure;0 PD5=Media Error;0 PD5=Other Error;0 PD5=Predictive Failure;0
It should return a status of zero (unless, of course, your RAID is b0rken):
$ echo $?
0
