5 # Monitor Dell server hardware status using Dell OpenManage Server
6 # Administrator, either locally via NRPE, or remotely via SNMP.
10 # Copyright (C) 2010 Trond H. Amundsen
12 # This program is free software: you can redistribute it and/or modify
13 # it under the terms of the GNU General Public License as published by
14 # the Free Software Foundation, either version 3 of the License, or
15 # (at your option) any later version.
17 # This program is distributed in the hope that it will be useful, but
18 # WITHOUT ANY WARRANTY; without even the implied warranty of
19 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
20 # General Public License for more details.
22 # You should have received a copy of the GNU General Public License
23 # along with this program. If not, see <http://www.gnu.org/licenses/>.
26 require 5.006; # Perl v5.6.0 or newer is required
29 use POSIX qw(isatty ceil);
30 use Getopt::Long qw(:config no_ignore_case);
32 # Global (package) variables used throughout the code
33 use vars qw( $NAME $VERSION $AUTHOR $CONTACT $E_OK $E_WARNING $E_CRITICAL
34 $E_UNKNOWN $FW_LOCK $USAGE $HELP $LICENSE
35 $snmp_session $snmp_error $omreport $globalstatus $global
36 $linebreak $omopt_chassis $omopt_system $blade
38 %check %opt %reverse_exitcode %status2nagios
39 %snmp_status %snmp_probestatus %probestatus2nagios %sysinfo
40 %blacklist %nagios_alert_count %count %snmp_enclosure %snmp_controller
41 @perl_warnings @controllers @enclosures @perfdata
42 @report_storage @report_chassis @report_other
45 #---------------------------------------------------------------------
46 # Initialization and global variables
47 #---------------------------------------------------------------------
49 # Collect perl warnings in an array
50 $SIG{__WARN__} = sub { push @perl_warnings, [@_]; };
52 # Version and similar info
53 $NAME = 'check_openmanage';
54 $VERSION = '3.5.11-beta1';
55 $AUTHOR = 'Trond H. Amundsen';
56 $CONTACT = 't.h.amundsen@usit.uio.no';
64 # Firmware update lock file [FIXME: location on Windows?]
65 $FW_LOCK = '/var/lock/.spsetup'; # default on Linux
68 $USAGE = <<"END_USAGE";
69 Usage: $NAME [OPTION]...
77 -p, --perfdata Output performance data
78 -t, --timeout Plugin timeout in seconds
79 -c, --critical Customise temperature critical limits
80 -w, --warning Customise temperature warning limits
81 -d, --debug Debug output, reports everything
82 -h, --help Display this help text
83 -V, --version Display version info
87 -H, --hostname Hostname or IP (required for SNMP)
88 -C, --community SNMP community string
89 -P, --protocol SNMP protocol version
90 --port SNMP port number
94 -i, --info Prefix any alerts with the service tag
95 -e, --extinfo Append system info to alerts
96 -s, --state Prefix alerts with alert state
97 -S, --short-state Prefix alerts with alert state (abbreviated)
98 -o, --okinfo Verbosity when check result is OK
99 -I, --htmlinfo HTML output with clickable links
101 CHECK CONTROL AND BLACKLISTING:
103 -a, --all Check everything, even log content
104 -b, --blacklist Blacklist missing and/or failed components
105 --only Only check a certain component or alert type
106 --check Fine-tune which components are checked
108 For more information and advanced options, see the manual page or URL:
109 http://folk.uio.no/trondham/software/check_openmanage.html
112 # Version and license text
113 $LICENSE = <<"END_LICENSE";
115 Copyright (C) 2010 $AUTHOR
116 License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
117 This is free software: you are free to change and redistribute it.
118 There is NO WARRANTY, to the extent permitted by law.
120 Written by $AUTHOR <$CONTACT>
123 # Options with default values
124 %opt = ( 'blacklist' => [], # blacklisting
125 'check' => [], # check control
126 'critical' => [], # temperature critical limits
127 'warning' => [], # temperature warning limits
128 'timeout' => 30, # default timeout is 30 seconds
129 'debug' => 0, # debugging / verbose output
130 'help' => 0, # display help output
131 'perfdata' => undef, # output performance data
132 'info' => 0, # display servicetag
133 'extinfo' => 0, # display extra info
134 'htmlinfo' => undef, # html tags in output
135 'postmsg' => undef, # post message
136 'state' => 0, # display alert type
137 'short-state' => 0, # display alert type (short)
138 'okinfo' => 0, # default "ok" output level
139 'linebreak' => undef, # specify linebreak
140 'version' => 0, # plugin version info
141 'all' => 0, # check everything
142 'only' => undef, # only one component
143 'omreport' => undef, # omreport path
144 'port' => 161, # default SNMP port
145 'hostname' => undef, # hostname or IP
146 'community' => 'public', # SMNP v1 or v2c
147 'protocol' => 2, # default SNMP protocol 2c
148 'username' => undef, # SMNP v3
149 'authpassword' => undef, # SMNP v3
150 'authkey' => undef, # SMNP v3
151 'authprotocol' => undef, # SMNP v3
152 'privpassword' => undef, # SMNP v3
153 'privkey' => undef, # SMNP v3
154 'privprotocol' => undef, # SMNP v3
155 'use_get_table' => 0, # hack for SNMPv3 on Windows with net-snmp
159 GetOptions('b|blacklist=s' => \@{ $opt{blacklist} },
160 'check=s' => \@{ $opt{check} },
161 'c|critical=s' => \@{ $opt{critical} },
162 'w|warning=s' => \@{ $opt{warning} },
163 't|timeout=i' => \$opt{timeout},
164 'd|debug' => \$opt{debug},
165 'h|help' => \$opt{help},
166 'V|version' => \$opt{version},
167 'p|perfdata:s' => \$opt{perfdata},
168 'i|info' => \$opt{info},
169 'e|extinfo' => \$opt{extinfo},
170 'I|htmlinfo:s' => \$opt{htmlinfo},
171 'postmsg=s' => \$opt{postmsg},
172 's|state' => \$opt{state},
173 'S|short-state' => \$opt{shortstate},
174 'o|ok-info=i' => \$opt{okinfo},
175 'linebreak=s' => \$opt{linebreak},
176 'a|all' => \$opt{all},
177 'only=s' => \$opt{only},
178 'omreport=s' => \$opt{omreport},
179 'port=i' => \$opt{port},
180 'H|hostname=s' => \$opt{hostname},
181 'C|community=s' => \$opt{community},
182 'P|protocol=i' => \$opt{protocol},
183 'U|username=s' => \$opt{username},
184 'authpassword=s' => \$opt{authpassword},
185 'authkey=s' => \$opt{authkey},
186 'authprotocol=s' => \$opt{authprotocol},
187 'privpassword=s' => \$opt{privpassword},
188 'privkey=s' => \$opt{privkey},
189 'privprotocol=s' => \$opt{privprotocol},
190 'use-get_table' => \$opt{use_get_table},
191 ) or do { print $USAGE; exit $E_UNKNOWN };
193 # If user requested help
199 # If user requested version info
207 print "PLUGIN TIMEOUT: $NAME timed out after $opt{timeout} seconds\n";
212 # If we're using SNMP
213 $snmp = defined $opt{hostname} ? 1 : 0;
215 # SNMP session variables
216 $snmp_session = undef;
219 # The omreport command
222 # Check flags, override available with the --check option
223 %check = ( 'storage' => 1, # check storage subsystem
224 'memory' => 1, # check memory (dimms)
225 'fans' => 1, # check fan status
226 'power' => 1, # check power supplies
227 'temp' => 1, # check temperature
228 'cpu' => 1, # check processors
229 'voltage' => 1, # check voltage
230 'batteries' => 1, # check battery probes
231 'amperage' => 1, # check power consumption
232 'intrusion' => 1, # check intrusion detection
233 'alertlog' => 0, # check the alert log
234 'esmlog' => 0, # check the ESM log (hardware log)
235 'esmhealth' => 1, # check the ESM log overall health
239 $linebreak = isatty(*STDOUT) ? "\n" : '<br/>';
241 # Line break from option
242 if (defined $opt{linebreak}) {
243 if ($opt{linebreak} eq 'REG') {
246 elsif ($opt{linebreak} eq 'HTML') {
247 $linebreak = '<br/>';
250 $linebreak = $opt{linebreak};
254 # Exit with status=UNKNOWN if there is firmware upgrade in progress
255 if (!$snmp && -f $FW_LOCK) {
256 print "MONITORING DISABLED - Firmware update in progress ($FW_LOCK exists)\n";
260 # List of controllers and enclosures
261 @controllers = (); # controllers
262 @enclosures = (); # enclosures
263 %snmp_enclosure = (); # enclosures
266 @report_storage = (); # messages with associated nagios level (storage)
267 @report_chassis = (); # messages with associated nagios level (chassis)
268 @report_other = (); # messages with associated nagios level (other)
270 # Counters for everything
273 'pdisk' => 0, # number of physical disks
274 'vdisk' => 0, # number of logical drives (virtual disks)
275 'temp' => 0, # number of temperature probes
276 'volt' => 0, # number of voltage probes
277 'amp' => 0, # number of amperage probes
278 'intr' => 0, # number of intrusion probes
279 'dimm' => 0, # number of memory modules
280 'mem' => 0, # total memory
281 'fan' => 0, # number of fan probes
282 'cpu' => 0, # number of CPUs
283 'bat' => 0, # number of batteries
284 'power' => 0, # number of power supplies
286 'Critical' => 0, # critical entries in ESM log
287 'Non-Critical' => 0, # warning entries in ESM log
288 'Ok' => 0, # ok entries in ESM log
291 'Critical' => 0, # critical entries in alert log
292 'Non-Critical' => 0, # warning entries in alert log
293 'Ok' => 0, # ok entries in alert log
300 # Global health status
301 $global = 1; # default is to check global status
302 $globalstatus = $E_OK; # default global health status is "OK"
304 # Nagios error levels reversed
308 $E_WARNING => 'WARNING',
309 $E_CRITICAL => 'CRITICAL',
310 $E_UNKNOWN => 'UNKNOWN',
313 # OpenManage (omreport) and SNMP error levels
316 'Unknown' => $E_CRITICAL,
317 'Critical' => $E_CRITICAL,
318 'Non-Critical' => $E_WARNING,
320 'Non-Recoverable' => $E_CRITICAL,
321 'Other' => $E_CRITICAL,
332 6 => 'Non-Recoverable',
335 # Probe Status via SNMP
338 1 => 'Other', # probe status is not one of the following:
339 2 => 'Unknown', # probe status is unknown (not known or monitored)
340 3 => 'Ok', # probe is reporting a value within the thresholds
341 4 => 'nonCriticalUpper', # probe has crossed upper noncritical threshold
342 5 => 'criticalUpper', # probe has crossed upper critical threshold
343 6 => 'nonRecoverableUpper', # probe has crossed upper non-recoverable threshold
344 7 => 'nonCriticalLower', # probe has crossed lower noncritical threshold
345 8 => 'criticalLower', # probe has crossed lower critical threshold
346 9 => 'nonRecoverableLower', # probe has crossed lower non-recoverable threshold
347 10 => 'failed', # probe is not functional
350 # Probe status translated to Nagios alarm levels
353 'Other' => $E_CRITICAL,
354 'Unknown' => $E_CRITICAL,
356 'nonCriticalUpper' => $E_WARNING,
357 'criticalUpper' => $E_CRITICAL,
358 'nonRecoverableUpper' => $E_CRITICAL,
359 'nonCriticalLower' => $E_WARNING,
360 'criticalLower' => $E_CRITICAL,
361 'nonRecoverableLower' => $E_CRITICAL,
362 'failed' => $E_CRITICAL,
365 # System information gathered
368 'bios' => 'N/A', # BIOS version
369 'biosdate' => 'N/A', # BIOS release date
370 'serial' => 'N/A', # serial number (service tag)
371 'model' => 'N/A', # system model
372 'rev' => undef, # system revision
373 'osname' => 'N/A', # OS name
374 'osver' => 'N/A', # OS version
375 'om' => 'N/A', # OMSA version
376 'bmc' => 0, # HAS baseboard management controller (BMC)
377 'rac' => 0, # HAS remote access controller (RAC)
378 'rac_name' => 'N/A', # remote access controller (RAC)
379 'bmc_fw' => 'N/A', # BMC firmware
380 'rac_fw' => 'N/A', # RAC firmware
383 # Adjust which checks to perform
384 adjust_checks() if defined $opt{check};
386 # Blacklisted components
387 %blacklist = defined $opt{blacklist} ? %{ get_blacklist() } : ();
389 # If blacklisting is in effect, don't check global health status
390 if (scalar keys %blacklist > 0) {
394 # Take into account new hardware and blades
395 $omopt_chassis = 'chassis'; # default "chassis" option to omreport
396 $omopt_system = 'system'; # default "system" option to omreport
397 $blade = 0; # if this is a blade system
399 # Some initializations and checking before we begin
401 snmp_initialize(); # initialize SNMP
402 snmp_check(); # check that SNMP works
403 snmp_detect_blade(); # detect blade via SNMP
406 # Find the omreport binary
408 # Check help output from omreport, see which options are available.
409 # Also detecting blade via omreport.
410 check_omreport_options();
414 #---------------------------------------------------------------------
416 #---------------------------------------------------------------------
419 # Store a message in one of the message arrays
422 my ($type, $msg, $exval, $id) = @_;
423 defined $id or $id = q{};
427 'storage' => \@report_storage,
428 'chassis' => \@report_chassis,
429 'other' => \@report_other,
432 return push @{ $type2array{$type} }, [ $msg, $exval, $id ];
437 # Run command, put resulting output lines in an array and return a
438 # pointer to that array
443 open my $CMD, '-|', $command
444 or do { report('other', "Couldn't run command '$command': $!", $E_UNKNOWN)
448 or do { report('other', "Couldn't close filehandle for command '$command': $!", $E_UNKNOWN)
449 and return \@lines };
454 # Run command, put resulting output in a string variable and return it
459 open my $CMD, '-|', $command
460 or do { report('other', "Couldn't run command '$command': $!", $E_UNKNOWN) and return };
461 my $rawtext = do { local $/ = undef; <$CMD> }; # slurping
464 # NOTE: We don't check the return value of close() since omreport
465 # does something weird sometimes.
473 sub snmp_initialize {
474 # Legal SNMP v3 protocols
475 my $snmp_v3_privprotocol = qr{\A des|aes|aes128|3des|3desde \z}xms;
476 my $snmp_v3_authprotocol = qr{\A md5|sha \z}xms;
478 # Parameters to Net::SNMP->session()
481 '-port' => $opt{port},
482 '-hostname' => $opt{hostname},
483 '-version' => $opt{protocol},
486 # Parameters for SNMP v3
487 if ($opt{protocol} == 3) {
489 # Username is mandatory
490 if (defined $opt{username}) {
491 $param{'-username'} = $opt{username};
494 print "SNMP ERROR: With SNMPv3 the username must be specified\n";
498 # Authpassword is optional
499 if (defined $opt{authpassword}) {
500 $param{'-authpassword'} = $opt{authpassword};
503 # Authkey is optional
504 if (defined $opt{authkey}) {
505 $param{'-authkey'} = $opt{authkey};
508 # Privpassword is optional
509 if (defined $opt{privpassword}) {
510 $param{'-privpassword'} = $opt{privpassword};
513 # Privkey is optional
514 if (defined $opt{privkey}) {
515 $param{'-privkey'} = $opt{privkey};
518 # Privprotocol is optional
519 if (defined $opt{privprotocol}) {
520 if ($opt{privprotocol} =~ m/$snmp_v3_privprotocol/xms) {
521 $param{'-privprotocol'} = $opt{privprotocol};
524 print "SNMP ERROR: Unknown privprotocol '$opt{privprotocol}', "
525 . "must be one of [des|aes|aes128|3des|3desde]\n";
530 # Authprotocol is optional
531 if (defined $opt{authprotocol}) {
532 if ($opt{authprotocol} =~ m/$snmp_v3_authprotocol/xms) {
533 $param{'-authprotocol'} = $opt{authprotocol};
536 print "SNMP ERROR: Unknown authprotocol '$opt{authprotocol}', "
537 . "must be one of [md5|sha]\n";
542 # Parameters for SNMP v2c or v1
543 elsif ($opt{protocol} == 2 or $opt{protocol} == 1) {
544 $param{'-community'} = $opt{community};
547 print "SNMP ERROR: Unknown SNMP version '$opt{protocol}'\n";
551 # Try to initialize the SNMP session
552 if ( eval { require Net::SNMP; 1 } ) {
553 ($snmp_session, $snmp_error) = Net::SNMP->session( %param );
554 if (!defined $snmp_session) {
555 printf "SNMP: %s\n", $snmp_error;
560 print "ERROR: You need perl module Net::SNMP to run $NAME in SNMP mode\n";
567 # Checking if SNMP works by probing for "chassisModelName", which all
568 # servers should have
571 my $chassisModelName = '1.3.6.1.4.1.674.10892.1.300.10.1.9.1';
572 my $result = $snmp_session->get_request(-varbindlist => [$chassisModelName]);
574 # Typically if remote host isn't responding
575 if (!defined $result) {
576 printf "SNMP CRITICAL: %s\n", $snmp_session->error;
580 # If OpenManage isn't installed or is not working
581 if ($result->{$chassisModelName} =~ m{\A noSuch (Instance|Object) \z}xms) {
582 print "ERROR: (SNMP) OpenManage is not installed or is not working correctly\n";
589 # Detecting blade via SNMP
591 sub snmp_detect_blade {
592 my $DellBaseBoardType = '1.3.6.1.4.1.674.10892.1.300.80.1.7.1.1';
593 my $result = $snmp_session->get_request(-varbindlist => [$DellBaseBoardType]);
595 # Identify blade. Older models (4th and 5th gen models) and/or old
596 # OMSA (4.x) don't have this OID. If we get "noSuchInstance" or
597 # similar, we assume that this isn't a blade
598 if (exists $result->{$DellBaseBoardType} && $result->{$DellBaseBoardType} eq '3') {
605 # Locate the omreport binary
608 # If user has specified path to omreport
609 if (defined $opt{omreport} and -x $opt{omreport}) {
610 $omreport = qq{"$opt{omreport}"};
614 # Possible full paths for omreport
617 '/usr/bin/omreport', # default on Linux
618 '/opt/dell/srvadmin/bin/omreport', # default on Linux with OMSA 6.2.0
619 '/opt/dell/srvadmin/oma/bin/omreport.sh', # alternate on Linux
620 '/opt/dell/srvadmin/oma/bin/omreport', # alternate on Linux
621 'C:\Program Files (x86)\Dell\SysMgt\oma\bin\omreport.exe', # default on Windows x64
622 'C:\Program Files\Dell\SysMgt\oma\bin\omreport.exe', # default on Windows x32
623 'c:\progra~1\dell\sysmgt\oma\bin\omreport.exe', # 8bit legacy default on Windows x32
624 'c:\progra~2\dell\sysmgt\oma\bin\omreport.exe', # 8bit legacy default on Windows x64
627 # Find the one to use
629 foreach my $bin (@omreport_paths) {
631 $omreport = qq{"$bin"};
636 # Exit with status=UNKNOWN if OM is not installed, or we don't
637 # have permission to execute the binary
638 if (!defined $omreport) {
639 print "ERROR: Dell OpenManage Server Administrator (OMSA) is not installed\n";
646 # Checks output from 'omreport -?' and searches for arguments to
647 # omreport, to accommodate deprecated options "chassis" and "system"
648 # (on newer hardware), as well as blade servers.
650 sub check_omreport_options {
651 foreach (@{ run_command("$omreport -? 2>&1") }) {
652 if (m/\A servermodule /xms) {
653 # If "servermodule" argument to omreport exists, use it
654 # instead of argument "system"
655 $omopt_system = 'servermodule';
657 elsif (m/\A mainsystem /xms) {
658 # If "mainsystem" argument to omreport exists, use it
659 # instead of argument "chassis"
660 $omopt_chassis = 'mainsystem';
662 elsif (m/\A modularenclosure /xms) {
663 # If "modularenclusure" argument to omreport exists, assume
664 # that this is a blade
672 # Read the blacklist option and return a hash containing the
673 # blacklisted components
679 if (scalar @{ $opt{blacklist} } >= 0) {
680 foreach my $black (@{ $opt{blacklist} }) {
683 open my $BL, '<', $black
684 or do { report('other', "Couldn't open blacklist file $black: $!", $E_UNKNOWN)
697 return {} if $#bl < 0;
699 # Parse blacklist string, put in hash
700 foreach my $black (@bl) {
701 my @comps = split m{/}xms, $black;
702 foreach my $c (@comps) {
703 next if $c !~ m/=/xms;
704 my ($key, $val) = split /=/xms, $c;
705 my @vals = split /,/xms, $val;
706 $blacklist{$key} = \@vals;
714 # Read the check option and adjust the hash %check, which is a rough
715 # list of components to be checked
720 # Adjust checking based on the '--all' option
723 if (defined $opt{only} and $opt{only} !~ m{\A critical|warning \z}xms) {
724 print qq{ERROR: Wrong simultaneous usage of the "--all" and "--only" options\n};
727 if (scalar @{ $opt{check} } > 0) {
728 print qq{ERROR: Wrong simultaneous usage of the "--all" and "--check" options\n};
732 # set the check hash to check everything
733 map { $_ = 1 } values %check;
738 # Adjust checking based on the '--only' option
739 if (defined $opt{only} and $opt{only} !~ m{\A critical|warning \z}xms) {
741 if (scalar @{ $opt{check} } > 0) {
742 print qq{ERROR: Wrong simultaneous usage of the "--only" and "--check" options\n};
745 if (! exists $check{$opt{only}} && $opt{only} ne 'chassis') {
746 print qq{ERROR: "$opt{only}" is not a known keyword for the "--only" option\n};
750 # reset the check hash
751 map { $_ = 0 } values %check;
753 # adjust the check hash
754 if ($opt{only} eq 'chassis') {
755 map { $check{$_} = 1 } qw(memory fans power temp cpu voltage
756 batteries amperage intrusion esmhealth);
759 $check{$opt{only}} = 1;
765 # Adjust checking based on the '--check' option
766 if (scalar @{ $opt{check} } >= 0) {
767 foreach my $check (@{ $opt{check} }) {
770 open my $CL, '<', $check
771 or do { report('other', "Couldn't open check file $check: $!", $E_UNKNOWN) and return };
784 # Parse checklist string, put in hash
785 foreach my $check (@cl) {
786 my @checks = split /,/xms, $check;
787 foreach my $c (@checks) {
788 next if $c !~ m/=/xms;
789 my ($key, $val) = split /=/xms, $c;
794 # Check if we should check global health status
796 foreach (keys %check) {
797 next CHECK_KEY if $_ eq 'esmlog'; # not part of global status
798 next CHECK_KEY if $_ eq 'alertlog'; # not part of global status
800 if ($check{$_} == 0) { # found something with checking turned off
810 # Runs omreport and returns an array of anonymous hashes containing
812 # Takes one argument: string containing parameters to omreport
819 # Errors that are OK. Some low-end poweredge (and blades) models
820 # don't have RAID controllers, intrusion detection sensor, or
821 # redundant/instrumented power supplies etc.
824 Intrusion\sinformation\sis\snot\sfound\sfor\sthis\ssystem # No intrusion probe
825 | No\sinstrumented\spower\ssupplies\sfound\son\sthis\ssystem # No instrumented PS (blades/low-end)
826 | No\scontrollers\sfound # No RAID controller
827 | No\sbattery\sprobes\sfound\son\sthis\ssystem # No battery probes
828 | Invalid\scommand:\spwrmonitoring # Older OMSAs lack this command(?)
829 # | Current\sprobes\snot\sfound # OMSA + RHEL5.4 bug
832 # Errors that are OK on blade servers
835 No\sfan\sprobes\sfound\son\sthis\ssystem # No fan probes
838 # Run omreport and fetch output
839 my $rawtext = slurp_command("$omreport $command -fmt ssv 2>&1");
840 return [] if !defined $rawtext;
842 # Workaround for Openmanage BUG introduced in OMSA 5.5.0
843 $rawtext =~ s{\n;}{;}gxms if $command eq 'storage controller';
845 # Openmanage sometimes puts a linebreak between "Error" and the
847 $rawtext =~ s{^Error\s*\n}{Error: }xms;
849 # Parse output, store in array
850 for ((split m{\n}xms, $rawtext)) {
852 next if m{$ok_errors}xms;
853 next if ($blade and m{$ok_blade_errors}xms);
854 report('other', "Problem running 'omreport $command': $_", $E_UNKNOWN);
857 next if !m/(.*?;){2}/xms; # ignore lines with less than 3 fields
858 my @vals = split /;/xms;
859 if ($vals[0] =~ m/\A (Index|ID|Severity|Processor|Current\sSpeed) \z/xms) {
864 push @output, { map { $_ => $vals[$i++] } @keys };
869 # Finally, return the collected information
875 # Checks if a component is blacklisted. Returns 1 if the component is
876 # blacklisted, 0 otherwise. Takes two arguments:
877 # arg1: component name
878 # arg2: component id or index
881 my $name = shift; # component name
882 my $id = shift; # component id
883 my $ret = 0; # return value
885 if (defined $blacklist{$name}) {
886 foreach my $comp (@{ $blacklist{$name} }) {
887 if (defined $id and ($comp eq $id or uc($comp) eq 'ALL')) {
896 # Converts the NexusID from SNMP to our version
899 $nexus =~ s{\A \\}{}xms;
900 $nexus =~ s{\\}{:}gxms;
904 # Sets custom temperature thresholds based on user supplied options
905 sub custom_temperature_thresholds {
906 my $type = shift; # type of threshold, either w (warning) or c (critical)
907 my %thres = (); # will contain the thresholds
908 my @limits = (); # holds the input
910 my @opt = $type eq 'w' ? @{ $opt{warning} } : @{ $opt{critical} };
912 if (scalar @opt >= 0) {
913 foreach my $t (@opt) {
917 or do { report('other', "Couldn't open temperature threshold file $t: $!",
918 $E_UNKNOWN) and return {} };
929 # Parse checklist string, put in hash
930 foreach my $th (@limits) {
931 my @tmp = split m{,}xms, $th;
932 foreach my $t (@tmp) {
933 next if $t !~ m{=}xms;
934 my ($key, $val) = split m{=}xms, $t;
935 if ($val =~ m{/}xms) {
936 my ($max, $min) = split m{/}xms, $val;
937 $thres{$key}{max} = $max;
938 $thres{$key}{min} = $min;
941 $thres{$key}{max} = $val;
950 # Gets the output from SNMP result according to the OIDs checked
951 sub get_snmp_output {
952 my ($result,$oidref) = @_;
956 foreach my $oid (keys %{ $result }) {
958 $short =~ s{\s}{}gxms; # remove whitespace
959 $short =~ s{\A (.+) \. (\d+) \z}{$1}xms; # remove last number
961 if (exists $oidref->{$short}) {
962 $temp[$id]{$oidref->{$short}} = $result->{$oid};
966 # Remove any empty indexes
967 foreach my $out (@temp) {
977 # Map the controller or other item in-place
979 my ($key, $val, $list) = @_;
981 foreach my $lst (@{ $list }) {
982 if (!exists $lst->{$key}) {
989 # Return the URL for official Dell documentation for a specific
991 sub documentation_url {
994 # create model short form, e.g. "r710"
995 $model =~ s{\A PowerEdge \s (.+?) \z}{lc($1)}exms;
997 # special case for blades (e.g. M600, M710), they have common
999 $model =~ s{\A m\d+ \z}{m}xms;
1001 return 'http://support.dell.com/support/edocs/systems/pe' . $model . '/';
1004 # Return the URL for warranty information for a server with a given
1005 # serial number (servicetag)
1009 # Dell support sites for different parts of the world
1012 'emea' => 'http://support.euro.dell.com/support/topics/topic.aspx/emea/shared/support/my_systems_info/',
1013 'ap' => 'http://supportapj.dell.com/support/topics/topic.aspx/ap/shared/support/my_systems_info/en/details?',
1014 'glob' => 'http://support.dell.com/support/topics/global.aspx/support/my_systems_info/details?',
1017 # warranty URLs for different country codes
1021 'at' => $supportsite{emea} . 'de/details?c=at&l=de&ServiceTag=', # Austria
1022 'be' => $supportsite{emea} . 'nl/details?c=be&l=nl&ServiceTag=', # Belgium
1023 'cz' => $supportsite{emea} . 'cs/details?c=cz&l=cs&ServiceTag=', # Czech Republic
1024 'de' => $supportsite{emea} . 'de/details?c=de&l=de&ServiceTag=', # Germany
1025 'dk' => $supportsite{emea} . 'da/details?c=dk&l=da&ServiceTag=', # Denmark
1026 'es' => $supportsite{emea} . 'es/details?c=es&l=es&ServiceTag=', # Spain
1027 'fi' => $supportsite{emea} . 'fi/details?c=fi&l=fi&ServiceTag=', # Finland
1028 'fr' => $supportsite{emea} . 'fr/details?c=fr&l=fr&ServiceTag=', # France
1029 'gr' => $supportsite{emea} . 'en/details?c=gr&l=el&ServiceTag=', # Greece
1030 'it' => $supportsite{emea} . 'it/details?c=it&l=it&ServiceTag=', # Italy
1031 'il' => $supportsite{emea} . 'en/details?c=il&l=en&ServiceTag=', # Israel
1032 'me' => $supportsite{emea} . 'en/details?c=me&l=en&ServiceTag=', # Middle East
1033 'no' => $supportsite{emea} . 'no/details?c=no&l=no&ServiceTag=', # Norway
1034 'nl' => $supportsite{emea} . 'nl/details?c=nl&l=nl&ServiceTag=', # The Netherlands
1035 'pl' => $supportsite{emea} . 'pl/details?c=pl&l=pl&ServiceTag=', # Poland
1036 'pt' => $supportsite{emea} . 'en/details?c=pt&l=pt&ServiceTag=', # Portugal
1037 'ru' => $supportsite{emea} . 'ru/details?c=ru&l=ru&ServiceTag=', # Russia
1038 'se' => $supportsite{emea} . 'sv/details?c=se&l=sv&ServiceTag=', # Sweden
1039 'uk' => $supportsite{emea} . 'en/details?c=uk&l=en&ServiceTag=', # United Kingdom
1040 'za' => $supportsite{emea} . 'en/details?c=za&l=en&ServiceTag=', # South Africa
1042 'br' => $supportsite{glob} . 'c=br&l=pt&ServiceTag=', # Brazil
1043 'ca' => $supportsite{glob} . 'c=ca&l=en&ServiceTag=', # Canada
1044 'mx' => $supportsite{glob} . 'c=mx&l=es&ServiceTag=', # Mexico
1045 'us' => $supportsite{glob} . 'c=us&l=en&ServiceTag=', # USA
1047 'au' => $supportsite{ap} . 'c=au&l=en&ServiceTag=', # Australia
1048 'cn' => $supportsite{ap} . 'c=cn&l=zh&ServiceTag=', # China
1049 'in' => $supportsite{ap} . 'c=in&l=en&ServiceTag=', # India
1051 'XX' => $supportsite{glob} . 'ServiceTag=', # default
1054 if (exists $url{$opt{htmlinfo}}) {
1055 return $url{$opt{htmlinfo}} . $tag;
1058 return $url{XX} . $tag;
1063 # This helper function returns the corresponding value of a hash key,
1064 # but takes into account that the key may not exist
1066 my $key = shift || return undef;
1068 return exists $hash->{$key} ? $hash->{$key} : "Undefined value $key";
1073 #---------------------------------------------------------------------
1075 #---------------------------------------------------------------------
1077 #-----------------------------------------
1078 # Check global health status
1079 #-----------------------------------------
1085 # Checks global status, i.e. both storage and chassis
1087 my $systemStateGlobalSystemStatus = '1.3.6.1.4.1.674.10892.1.200.10.1.2.1';
1088 my $result = $snmp_session->get_request(-varbindlist => [$systemStateGlobalSystemStatus]);
1089 if (!defined $result) {
1090 printf "SNMP ERROR [global]: %s\n", $snmp_error;
1093 $health = $status2nagios{$snmp_status{$result->{$systemStateGlobalSystemStatus}}};
1097 # NB! This does not check storage, only chassis...
1099 foreach (@{ run_command("$omreport $omopt_system -fmt ssv") }) {
1101 next if m/\A SEVERITY;COMPONENT/xms;
1102 if (m/\A (.+?);Main\sSystem(\sChassis)? /xms) {
1103 $health = $status2nagios{$1};
1114 #-----------------------------------------
1115 # STORAGE: Check controllers
1116 #-----------------------------------------
1117 sub check_controllers {
1118 return if blacklisted('ctrl', 'all');
1127 my $firmware = undef;
1129 my $minstdr = undef; # Minimum required Storport driver version
1130 my $stdr = undef; # Storport driver version
1136 '1.3.6.1.4.1.674.10893.1.20.130.1.1.1' => 'controllerNumber',
1137 '1.3.6.1.4.1.674.10893.1.20.130.1.1.2' => 'controllerName',
1138 '1.3.6.1.4.1.674.10893.1.20.130.1.1.5' => 'controllerState',
1139 '1.3.6.1.4.1.674.10893.1.20.130.1.1.8' => 'controllerFWVersion',
1140 '1.3.6.1.4.1.674.10893.1.20.130.1.1.38' => 'controllerComponentStatus',
1141 '1.3.6.1.4.1.674.10893.1.20.130.1.1.39' => 'controllerNexusID',
1142 '1.3.6.1.4.1.674.10893.1.20.130.1.1.41' => 'controllerDriverVersion',
1143 '1.3.6.1.4.1.674.10893.1.20.130.1.1.44' => 'controllerMinFWVersion',
1144 '1.3.6.1.4.1.674.10893.1.20.130.1.1.45' => 'controllerMinDriverVersion',
1145 '1.3.6.1.4.1.674.10893.1.20.130.1.1.55' => 'controllerStorportDriverVersion',
1146 '1.3.6.1.4.1.674.10893.1.20.130.1.1.56' => 'controllerMinRequiredStorportVer',
1149 # We use get_table() here for the odd case where a server has
1150 # two or more controllers, and where some OIDs are missing on
1151 # one of the controllers.
1152 my $controllerTable = '1.3.6.1.4.1.674.10893.1.20.130.1';
1153 my $result = $snmp_session->get_table(-baseoid => $controllerTable);
1155 # No controllers is OK
1156 return if !defined $result;
1158 @output = @{ get_snmp_output($result, \%ctrl_oid) };
1161 @output = @{ run_omreport('storage controller') };
1175 foreach my $out (@output) {
1177 $name = $out->{controllerName};
1178 $state = get_hashval($out->{controllerState}, \%ctrl_state);
1179 $status = $snmp_status{$out->{controllerComponentStatus}};
1180 $minfw = exists $out->{controllerMinFWVersion}
1181 ? $out->{controllerMinFWVersion} : undef;
1182 $mindr = exists $out->{controllerMinDriverVersion}
1183 ? $out->{controllerMinDriverVersion} : undef;
1184 $firmware = exists $out->{controllerFWVersion}
1185 ? $out->{controllerFWVersion} : 'N/A';
1186 $driver = exists $out->{controllerDriverVersion}
1187 ? $out->{controllerDriverVersion} : 'N/A';
1188 $minstdr = exists $out->{'controllerMinRequiredStorportVer'}
1189 ? $out->{controllerMinRequiredStorportVer} : undef;
1190 $stdr = exists $out->{controllerStorportDriverVersion}
1191 ? $out->{controllerStorportDriverVersion} : undef;
1192 $nexus = convert_nexus($out->{controllerNexusID});
1197 $name = $out->{Name};
1198 $state = $out->{State};
1199 $status = $out->{Status};
1200 $minfw = $out->{'Minimum Required Firmware Version'} ne 'Not Applicable'
1201 ? $out->{'Minimum Required Firmware Version'} : undef;
1202 $mindr = $out->{'Minimum Required Driver Version'} ne 'Not Applicable'
1203 ? $out->{'Minimum Required Driver Version'} : undef;
1204 $firmware = $out->{'Firmware Version'} ne 'Not Applicable'
1205 ? $out->{'Firmware Version'} : 'N/A';
1206 $driver = $out->{'Driver Version'} ne 'Not Applicable'
1207 ? $out->{'Driver Version'} : 'N/A';
1208 $minstdr = (exists $out->{'Minimum Required Storport Driver Version'}
1209 and $out->{'Minimum Required Storport Driver Version'} ne 'Not Applicable')
1210 ? $out->{'Minimum Required Storport Driver Version'} : undef;
1211 $stdr = (exists $out->{'Storport Driver Version'}
1212 and $out->{'Storport Driver Version'} ne 'Not Applicable')
1213 ? $out->{'Storport Driver Version'} : undef;
1217 $name =~ s{\s+\z}{}xms; # remove trailing whitespace
1218 push @controllers, $id;
1220 # Collecting some storage info
1221 $sysinfo{'controller'}{$id}{'id'} = $nexus;
1222 $sysinfo{'controller'}{$id}{'name'} = $name;
1223 $sysinfo{'controller'}{$id}{'driver'} = $driver;
1224 $sysinfo{'controller'}{$id}{'firmware'} = $firmware;
1225 $sysinfo{'controller'}{$id}{'storport'} = $stdr;
1227 # Store controller info for future use (SNMP)
1229 $snmp_controller{$out->{controllerNumber}} = $nexus;
1232 next CTRL if blacklisted('ctrl', $nexus);
1234 # Special case: old firmware
1235 if (!blacklisted('ctrl_fw', $id) && defined $minfw) {
1237 my $msg = sprintf q{Controller %d [%s]: Firmware '%s' is out of date},
1238 $id, $name, $firmware;
1239 report('storage', $msg, $E_WARNING, $nexus);
1241 # Special case: old driver
1242 if (!blacklisted('ctrl_driver', $id) && defined $mindr) {
1244 my $msg = sprintf q{Controller %d [%s]: Driver '%s' is out of date},
1245 $id, $name, $driver;
1246 report('storage', $msg, $E_WARNING, $nexus);
1248 # Special case: old storport driver
1249 if (!blacklisted('ctrl_stdr', $id) && defined $minstdr) {
1251 my $msg = sprintf q{Controller %d [%s]: Storport driver '%s' is out of date},
1253 report('storage', $msg, $E_WARNING, $nexus);
1256 if ($status eq 'Ok' or ($status eq 'Non-Critical'
1257 and (defined $minfw or defined $mindr or defined $minstdr))) {
1258 my $msg = sprintf 'Controller %d [%s] is %s',
1260 report('storage', $msg, $E_OK, $nexus);
1264 my $msg = sprintf 'Controller %d [%s] needs attention: %s',
1266 report('storage', $msg, $status2nagios{$status}, $nexus);
1273 #-----------------------------------------
1274 # STORAGE: Check physical drives
1275 #-----------------------------------------
1276 sub check_physical_disks {
1277 return if $#controllers == -1;
1278 return if blacklisted('pdisk', 'all');
1288 my $vendor = undef; # disk vendor
1289 my $product = undef; # product ID
1290 my $capacity = undef; # disk length (size) in bytes
1291 my $media = undef; # media type (e.g. HDD, SSD)
1292 my $bus = undef; # bus protocol (e.g. SAS, SATA)
1293 my $spare = undef; # spare state (e.g. global hotspare)
1299 '1.3.6.1.4.1.674.10893.1.20.130.4.1.1' => 'arrayDiskNumber',
1300 '1.3.6.1.4.1.674.10893.1.20.130.4.1.2' => 'arrayDiskName',
1301 '1.3.6.1.4.1.674.10893.1.20.130.4.1.3' => 'arrayDiskVendor',
1302 '1.3.6.1.4.1.674.10893.1.20.130.4.1.4' => 'arrayDiskState',
1303 '1.3.6.1.4.1.674.10893.1.20.130.4.1.6' => 'arrayDiskProductID',
1304 '1.3.6.1.4.1.674.10893.1.20.130.4.1.9' => 'arrayDiskEnclosureID',
1305 '1.3.6.1.4.1.674.10893.1.20.130.4.1.10' => 'arrayDiskChannel',
1306 '1.3.6.1.4.1.674.10893.1.20.130.4.1.11' => 'arrayDiskLengthInMB',
1307 '1.3.6.1.4.1.674.10893.1.20.130.4.1.15' => 'arrayDiskTargetID',
1308 '1.3.6.1.4.1.674.10893.1.20.130.4.1.21' => 'arrayDiskBusType',
1309 '1.3.6.1.4.1.674.10893.1.20.130.4.1.22' => 'arrayDiskSpareState',
1310 '1.3.6.1.4.1.674.10893.1.20.130.4.1.24' => 'arrayDiskComponentStatus',
1311 '1.3.6.1.4.1.674.10893.1.20.130.4.1.26' => 'arrayDiskNexusID',
1312 '1.3.6.1.4.1.674.10893.1.20.130.4.1.31' => 'arrayDiskSmartAlertIndication',
1313 '1.3.6.1.4.1.674.10893.1.20.130.4.1.35' => 'arrayDiskMediaType',
1314 '1.3.6.1.4.1.674.10893.1.20.130.5.1.7' => 'arrayDiskEnclosureConnectionControllerNumber',
1315 '1.3.6.1.4.1.674.10893.1.20.130.6.1.7' => 'arrayDiskChannelConnectionControllerNumber',
1318 if ($opt{use_get_table}) {
1319 my $arrayDiskTable = '1.3.6.1.4.1.674.10893.1.20.130.4';
1320 my $arrayDiskEnclosureConnectionControllerNumber = '1.3.6.1.4.1.674.10893.1.20.130.5.1.7';
1321 my $arrayDiskChannelConnectionControllerNumber = '1.3.6.1.4.1.674.10893.1.20.130.6.1.7';
1323 $result = $snmp_session->get_table(-baseoid => $arrayDiskTable);
1324 my $ext1 = $snmp_session->get_table(-baseoid => $arrayDiskEnclosureConnectionControllerNumber);
1325 my $ext2 = $snmp_session->get_table(-baseoid => $arrayDiskChannelConnectionControllerNumber);
1327 if (defined $result) {
1328 defined $ext1 && map { $$result{$_} = $$ext1{$_} } keys %{ $ext1 };
1329 defined $ext2 && map { $$result{$_} = $$ext2{$_} } keys %{ $ext2 };
1333 $result = $snmp_session->get_entries(-columns => [keys %pdisk_oid]);
1336 if (!defined $result) {
1337 printf "SNMP ERROR [storage / pdisk]: %s.\n", $snmp_session->error;
1338 $snmp_session->close;
1342 @output = @{ get_snmp_output($result, \%pdisk_oid) };
1345 foreach my $c (@controllers) {
1346 # This blacklists disks with broken firmware, which includes
1347 # illegal XML characters that makes openmanage choke on itself
1348 next if blacklisted('ctrl_pdisk', $c);
1350 push @output, @{ run_omreport("storage pdisk controller=$c") };
1351 map_item('ctrl', $c, \@output);
1357 1 => 'VD member', # disk is a member of a virtual disk
1358 2 => 'DG member', # disk is a member of a disk group
1359 3 => 'Global HS', # disk is a global hot spare
1360 4 => 'Dedicated HS', # disk is a dedicated hot spare
1361 5 => 'no', # not a spare
1362 99 => 'n/a', # not applicable
1376 3 => 'Fibre Channel',
1394 22 => 'Replacing', # FIXME: this one is not defined in the OMSA MIBs
1398 28 => 'Diagnostics',
1399 34 => 'Predictive failure',
1400 35 => 'Initializing',
1403 41 => 'Unsupported',
1404 53 => 'Incompatible',
1407 # Check physical disks on each of the controllers
1409 foreach my $out (@output) {
1411 $name = $out->{arrayDiskName};
1412 if (exists $out->{arrayDiskEnclosureID}) {
1413 $id = join q{:}, ($out->{arrayDiskChannel}, $out->{arrayDiskEnclosureID},
1414 $out->{arrayDiskTargetID});
1417 $id = join q{:}, ($out->{arrayDiskChannel}, $out->{arrayDiskTargetID});
1419 $state = get_hashval($out->{arrayDiskState}, \%pdisk_state);
1420 $status = $snmp_status{$out->{arrayDiskComponentStatus}};
1421 $fpred = exists $out->{arrayDiskSmartAlertIndication}
1422 && $out->{arrayDiskSmartAlertIndication} == 2 ? 1 : 0;
1424 $nexus = convert_nexus($out->{arrayDiskNexusID});
1425 $vendor = $out->{arrayDiskVendor};
1426 $product = $out->{arrayDiskProductID};
1427 $spare = get_hashval($out->{arrayDiskSpareState}, \%spare_state);
1428 $bus = exists $out->{arrayDiskBusType}
1429 ? get_hashval($out->{arrayDiskBusType}, \%bus_type) : undef;
1430 $media = exists $out->{arrayDiskMediaType}
1431 ? get_hashval($out->{arrayDiskMediaType}, \%media_type) : undef;
1432 $capacity = $out->{arrayDiskLengthInMB} * 1024**2;
1434 # try to find the controller where the disk belongs
1435 if (exists $out->{arrayDiskEnclosureConnectionControllerNumber}) {
1436 # for disks that are attached to an enclosure
1437 $ctrl = $snmp_controller{$out->{arrayDiskEnclosureConnectionControllerNumber}};
1439 elsif (exists $out->{arrayDiskChannelConnectionControllerNumber}) {
1440 # for disks that are not attached to an enclosure
1441 $ctrl = $snmp_controller{$out->{arrayDiskChannelConnectionControllerNumber}};
1444 # last resort... use the nexus id (old/broken hardware)
1446 $ctrl =~ s{\A (\d+) : .* \z}{$1}xms;
1451 $name = $out->{'Name'};
1452 $state = $out->{'State'};
1453 $status = $out->{'Status'};
1454 $fpred = lc($out->{'Failure Predicted'}) eq 'yes' ? 1 : 0;
1455 $progr = ' [' . $out->{'Progress'} . ']';
1456 $ctrl = $out->{'ctrl'};
1457 $nexus = join q{:}, $out->{ctrl}, $id;
1458 $vendor = $out->{'Vendor ID'};
1459 $product = $out->{'Product ID'};
1460 $media = $out->{'Media'};
1461 $spare = $out->{'Hot Spare'};
1462 $bus = $out->{'Bus Protocol'};
1463 $capacity = $out->{'Capacity'};
1464 $capacity =~ s{\A .*? \((\d+) \s bytes\) \z}{$1}xms;
1467 next PDISK if blacklisted('pdisk', $nexus);
1470 $vendor =~ s{\s+\z}{}xms; # remove trailing whitespace
1471 $product =~ s{\s+\z}{}xms; # remove trailing whitespace
1474 if ($spare eq 'Global') { $spare = 'Global HS'; }
1475 elsif ($spare eq 'Dedicated') { $spare = 'Dedicated HS'; }
1476 elsif ($spare !~ m{\A Global|Dedicated}xms) { $spare = undef; }
1478 # Calculate human readable capacity
1479 $capacity = ceil($capacity / 1000**3) >= 1000
1480 ? sprintf '%.1fTB', ($capacity / 1000**4)
1481 : sprintf '%.0fGB', ($capacity / 1000**3);
1482 $capacity = '450GB' if $capacity eq '449GB'; # quick fix for 450GB disks
1483 $capacity = '300GB' if $capacity eq '299GB'; # quick fix for 300GB disks
1484 $capacity = '146GB' if $capacity eq '147GB'; # quick fix for 146GB disks
1485 $capacity = '100GB' if $capacity eq '99GB'; # quick fix for 100GB disks
1487 # Capitalize only the first letter of the vendor name
1488 $vendor = (substr $vendor, 0, 1) . lc (substr $vendor, 1, length $vendor);
1490 # Remove unnecessary trademark rubbish from vendor name
1491 $vendor =~ s{\(tm\)\z}{}xms;
1493 # bus and media aren't always defined
1495 if (defined $bus && defined $media) { $busmedia = "$bus-$media "; }
1496 elsif (defined $bus && ! defined $media) { $busmedia = "$bus "; }
1497 elsif (! defined $bus && defined $media) { $busmedia = "$media "; }
1499 # Special case: Failure predicted
1501 my $msg = sprintf '%s [%s %s, %s] on ctrl %d needs attention: Failure Predicted',
1502 $name, $vendor, $product, $capacity, $ctrl;
1503 $msg .= " ($state)" if $state ne 'Predictive failure';
1504 report('storage', $msg,
1505 ($status2nagios{$status} == $E_CRITICAL ? $E_CRITICAL : $E_WARNING), $nexus);
1507 # Special case: Rebuilding / Replacing
1508 elsif ($state =~ m{\A Rebuilding|Replacing \z}xms) {
1509 my $msg = sprintf '%s [%s %s, %s] on ctrl %d is %s%s',
1510 $name, $vendor, $product, $capacity, $ctrl, $state, $progr;
1511 report('storage', $msg, $E_WARNING, $nexus);
1514 elsif ($status ne 'Ok') {
1515 my $msg = sprintf '%s [%s %s, %s] on ctrl %d needs attention: %s',
1516 $name, $vendor, $product, $capacity, $ctrl, $state;
1517 report('storage', $msg, $status2nagios{$status}, $nexus);
1521 my $msg = sprintf '%s [%s%s] on ctrl %d is %s',
1522 $name, $busmedia, $capacity, $ctrl, $state;
1523 if (defined $spare) { $msg .= " ($spare)"; }
1524 report('storage', $msg, $E_OK, $nexus);
1531 #-----------------------------------------
1532 # STORAGE: Check logical drives
1533 #-----------------------------------------
1534 sub check_virtual_disks {
1535 return if $#controllers == -1;
1536 return if blacklisted('vdisk', 'all');
1553 '1.3.6.1.4.1.674.10893.1.20.140.1.1.3' => 'virtualDiskDeviceName',
1554 '1.3.6.1.4.1.674.10893.1.20.140.1.1.4' => 'virtualDiskState',
1555 '1.3.6.1.4.1.674.10893.1.20.140.1.1.6' => 'virtualDiskLengthInMB',
1556 '1.3.6.1.4.1.674.10893.1.20.140.1.1.13' => 'virtualDiskLayout',
1557 '1.3.6.1.4.1.674.10893.1.20.140.1.1.17' => 'virtualDiskTargetID',
1558 '1.3.6.1.4.1.674.10893.1.20.140.1.1.20' => 'virtualDiskComponentStatus',
1559 '1.3.6.1.4.1.674.10893.1.20.140.1.1.21' => 'virtualDiskNexusID',
1562 if ($opt{use_get_table}) {
1563 my $virtualDiskTable = '1.3.6.1.4.1.674.10893.1.20.140.1';
1564 $result = $snmp_session->get_table(-baseoid => $virtualDiskTable);
1567 $result = $snmp_session->get_entries(-columns => [keys %vdisk_oid]);
1570 # No logical drives is OK
1571 return if !defined $result;
1573 @output = @{ get_snmp_output($result, \%vdisk_oid) };
1576 foreach my $c (@controllers) {
1577 push @output, @{ run_omreport("storage vdisk controller=$c") };
1578 map_item('ctrl', $c, \@output);
1591 16 => 'Regenerating',
1594 32 => 'Reconstructing',
1595 35 => 'Initializing',
1596 36 => 'Background Initialization',
1597 38 => 'Resynching Paused',
1598 52 => 'Permanently Degraded',
1599 54 => 'Degraded Redundancy',
1604 1 => 'Concatenated',
1611 19 => 'Concatenated RAID-1',
1615 # Check virtual disks on each of the controllers
1617 foreach my $out (@output) {
1619 $id = $out->{virtualDiskTargetID};
1620 $dev = $out->{virtualDiskDeviceName};
1621 $state = get_hashval($out->{virtualDiskState}, \%vdisk_state);
1622 $layout = get_hashval($out->{virtualDiskLayout}, \%vdisk_layout);
1623 $status = $snmp_status{$out->{virtualDiskComponentStatus}};
1624 $size = sprintf '%.2f GB', $out->{virtualDiskLengthInMB} / 1024;
1625 $progr = q{}; # can't get this from SNMP(?)
1626 $nexus = convert_nexus($out->{virtualDiskNexusID});
1630 $dev = $out->{'Device Name'};
1631 $state = $out->{State};
1632 $status = $out->{Status};
1633 $layout = $out->{Layout};
1634 $size = $out->{Size};
1635 $progr = ' [' . $out->{Progress} . ']';
1636 $size =~ s{\A (.*GB).* \z}{$1}xms;
1637 $nexus = join q{:}, $out->{ctrl}, $id;
1638 $ctrl = $out->{ctrl};
1641 next VDISK if blacklisted('vdisk', $nexus);
1644 # The device name is undefined sometimes
1645 $dev = q{} if !defined $dev;
1647 # Special case: Regenerating
1648 if ($state eq 'Regenerating') {
1649 my $msg = sprintf q{Logical Drive '%s' [%s, %s] is %s%s},
1650 $dev, $layout, $size, $state, $progr;
1651 report('storage', $msg, $E_WARNING, $nexus);
1654 elsif ($status ne 'Ok') {
1655 my $msg = sprintf q{Logical Drive '%s' [%s, %s] needs attention: %s},
1656 $dev, $layout, $size, $state;
1657 report('storage', $msg, $status2nagios{$status}, $nexus);
1661 my $msg = sprintf q{Logical Drive '%s' [%s, %s] is %s},
1662 $dev, $layout, $size, $state;
1663 report('storage', $msg, $E_OK, $nexus);
1670 #-----------------------------------------
1671 # STORAGE: Check cache batteries
1672 #-----------------------------------------
1673 sub check_cache_battery {
1674 return if $#controllers == -1;
1675 return if blacklisted('bat', 'all');
1682 my $learn = undef; # learn state
1683 my $pred = undef; # battery's ability to be charged
1689 '1.3.6.1.4.1.674.10893.1.20.130.15.1.4' => 'batteryState',
1690 '1.3.6.1.4.1.674.10893.1.20.130.15.1.6' => 'batteryComponentStatus',
1691 '1.3.6.1.4.1.674.10893.1.20.130.15.1.9' => 'batteryNexusID',
1692 '1.3.6.1.4.1.674.10893.1.20.130.15.1.10' => 'batteryPredictedCapacity',
1693 '1.3.6.1.4.1.674.10893.1.20.130.15.1.12' => 'batteryLearnState',
1694 '1.3.6.1.4.1.674.10893.1.20.130.16.1.5' => 'batteryConnectionControllerNumber',
1697 if ($opt{use_get_table}) {
1698 my $batteryTable = '1.3.6.1.4.1.674.10893.1.20.130.15';
1699 my $batteryConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.16';
1701 $result = $snmp_session->get_table(-baseoid => $batteryTable);
1702 my $ext = $snmp_session->get_table(-baseoid => $batteryConnectionTable);
1704 if (defined $result) {
1705 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
1709 $result = $snmp_session->get_entries(-columns => [keys %bat_oid]);
1712 # No cache battery is OK
1713 return if !defined $result;
1715 @output = @{ get_snmp_output($result, \%bat_oid) };
1718 foreach my $c (@controllers) {
1719 push @output, @{ run_omreport("storage battery controller=$c") };
1720 map_item('ctrl', $c, \@output);
1730 7 => 'Reconditioning',
1738 # Specifies the learn state activity of the battery
1748 # This property displays the battery's ability to be charged
1751 1 => 'Failed', # The battery cannot be charged and needs to be replaced
1752 2 => 'Ready', # The battery can be charged to full capacity
1753 4 => 'Unknown', # The battery is completing a Learn cycle. The charge capacity of the
1754 # battery cannot be determined until the Learn cycle is complete
1757 # Check battery on each of the controllers
1759 foreach my $out (@output) {
1761 $status = $snmp_status{$out->{batteryComponentStatus}};
1762 $state = get_hashval($out->{batteryState}, \%bat_state);
1763 $learn = get_hashval($out->{batteryLearnState}, \%bat_learn_state);
1764 $pred = get_hashval($out->{batteryPredictedCapacity}, \%bat_pred_cap);
1765 $ctrl = $out->{batteryConnectionControllerNumber} - 1;
1766 $nexus = convert_nexus($out->{batteryNexusID});
1768 $id =~ s{\A \d+:(\d+) \z}{$1}xms;
1772 $state = $out->{'State'};
1773 $status = $out->{'Status'};
1774 $learn = $out->{'Learn State'};
1775 $pred = $out->{'Predicted Capacity Status'};
1776 $ctrl = $out->{'ctrl'};
1777 $nexus = join q{:}, $out->{ctrl}, $id;
1780 next BATTERY if blacklisted('bat', $nexus);
1782 # Special case: Charging
1783 if ($state eq 'Charging') {
1784 if ($pred eq 'Failed') {
1785 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [replace battery]',
1786 $id, $ctrl, $state, $pred;
1787 report('storage', $msg, $E_CRITICAL, $nexus);
1790 next BATTERY if blacklisted('bat_charge', $nexus);
1791 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [probably harmless]',
1792 $id, $ctrl, $state, $pred;
1793 report('storage', $msg, $E_WARNING, $nexus);
1796 # Special case: Learning (battery learns its capacity)
1797 elsif ($state eq 'Learning') {
1798 if ($learn eq 'Failed') {
1799 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s)',
1800 $id, $ctrl, $state, $learn;
1801 report('storage', $msg, $E_CRITICAL, $nexus);
1804 next BATTERY if blacklisted('bat_charge', $nexus);
1805 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [probably harmless]',
1806 $id, $ctrl, $state, $learn;
1807 report('storage', $msg, $E_WARNING, $nexus);
1810 # Special case: Power Low (first part of recharge cycle)
1811 elsif ($state eq 'Power Low') {
1812 next BATTERY if blacklisted('bat_charge', $nexus);
1813 my $msg = sprintf 'Cache Battery %d in controller %d is %s [probably harmless]',
1815 report('storage', $msg, $E_WARNING, $nexus);
1817 # Special case: Degraded and Non-Critical (usually part of recharge cycle)
1818 elsif ($state eq 'Degraded' && $status eq 'Non-Critical') {
1819 next BATTERY if blacklisted('bat_charge', $nexus);
1820 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [probably harmless]',
1821 $id, $ctrl, $state, $status;
1822 report('storage', $msg, $E_WARNING, $nexus);
1825 elsif ($status ne 'Ok') {
1826 my $msg = sprintf 'Cache Battery %d in controller %d needs attention: %s (%s)',
1827 $id, $ctrl, $state, $status;
1828 report('storage', $msg, $status2nagios{$status}, $nexus);
1832 my $msg = sprintf 'Cache Battery %d in controller %d is %s',
1834 report('storage', $msg, $E_OK, $nexus);
1841 #-----------------------------------------
1842 # STORAGE: Check connectors (channels)
1843 #-----------------------------------------
1844 sub check_connectors {
1845 return if $#controllers == -1;
1846 return if blacklisted('conn', 'all');
1860 '1.3.6.1.4.1.674.10893.1.20.130.2.1.1' => 'channelNumber',
1861 '1.3.6.1.4.1.674.10893.1.20.130.2.1.2' => 'channelName',
1862 '1.3.6.1.4.1.674.10893.1.20.130.2.1.3' => 'channelState',
1863 '1.3.6.1.4.1.674.10893.1.20.130.2.1.8' => 'channelComponentStatus',
1864 '1.3.6.1.4.1.674.10893.1.20.130.2.1.9' => 'channelNexusID',
1865 '1.3.6.1.4.1.674.10893.1.20.130.2.1.11' => 'channelBusType',
1868 if ($opt{use_get_table}) {
1869 my $channelTable = '1.3.6.1.4.1.674.10893.1.20.130.2';
1870 $result = $snmp_session->get_table(-baseoid => $channelTable);
1873 $result = $snmp_session->get_entries(-columns => [keys %conn_oid]);
1876 if (!defined $result) {
1877 printf "SNMP ERROR [storage / channel]: %s.\n", $snmp_session->error;
1878 $snmp_session->close;
1882 @output = @{ get_snmp_output($result, \%conn_oid) };
1885 foreach my $c (@controllers) {
1886 push @output, @{ run_omreport("storage connector controller=$c") };
1887 map_item('ctrl', $c, \@output);
1905 3 => 'Fibre Channel',
1912 # Check connectors on each of the controllers
1914 foreach my $out (@output) {
1916 $id = $out->{channelNumber} - 1;
1917 $name = $out->{channelName};
1918 $status = $snmp_status{$out->{channelComponentStatus}};
1919 $state = get_hashval($out->{channelState}, \%conn_state);
1920 $type = get_hashval($out->{channelBusType}, \%conn_bustype);
1921 $nexus = convert_nexus($out->{channelNexusID});
1923 $ctrl =~ s{(\d+):\d+}{$1}xms;
1924 # workaround for ancient OMSA versions
1925 if (! defined $type) { $type = 'n/a'; }
1929 $name = $out->{'Name'};
1930 $state = $out->{'State'};
1931 $status = $out->{'Status'};
1932 $type = $out->{'Connector Type'};
1933 $ctrl = $out->{ctrl};
1934 $nexus = join q{:}, $out->{ctrl}, $id;
1937 next CHANNEL if blacklisted('conn', $nexus);
1939 my $msg = sprintf '%s [%s] on controller %d is %s',
1940 $name, $type, $ctrl, $state;
1941 report('storage', $msg, $status2nagios{$status}, $nexus);
1947 #-----------------------------------------
1948 # STORAGE: Check enclosures
1949 #-----------------------------------------
1950 sub check_enclosures {
1951 return if blacklisted('encl', 'all');
1958 my $firmware = undef;
1960 my $occupied_slots = undef; # number of occupied slots
1961 my $total_slots = undef; # number of total slots
1967 '1.3.6.1.4.1.674.10893.1.20.130.3.1.1' => 'enclosureNumber',
1968 '1.3.6.1.4.1.674.10893.1.20.130.3.1.2' => 'enclosureName',
1969 '1.3.6.1.4.1.674.10893.1.20.130.3.1.4' => 'enclosureState',
1970 '1.3.6.1.4.1.674.10893.1.20.130.3.1.19' => 'enclosureChannelNumber',
1971 '1.3.6.1.4.1.674.10893.1.20.130.3.1.24' => 'enclosureComponentStatus',
1972 '1.3.6.1.4.1.674.10893.1.20.130.3.1.25' => 'enclosureNexusID',
1973 '1.3.6.1.4.1.674.10893.1.20.130.3.1.26' => 'enclosureFirmwareVersion',
1974 '1.3.6.1.4.1.674.10893.1.20.130.3.1.31' => 'enclosureOccupiedSlotCount', # new in OMSA 6.3.0
1975 '1.3.6.1.4.1.674.10893.1.20.130.3.1.32' => 'enclosureTotalSlots', # new in OMSA 6.3.0
1978 if ($opt{use_get_table}) {
1979 my $enclosureTable = '1.3.6.1.4.1.674.10893.1.20.130.3';
1980 $result = $snmp_session->get_table(-baseoid => $enclosureTable);
1983 $result = $snmp_session->get_entries(-columns => [keys %encl_oid]);
1986 # No enclosures is OK
1987 return if !defined $result;
1989 @output = @{ get_snmp_output($result, \%encl_oid) };
1992 foreach my $c (@controllers) {
1993 push @output, @{ run_omreport("storage enclosure controller=$c") };
1994 map_item('ctrl', $c, \@output);
2009 foreach my $out (@output) {
2011 $id = $out->{enclosureNumber} - 1;
2012 $name = $out->{enclosureName};
2013 $state = get_hashval($out->{enclosureState}, \%encl_state);
2014 $status = $snmp_status{$out->{enclosureComponentStatus}};
2015 $firmware = exists $out->{enclosureFirmwareVersion}
2016 ? $out->{enclosureFirmwareVersion} : 'N/A';
2017 $nexus = convert_nexus($out->{enclosureNexusID});
2019 $ctrl =~ s{\A (\d+):.* \z}{$1}xms;
2020 # for the next two, a value of 9999 means feature not available
2021 $occupied_slots = exists $out->{enclosureOccupiedSlotCount}
2022 && $out->{enclosureOccupiedSlotCount} != 9999
2023 ? $out->{enclosureOccupiedSlotCount} : undef;
2024 $total_slots = exists $out->{enclosureTotalSlots}
2025 && $out->{enclosureTotalSlots} != 9999
2026 ? $out->{enclosureTotalSlots} : undef;
2030 $name = $out->{Name};
2031 $state = $out->{State};
2032 $status = $out->{Status};
2033 $firmware = $out->{'Firmware Version'} ne 'Not Applicable'
2034 ? $out->{'Firmware Version'} : 'N/A';
2035 $nexus = join q{:}, $out->{ctrl}, $id;
2036 $ctrl = $out->{ctrl};
2039 $name =~ s{\s+\z}{}xms; # remove trailing whitespace
2040 $firmware =~ s{\s+\z}{}xms; # remove trailing whitespace
2042 # store enclosure data for future use
2044 $snmp_enclosure{$out->{enclosureNumber}}{id} = $id;
2045 $snmp_enclosure{$out->{enclosureNumber}}{name} = $name;
2046 $snmp_enclosure{$out->{enclosureNumber}}{nexus} = $nexus;
2049 push @enclosures, { 'id' => $id,
2050 'ctrl' => $out->{ctrl},
2054 # Collecting some storage info
2055 $sysinfo{'enclosure'}{$nexus}{'id'} = $nexus;
2056 $sysinfo{'enclosure'}{$nexus}{'name'} = $name;
2057 $sysinfo{'enclosure'}{$nexus}{'firmware'} = $firmware;
2059 next ENCLOSURE if blacklisted('encl', $nexus);
2062 if (defined $occupied_slots && defined $total_slots) {
2063 $msg = sprintf 'Enclosure %s [%s, %d/%d slots occupied] on ctrl %d is %s',
2064 $nexus, $name, $occupied_slots, $total_slots, $ctrl, $state;
2067 $msg = sprintf 'Enclosure %s [%s] on controller %d is %s',
2068 $nexus, $name, $ctrl, $state;
2070 report('storage', $msg, $status2nagios{$status}, $nexus);
2076 #-----------------------------------------
2077 # STORAGE: Check enclosure fans
2078 #-----------------------------------------
2079 sub check_enclosure_fans {
2080 return if $#controllers == -1;
2081 return if blacklisted('encl_fan', 'all');
2089 my $encl_id = undef;
2090 my $encl_name = undef;
2096 '1.3.6.1.4.1.674.10893.1.20.130.7.1.1' => 'fanNumber',
2097 '1.3.6.1.4.1.674.10893.1.20.130.7.1.2' => 'fanName',
2098 '1.3.6.1.4.1.674.10893.1.20.130.7.1.4' => 'fanState',
2099 '1.3.6.1.4.1.674.10893.1.20.130.7.1.11' => 'fanProbeCurrValue',
2100 '1.3.6.1.4.1.674.10893.1.20.130.7.1.15' => 'fanComponentStatus',
2101 '1.3.6.1.4.1.674.10893.1.20.130.7.1.16' => 'fanNexusID',
2102 '1.3.6.1.4.1.674.10893.1.20.130.8.1.4' => 'fanConnectionEnclosureName',
2103 '1.3.6.1.4.1.674.10893.1.20.130.8.1.5' => 'fanConnectionEnclosureNumber',
2106 if ($opt{use_get_table}) {
2107 my $fanTable = '1.3.6.1.4.1.674.10893.1.20.130.7';
2108 my $fanConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.8';
2110 $result = $snmp_session->get_table(-baseoid => $fanTable);
2111 my $ext = $snmp_session->get_table(-baseoid => $fanConnectionTable);
2113 if (defined $result) {
2114 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2118 $result = $snmp_session->get_entries(-columns => [keys %fan_oid]);
2121 # No enclosure fans is OK
2122 return if !defined $result;
2124 @output = @{ get_snmp_output($result, \%fan_oid) };
2127 foreach my $enc (@enclosures) {
2128 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=fans") };
2129 map_item('ctrl', $enc->{ctrl}, \@output);
2130 map_item('encl_id', $enc->{id}, \@output);
2131 map_item('encl_name', $enc->{name}, \@output);
2146 # Check fans on each of the enclosures
2148 foreach my $out (@output) {
2150 $id = $out->{fanNumber} - 1;
2151 $name = $out->{fanName};
2152 $state = get_hashval($out->{fanState}, \%fan_state);
2153 $status = $snmp_status{$out->{fanComponentStatus}};
2154 $speed = $out->{fanProbeCurrValue};
2155 $encl_name = $out->{fanConnectionEnclosureName};
2156 $encl_id = $snmp_enclosure{$out->{fanConnectionEnclosureNumber}}{nexus};
2157 $nexus = convert_nexus($out->{fanNexusID});
2161 $name = $out->{'Name'};
2162 $state = $out->{'State'};
2163 $status = $out->{'Status'};
2164 $speed = $out->{'Speed'};
2165 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2166 $encl_name = $out->{encl_name};
2167 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2170 next FAN if blacklisted('encl_fan', $nexus);
2173 if ($status ne 'Ok') {
2174 my $msg = sprintf '%s in enclosure %s [%s] needs attention: %s',
2175 $name, $encl_id, $encl_name, $state;
2176 report('storage', $msg, $status2nagios{$status}, $nexus);
2180 my $msg = sprintf '%s in enclosure %s [%s] is %s (speed=%s)',
2181 $name, $encl_id, $encl_name, $state, $speed;
2182 report('storage', $msg, $E_OK, $nexus);
2189 #-----------------------------------------
2190 # STORAGE: Check enclosure power supplies
2191 #-----------------------------------------
2192 sub check_enclosure_pwr {
2193 return if $#controllers == -1;
2194 return if blacklisted('encl_ps', 'all');
2201 my $encl_id = undef;
2202 my $encl_name = undef;
2208 '1.3.6.1.4.1.674.10893.1.20.130.9.1.1' => 'powerSupplyNumber',
2209 '1.3.6.1.4.1.674.10893.1.20.130.9.1.2' => 'powerSupplyName',
2210 '1.3.6.1.4.1.674.10893.1.20.130.9.1.4' => 'powerSupplyState',
2211 '1.3.6.1.4.1.674.10893.1.20.130.9.1.9' => 'powerSupplyComponentStatus',
2212 '1.3.6.1.4.1.674.10893.1.20.130.9.1.10' => 'powerSupplyNexusID',
2213 '1.3.6.1.4.1.674.10893.1.20.130.10.1.4' => 'powerSupplyConnectionEnclosureName',
2214 '1.3.6.1.4.1.674.10893.1.20.130.10.1.5' => 'powerSupplyConnectionEnclosureNumber',
2217 if ($opt{use_get_table}) {
2218 my $powerSupplyTable = '1.3.6.1.4.1.674.10893.1.20.130.9';
2219 my $powerSupplyConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.10';
2221 $result = $snmp_session->get_table(-baseoid => $powerSupplyTable);
2222 my $ext = $snmp_session->get_table(-baseoid => $powerSupplyConnectionTable);
2224 if (defined $result) {
2225 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2229 $result = $snmp_session->get_entries(-columns => [keys %ps_oid]);
2232 # No enclosure power supplies is OK
2233 return if !defined $result;
2235 @output = @{ get_snmp_output($result, \%ps_oid) };
2238 foreach my $enc (@enclosures) {
2239 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=pwrsupplies") };
2240 map_item('ctrl', $enc->{ctrl}, \@output);
2241 map_item('encl_id', $enc->{id}, \@output);
2242 map_item('encl_name', $enc->{name}, \@output);
2251 5 => 'Not Installed',
2257 # Check power supplies on each of the enclosures
2259 foreach my $out (@output) {
2261 $id = $out->{powerSupplyNumber};
2262 $name = $out->{powerSupplyName};
2263 $state = get_hashval($out->{powerSupplyState}, \%ps_state);
2264 $status = $snmp_status{$out->{powerSupplyComponentStatus}};
2265 $encl_id = $snmp_enclosure{$out->{powerSupplyConnectionEnclosureNumber}}{nexus};
2266 $encl_name = $out->{powerSupplyConnectionEnclosureName};
2267 $nexus = convert_nexus($out->{powerSupplyNexusID});
2271 $name = $out->{'Name'};
2272 $state = $out->{'State'};
2273 $status = $out->{'Status'};
2274 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2275 $encl_name = $out->{encl_name};
2276 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2279 next PS if blacklisted('encl_ps', $nexus);
2282 if ($status ne 'Ok') {
2283 my $msg = sprintf '%s in enclosure %s [%s] needs attention: %s',
2284 $name, $encl_id, $encl_name, $state;
2285 report('storage', $msg, $status2nagios{$status}, $nexus);
2289 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2290 $name, $encl_id, $encl_name, $state;
2291 report('storage', $msg, $E_OK, $nexus);
2298 #-----------------------------------------
2299 # STORAGE: Check enclosure temperatures
2300 #-----------------------------------------
2301 sub check_enclosure_temp {
2302 return if $#controllers == -1;
2303 return if blacklisted('encl_temp', 'all');
2310 my $reading = undef;
2312 my $max_warn = undef;
2313 my $max_crit = undef;
2314 my $min_warn = undef;
2315 my $min_crit = undef;
2316 my $encl_id = undef;
2317 my $encl_name = undef;
2323 '1.3.6.1.4.1.674.10893.1.20.130.11.1.1' => 'temperatureProbeNumber',
2324 '1.3.6.1.4.1.674.10893.1.20.130.11.1.2' => 'temperatureProbeName',
2325 '1.3.6.1.4.1.674.10893.1.20.130.11.1.4' => 'temperatureProbeState',
2326 '1.3.6.1.4.1.674.10893.1.20.130.11.1.6' => 'temperatureProbeUnit',
2327 '1.3.6.1.4.1.674.10893.1.20.130.11.1.7' => 'temperatureProbeMinWarning',
2328 '1.3.6.1.4.1.674.10893.1.20.130.11.1.8' => 'temperatureProbeMinCritical',
2329 '1.3.6.1.4.1.674.10893.1.20.130.11.1.9' => 'temperatureProbeMaxWarning',
2330 '1.3.6.1.4.1.674.10893.1.20.130.11.1.10' => 'temperatureProbeMaxCritical',
2331 '1.3.6.1.4.1.674.10893.1.20.130.11.1.11' => 'temperatureProbeCurValue',
2332 '1.3.6.1.4.1.674.10893.1.20.130.11.1.13' => 'temperatureProbeComponentStatus',
2333 '1.3.6.1.4.1.674.10893.1.20.130.11.1.14' => 'temperatureProbeNexusID',
2334 '1.3.6.1.4.1.674.10893.1.20.130.12.1.4' => 'temperatureConnectionEnclosureName',
2335 '1.3.6.1.4.1.674.10893.1.20.130.12.1.5' => 'temperatureConnectionEnclosureNumber',
2338 if ($opt{use_get_table}) {
2339 my $temperatureProbeTable = '1.3.6.1.4.1.674.10893.1.20.130.11';
2340 my $temperatureConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.12';
2342 $result = $snmp_session->get_table(-baseoid => $temperatureProbeTable);
2343 my $ext = $snmp_session->get_table(-baseoid => $temperatureConnectionTable);
2345 if (defined $result) {
2346 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2350 $result = $snmp_session->get_entries(-columns => [keys %temp_oid]);
2353 # No enclosure temperature probes is OK
2354 return if !defined $result;
2356 @output = @{ get_snmp_output($result, \%temp_oid) };
2359 foreach my $enc (@enclosures) {
2360 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=temps") };
2361 map_item('ctrl', $enc->{ctrl}, \@output);
2362 map_item('encl_id', $enc->{id}, \@output);
2363 map_item('encl_name', $enc->{name}, \@output);
2378 # Check temperature probes on each of the enclosures
2380 foreach my $out (@output) {
2382 $id = $out->{temperatureProbeNumber} - 1;
2383 $name = $out->{temperatureProbeName};
2384 $state = get_hashval($out->{temperatureProbeState}, \%temp_state);
2385 $status = $snmp_status{$out->{temperatureProbeComponentStatus}};
2386 $unit = $out->{temperatureProbeUnit};
2387 $reading = exists $out->{temperatureProbeCurValue}
2388 ? $out->{temperatureProbeCurValue} : '[N/A]';
2389 $max_warn = exists $out->{temperatureProbeMaxWarning}
2390 ? $out->{temperatureProbeMaxWarning} : '[N/A]';
2391 $max_crit = exists $out->{temperatureProbeMaxCritical}
2392 ? $out->{temperatureProbeMaxCritical} : '[N/A]';
2393 $min_warn = exists $out->{temperatureProbeMinWarning}
2394 ? $out->{temperatureProbeMinWarning} : '[N/A]';
2395 $min_crit = exists $out->{temperatureProbeMinCritical}
2396 ? $out->{temperatureProbeMinCritical} : '[N/A]';
2397 $encl_id = $snmp_enclosure{$out->{temperatureConnectionEnclosureNumber}}{nexus};
2398 $encl_name = $out->{temperatureConnectionEnclosureName};
2399 $nexus = convert_nexus($out->{temperatureProbeNexusID});
2403 $name = $out->{'Name'};
2404 $state = $out->{'State'};
2405 $status = $out->{'Status'};
2407 $reading = $out->{'Reading'};
2408 $max_warn = $out->{'Maximum Warning Threshold'};
2409 $max_crit = $out->{'Maximum Failure Threshold'};
2410 $min_warn = $out->{'Minimum Warning Threshold'};
2411 $min_crit = $out->{'Minimum Failure Threshold'};
2412 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2413 $encl_name = $out->{encl_name};
2414 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2417 next TEMP if blacklisted('encl_temp', $nexus);
2419 # Make sure these values are integers
2420 $reading =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $reading = '[N/A]';
2421 $max_warn =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $max_warn = '[N/A]';
2422 $max_crit =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $max_crit = '[N/A]';
2423 $min_warn =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $min_warn = '[N/A]';
2424 $min_crit =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $min_crit = '[N/A]';
2426 # Inactive temp probes
2427 if ($status eq 'Unknown' and $state eq 'Inactive') {
2428 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2429 $name, $encl_id, $encl_name, $state;
2430 report('storage', $msg, $E_OK, $nexus);
2432 elsif ($status ne 'Ok' and $max_crit ne '[N/A]' and $reading > $max_crit) {
2433 my $msg = sprintf '%s in enclosure %s [%s] is critically high at %d C',
2434 $name, $encl_id, $encl_name, $reading;
2435 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2436 report('chassis', $msg, $err, $nexus);
2438 elsif ($status ne 'Ok' and $max_warn ne '[N/A]' and $reading > $max_warn) {
2439 my $msg = sprintf '%s in enclosure %s [%s] is too high at %d C',
2440 $name, $encl_id, $encl_name, $reading;
2441 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2442 report('chassis', $msg, $err, $nexus);
2444 elsif ($status ne 'Ok' and $min_crit ne '[N/A]' and $reading < $min_crit) {
2445 my $msg = sprintf '%s in enclosure %s [%s] is critically low at %d C',
2446 $name, $encl_id, $encl_name, $reading;
2447 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2448 report('chassis', $msg, $err, $nexus);
2450 elsif ($status ne 'Ok' and $min_warn ne '[N/A]' and $reading < $min_warn) {
2451 my $msg = sprintf '%s in enclosure %s [%s] is too low at %d C',
2452 $name, $encl_id, $encl_name, $reading;
2453 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2454 report('chassis', $msg, $err, $nexus);
2457 elsif ($status ne 'Ok') {
2458 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2459 $name, $encl_id, $encl_name, $state;
2460 if (defined $reading && $reading =~ m{\A -?\d+ \z}xms) {
2461 # take into account that with certain states the
2462 # reading doesn't exist or is not an integer
2463 $msg .= sprintf ' at %s C', $reading;
2464 if ($min_warn eq '[N/A]' or $min_crit eq '[N/A]') {
2465 $msg .= sprintf ' (max=%s/%s)', $max_warn, $max_crit;
2468 $msg .= sprintf ' (min=%s/%s, max=%s/%s)',
2469 $min_warn, $min_crit, $max_warn, $max_crit;
2472 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2473 report('storage', $msg, $err, $nexus);
2477 my $msg = sprintf '%s in enclosure %s [%s]',
2478 $name, $encl_id, $encl_name;
2479 if (defined $reading && $reading ne '[N/A]') {
2480 # take into account that with certain states the
2481 # reading doesn't exist or is not an integer
2482 $msg .= sprintf ' reads %d C', $reading;
2483 if ($min_warn eq '[N/A]' or $min_crit eq '[N/A]') {
2484 $msg .= sprintf ' (max=%s/%s)', $max_warn, $max_crit;
2487 $msg .= sprintf ' (min=%s/%s, max=%s/%s)',
2488 $min_warn, $min_crit, $max_warn, $max_crit;
2492 $msg .= sprintf ' is %s', $state;
2494 report('storage', $msg, $E_OK, $nexus);
2497 # Collect performance data
2498 if (defined $opt{perfdata} && $reading ne '[N/A]') {
2499 $name =~ s{\A Temperature\sProbe\s(\d+) \z}{temp_$1}gxms;
2500 my $label = "enclosure_${encl_id}_${name}";
2502 $mini =~ s{enclosure_(.+?)_temp_(.+?)}{e$1t$2}xms;
2516 #-----------------------------------------
2517 # STORAGE: Check enclosure management modules (EMM)
2518 #-----------------------------------------
2519 sub check_enclosure_emms {
2520 return if $#controllers == -1;
2521 return if blacklisted('encl_emm', 'all');
2528 my $encl_id = undef;
2529 my $encl_name = undef;
2535 '1.3.6.1.4.1.674.10893.1.20.130.13.1.1' => 'enclosureManagementModuleNumber',
2536 '1.3.6.1.4.1.674.10893.1.20.130.13.1.2' => 'enclosureManagementModuleName',
2537 '1.3.6.1.4.1.674.10893.1.20.130.13.1.4' => 'enclosureManagementModuleState',
2538 '1.3.6.1.4.1.674.10893.1.20.130.13.1.11' => 'enclosureManagementModuleComponentStatus',
2539 '1.3.6.1.4.1.674.10893.1.20.130.13.1.12' => 'enclosureManagementModuleNexusID',
2540 '1.3.6.1.4.1.674.10893.1.20.130.14.1.4' => 'enclosureManagementModuleConnectionEnclosureName',
2541 '1.3.6.1.4.1.674.10893.1.20.130.14.1.5' => 'enclosureManagementModuleConnectionEnclosureNumber',
2544 if ($opt{use_get_table}) {
2545 my $enclosureManagementModuleTable = '1.3.6.1.4.1.674.10893.1.20.130.13';
2546 my $enclosureManagementModuleConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.14';
2548 $result = $snmp_session->get_table(-baseoid => $enclosureManagementModuleTable);
2549 my $ext = $snmp_session->get_table(-baseoid => $enclosureManagementModuleConnectionTable);
2551 if (defined $result) {
2552 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2556 $result = $snmp_session->get_entries(-columns => [keys %emms_oid]);
2559 # No enclosure EMMs is OK
2560 return if !defined $result;
2562 @output = @{ get_snmp_output($result, \%emms_oid) };
2565 foreach my $enc (@enclosures) {
2566 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=emms") };
2567 map_item('ctrl', $enc->{ctrl}, \@output);
2568 map_item('encl_id', $enc->{id}, \@output);
2569 map_item('encl_name', $enc->{name}, \@output);
2580 5 => 'Not Installed',
2585 # Check EMMs on each of the enclosures
2587 foreach my $out (@output) {
2589 $id = $out->{enclosureManagementModuleNumber} - 1;
2590 $name = $out->{enclosureManagementModuleName};
2591 $state = get_hashval($out->{enclosureManagementModuleState}, \%emms_state);
2592 $status = $snmp_status{$out->{enclosureManagementModuleComponentStatus}};
2593 $encl_id = $snmp_enclosure{$out->{enclosureManagementModuleConnectionEnclosureNumber}}{nexus};
2594 $encl_name = $out->{enclosureManagementModuleConnectionEnclosureName};
2595 $nexus = convert_nexus($out->{enclosureManagementModuleNexusID});
2599 $name = $out->{'Name'};
2600 $state = $out->{'State'};
2601 $status = $out->{'Status'};
2602 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2603 $encl_name = $out->{encl_name};
2604 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2607 next EMM if blacklisted('encl_emm', $nexus);
2610 if ($status =~ m{\A Other|Unknown \z}xms and $state eq 'Not Installed') {
2611 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2612 $name, $encl_id, $encl_name, $state;
2613 report('storage', $msg, $E_OK, $nexus);
2616 elsif ($status ne 'Ok') {
2617 my $msg = sprintf '%s in enclosure %s [%s] needs attention: %s',
2618 $name, $encl_id, $encl_name, $state;
2619 report('storage', $msg, $status2nagios{$status}, $nexus);
2623 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2624 $name, $encl_id, $encl_name, $state;
2625 report('storage', $msg, $E_OK, $nexus);
2632 #-----------------------------------------
2633 # CHASSIS: Check memory modules
2634 #-----------------------------------------
2636 return if blacklisted('dimm', 'all');
2640 my $location = undef;
2649 '1.3.6.1.4.1.674.10892.1.1100.50.1.2.1' => 'memoryDeviceIndex',
2650 '1.3.6.1.4.1.674.10892.1.1100.50.1.5.1' => 'memoryDeviceStatus',
2651 '1.3.6.1.4.1.674.10892.1.1100.50.1.8.1' => 'memoryDeviceLocationName',
2652 '1.3.6.1.4.1.674.10892.1.1100.50.1.14.1' => 'memoryDeviceSize',
2653 '1.3.6.1.4.1.674.10892.1.1100.50.1.20.1' => 'memoryDeviceFailureModes',
2656 if ($opt{use_get_table}) {
2657 my $memoryDeviceTable = '1.3.6.1.4.1.674.10892.1.1100.50.1';
2658 $result = $snmp_session->get_table(-baseoid => $memoryDeviceTable);
2661 $result = $snmp_session->get_entries(-columns => [keys %dimm_oid]);
2664 if (!defined $result) {
2665 printf "SNMP ERROR [memory]: %s.\n", $snmp_session->error;
2666 $snmp_session->close;
2670 @output = @{ get_snmp_output($result, \%dimm_oid) };
2673 @output = @{ run_omreport("$omopt_chassis memory") };
2676 # Note: These values are bit masks, so combination values are
2677 # possible. If value is 0 (zero), memory device has no faults.
2680 1 => 'ECC single bit correction warning rate exceeded',
2681 2 => 'ECC single bit correction failure rate exceeded',
2682 4 => 'ECC multibit fault encountered',
2683 8 => 'ECC single bit correction logging disabled',
2684 16 => 'device disabled because of spare activation',
2688 foreach my $out (@output) {
2689 @failures = (); # Initialize
2691 $index = $out->{memoryDeviceIndex};
2692 $status = $snmp_status{$out->{memoryDeviceStatus}};
2693 $location = $out->{memoryDeviceLocationName};
2694 $size = sprintf '%d MB', $out->{memoryDeviceSize}/1024;
2695 $modes = $out->{memoryDeviceFailureModes};
2697 foreach my $mask (sort keys %failure_mode) {
2698 if (($modes & $mask) != 0) { push @failures, $failure_mode{$mask}; }
2703 $index = $out->{'Type'} eq '[Not Occupied]' ? undef : $out->{'Index'};
2704 $status = $out->{'Status'};
2705 $location = $out->{'Connector Name'};
2706 $size = $out->{'Size'};
2707 if (defined $size) {
2708 $size =~ s{\s\s}{ }gxms;
2710 # Run 'omreport chassis memory index=X' to get the failures
2711 if ($status ne 'Ok' && defined $index) {
2712 foreach (@{ run_command("$omreport $omopt_chassis memory index=$index -fmt ssv") }) {
2713 if (m/\A Failures; (.+?) \z/xms) {
2714 chop(my $fail = $1);
2715 push @failures, split m{\.}xms, $fail;
2720 $location =~ s{\A \s*(.*?)\s* \z}{$1}xms;
2722 # calculate total memory
2723 my $msize = defined $size ? $size : 0;
2724 $msize =~ s{\A (\d+) \s MB}{$1}xms;
2725 $count{mem} += $msize;
2727 next DIMM if blacklisted('dimm', $index);
2729 # Ignore empty memory slots
2730 next DIMM if !defined $index;
2733 if ($status ne 'Ok') {
2735 if (scalar @failures == 0) {
2736 $msg = sprintf 'Memory module %d [%s, %s] needs attention (%s)',
2737 $index, $location, $size, $status;
2740 $msg = sprintf 'Memory module %d [%s, %s] needs attention: %s',
2741 $index, $location, $size, (join q{, }, @failures);
2744 report('chassis', $msg, $status2nagios{$status}, $index);
2748 my $msg = sprintf 'Memory module %d [%s, %s] is %s',
2749 $index, $location, $size, $status;
2750 report('chassis', $msg, $E_OK, $index);
2757 #-----------------------------------------
2758 # CHASSIS: Check fans
2759 #-----------------------------------------
2761 return if blacklisted('fan', 'all');
2765 my $reading = undef;
2766 my $location = undef;
2767 my $max_crit = undef;
2768 my $max_warn = undef;
2774 '1.3.6.1.4.1.674.10892.1.700.12.1.2.1' => 'coolingDeviceIndex',
2775 '1.3.6.1.4.1.674.10892.1.700.12.1.5.1' => 'coolingDeviceStatus',
2776 '1.3.6.1.4.1.674.10892.1.700.12.1.6.1' => 'coolingDeviceReading',
2777 '1.3.6.1.4.1.674.10892.1.700.12.1.8.1' => 'coolingDeviceLocationName',
2778 '1.3.6.1.4.1.674.10892.1.700.12.1.10.1' => 'coolingDeviceUpperCriticalThreshold',
2779 '1.3.6.1.4.1.674.10892.1.700.12.1.11.1' => 'coolingDeviceUpperNonCriticalThreshold',
2782 if ($opt{use_get_table}) {
2783 my $coolingDeviceTable = '1.3.6.1.4.1.674.10892.1.700.12.1';
2784 $result = $snmp_session->get_table(-baseoid => $coolingDeviceTable);
2787 $result = $snmp_session->get_entries(-columns => [keys %cool_oid]);
2790 if ($blade && !defined $result) {
2793 elsif (!$blade && !defined $result) {
2794 printf "SNMP ERROR [cooling]: %s.\n", $snmp_session->error;
2795 $snmp_session->close;
2799 @output = @{ get_snmp_output($result, \%cool_oid) };
2802 @output = @{ run_omreport("$omopt_chassis fans") };
2806 foreach my $out (@output) {
2808 $index = $out->{coolingDeviceIndex};
2809 $status = $snmp_probestatus{$out->{coolingDeviceStatus}};
2810 $reading = $out->{coolingDeviceReading};
2811 $location = $out->{coolingDeviceLocationName};
2812 $max_crit = exists $out->{coolingDeviceUpperCriticalThreshold}
2813 ? $out->{coolingDeviceUpperCriticalThreshold} : 0;
2814 $max_warn = exists $out->{coolingDeviceUpperNonCriticalThreshold}
2815 ? $out->{coolingDeviceUpperNonCriticalThreshold} : 0;
2818 $index = $out->{'Index'};
2819 $status = $out->{'Status'};
2820 $reading = $out->{'Reading'};
2821 $location = $out->{'Probe Name'};
2822 $max_crit = $out->{'Maximum Failure Threshold'} ne '[N/A]'
2823 ? $out->{'Maximum Failure Threshold'} : 0;
2824 $max_warn = $out->{'Maximum Warning Threshold'} ne '[N/A]'
2825 ? $out->{'Maximum Warning Threshold'} : 0;
2826 $reading =~ s{\A (\d+).* \z}{$1}xms;
2827 $max_warn =~ s{\A (\d+).* \z}{$1}xms;
2828 $max_crit =~ s{\A (\d+).* \z}{$1}xms;
2831 next FAN if blacklisted('fan', $index);
2834 if ($status ne 'Ok') {
2835 my $msg = sprintf 'Chassis fan %d [%s] needs attention: %s',
2836 $index, $location, $status;
2837 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2838 report('chassis', $msg, $err, $index);
2841 my $msg = sprintf 'Chassis fan %d [%s]: %s',
2842 $index, $location, $reading;
2843 report('chassis', $msg, $E_OK, $index);
2846 # Collect performance data
2847 if (defined $opt{perfdata}) {
2848 my $pname = lc $location;
2849 $pname =~ s{\s}{_}gxms;
2850 $pname =~ s{proc_}{cpu#}xms;
2852 label => "fan_${index}_${pname}",
2864 #-----------------------------------------
2865 # CHASSIS: Check power supplies
2866 #-----------------------------------------
2867 sub check_powersupplies {
2868 return if blacklisted('ps', 'all');
2873 my $err_type = undef;
2881 '1.3.6.1.4.1.674.10892.1.600.12.1.2.1' => 'powerSupplyIndex',
2882 '1.3.6.1.4.1.674.10892.1.600.12.1.5.1' => 'powerSupplyStatus',
2883 '1.3.6.1.4.1.674.10892.1.600.12.1.7.1' => 'powerSupplyType',
2884 '1.3.6.1.4.1.674.10892.1.600.12.1.11.1' => 'powerSupplySensorState',
2885 '1.3.6.1.4.1.674.10892.1.600.12.1.12.1' => 'powerSupplyConfigurationErrorType',
2888 if ($opt{use_get_table}) {
2889 my $powerDeviceTable = '1.3.6.1.4.1.674.10892.1.600.12.1';
2890 $result = $snmp_session->get_table(-baseoid => $powerDeviceTable);
2893 $result = $snmp_session->get_entries(-columns => [keys %ps_oid]);
2896 # No instrumented PSU is OK (blades, low-end servers)
2897 return 0 if !defined $result;
2899 @output = @{ get_snmp_output($result, \%ps_oid) };
2902 @output = @{ run_omreport("$omopt_chassis pwrsupplies") };
2912 6 => 'Uninterruptible Power Supply',
2922 1 => 'Presence detected',
2923 2 => 'Failure detected',
2924 4 => 'Predictive Failure',
2926 16 => 'AC lost or out-of-range',
2927 32 => 'AC out-of-range but present',
2928 64 => 'Configuration error',
2931 my %ps_config_error_type
2933 1 => 'Vendor mismatch',
2934 2 => 'Revision mismatch',
2935 3 => 'Processor missing',
2939 foreach my $out (@output) {
2941 @states = (); # contains states for the PS
2943 $index = $out->{powerSupplyIndex} - 1;
2944 $status = $snmp_status{$out->{powerSupplyStatus}};
2945 $type = get_hashval($out->{powerSupplyType}, \%ps_type);
2946 $err_type = defined $out->{powerSupplyConfigurationErrorType}
2947 ? $ps_config_error_type{$out->{powerSupplyConfigurationErrorType}} : undef;
2949 # get the combined state from the StatusReading OID
2950 foreach my $mask (sort keys %ps_state) {
2951 if (($out->{powerSupplySensorState} & $mask) != 0) {
2952 push @states, $ps_state{$mask};
2956 # If configuration error, also include the error type
2957 if (defined $err_type) {
2958 push @states, $err_type;
2961 # Finally, construct the state string
2962 $state = join q{, }, @states;
2965 $index = $out->{'Index'};
2966 $status = $out->{'Status'};
2967 $type = $out->{'Type'};
2968 $state = $out->{'Online Status'};
2971 next PS if blacklisted('ps', $index);
2974 if ($status ne 'Ok') {
2975 my $msg = sprintf 'Power Supply %d [%s] needs attention: %s',
2976 $index, $type, $state;
2977 report('chassis', $msg, $status2nagios{$status}, $index);
2980 my $msg = sprintf 'Power Supply %d [%s]: %s',
2981 $index, $type, $state;
2982 report('chassis', $msg, $E_OK, $index);
2989 #-----------------------------------------
2990 # CHASSIS: Check temperatures
2991 #-----------------------------------------
2992 sub check_temperatures {
2993 return if blacklisted('temp', 'all');
2997 my $reading = undef;
2998 my $location = undef;
2999 my $max_crit = undef;
3000 my $max_warn = undef;
3001 my $min_warn = undef;
3002 my $min_crit = undef;
3004 my $discrete = undef;
3007 # Getting custom temperature thresholds (user option)
3008 my %warn_threshold = %{ custom_temperature_thresholds('w') };
3009 my %crit_threshold = %{ custom_temperature_thresholds('c') };
3014 '1.3.6.1.4.1.674.10892.1.700.20.1.2.1' => 'temperatureProbeIndex',
3015 '1.3.6.1.4.1.674.10892.1.700.20.1.5.1' => 'temperatureProbeStatus',
3016 '1.3.6.1.4.1.674.10892.1.700.20.1.6.1' => 'temperatureProbeReading',
3017 '1.3.6.1.4.1.674.10892.1.700.20.1.7.1' => 'temperatureProbeType',
3018 '1.3.6.1.4.1.674.10892.1.700.20.1.8.1' => 'temperatureProbeLocationName',
3019 '1.3.6.1.4.1.674.10892.1.700.20.1.10.1' => 'temperatureProbeUpperCriticalThreshold',
3020 '1.3.6.1.4.1.674.10892.1.700.20.1.11.1' => 'temperatureProbeUpperNonCriticalThreshold',
3021 '1.3.6.1.4.1.674.10892.1.700.20.1.12.1' => 'temperatureProbeLowerNonCriticalThreshold',
3022 '1.3.6.1.4.1.674.10892.1.700.20.1.13.1' => 'temperatureProbeLowerCriticalThreshold',
3023 '1.3.6.1.4.1.674.10892.1.700.20.1.16.1' => 'temperatureProbeDiscreteReading',
3025 # this didn't work well for some reason
3026 #my $result = $snmp_session->get_entries(-columns => [keys %temp_oid]);
3028 # Getting values using the table
3029 my $temperatureProbeTable = '1.3.6.1.4.1.674.10892.1.700.20';
3030 my $result = $snmp_session->get_table(-baseoid => $temperatureProbeTable);
3032 if (!defined $result) {
3033 printf "SNMP ERROR [temperatures]: %s.\n", $snmp_session->error;
3034 $snmp_session->close;
3038 @output = @{ get_snmp_output($result, \%temp_oid) };
3041 @output = @{ run_omreport("$omopt_chassis temps") };
3046 1 => 'Other', # type is other than following values
3047 2 => 'Unknown', # type is unknown
3048 3 => 'AmbientESM', # type is Ambient Embedded Systems Management temperature probe
3049 16 => 'Discrete', # type is temperature probe with discrete reading
3053 foreach my $out (@output) {
3055 $index = $out->{temperatureProbeIndex} - 1;
3056 $status = $snmp_probestatus{$out->{temperatureProbeStatus}};
3057 $location = $out->{temperatureProbeLocationName};
3058 $reading = exists $out->{temperatureProbeReading}
3059 ? $out->{temperatureProbeReading} / 10 : '[N/A]';
3060 $max_crit = exists $out->{temperatureProbeUpperCriticalThreshold}
3061 ? $out->{temperatureProbeUpperCriticalThreshold} / 10 : '[N/A]';
3062 $max_warn = exists $out->{temperatureProbeUpperNonCriticalThreshold}
3063 ? $out->{temperatureProbeUpperNonCriticalThreshold} / 10 : '[N/A]';
3064 $min_crit = exists $out->{temperatureProbeLowerCriticalThreshold}
3065 ? $out->{temperatureProbeLowerCriticalThreshold} / 10 : '[N/A]';
3066 $min_warn = exists $out->{temperatureProbeLowerNonCriticalThreshold}
3067 ? $out->{temperatureProbeLowerNonCriticalThreshold} / 10 : '[N/A]';
3068 $type = get_hashval($out->{temperatureProbeType}, \%probe_type);
3069 $discrete = exists $out->{temperatureProbeDiscreteReading}
3070 ? $out->{temperatureProbeDiscreteReading} : '[N/A]';
3071 # workaround for bad temp probes
3072 if ($type eq 'AmbientESM' and $reading !~ m{\A \d+(\.\d+)? \z}xms) {
3077 $index = $out->{'Index'};
3078 $status = $out->{'Status'};
3079 $reading = $out->{'Reading'}; $reading =~ s{\.0\s+C}{}xms;
3080 $location = $out->{'Probe Name'};
3081 $max_crit = $out->{'Maximum Failure Threshold'}; $max_crit =~ s{\.0\s+C}{}xms;
3082 $max_warn = $out->{'Maximum Warning Threshold'}; $max_warn =~ s{\.0\s+C}{}xms;
3083 $min_crit = $out->{'Minimum Failure Threshold'}; $min_crit =~ s{\.0\s+C}{}xms;
3084 $min_warn = $out->{'Minimum Warning Threshold'}; $min_warn =~ s{\.0\s+C}{}xms;
3085 $type = $reading =~ m{\A\d+\z}xms ? 'AmbientESM' : 'Discrete';
3086 $discrete = $reading;
3089 next TEMP if blacklisted('temp', $index);
3092 if ($type eq 'Discrete') {
3093 my $msg = sprintf 'Temperature probe %d [%s] is %s',
3094 $index, $location, $discrete;
3095 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3096 report('chassis', $msg, $err, $index);
3099 # First check according to custom thresholds
3100 if (exists $crit_threshold{$index}{max} and $reading > $crit_threshold{$index}{max}) {
3101 # Custom critical MAX
3102 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom max=%d)',
3103 $index, $location, $reading, $crit_threshold{$index}{max};
3104 report('chassis', $msg, $E_CRITICAL, $index);
3106 elsif (exists $warn_threshold{$index}{max} and $reading > $warn_threshold{$index}{max}) {
3107 # Custom warning MAX
3108 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom max=%d)',
3109 $index, $location, $reading, $warn_threshold{$index}{max};
3110 report('chassis', $msg, $E_WARNING, $index);
3112 elsif (exists $crit_threshold{$index}{min} and $reading < $crit_threshold{$index}{min}) {
3113 # Custom critical MIN
3114 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom min=%d)',
3115 $index, $location, $reading, $crit_threshold{$index}{min};
3116 report('chassis', $msg, $E_CRITICAL, $index);
3118 elsif (exists $warn_threshold{$index}{min} and $reading < $warn_threshold{$index}{min}) {
3119 # Custom warning MIN
3120 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom min=%d)',
3121 $index, $location, $reading, $warn_threshold{$index}{min};
3122 report('chassis', $msg, $E_WARNING, $index);
3124 elsif ($status ne 'Ok' and $max_crit ne '[N/A]' and $reading > $max_crit) {
3125 my $msg = sprintf 'Temperature Probe %d [%s] is critically high at %d C',
3126 $index, $location, $reading;
3127 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3128 report('chassis', $msg, $err, $index);
3130 elsif ($status ne 'Ok' and $max_warn ne '[N/A]' and $reading > $max_warn) {
3131 my $msg = sprintf 'Temperature Probe %d [%s] is too high at %d C',
3132 $index, $location, $reading;
3133 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3134 report('chassis', $msg, $err, $index);
3136 elsif ($status ne 'Ok' and $min_crit ne '[N/A]' and $reading < $min_crit) {
3137 my $msg = sprintf 'Temperature Probe %d [%s] is critically low at %d C',
3138 $index, $location, $reading;
3139 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3140 report('chassis', $msg, $err, $index);
3142 elsif ($status ne 'Ok' and $min_warn ne '[N/A]' and $reading < $min_warn) {
3143 my $msg = sprintf 'Temperature Probe %d [%s] is too low at %d C',
3144 $index, $location, $reading;
3145 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3146 report('chassis', $msg, $err, $index);
3150 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C',
3151 $index, $location, $reading;
3152 if ($min_warn eq '[N/A]' and $min_crit eq '[N/A]') {
3153 $msg .= sprintf ' (max=%s/%s)', $max_warn, $max_crit;
3156 $msg .= sprintf ' (min=%s/%s, max=%s/%s)',
3157 $min_warn, $min_crit, $max_warn, $max_crit;
3159 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3160 report('chassis', $msg, $err, $index);
3163 # Collect performance data
3164 if (defined $opt{perfdata}) {
3165 my $pname = lc $location;
3166 $pname =~ s{\s}{_}gxms;
3167 $pname =~ s{_temp\z}{}xms;
3168 $pname =~ s{proc_}{cpu#}xms;
3170 label => "temp_${index}_${pname}",
3183 #-----------------------------------------
3184 # CHASSIS: Check processors
3185 #-----------------------------------------
3186 sub check_processors {
3187 return if blacklisted('cpu', 'all');
3200 # NOTE: For some reason, older models don't have the
3201 # "Processor Device Status" OIDs. We check both the newer
3202 # (preferred) OIDs and the old ones.
3206 '1.3.6.1.4.1.674.10892.1.1100.30.1.2.1' => 'processorDeviceIndex',
3207 '1.3.6.1.4.1.674.10892.1.1100.30.1.5.1' => 'processorDeviceStatus',
3208 '1.3.6.1.4.1.674.10892.1.1100.30.1.8.1' => 'processorDeviceManufacturerName',
3209 '1.3.6.1.4.1.674.10892.1.1100.30.1.9.1' => 'processorDeviceStatusState',
3210 '1.3.6.1.4.1.674.10892.1.1100.30.1.10.1' => 'processorDeviceFamily',
3211 '1.3.6.1.4.1.674.10892.1.1100.30.1.12.1' => 'processorDeviceCurrentSpeed',
3212 '1.3.6.1.4.1.674.10892.1.1100.30.1.23.1' => 'processorDeviceBrandName',
3213 '1.3.6.1.4.1.674.10892.1.1100.32.1.2.1' => 'processorDeviceStatusIndex',
3214 '1.3.6.1.4.1.674.10892.1.1100.32.1.5.1' => 'processorDeviceStatusStatus',
3215 '1.3.6.1.4.1.674.10892.1.1100.32.1.6.1' => 'processorDeviceStatusReading',
3218 if ($opt{use_get_table}) {
3219 my $processorDeviceTable = '1.3.6.1.4.1.674.10892.1.1100.30.1';
3220 my $processorDeviceStatusTable = '1.3.6.1.4.1.674.10892.1.1100.32.1';
3222 $result = $snmp_session->get_table(-baseoid => $processorDeviceTable);
3223 my $ext = $snmp_session->get_table(-baseoid => $processorDeviceStatusTable);
3225 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
3228 $result = $snmp_session->get_entries(-columns => [keys %cpu_oid]);
3231 if (!defined $result) {
3232 printf "SNMP ERROR [processors]: %s.\n", $snmp_session->error;
3233 $snmp_session->close;
3237 @output = @{ get_snmp_output($result, \%cpu_oid) };
3240 @output = @{ run_omreport("$omopt_chassis processors") };
3245 1 => 'Other', # other than following values
3246 2 => 'Unknown', # unknown
3247 3 => 'Enabled', # enabled
3248 4 => 'User Disabled', # disabled by user via BIOS setup
3249 5 => 'BIOS Disabled', # disabled by BIOS (POST error)
3255 1 => 'Internal Error', # Internal Error
3256 2 => 'Thermal Trip', # Thermal Trip
3257 32 => 'Configuration Error', # Configuration Error
3258 128 => 'Present', # Processor Present
3259 256 => 'Disabled', # Processor Disabled
3260 512 => 'Terminator Present', # Terminator Present
3261 1024 => 'Throttled', # Processor Throttled
3264 # Mapping between family numbers from SNMP and actual CPU family
3267 1 => 'Other', 2 => 'Unknown',
3268 3 => '8086', 4 => '80286',
3269 5 => '386', 6 => '486',
3270 7 => '8087', 8 => '80287',
3271 9 => '80387', 10 => '80487',
3272 11 => 'Pentium', 12 => 'Pentium Pro',
3273 13 => 'Pentium II', 14 => 'Pentium with MMX',
3274 15 => 'Celeron', 16 => 'Pentium II Xeon',
3275 17 => 'Pentium III', 18 => 'Pentium III Xeon',
3276 19 => 'Pentium III', 20 => 'Itanium',
3277 21 => 'Xeon', 22 => 'Pentium 4',
3278 23 => 'Xeon MP', 24 => 'Itanium 2',
3279 25 => 'K5', 26 => 'K6',
3280 27 => 'K6-2', 28 => 'K6-3',
3281 29 => 'Athlon', 30 => 'AMD2900',
3282 31 => 'K6-2+', 32 => 'Power PC',
3283 33 => 'Power PC 601', 34 => 'Power PC 603',
3284 35 => 'Power PC 603+', 36 => 'Power PC 604',
3285 37 => 'Power PC 620', 38 => 'Power PC x704',
3286 39 => 'Power PC 750', 40 => 'Core Duo',
3287 41 => 'Core Duo mobile', 42 => 'Core Solo mobile',
3288 43 => 'Intel Atom', 44 => undef,
3289 45 => undef, 46 => undef,
3290 47 => undef, 48 => 'Alpha',
3291 49 => 'Alpha 21064', 50 => 'Alpha 21066',
3292 51 => 'Alpha 21164', 52 => 'Alpha 21164PC',
3293 53 => 'Alpha 21164a', 54 => 'Alpha 21264',
3294 55 => 'Alpha 21364', 56 => 'Turion II Ultra Dual-Core Mobile M',
3295 57 => 'Turion II Dual-Core Mobile M', 58 => 'Athlon II Dual-Core Mobile M ',
3296 59 => 'Opteron 6100', 60 => 'Opteron 4100',
3297 61 => undef, 62 => undef,
3298 63 => undef, 64 => 'MIPS',
3299 65 => 'MIPS R4000', 66 => 'MIPS R4200',
3300 67 => 'MIPS R4400', 68 => 'MIPS R4600',
3301 69 => 'MIPS R10000', 70 => undef,
3302 71 => undef, 72 => undef,
3303 73 => undef, 74 => undef,
3304 75 => undef, 76 => undef,
3305 77 => undef, 78 => undef,
3306 79 => undef, 80 => 'SPARC',
3307 81 => 'SuperSPARC', 82 => 'microSPARC II',
3308 83 => 'microSPARC IIep', 84 => 'UltraSPARC',
3309 85 => 'UltraSPARC II', 86 => 'UltraSPARC IIi',
3310 87 => 'UltraSPARC III', 88 => 'UltraSPARC IIIi',
3311 89 => undef, 90 => undef,
3312 91 => undef, 92 => undef,
3313 93 => undef, 94 => undef,
3314 95 => undef, 96 => '68040',
3315 97 => '68xxx', 98 => '68000',
3316 99 => '68010', 100 => '68020',
3317 101 => '68030', 102 => undef,
3318 103 => undef, 104 => undef,
3319 105 => undef, 106 => undef,
3320 107 => undef, 108 => undef,
3321 109 => undef, 110 => undef,
3322 111 => undef, 112 => 'Hobbit',
3323 113 => undef, 114 => undef,
3324 115 => undef, 116 => undef,
3325 117 => undef, 118 => undef,
3326 119 => undef, 120 => 'Crusoe TM5000',
3327 121 => 'Crusoe TM3000', 122 => 'Efficeon TM8000',
3328 123 => undef, 124 => undef,
3329 125 => undef, 126 => undef,
3330 127 => undef, 128 => 'Weitek',
3331 129 => undef, 130 => 'Celeron M',
3332 131 => 'Athlon 64', 132 => 'Opteron',
3333 133 => 'Sempron', 134 => 'Turion 64 Mobile',
3334 135 => 'Dual-Core Opteron', 136 => 'Athlon 64 X2 DC',
3335 137 => 'Turion 64 X2 M', 138 => 'Quad-Core Opteron',
3336 139 => '3rd gen Opteron', 140 => 'AMD Phenom FX Quad-Core',
3337 141 => 'AMD Phenom X4 Quad-Core', 142 => 'AMD Phenom X2 Dual-Core',
3338 143 => 'AMD Athlon X2 Dual-Core', 144 => 'PA-RISC',
3339 145 => 'PA-RISC 8500', 146 => 'PA-RISC 8000',
3340 147 => 'PA-RISC 7300LC', 148 => 'PA-RISC 7200',
3341 149 => 'PA-RISC 7100LC', 150 => 'PA-RISC 7100',
3342 151 => undef, 152 => undef,
3343 153 => undef, 154 => undef,
3344 155 => undef, 156 => undef,
3345 157 => undef, 158 => undef,
3346 159 => undef, 160 => 'V30',
3347 161 => 'Quad-Core Xeon 3200', 162 => 'Dual-Core Xeon 3000',
3348 163 => 'Quad-Core Xeon 5300', 164 => 'Dual-Core Xeon 5100',
3349 165 => 'Dual-Core Xeon 5000', 166 => 'Dual-Core Xeon LV',
3350 167 => 'Dual-Core Xeon ULV', 168 => 'Dual-Core Xeon 7100',
3351 169 => 'Quad-Core Xeon 5400', 170 => 'Quad-Core Xeon',
3352 171 => 'Dual-Core Xeon 5200', 172 => 'Dual-Core Xeon 7200',
3353 173 => 'Quad-Core Xeon 7300', 174 => 'Quad-Core Xeon 7400',
3354 175 => 'Multi-Core Xeon 7400', 176 => 'M1',
3355 177 => 'M2', 178 => undef,
3356 179 => 'Pentium 4 HT', 180 => 'AS400',
3357 181 => undef, 182 => 'Athlon XP',
3358 183 => 'Athlon MP', 184 => 'Duron',
3359 185 => 'Pentium M', 186 => 'Celeron D',
3360 187 => 'Pentium D', 188 => 'Pentium Extreme',
3361 189 => 'Core Solo', 190 => 'Core2',
3362 191 => 'Core2 Duo', 192 => 'Core2 Solo',
3363 193 => 'Core2 Extreme', 194 => 'Core2 Quad',
3364 195 => 'Core2 Extreme mobile', 196 => 'Core2 Duo mobile',
3365 197 => 'Core2 Solo mobile', 198 => 'Core i7',
3366 199 => 'Dual-Core Celeron', 200 => 'IBM390',
3367 201 => 'G4', 202 => 'G5',
3368 203 => 'ESA/390 G6', 204 => 'z/Architectur',
3369 205 => 'Core i5', 206 => 'Core i3',
3370 207 => undef, 208 => undef,
3371 209 => undef, 210 => 'C7-M',
3372 211 => 'C7-D', 212 => 'C7',
3373 213 => 'Eden', 214 => 'Multi-Core Xeon',
3374 215 => 'Dual-Core Xeon 3xxx', 216 => 'Quad-Core Xeon 3xxx',
3375 217 => 'VIA Nano', 218 => 'Dual-Core Xeon 5xxx',
3376 219 => 'Quad-Core Xeon 5xxx', 220 => undef,
3377 221 => 'Dual-Core Xeon 7xxx', 222 => 'Quad-Core Xeon 7xxx',
3378 223 => 'Multi-Core Xeon 7xxx', 224 => 'Multi-Core Xeon 3400',
3379 225 => undef, 226 => undef,
3380 227 => undef, 228 => undef,
3381 229 => undef, 230 => 'Embedded AMD Opteron Quad-Core',
3382 231 => 'AMD Phenom Triple-Core', 232 => 'AMD Turion Ultra Dual-Core Mobile',
3383 233 => 'AMD Turion Dual-Core Mobile', 234 => 'AMD Athlon Dual-Core',
3384 235 => 'AMD Sempron SI', 236 => 'AMD Phenom II',
3385 237 => 'AMD Athlon II', 238 => 'Six-Core AMD Opteron',
3386 239 => 'AMD Sempron M', 240 => undef,
3387 241 => undef, 242 => undef,
3388 243 => undef, 244 => undef,
3389 245 => undef, 246 => undef,
3390 247 => undef, 248 => undef,
3391 249 => undef, 250 => 'i860',
3396 foreach my $out (@output) {
3398 $index = exists $out->{processorDeviceStatusIndex}
3399 ? $out->{processorDeviceStatusIndex} - 1
3400 : $out->{processorDeviceIndex} - 1;
3401 $status = exists $out->{processorDeviceStatusStatus}
3402 ? $snmp_status{$out->{processorDeviceStatusStatus}}
3403 : $snmp_status{$out->{processorDeviceStatus}};
3404 if (exists $out->{processorDeviceStatusReading}) {
3405 my @states = (); # contains states for the CPU
3407 # get the combined state from the StatusReading OID
3408 foreach my $mask (sort keys %cpu_reading) {
3409 if (($out->{processorDeviceStatusReading} & $mask) != 0) {
3410 push @states, $cpu_reading{$mask};
3414 # Finally, create the state string
3415 $state = join q{, }, @states;
3418 $state = get_hashval($out->{processorDeviceStatusState}, \%cpu_state);
3420 $man = $out->{processorDeviceManufacturerName};
3421 $family = (exists $out->{processorDeviceFamily}
3422 and exists $cpu_family{$out->{processorDeviceFamily}})
3423 ? $cpu_family{$out->{processorDeviceFamily}} : undef;
3424 $speed = $out->{processorDeviceCurrentSpeed};
3425 $brand = $out->{processorDeviceBrandName};
3428 $index = $out->{'Index'};
3429 $status = $out->{'Status'};
3430 $state = $out->{'State'};
3431 $brand = exists $out->{'Processor Brand'} ? $out->{'Processor Brand'} : undef;
3432 $family = exists $out->{'Processor Family'} ? $out->{'Processor Family'} : undef;
3433 $man = exists $out->{'Processor Manufacturer'} ? $out->{'Processor Manufacturer'} : undef;
3434 $speed = exists $out->{'Current Speed'} ? $out->{'Current Speed'} : undef;
3437 next CPU if blacklisted('cpu', $index);
3439 # Ignore unoccupied CPU slots (omreport)
3440 next CPU if (defined $out->{'Processor Manufacturer'}
3441 and $out->{'Processor Manufacturer'} eq '[Not Occupied]')
3442 or (defined $out->{'Processor Brand'} and $out->{'Processor Brand'} eq '[Not Occupied]');
3444 # Ignore unoccupied CPU slots (snmp)
3445 if ($snmp and exists $out->{processorDeviceStatusReading}
3446 and $out->{processorDeviceStatusReading} == 0) {
3452 if (defined $brand) {
3453 $brand =~ s{\s\s+}{ }gxms;
3454 $brand =~ s{\((R|tm)\)}{}gxms;
3455 $brand =~ s{\s(CPU|Processor)}{}xms;
3456 $brand =~ s{\s\@}{}xms;
3458 elsif (defined $family and defined $man and defined $speed) {
3459 $speed =~ s{\A (\d+) .*}{$1}xms;
3460 $brand = sprintf '%s %s %.2fGHz', $man, $family, $speed / 1000;
3467 if ($status ne 'Ok') {
3468 my $msg = sprintf 'Processor %d [%s] needs attention: %s',
3469 $index, $brand, $state;
3470 report('chassis', $msg, $status2nagios{$status}, $index);
3474 my $msg = sprintf 'Processor %d [%s] is %s',
3475 $index, $brand, $state;
3476 report('chassis', $msg, $E_OK, $index);
3483 #-----------------------------------------
3484 # CHASSIS: Check voltage probes
3485 #-----------------------------------------
3487 return if blacklisted('volt', 'all');
3491 my $reading = undef;
3492 my $location = undef;
3498 '1.3.6.1.4.1.674.10892.1.600.20.1.2.1' => 'voltageProbeIndex',
3499 '1.3.6.1.4.1.674.10892.1.600.20.1.5.1' => 'voltageProbeStatus',
3500 '1.3.6.1.4.1.674.10892.1.600.20.1.6.1' => 'voltageProbeReading',
3501 '1.3.6.1.4.1.674.10892.1.600.20.1.8.1' => 'voltageProbeLocationName',
3502 '1.3.6.1.4.1.674.10892.1.600.20.1.16.1' => 'voltageProbeDiscreteReading',
3505 my $voltageProbeTable = '1.3.6.1.4.1.674.10892.1.600.20.1';
3506 my $result = $snmp_session->get_table(-baseoid => $voltageProbeTable);
3508 if (!defined $result) {
3509 printf "SNMP ERROR [voltage]: %s.\n", $snmp_session->error;
3510 $snmp_session->close;
3514 @output = @{ get_snmp_output($result, \%volt_oid) };
3517 @output = @{ run_omreport("$omopt_chassis volts") };
3520 my %volt_discrete_reading
3527 foreach my $out (@output) {
3529 $index = $out->{voltageProbeIndex} - 1;
3530 $status = $snmp_probestatus{$out->{voltageProbeStatus}};
3531 $reading = exists $out->{voltageProbeReading}
3532 ? sprintf('%.3f V', $out->{voltageProbeReading}/1000)
3533 : get_hashval($out->{voltageProbeDiscreteReading}, \%volt_discrete_reading);
3534 $location = $out->{voltageProbeLocationName};
3537 $index = $out->{'Index'};
3538 $status = $out->{'Status'};
3539 $reading = $out->{'Reading'};
3540 $location = $out->{'Probe Name'};
3543 next VOLT if blacklisted('volt', $index);
3546 my $msg = sprintf 'Voltage sensor %d [%s] is %s',
3547 $index, $location, $reading;
3548 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3549 report('chassis', $msg, $err, $index);
3555 #-----------------------------------------
3556 # CHASSIS: Check batteries
3557 #-----------------------------------------
3558 sub check_batteries {
3559 return if blacklisted('bp', 'all');
3563 my $reading = undef;
3564 my $location = undef;
3570 '1.3.6.1.4.1.674.10892.1.600.50.1.2.1' => 'batteryIndex',
3571 '1.3.6.1.4.1.674.10892.1.600.50.1.5.1' => 'batteryStatus',
3572 '1.3.6.1.4.1.674.10892.1.600.50.1.6.1' => 'batteryReading',
3573 '1.3.6.1.4.1.674.10892.1.600.50.1.7.1' => 'batteryLocationName',
3576 if ($opt{use_get_table}) {
3577 my $batteryTable = '1.3.6.1.4.1.674.10892.1.600.50.1';
3578 $result = $snmp_session->get_table(-baseoid => $batteryTable);
3581 $result = $snmp_session->get_entries(-columns => [keys %bat_oid]);
3584 # No batteries is OK
3585 return 0 if !defined $result;
3587 @output = @{ get_snmp_output($result, \%bat_oid) };
3590 @output = @{ run_omreport("$omopt_chassis batteries") };
3595 1 => 'Predictive Failure',
3597 4 => 'Presence Detected',
3601 foreach my $out (@output) {
3603 $index = $out->{batteryIndex} - 1;
3604 $status = $snmp_status{$out->{batteryStatus}};
3605 $reading = get_hashval($out->{batteryReading}, \%bat_reading);
3606 $location = $out->{batteryLocationName};
3609 $index = $out->{'Index'};
3610 $status = $out->{'Status'};
3611 $reading = $out->{'Reading'};
3612 $location = $out->{'Probe Name'};
3615 next BATTERY if blacklisted('bp', $index);
3618 my $msg = sprintf 'Battery probe %d [%s] is %s',
3619 $index, $location, $reading;
3620 report('chassis', $msg, $status2nagios{$status}, $index);
3626 #-----------------------------------------
3627 # CHASSIS: Check amperage probes (power monitoring)
3628 #-----------------------------------------
3629 sub check_pwrmonitoring {
3630 return if blacklisted('amp', 'all');
3634 my $reading = undef;
3635 my $location = undef;
3636 my $max_crit = undef;
3637 my $max_warn = undef;
3645 '1.3.6.1.4.1.674.10892.1.600.30.1.2.1' => 'amperageProbeIndex',
3646 '1.3.6.1.4.1.674.10892.1.600.30.1.5.1' => 'amperageProbeStatus',
3647 '1.3.6.1.4.1.674.10892.1.600.30.1.6.1' => 'amperageProbeReading',
3648 '1.3.6.1.4.1.674.10892.1.600.30.1.7.1' => 'amperageProbeType',
3649 '1.3.6.1.4.1.674.10892.1.600.30.1.8.1' => 'amperageProbeLocationName',
3650 '1.3.6.1.4.1.674.10892.1.600.30.1.10.1' => 'amperageProbeUpperCriticalThreshold',
3651 '1.3.6.1.4.1.674.10892.1.600.30.1.11.1' => 'amperageProbeUpperNonCriticalThreshold',
3652 '1.3.6.1.4.1.674.10892.1.600.30.1.16.1' => 'amperageProbeDiscreteReading',
3655 if ($opt{use_get_table}) {
3656 my $amperageProbeTable = '1.3.6.1.4.1.674.10892.1.600.30.1';
3657 $result = $snmp_session->get_table(-baseoid => $amperageProbeTable);
3660 $result = $snmp_session->get_entries(-columns => [keys %amp_oid]);
3663 # No pwrmonitoring is OK
3664 return 0 if !defined $result;
3666 @output = @{ get_snmp_output($result, \%amp_oid) };
3669 @output = @{ run_omreport("$omopt_chassis pwrmonitoring") };
3672 my %amp_type # Amperage probe types
3674 1 => 'amperageProbeTypeIsOther', # other than following values
3675 2 => 'amperageProbeTypeIsUnknown', # unknown
3676 3 => 'amperageProbeTypeIs1Point5Volt', # 1.5 amperage probe
3677 4 => 'amperageProbeTypeIs3Point3volt', # 3.3 amperage probe
3678 5 => 'amperageProbeTypeIs5Volt', # 5 amperage probe
3679 6 => 'amperageProbeTypeIsMinus5Volt', # -5 amperage probe
3680 7 => 'amperageProbeTypeIs12Volt', # 12 amperage probe
3681 8 => 'amperageProbeTypeIsMinus12Volt', # -12 amperage probe
3682 9 => 'amperageProbeTypeIsIO', # I/O probe
3683 10 => 'amperageProbeTypeIsCore', # Core probe
3684 11 => 'amperageProbeTypeIsFLEA', # FLEA (standby) probe
3685 12 => 'amperageProbeTypeIsBattery', # Battery probe
3686 13 => 'amperageProbeTypeIsTerminator', # SCSI Termination probe
3687 14 => 'amperageProbeTypeIs2Point5Volt', # 2.5 amperage probe
3688 15 => 'amperageProbeTypeIsGTL', # GTL (ground termination logic) probe
3689 16 => 'amperageProbeTypeIsDiscrete', # amperage probe with discrete reading
3690 23 => 'amperageProbeTypeIsPowerSupplyAmps', # Power Supply probe with reading in Amps
3691 24 => 'amperageProbeTypeIsPowerSupplyWatts', # Power Supply probe with reading in Watts
3692 25 => 'amperageProbeTypeIsSystemAmps', # System probe with reading in Amps
3693 26 => 'amperageProbeTypeIsSystemWatts', # System probe with reading in Watts
3704 'amperageProbeTypeIsPowerSupplyAmps' => 'hA', # tenths of Amps
3705 'amperageProbeTypeIsSystemAmps' => 'hA', # tenths of Amps
3706 'amperageProbeTypeIsPowerSupplyWatts' => 'W', # Watts
3707 'amperageProbeTypeIsSystemWatts' => 'W', # Watts
3708 'amperageProbeTypeIsDiscrete' => q{}, # discrete reading, no unit
3712 foreach my $out (@output) {
3714 $index = $out->{amperageProbeIndex} - 1;
3715 $status = $snmp_status{$out->{amperageProbeStatus}};
3716 $type = get_hashval($out->{amperageProbeType}, \%amp_type);
3717 $reading = $type eq 'amperageProbeTypeIsDiscrete'
3718 ? get_hashval($out->{amperageProbeDiscreteReading}, \%amp_discrete)
3719 : $out->{amperageProbeReading};
3720 $location = $out->{amperageProbeLocationName};
3721 $max_crit = exists $out->{amperageProbeUpperCriticalThreshold}
3722 ? $out->{amperageProbeUpperCriticalThreshold} : 0;
3723 $max_warn = exists $out->{amperageProbeUpperNonCriticalThreshold}
3724 ? $out->{amperageProbeUpperNonCriticalThreshold} : 0;
3725 $unit = exists $amp_unit{$amp_type{$out->{amperageProbeType}}}
3726 ? $amp_unit{$amp_type{$out->{amperageProbeType}}} : 'mA';
3728 # workaround for broken probes
3729 if (!defined $reading) {
3730 $type = 'amperageProbeTypeIsDiscrete';
3735 # calculate proper values and set unit for ampere probes
3736 if ($unit eq 'hA' and $type ne 'amperageProbeTypeIsDiscrete') {
3744 $index = $out->{'Index'};
3745 next AMP if (!defined $index || $index !~ m/^\d+$/x);
3746 $status = $out->{'Status'};
3747 $reading = $out->{'Reading'};
3748 $location = $out->{'Probe Name'};
3749 $max_crit = $out->{'Failure Threshold'} ne '[N/A]'
3750 ? $out->{'Failure Threshold'} : 0;
3751 $max_warn = $out->{'Warning Threshold'} ne '[N/A]'
3752 ? $out->{'Warning Threshold'} : 0;
3753 $reading =~ s{\A (\d+.*?)\s+([a-zA-Z]+) \s*\z}{$1}xms;
3755 $max_warn =~ s{\A (\d+.*?)\s+[a-zA-Z]+ \s*\z}{$1}xms;
3756 $max_crit =~ s{\A (\d+.*?)\s+[a-zA-Z]+ \s*\z}{$1}xms;
3759 next AMP if blacklisted('amp', $index);
3760 next AMP if $index !~ m{\A \d+ \z}xms;
3763 if (defined $type and $type eq 'amperageProbeTypeIsDiscrete') {
3764 my $msg = sprintf 'Amperage probe %d [%s] is %s',
3765 $index, $location, $reading;
3766 report('chassis', $msg, $status2nagios{$status}, $index);
3769 my $msg = sprintf 'Amperage probe %d [%s] reads %s %s',
3770 $index, $location, $reading, $unit;
3771 report('chassis', $msg, $status2nagios{$status}, $index);
3774 # Collect performance data
3775 if (defined $opt{perfdata}) {
3776 next AMP if $reading !~ m{\A \d+(\.\d+)? \z}xms; # discrete reading (not number)
3777 #next AMP if $type eq 'amperageProbeTypeIsDiscrete';
3778 my $label = join q{_}, 'pwr_mon', $index, lc $location;
3779 $label =~ s{\s}{_}gxms;
3782 mini => "p${index}" . lc $unit,
3790 # Collect EXTRA performance data not found at first run. This is a
3792 if (defined $opt{perfdata} && !$snmp) {
3798 foreach (@perfdata) {
3799 if ($_->{label} =~ m/\A pwr_mon_(\d+)/xms) {
3805 foreach my $line (@{ run_command("$omreport $omopt_chassis pwrmonitoring -fmt ssv") }) {
3807 if ($line eq 'Location;Reading') {
3815 if ($found and $line =~ m/\A ([^;]+?) ; (\d*\.\d+) \s [AW] \z/xms) {
3818 $aname =~ s{\s}{_}gxms;
3820 # don't use an existing index
3821 while (exists $used{$index}) { ++$index; }
3824 label => "pwr_mon_${index}_${aname}",
3825 mini => "p${index}a",
3839 #-----------------------------------------
3840 # CHASSIS: Check intrusion
3841 #-----------------------------------------
3842 sub check_intrusion {
3843 return if blacklisted('intr', 'all');
3847 my $reading = undef;
3853 '1.3.6.1.4.1.674.10892.1.300.70.1.2.1' => 'intrusionIndex',
3854 '1.3.6.1.4.1.674.10892.1.300.70.1.5.1' => 'intrusionStatus',
3855 '1.3.6.1.4.1.674.10892.1.300.70.1.6.1' => 'intrusionReading',
3858 if ($opt{use_get_table}) {
3859 my $intrusionTable = '1.3.6.1.4.1.674.10892.1.300.70.1';
3860 $result = $snmp_session->get_table(-baseoid => $intrusionTable);
3863 $result = $snmp_session->get_entries(-columns => [keys %int_oid]);
3866 # No intrusion is OK
3867 return 0 if !defined $result;
3869 @output = @{ get_snmp_output($result, \%int_oid) };
3872 @output = @{ run_omreport("$omopt_chassis intrusion") };
3877 1 => 'Not Breached', # chassis not breached and no uncleared breaches
3878 2 => 'Breached', # chassis currently breached
3879 3 => 'Breached Prior', # chassis breached prior to boot and has not been cleared
3880 4 => 'Breach Sensor Failure', # intrusion sensor has failed
3884 foreach my $out (@output) {
3886 $index = $out->{intrusionIndex} - 1;
3887 $status = $snmp_status{$out->{intrusionStatus}};
3888 $reading = get_hashval($out->{intrusionReading}, \%int_reading);
3891 $index = $out->{'Index'};
3892 $status = $out->{'Status'};
3893 $reading = $out->{'State'};
3896 next INTRUSION if blacklisted('intr', $index);
3899 if ($status ne 'Ok') {
3900 my $msg = sprintf 'Chassis intrusion %d detected: %s',
3902 report('chassis', $msg, $E_WARNING, $index);
3906 my $msg = sprintf 'Chassis intrusion %d detection: %s (%s)',
3907 $index, $status, $reading;
3908 report('chassis', $msg, $E_OK, $index);
3915 #-----------------------------------------
3916 # CHASSIS: Check alert log
3917 #-----------------------------------------
3918 sub check_alertlog {
3919 return if $snmp; # Not supported with SNMP
3921 my @output = @{ run_omreport("$omopt_system alertlog") };
3922 foreach my $out (@output) {
3923 ++$count{alert}{$out->{Severity}};
3926 # Create error messages and set exit value if appropriate
3928 if ($count{alert}{'Critical'} > 0) { $err = $E_CRITICAL; }
3929 elsif ($count{alert}{'Non-Critical'} > 0) { $err = $E_WARNING; }
3931 my $msg = sprintf 'Alert log content: %d critical, %d non-critical, %d ok',
3932 $count{alert}{'Critical'}, $count{alert}{'Non-Critical'}, $count{alert}{'Ok'};
3933 report('other', $msg, $err);
3938 #-----------------------------------------
3939 # CHASSIS: Check ESM log overall health
3940 #-----------------------------------------
3941 sub check_esmlog_health {
3945 my $systemStateEventLogStatus = '1.3.6.1.4.1.674.10892.1.200.10.1.41.1';
3946 my $result = $snmp_session->get_request(-varbindlist => [$systemStateEventLogStatus]);
3947 if (!defined $result) {
3948 my $msg = sprintf 'SNMP ERROR [esmhealth]: %s',
3949 $snmp_session->error;
3950 report('other', $msg, $E_UNKNOWN);
3952 $health = $snmp_status{$result->{$systemStateEventLogStatus}};
3955 foreach (@{ run_command("$omreport $omopt_system esmlog -fmt ssv") }) {
3956 if (m/\A Health;(.+) \z/xms) {
3964 # If the overall health of the ESM log is other than "Ok", the
3965 # fill grade of the log is more than 80% and the log should be
3967 if ($health eq 'Ok') {
3968 my $msg = sprintf 'ESM log health is Ok (less than 80%% full)';
3969 report('other', $msg, $E_OK);
3971 elsif ($health eq 'Critical') {
3972 my $msg = sprintf 'ESM log is 100%% full';
3973 report('other', $msg, $status2nagios{$health});
3976 my $msg = sprintf 'ESM log is more than 80%% full';
3977 report('other', $msg, $status2nagios{$health});
3983 #-----------------------------------------
3984 # CHASSIS: Check ESM log
3985 #-----------------------------------------
3992 '1.3.6.1.4.1.674.10892.1.300.40.1.7.1' => 'eventLogSeverityStatus',
3994 my $result = $snmp_session->get_entries(-columns => [keys %esm_oid]);
3997 return if !defined $result;
3999 @output = @{ get_snmp_output($result, \%esm_oid) };
4000 foreach my $out (@output) {
4001 ++$count{esm}{$snmp_status{$out->{eventLogSeverityStatus}}};
4005 @output = @{ run_omreport("$omopt_system esmlog") };
4006 foreach my $out (@output) {
4007 ++$count{esm}{$out->{Severity}};
4011 # Create error messages and set exit value if appropriate
4013 if ($count{esm}{'Critical'} > 0) { $err = $E_CRITICAL; }
4014 elsif ($count{esm}{'Non-Critical'} > 0) { $err = $E_WARNING; }
4016 my $msg = sprintf 'ESM log content: %d critical, %d non-critical, %d ok',
4017 $count{esm}{'Critical'}, $count{esm}{'Non-Critical'}, $count{esm}{'Ok'};
4018 report('other', $msg, $err);
4024 # Handy function for checking all storage components
4027 check_controllers();
4028 check_physical_disks();
4029 check_virtual_disks();
4030 check_cache_battery();
4033 check_enclosure_fans();
4034 check_enclosure_pwr();
4035 check_enclosure_temp();
4036 check_enclosure_emms();
4042 #---------------------------------------------------------------------
4044 #---------------------------------------------------------------------
4047 # Fetch output from 'omreport chassis info', put in sysinfo hash
4049 sub get_omreport_chassis_info {
4050 if (open my $INFO, '-|', "$omreport $omopt_chassis info -fmt ssv") {
4051 my @lines = <$INFO>;
4054 next if !m/\A (Chassis\sModel|Chassis\sService\sTag|Model|Service\sTag|System\sRevision)/xms;
4055 my ($key, $val) = split /;/xms;
4056 $key =~ s{\s+\z}{}xms; # remove trailing whitespace
4057 $val =~ s{\s+\z}{}xms; # remove trailing whitespace
4058 if ($key eq 'Chassis Model' or $key eq 'Model') {
4059 $sysinfo{model} = $val;
4061 if ($key eq 'Chassis Service Tag' or $key eq 'Service Tag') {
4062 $sysinfo{serial} = $val;
4064 if ($key eq 'System Revision') {
4065 $sysinfo{rev} = $val;
4073 # Fetch output from 'omreport chassis bios', put in sysinfo hash
4075 sub get_omreport_chassis_bios {
4076 if (open my $BIOS, '-|', "$omreport $omopt_chassis bios -fmt ssv") {
4077 my @lines = <$BIOS>;
4081 my ($key, $val) = split /;/xms;
4082 $key =~ s{\s+\z}{}xms; # remove trailing whitespace
4083 $val =~ s{\s+\z}{}xms; # remove trailing whitespace
4084 $sysinfo{bios} = $val if $key eq 'Version';
4085 $sysinfo{biosdate} = $val if $key eq 'Release Date';
4092 # Fetch output from 'omreport system operatingsystem', put in sysinfo hash
4094 sub get_omreport_system_operatingsystem {
4095 if (open my $VER, '-|', "$omreport $omopt_system operatingsystem -fmt ssv") {
4100 my ($key, $val) = split /;/xms;
4101 $key =~ s{\s+\z}{}xms; # remove trailing whitespace
4102 $val =~ s{\s+\z}{}xms; # remove trailing whitespace
4103 if ($key eq 'Operating System') {
4104 $sysinfo{osname} = $val;
4106 elsif ($key eq 'Operating System Version') {
4107 $sysinfo{osver} = $val;
4115 # Fetch output from 'omreport about', put in sysinfo hash
4117 sub get_omreport_about {
4118 if (open my $OM, '-|', "$omreport about -fmt ssv") {
4122 if (m/\A Version;(.+) \z/xms) {
4132 # Fetch chassis info via SNMP, put in sysinfo hash
4134 sub get_snmp_chassis_info {
4137 '1.3.6.1.4.1.674.10892.1.300.10.1.9.1' => 'chassisModelName',
4138 '1.3.6.1.4.1.674.10892.1.300.10.1.11.1' => 'chassisServiceTagName',
4139 '1.3.6.1.4.1.674.10892.1.300.10.1.48.1' => 'chassisSystemRevisionName',
4142 my $chassisInformationTable = '1.3.6.1.4.1.674.10892.1.300.10.1';
4143 my $result = $snmp_session->get_table(-baseoid => $chassisInformationTable);
4145 if (defined $result) {
4146 foreach my $oid (keys %{ $result }) {
4147 if (exists $chassis_oid{$oid} and $chassis_oid{$oid} eq 'chassisModelName') {
4148 $sysinfo{model} = $result->{$oid};
4149 $sysinfo{model} =~ s{\s+\z}{}xms; # remove trailing whitespace
4151 elsif (exists $chassis_oid{$oid} and $chassis_oid{$oid} eq 'chassisServiceTagName') {
4152 $sysinfo{serial} = $result->{$oid};
4154 elsif (exists $chassis_oid{$oid} and $chassis_oid{$oid} eq 'chassisSystemRevisionName') {
4155 $sysinfo{rev} = $result->{$oid};
4160 my $msg = sprintf 'SNMP ERROR getting chassis info: %s',
4161 $snmp_session->error;
4162 report('other', $msg, $E_UNKNOWN);
4168 # Fetch BIOS info via SNMP, put in sysinfo hash
4170 sub get_snmp_chassis_bios {
4173 '1.3.6.1.4.1.674.10892.1.300.50.1.7.1.1' => 'systemBIOSReleaseDateName',
4174 '1.3.6.1.4.1.674.10892.1.300.50.1.8.1.1' => 'systemBIOSVersionName',
4177 my $systemBIOSTable = '1.3.6.1.4.1.674.10892.1.300.50.1';
4178 my $result = $snmp_session->get_table(-baseoid => $systemBIOSTable);
4180 if (defined $result) {
4181 foreach my $oid (keys %{ $result }) {
4182 if (exists $bios_oid{$oid} and $bios_oid{$oid} eq 'systemBIOSReleaseDateName') {
4183 $sysinfo{biosdate} = $result->{$oid};
4184 $sysinfo{biosdate} =~ s{\A (\d{4})(\d{2})(\d{2}).*}{$2/$3/$1}xms;
4186 elsif (exists $bios_oid{$oid} and $bios_oid{$oid} eq 'systemBIOSVersionName') {
4187 $sysinfo{bios} = $result->{$oid};
4192 my $msg = sprintf 'SNMP ERROR getting BIOS info: %s',
4193 $snmp_session->error;
4194 report('other', $msg, $E_UNKNOWN);
4200 # Fetch OS info via SNMP, put in sysinfo hash
4202 sub get_snmp_system_operatingsystem {
4205 '1.3.6.1.4.1.674.10892.1.400.10.1.6.1' => 'operatingSystemOperatingSystemName',
4206 '1.3.6.1.4.1.674.10892.1.400.10.1.7.1' => 'operatingSystemOperatingSystemVersionName',
4209 my $operatingSystemTable = '1.3.6.1.4.1.674.10892.1.400.10.1';
4210 my $result = $snmp_session->get_table(-baseoid => $operatingSystemTable);
4212 if (defined $result) {
4213 foreach my $oid (keys %{ $result }) {
4214 if (exists $os_oid{$oid} and $os_oid{$oid} eq 'operatingSystemOperatingSystemName') {
4215 $sysinfo{osname} = ($result->{$oid});
4217 elsif (exists $os_oid{$oid} and $os_oid{$oid} eq 'operatingSystemOperatingSystemVersionName') {
4218 $sysinfo{osver} = $result->{$oid};
4223 my $msg = sprintf 'SNMP ERROR getting OS info: %s',
4224 $snmp_session->error;
4225 report('other', $msg, $E_UNKNOWN);
4231 # Fetch OMSA version via SNMP, put in sysinfo hash
4233 sub get_snmp_about {
4234 # systemManagementSoftwareGlobalVersionName
4235 my $oid = '1.3.6.1.4.1.674.10892.1.100.10.0';
4236 my $result = $snmp_session->get_request(-varbindlist => [$oid]);
4238 if (defined $result) {
4239 $sysinfo{om} = exists $result->{$oid} && $result->{$oid} ne q{}
4240 ? $result->{$oid} : 'unknown';
4243 my $msg = sprintf 'SNMP ERROR: Getting OMSA version failed: %s', $snmp_session->error;
4244 report('other', $msg, $E_UNKNOWN);
4250 # Collects some information about the system
4254 # Get system model and serial number
4255 $snmp ? get_snmp_chassis_info() : get_omreport_chassis_info();
4257 # Get BIOS information. Only if needed
4258 if ( $opt{okinfo} >= 1
4260 or (defined $opt{postmsg} and $opt{postmsg} =~ m/[%][bd]/xms) ) {
4261 $snmp ? get_snmp_chassis_bios() : get_omreport_chassis_bios();
4264 # Get OMSA information. Only if needed
4265 if ($opt{okinfo} >= 3 or $opt{debug}) {
4266 $snmp ? get_snmp_about() : get_omreport_about();
4269 # Return now if debug
4270 return if $opt{debug};
4272 # Get OS information. Only if needed
4273 if (defined $opt{postmsg} and $opt{postmsg} =~ m/[%][or]/xms) {
4274 $snmp ? get_snmp_system_operatingsystem() : get_omreport_system_operatingsystem();
4281 # Helper function for running omreport when the results are strictly
4283 sub run_omreport_info {
4284 my $command = shift;
4288 # Run omreport and fetch output
4289 my $rawtext = slurp_command("$omreport $command -fmt ssv 2>&1");
4291 # Parse output, store in array
4292 for ((split /\n/xms, $rawtext)) {
4293 if (m/\A Error/xms) {
4294 my $msg = "Problem running 'omreport $command': $_";
4295 report('other', $msg, $E_UNKNOWN);
4297 next if !m/;/xms; # ignore lines with less than two fields
4298 my @vals = split m/;/xms;
4299 $output{$vals[0]} = $vals[1];
4302 # Finally, return the collected information
4306 # Get various firmware information (BMC, RAC)
4307 sub get_firmware_info {
4308 my @snmp_output = ();
4309 my %nrpe_output = ();
4314 '1.3.6.1.4.1.674.10892.1.300.60.1.7.1' => 'firmwareType',
4315 '1.3.6.1.4.1.674.10892.1.300.60.1.8.1' => 'firmwareTypeName',
4316 '1.3.6.1.4.1.674.10892.1.300.60.1.11.1' => 'firmwareVersionName',
4319 my $firmwareTable = '1.3.6.1.4.1.674.10892.1.300.60.1';
4320 my $result = $snmp_session->get_table(-baseoid => $firmwareTable);
4322 # Some don't have this OID, this is ok
4323 if (!defined $result) {
4327 @snmp_output = @{ get_snmp_output($result, \%fw_oid) };
4330 %nrpe_output = %{ run_omreport_info("$omopt_chassis info") };
4333 my %fw_type # Firmware types
4335 1 => 'other', # other than following values
4336 2 => 'unknown', # unknown
4337 3 => 'systemBIOS', # System BIOS
4338 4 => 'embeddedSystemManagementController', # Embedded System Management Controller
4339 5 => 'powerSupplyParallelingBoard', # Power Supply Paralleling Board
4340 6 => 'systemBackPlane', # System (Primary) Backplane
4341 7 => 'powerVault2XXSKernel', # PowerVault 2XXS Kernel
4342 8 => 'powerVault2XXSApplication', # PowerVault 2XXS Application
4343 9 => 'frontPanel', # Front Panel Controller
4344 10 => 'baseboardManagementController', # Baseboard Management Controller
4345 11 => 'hotPlugPCI', # Hot Plug PCI Controller
4346 12 => 'sensorData', # Sensor Data Records
4347 13 => 'peripheralBay', # Peripheral Bay Backplane
4348 14 => 'secondaryBackPlane', # Secondary Backplane for ESM 2 systems
4349 15 => 'secondaryBackPlaneESM3And4', # Secondary Backplane for ESM 3 and 4 systems
4350 16 => 'rac', # Remote Access Controller
4351 17 => 'imc' # Integrated Management Controller
4356 foreach my $out (@snmp_output) {
4357 if ($fw_type{$out->{firmwareType}} eq 'baseboardManagementController') {
4358 $sysinfo{'bmc'} = 1;
4359 $sysinfo{'bmc_fw'} = $out->{firmwareVersionName};
4361 elsif ($fw_type{$out->{firmwareType}} =~ m{\A rac|imc \z}xms) {
4362 my $name = $out->{firmwareTypeName}; $name =~ s/\s//gxms;
4363 $sysinfo{'rac'} = 1;
4364 $sysinfo{'rac_name'} = $name;
4365 $sysinfo{'rac_fw'} = $out->{firmwareVersionName};
4370 foreach my $key (keys %nrpe_output) {
4371 next if !defined $nrpe_output{$key};
4372 if ($key eq 'BMC Version' or $key eq 'Baseboard Management Controller Version') {
4373 $sysinfo{'bmc'} = 1;
4374 $sysinfo{'bmc_fw'} = $nrpe_output{$key};
4376 elsif ($key =~ m{\A (i?DRAC)\s*(\d?)\s+Version}xms) {
4378 $sysinfo{'rac'} = 1;
4379 $sysinfo{'rac_fw'} = $nrpe_output{$key};
4380 $sysinfo{'rac_name'} = $name;
4390 #=====================================================================
4392 #=====================================================================
4394 # Here we do the actual checking of components
4395 # Check global status if applicable
4397 $globalstatus = check_global();
4400 # Do multiple selected checks
4401 if ($check{storage}) { check_storage(); }
4402 if ($check{memory}) { check_memory(); }
4403 if ($check{fans}) { check_fans(); }
4404 if ($check{power}) { check_powersupplies(); }
4405 if ($check{temp}) { check_temperatures(); }
4406 if ($check{cpu}) { check_processors(); }
4407 if ($check{voltage}) { check_volts(); }
4408 if ($check{batteries}) { check_batteries(); }
4409 if ($check{amperage}) { check_pwrmonitoring(); }
4410 if ($check{intrusion}) { check_intrusion(); }
4411 if ($check{alertlog}) { check_alertlog(); }
4412 if ($check{esmlog}) { check_esmlog(); }
4413 if ($check{esmhealth}) { check_esmlog_health(); }
4416 #---------------------------------------------------------------------
4418 #---------------------------------------------------------------------
4429 # Get system information
4432 # Get firmware info if requested via option
4433 if ($opt{okinfo} >= 1) {
4434 get_firmware_info();
4437 # Close SNMP session
4439 $snmp_session->close;
4444 print " System: $sysinfo{model}", defined $sysinfo{rev} ? " $sysinfo{rev}\n" : "\n";
4445 print " ServiceTag: $sysinfo{serial}";
4446 print q{ } x (25 - length $sysinfo{serial}), "OMSA version: $sysinfo{om}\n";
4447 print " BIOS/date: $sysinfo{bios} $sysinfo{biosdate}";
4448 print q{ } x (25 - length "$sysinfo{bios} $sysinfo{biosdate}"), "Plugin version: $VERSION\n";
4449 if ($#report_storage >= 0) {
4450 print "-----------------------------------------------------------------------------\n";
4451 print " Storage Components \n";
4452 print "=============================================================================\n";
4453 print " STATE | ID | MESSAGE TEXT \n";
4454 print "---------+----------+--------------------------------------------------------\n";
4455 foreach (@report_storage) {
4456 my ($msg, $level, $nexus) = @{$_};
4457 print q{ } x (8 - length $reverse_exitcode{$level}) . "$reverse_exitcode{$level} | "
4458 . q{ } x (8 - length $nexus) . "$nexus | $msg\n";
4459 $nagios_alert_count{$reverse_exitcode{$level}}++;
4462 if ($#report_chassis >= 0) {
4463 print "-----------------------------------------------------------------------------\n";
4464 print " Chassis Components \n";
4465 print "=============================================================================\n";
4466 print " STATE | ID | MESSAGE TEXT \n";
4467 print "---------+------+------------------------------------------------------------\n";
4468 foreach (@report_chassis) {
4469 my ($msg, $level, $nexus) = @{$_};
4470 print q{ } x (8 - length $reverse_exitcode{$level}) . "$reverse_exitcode{$level} | "
4471 . q{ } x (4 - length $nexus) . "$nexus | $msg\n";
4472 $nagios_alert_count{$reverse_exitcode{$level}}++;
4475 if ($#report_other >= 0) {
4476 print "-----------------------------------------------------------------------------\n";
4477 print " Other messages \n";
4478 print "=============================================================================\n";
4479 print " STATE | MESSAGE TEXT \n";
4480 print "---------+-------------------------------------------------------------------\n";
4481 foreach (@report_other) {
4482 my ($msg, $level, $nexus) = @{$_};
4483 print q{ } x (8 - length $reverse_exitcode{$level}) . "$reverse_exitcode{$level} | $msg\n";
4484 $nagios_alert_count{$reverse_exitcode{$level}}++;
4489 my $c = 0; # counter to determine linebreaks
4491 # Run through each message, sorted by severity level
4493 foreach (sort {$a->[1] < $b->[1]} (@report_storage, @report_chassis, @report_other)) {
4494 my ($msg, $level, $nexus) = @{ $_ };
4495 next ALERT if $level == $E_OK;
4497 if (defined $opt{only}) {
4498 # If user wants only critical alerts
4499 next ALERT if ($opt{only} eq 'critical' and $level == $E_WARNING);
4501 # If user wants only warning alerts
4502 next ALERT if ($opt{only} eq 'warning' and $level == $E_CRITICAL);
4505 # Prefix with service tag if specified with option '-i|--info'
4507 if (defined $opt{htmlinfo}) {
4508 $msg = '[<a href="' . warranty_url($sysinfo{serial})
4509 . "\">$sysinfo{serial}</a>] " . $msg;
4512 $msg = "[$sysinfo{serial}] " . $msg;
4516 # Prefix with nagios level if specified with option '--state'
4517 $msg = $reverse_exitcode{$level} . ": $msg" if $opt{state};
4519 # Prefix with one-letter nagios level if specified with option '--short-state'
4520 $msg = (substr $reverse_exitcode{$level}, 0, 1) . ": $msg" if $opt{shortstate};
4522 ($c++ == 0) ? print $msg : print $linebreak, $msg;
4524 $nagios_alert_count{$reverse_exitcode{$level}}++;
4528 # Determine our exit code
4530 $exit_code = $E_UNKNOWN if $nagios_alert_count{'UNKNOWN'} > 0;
4531 $exit_code = $E_WARNING if $nagios_alert_count{'WARNING'} > 0;
4532 $exit_code = $E_CRITICAL if $nagios_alert_count{'CRITICAL'} > 0;
4534 # Global status via SNMP.. extra safety check
4535 if ($globalstatus != $E_OK && $exit_code == $E_OK && !defined $opt{only}) {
4536 print "OOPS! Something is wrong with this server, but I don't know what. ";
4537 print "The global system health status is $reverse_exitcode{$globalstatus}, ";
4538 print "but every component check is OK. This may be a bug in the Nagios plugin, ";
4539 print "please file a bug report.\n";
4544 if ($exit_code == $E_OK && defined $opt{only} && $opt{only} !~ m{\A critical|warning|chassis \z}xms && !$opt{debug}) {
4546 = ( 'storage' => "STORAGE OK - $count{pdisk} physical drives, $count{vdisk} logical drives",
4547 'fans' => $count{fan} == 0 && $blade ? 'OK - blade system with no fan probes' : "FANS OK - $count{fan} fan probes checked",
4548 'temp' => "TEMPERATURES OK - $count{temp} temperature probes checked",
4549 'memory' => "MEMORY OK - $count{dimm} memory modules, $count{mem} MB total memory",
4550 'power' => $count{power} == 0 ? 'OK - no instrumented power supplies found' : "POWER OK - $count{power} power supplies checked",
4551 'cpu' => "PROCESSORS OK - $count{cpu} processors checked",
4552 'voltage' => "VOLTAGE OK - $count{volt} voltage probes checked",
4553 'batteries' => $count{bat} == 0 ? 'OK - no batteries found' : "BATTERIES OK - $count{bat} batteries checked",
4554 'amperage' => $count{amp} == 0 ? 'OK - no power monitoring probes found' : "AMPERAGE OK - $count{amp} amperage (power monitoring) probes checked",
4555 'intrusion' => $count{intr} == 0 ? 'OK - no intrusion detection probes found' : "INTRUSION OK - $count{intr} intrusion detection probes checked",
4556 'alertlog' => $snmp ? 'OK - not supported via snmp' : "OK - Alert Log content: $count{alert}{Ok} ok, $count{alert}{'Non-Critical'} warning and $count{alert}{Critical} critical",
4557 'esmlog' => "OK - ESM Log content: $count{esm}{Ok} ok, $count{esm}{'Non-Critical'} warning and $count{esm}{Critical} critical",
4558 'esmhealth' => "ESM LOG OK - less than 80% used",
4561 print $okmsg{$opt{only}};
4563 elsif ($exit_code == $E_OK && !$opt{debug}) {
4564 if (defined $opt{htmlinfo}) {
4565 printf q{OK - System: '<a href="%s">%s%s</a>', SN: '<a href="%s">%s</a>'},
4566 documentation_url($sysinfo{model}), $sysinfo{model},
4567 defined $sysinfo{rev} ? " $sysinfo{rev}" : q{},
4568 warranty_url($sysinfo{serial}), $sysinfo{serial};
4571 printf q{OK - System: '%s%s', SN: '%s'},
4572 $sysinfo{model}, defined $sysinfo{rev} ? " $sysinfo{rev}" : q{}, $sysinfo{serial};
4575 if ($check{memory}) {
4577 if ($count{mem} >= 1024) {
4578 $count{mem} /= 1024;
4581 printf ', %d %s ram (%d dimms)', $count{mem}, $unit, $count{dimm};
4584 print ', not checking memory';
4587 if ($check{storage}) {
4588 printf ', %d logical drives, %d physical drives',
4589 $count{vdisk}, $count{pdisk};
4592 print ', not checking storage';
4595 if ($opt{okinfo} >= 1) {
4597 printf q{----- BIOS='%s %s'}, $sysinfo{bios}, $sysinfo{biosdate};
4599 if ($sysinfo{rac}) {
4600 printf q{, %s='%s'}, $sysinfo{rac_name}, $sysinfo{rac_fw};
4602 if ($sysinfo{bmc}) {
4603 printf q{, BMC='%s'}, $sysinfo{bmc_fw};
4607 if ($opt{okinfo} >= 2) {
4608 if ($check{storage}) {
4609 my @storageprint = ();
4610 foreach my $id (sort keys %{ $sysinfo{controller} }) {
4611 chomp $sysinfo{controller}{$id}{driver};
4612 my $msg = sprintf q{----- Ctrl %s [%s]: Fw='%s', Dr='%s'},
4613 $sysinfo{controller}{$id}{id}, $sysinfo{controller}{$id}{name},
4614 $sysinfo{controller}{$id}{firmware}, $sysinfo{controller}{$id}{driver};
4615 if (defined $sysinfo{controller}{$id}{storport}) {
4616 $msg .= sprintf q{, Storport: '%s'}, $sysinfo{controller}{$id}{storport};
4618 push @storageprint, $msg;
4620 foreach my $id (sort keys %{ $sysinfo{enclosure} }) {
4621 push @storageprint, sprintf q{----- Encl %s [%s]: Fw='%s'},
4622 $sysinfo{enclosure}{$id}->{id}, $sysinfo{enclosure}{$id}->{name},
4623 $sysinfo{enclosure}{$id}->{firmware};
4627 foreach my $line (@storageprint) {
4628 print $linebreak, $line;
4633 if ($opt{okinfo} >= 3) {
4634 print "$linebreak----- OpenManage Server Administrator (OMSA) version: '$sysinfo{om}'";
4639 if ($opt{extinfo}) {
4641 if (defined $opt{htmlinfo}) {
4642 printf '------ SYSTEM: <a href="%s">%s%s</a>, SN: <a href="%s">%s</a>',
4643 documentation_url($sysinfo{model}), $sysinfo{model},
4644 defined $sysinfo{rev} ? " $sysinfo{rev}" : q{},
4645 warranty_url($sysinfo{serial}), $sysinfo{serial};
4648 printf '------ SYSTEM: %s%s, SN: %s',
4649 $sysinfo{model}, defined $sysinfo{rev} ? " $sysinfo{rev}" : q{}, $sysinfo{serial};
4652 if (defined $opt{postmsg}) {
4654 if (-f $opt{postmsg}) {
4655 open my $POST, '<', $opt{postmsg}
4656 or ( print $linebreak
4657 and print "ERROR: Couldn't open post message file $opt{postmsg}: $!\n"
4658 and exit $E_UNKNOWN );
4664 $post = $opt{postmsg};
4666 if (defined $post) {
4668 my $mod = defined $sysinfo{rev} ? "$sysinfo{model} $sysinfo{rev}" : $sysinfo{model};
4669 $post =~ s{[%]s}{$sysinfo{serial}}gxms;
4670 $post =~ s{[%]m}{$mod}gxms;
4671 $post =~ s{[%]b}{$sysinfo{bios}}gxms;
4672 $post =~ s{[%]d}{$sysinfo{biosdate}}gxms;
4673 $post =~ s{[%]o}{$sysinfo{osname}}gxms;
4674 $post =~ s{[%]r}{$sysinfo{osver}}gxms;
4675 $post =~ s{[%]p}{$count{pdisk}}gxms;
4676 $post =~ s{[%]l}{$count{vdisk}}gxms;
4677 $post =~ s{[%]n}{$linebreak}gxms;
4678 $post =~ s{[%]{2}}{%}gxms;
4684 # Reset the WARN signal
4685 $SIG{__WARN__} = 'DEFAULT';
4687 # Print any perl warnings that have occured
4688 if (@perl_warnings) {
4689 foreach (@perl_warnings) {
4691 print "${linebreak}INTERNAL ERROR: @$_";
4693 $exit_code = $E_UNKNOWN;
4696 # Print performance data
4697 if (defined $opt{perfdata} && !$opt{debug} && @perfdata) {
4698 my $lb = $opt{perfdata} eq 'multiline' ? "\n" : q{ }; # line break for perfdata
4701 # Sort routine for performance data
4703 my %order = ( fan => 0, pwr => 1, tem => 2, enc => 3, );
4704 return ($order{(substr $a->{label}, 0, 3)} cmp $order{(substr $b->{label}, 0, 3)}) ||
4705 $a->{label} cmp $b->{label};
4708 # Print performance data sorted
4709 my $type = $opt{perfdata} eq 'minimal' ? 'mini' : 'label';
4710 print join $lb, map { "$_->{$type}=$_->{value};$_->{warn};$_->{crit}" } sort perfsort @perfdata;
4713 # Print a linebreak at the end
4714 print "\n" if !$opt{debug};
4716 # Exit with proper exit code