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 = '3.5.10-beta8';
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 'osname' => 'N/A', # OS name
373 'osver' => 'N/A', # OS version
374 'om' => 'N/A', # OMSA version
375 'bmc' => 0, # HAS baseboard management controller (BMC)
376 'rac' => 0, # HAS remote access controller (RAC)
377 'rac_name' => 'N/A', # remote access controller (RAC)
378 'bmc_fw' => 'N/A', # BMC firmware
379 'rac_fw' => 'N/A', # RAC firmware
382 # Adjust which checks to perform
383 adjust_checks() if defined $opt{check};
385 # Blacklisted components
386 %blacklist = defined $opt{blacklist} ? %{ get_blacklist() } : ();
388 # If blacklisting is in effect, don't check global health status
389 if (scalar keys %blacklist > 0) {
393 # Take into account new hardware and blades
394 $omopt_chassis = 'chassis'; # default "chassis" option to omreport
395 $omopt_system = 'system'; # default "system" option to omreport
396 $blade = 0; # if this is a blade system
398 # Some initializations and checking before we begin
400 snmp_initialize(); # initialize SNMP
401 snmp_check(); # check that SNMP works
402 snmp_detect_blade(); # detect blade via SNMP
405 # Find the omreport binary
407 # Check help output from omreport, see which options are available.
408 # Also detecting blade via omreport.
409 check_omreport_options();
413 #---------------------------------------------------------------------
415 #---------------------------------------------------------------------
418 # Store a message in one of the message arrays
421 my ($type, $msg, $exval, $id) = @_;
422 defined $id or $id = q{};
426 'storage' => \@report_storage,
427 'chassis' => \@report_chassis,
428 'other' => \@report_other,
431 return push @{ $type2array{$type} }, [ $msg, $exval, $id ];
436 # Run command, put resulting output lines in an array and return a
437 # pointer to that array
442 open my $CMD, '-|', $command
443 or do { report('other', "Couldn't run command '$command': $!", $E_UNKNOWN)
447 or do { report('other', "Couldn't close filehandle for command '$command': $!", $E_UNKNOWN)
448 and return \@lines };
453 # Run command, put resulting output in a string variable and return it
458 open my $CMD, '-|', $command
459 or do { report('other', "Couldn't run command '$command': $!", $E_UNKNOWN) and return };
460 my $rawtext = do { local $/ = undef; <$CMD> }; # slurping
463 # NOTE: We don't check the return value of close() since omreport
464 # does something weird sometimes.
472 sub snmp_initialize {
473 # Legal SNMP v3 protocols
474 my $snmp_v3_privprotocol = qr{\A des|aes|aes128|3des|3desde \z}xms;
475 my $snmp_v3_authprotocol = qr{\A md5|sha \z}xms;
477 # Parameters to Net::SNMP->session()
480 '-port' => $opt{port},
481 '-hostname' => $opt{hostname},
482 '-version' => $opt{protocol},
485 # Parameters for SNMP v3
486 if ($opt{protocol} == 3) {
488 # Username is mandatory
489 if (defined $opt{username}) {
490 $param{'-username'} = $opt{username};
493 print "SNMP ERROR: With SNMPv3 the username must be specified\n";
497 # Authpassword is optional
498 if (defined $opt{authpassword}) {
499 $param{'-authpassword'} = $opt{authpassword};
502 # Authkey is optional
503 if (defined $opt{authkey}) {
504 $param{'-authkey'} = $opt{authkey};
507 # Privpassword is optional
508 if (defined $opt{privpassword}) {
509 $param{'-privpassword'} = $opt{privpassword};
512 # Privkey is optional
513 if (defined $opt{privkey}) {
514 $param{'-privkey'} = $opt{privkey};
517 # Privprotocol is optional
518 if (defined $opt{privprotocol}) {
519 if ($opt{privprotocol} =~ m/$snmp_v3_privprotocol/xms) {
520 $param{'-privprotocol'} = $opt{privprotocol};
523 print "SNMP ERROR: Unknown privprotocol '$opt{privprotocol}', "
524 . "must be one of [des|aes|aes128|3des|3desde]\n";
529 # Authprotocol is optional
530 if (defined $opt{authprotocol}) {
531 if ($opt{authprotocol} =~ m/$snmp_v3_authprotocol/xms) {
532 $param{'-authprotocol'} = $opt{authprotocol};
535 print "SNMP ERROR: Unknown authprotocol '$opt{authprotocol}', "
536 . "must be one of [md5|sha]\n";
541 # Parameters for SNMP v2c or v1
542 elsif ($opt{protocol} == 2 or $opt{protocol} == 1) {
543 $param{'-community'} = $opt{community};
546 print "SNMP ERROR: Unknown SNMP version '$opt{protocol}'\n";
550 # Try to initialize the SNMP session
551 if ( eval { require Net::SNMP; 1 } ) {
552 ($snmp_session, $snmp_error) = Net::SNMP->session( %param );
553 if (!defined $snmp_session) {
554 printf "SNMP: %s\n", $snmp_error;
559 print "ERROR: You need perl module Net::SNMP to run $NAME in SNMP mode\n";
566 # Checking if SNMP works by probing for "chassisModelName", which all
567 # servers should have
570 my $chassisModelName = '1.3.6.1.4.1.674.10892.1.300.10.1.9.1';
571 my $result = $snmp_session->get_request(-varbindlist => [$chassisModelName]);
573 # Typically if remote host isn't responding
574 if (!defined $result) {
575 printf "SNMP CRITICAL: %s\n", $snmp_session->error;
579 # If OpenManage isn't installed or is not working
580 if ($result->{$chassisModelName} =~ m{\A noSuch (Instance|Object) \z}xms) {
581 print "ERROR: (SNMP) OpenManage is not installed or is not working correctly\n";
588 # Detecting blade via SNMP
590 sub snmp_detect_blade {
591 my $DellBaseBoardType = '1.3.6.1.4.1.674.10892.1.300.80.1.7.1.1';
592 my $result = $snmp_session->get_request(-varbindlist => [$DellBaseBoardType]);
594 # Identify blade. Older models (4th and 5th gen models) and/or old
595 # OMSA (4.x) don't have this OID. If we get "noSuchInstance" or
596 # similar, we assume that this isn't a blade
597 if (exists $result->{$DellBaseBoardType} && $result->{$DellBaseBoardType} eq '3') {
604 # Locate the omreport binary
607 # If user has specified path to omreport
608 if (defined $opt{omreport} and -x $opt{omreport}) {
609 $omreport = qq{"$opt{omreport}"};
613 # Possible full paths for omreport
616 '/usr/bin/omreport', # default on Linux
617 '/opt/dell/srvadmin/bin/omreport', # default on Linux with OMSA 6.2.0
618 '/opt/dell/srvadmin/oma/bin/omreport.sh', # alternate on Linux
619 '/opt/dell/srvadmin/oma/bin/omreport', # alternate on Linux
620 'C:\Program Files (x86)\Dell\SysMgt\oma\bin\omreport.exe', # default on Windows x64
621 'C:\Program Files\Dell\SysMgt\oma\bin\omreport.exe', # default on Windows x32
622 'c:\progra~1\dell\sysmgt\oma\bin\omreport.exe', # 8bit legacy default on Windows x32
623 'c:\progra~2\dell\sysmgt\oma\bin\omreport.exe', # 8bit legacy default on Windows x64
626 # Find the one to use
628 foreach my $bin (@omreport_paths) {
630 $omreport = qq{"$bin"};
635 # Exit with status=UNKNOWN if OM is not installed, or we don't
636 # have permission to execute the binary
637 if (!defined $omreport) {
638 print "ERROR: Dell OpenManage Server Administrator (OMSA) is not installed\n";
645 # Checks output from 'omreport -?' and searches for arguments to
646 # omreport, to accommodate deprecated options "chassis" and "system"
647 # (on newer hardware), as well as blade servers.
649 sub check_omreport_options {
650 foreach (@{ run_command("$omreport -? 2>&1") }) {
651 if (m/\A servermodule /xms) {
652 # If "servermodule" argument to omreport exists, use it
653 # instead of argument "system"
654 $omopt_system = 'servermodule';
656 elsif (m/\A mainsystem /xms) {
657 # If "mainsystem" argument to omreport exists, use it
658 # instead of argument "chassis"
659 $omopt_chassis = 'mainsystem';
661 elsif (m/\A modularenclosure /xms) {
662 # If "modularenclusure" argument to omreport exists, assume
663 # that this is a blade
671 # Read the blacklist option and return a hash containing the
672 # blacklisted components
678 if (scalar @{ $opt{blacklist} } >= 0) {
679 foreach my $black (@{ $opt{blacklist} }) {
682 open my $BL, '<', $black
683 or do { report('other', "Couldn't open blacklist file $black: $!", $E_UNKNOWN)
696 return {} if $#bl < 0;
698 # Parse blacklist string, put in hash
699 foreach my $black (@bl) {
700 my @comps = split m{/}xms, $black;
701 foreach my $c (@comps) {
702 next if $c !~ m/=/xms;
703 my ($key, $val) = split /=/xms, $c;
704 my @vals = split /,/xms, $val;
705 $blacklist{$key} = \@vals;
713 # Read the check option and adjust the hash %check, which is a rough
714 # list of components to be checked
719 # Adjust checking based on the '--all' option
722 if (defined $opt{only} and $opt{only} !~ m{\A critical|warning \z}xms) {
723 print qq{ERROR: Wrong simultaneous usage of the "--all" and "--only" options\n};
726 if (scalar @{ $opt{check} } > 0) {
727 print qq{ERROR: Wrong simultaneous usage of the "--all" and "--check" options\n};
731 # set the check hash to check everything
732 map { $_ = 1 } values %check;
737 # Adjust checking based on the '--only' option
738 if (defined $opt{only} and $opt{only} !~ m{\A critical|warning \z}xms) {
740 if (scalar @{ $opt{check} } > 0) {
741 print qq{ERROR: Wrong simultaneous usage of the "--only" and "--check" options\n};
744 if (! exists $check{$opt{only}} && $opt{only} ne 'chassis') {
745 print qq{ERROR: "$opt{only}" is not a known keyword for the "--only" option\n};
749 # reset the check hash
750 map { $_ = 0 } values %check;
752 # adjust the check hash
753 if ($opt{only} eq 'chassis') {
754 map { $check{$_} = 1 } qw(memory fans power temp cpu voltage
755 batteries amperage intrusion esmhealth);
758 $check{$opt{only}} = 1;
764 # Adjust checking based on the '--check' option
765 if (scalar @{ $opt{check} } >= 0) {
766 foreach my $check (@{ $opt{check} }) {
769 open my $CL, '<', $check
770 or do { report('other', "Couldn't open check file $check: $!", $E_UNKNOWN) and return };
783 # Parse checklist string, put in hash
784 foreach my $check (@cl) {
785 my @checks = split /,/xms, $check;
786 foreach my $c (@checks) {
787 next if $c !~ m/=/xms;
788 my ($key, $val) = split /=/xms, $c;
793 # Check if we should check global health status
795 foreach (keys %check) {
796 next CHECK_KEY if $_ eq 'esmlog'; # not part of global status
797 next CHECK_KEY if $_ eq 'alertlog'; # not part of global status
799 if ($check{$_} == 0) { # found something with checking turned off
809 # Runs omreport and returns an array of anonymous hashes containing
811 # Takes one argument: string containing parameters to omreport
818 # Errors that are OK. Some low-end poweredge (and blades) models
819 # don't have RAID controllers, intrusion detection sensor, or
820 # redundant/instrumented power supplies etc.
823 Intrusion\sinformation\sis\snot\sfound\sfor\sthis\ssystem # No intrusion probe
824 | No\sinstrumented\spower\ssupplies\sfound\son\sthis\ssystem # No instrumented PS (blades/low-end)
825 | No\scontrollers\sfound # No RAID controller
826 | No\sbattery\sprobes\sfound\son\sthis\ssystem # No battery probes
827 | Invalid\scommand:\spwrmonitoring # Older OMSAs lack this command(?)
828 # | Current\sprobes\snot\sfound # OMSA + RHEL5.4 bug
831 # Errors that are OK on blade servers
834 No\sfan\sprobes\sfound\son\sthis\ssystem # No fan probes
837 # Run omreport and fetch output
838 my $rawtext = slurp_command("$omreport $command -fmt ssv 2>&1");
839 return [] if !defined $rawtext;
841 # Workaround for Openmanage BUG introduced in OMSA 5.5.0
842 $rawtext =~ s{\n;}{;}gxms if $command eq 'storage controller';
844 # Openmanage sometimes puts a linebreak between "Error" and the
846 $rawtext =~ s{^Error\s*\n}{Error: }xms;
848 # Parse output, store in array
849 for ((split m{\n}xms, $rawtext)) {
851 next if m{$ok_errors}xms;
852 next if ($blade and m{$ok_blade_errors}xms);
853 report('other', "Problem running 'omreport $command': $_", $E_UNKNOWN);
856 next if !m/(.*?;){2}/xms; # ignore lines with less than 3 fields
857 my @vals = split /;/xms;
858 if ($vals[0] =~ m/\A (Index|ID|Severity|Processor|Current\sSpeed) \z/xms) {
863 push @output, { map { $_ => $vals[$i++] } @keys };
868 # Finally, return the collected information
874 # Checks if a component is blacklisted. Returns 1 if the component is
875 # blacklisted, 0 otherwise. Takes two arguments:
876 # arg1: component name
877 # arg2: component id or index
880 my $name = shift; # component name
881 my $id = shift; # component id
882 my $ret = 0; # return value
884 if (defined $blacklist{$name}) {
885 foreach my $comp (@{ $blacklist{$name} }) {
886 if (defined $id and ($comp eq $id or uc($comp) eq 'ALL')) {
895 # Converts the NexusID from SNMP to our version
898 $nexus =~ s{\A \\}{}xms;
899 $nexus =~ s{\\}{:}gxms;
903 # Sets custom temperature thresholds based on user supplied options
904 sub custom_temperature_thresholds {
905 my $type = shift; # type of threshold, either w (warning) or c (critical)
906 my %thres = (); # will contain the thresholds
907 my @limits = (); # holds the input
909 my @opt = $type eq 'w' ? @{ $opt{warning} } : @{ $opt{critical} };
911 if (scalar @opt >= 0) {
912 foreach my $t (@opt) {
916 or do { report('other', "Couldn't open temperature threshold file $t: $!",
917 $E_UNKNOWN) and return {} };
928 # Parse checklist string, put in hash
929 foreach my $th (@limits) {
930 my @tmp = split m{,}xms, $th;
931 foreach my $t (@tmp) {
932 next if $t !~ m{=}xms;
933 my ($key, $val) = split m{=}xms, $t;
934 if ($val =~ m{/}xms) {
935 my ($max, $min) = split m{/}xms, $val;
936 $thres{$key}{max} = $max;
937 $thres{$key}{min} = $min;
940 $thres{$key}{max} = $val;
949 # Gets the output from SNMP result according to the OIDs checked
950 sub get_snmp_output {
951 my ($result,$oidref) = @_;
955 foreach my $oid (keys %{ $result }) {
957 $short =~ s{\s}{}gxms; # remove whitespace
958 $short =~ s{\A (.+) \. (\d+) \z}{$1}xms; # remove last number
960 if (exists $oidref->{$short}) {
961 $temp[$id]{$oidref->{$short}} = $result->{$oid};
965 # Remove any empty indexes
966 foreach my $out (@temp) {
976 # Map the controller or other item in-place
978 my ($key, $val, $list) = @_;
980 foreach my $lst (@{ $list }) {
981 if (!exists $lst->{$key}) {
988 # Return the URL for official Dell documentation for a specific
990 sub documentation_url {
993 # create model short form, e.g. "r710"
994 $model =~ s{\A PowerEdge \s (.+?) \z}{lc($1)}exms;
996 # special case for blades (e.g. M600, M710), they have common
998 $model =~ s{\A m\d+ \z}{m}xms;
1000 return 'http://support.dell.com/support/edocs/systems/pe' . $model . '/';
1003 # Return the URL for warranty information for a server with a given
1004 # serial number (servicetag)
1008 # Dell support sites for different parts of the world
1011 'emea' => 'http://support.euro.dell.com/support/topics/topic.aspx/emea/shared/support/my_systems_info/',
1012 'ap' => 'http://supportapj.dell.com/support/topics/topic.aspx/ap/shared/support/my_systems_info/en/details?',
1013 'glob' => 'http://support.dell.com/support/topics/global.aspx/support/my_systems_info/details?',
1016 # warranty URLs for different country codes
1020 'at' => $supportsite{emea} . 'de/details?c=at&l=de&ServiceTag=', # Austria
1021 'be' => $supportsite{emea} . 'nl/details?c=be&l=nl&ServiceTag=', # Belgium
1022 'cz' => $supportsite{emea} . 'cs/details?c=cz&l=cs&ServiceTag=', # Czech Republic
1023 'de' => $supportsite{emea} . 'de/details?c=de&l=de&ServiceTag=', # Germany
1024 'dk' => $supportsite{emea} . 'da/details?c=dk&l=da&ServiceTag=', # Denmark
1025 'es' => $supportsite{emea} . 'es/details?c=es&l=es&ServiceTag=', # Spain
1026 'fi' => $supportsite{emea} . 'fi/details?c=fi&l=fi&ServiceTag=', # Finland
1027 'fr' => $supportsite{emea} . 'fr/details?c=fr&l=fr&ServiceTag=', # France
1028 'gr' => $supportsite{emea} . 'en/details?c=gr&l=el&ServiceTag=', # Greece
1029 'it' => $supportsite{emea} . 'it/details?c=it&l=it&ServiceTag=', # Italy
1030 'il' => $supportsite{emea} . 'en/details?c=il&l=en&ServiceTag=', # Israel
1031 'me' => $supportsite{emea} . 'en/details?c=me&l=en&ServiceTag=', # Middle East
1032 'no' => $supportsite{emea} . 'no/details?c=no&l=no&ServiceTag=', # Norway
1033 'nl' => $supportsite{emea} . 'nl/details?c=nl&l=nl&ServiceTag=', # The Netherlands
1034 'pl' => $supportsite{emea} . 'pl/details?c=pl&l=pl&ServiceTag=', # Poland
1035 'pt' => $supportsite{emea} . 'en/details?c=pt&l=pt&ServiceTag=', # Portugal
1036 'ru' => $supportsite{emea} . 'ru/details?c=ru&l=ru&ServiceTag=', # Russia
1037 'se' => $supportsite{emea} . 'sv/details?c=se&l=sv&ServiceTag=', # Sweden
1038 'uk' => $supportsite{emea} . 'en/details?c=uk&l=en&ServiceTag=', # United Kingdom
1039 'za' => $supportsite{emea} . 'en/details?c=za&l=en&ServiceTag=', # South Africa
1041 'br' => $supportsite{glob} . 'c=br&l=pt&ServiceTag=', # Brazil
1042 'ca' => $supportsite{glob} . 'c=ca&l=en&ServiceTag=', # Canada
1043 'mx' => $supportsite{glob} . 'c=mx&l=es&ServiceTag=', # Mexico
1044 'us' => $supportsite{glob} . 'c=us&l=en&ServiceTag=', # USA
1046 'au' => $supportsite{ap} . 'c=au&l=en&ServiceTag=', # Australia
1047 'cn' => $supportsite{ap} . 'c=cn&l=zh&ServiceTag=', # China
1048 'in' => $supportsite{ap} . 'c=in&l=en&ServiceTag=', # India
1050 'XX' => $supportsite{glob} . 'ServiceTag=', # default
1053 if (exists $url{$opt{htmlinfo}}) {
1054 return $url{$opt{htmlinfo}} . $tag;
1057 return $url{XX} . $tag;
1062 # This helper function returns the corresponding value of a hash key,
1063 # but takes into account that the key may not exist
1065 my $key = shift || return undef;
1067 return exists $hash->{$key} ? $hash->{$key} : "Undefined value $key";
1072 #---------------------------------------------------------------------
1074 #---------------------------------------------------------------------
1076 #-----------------------------------------
1077 # Check global health status
1078 #-----------------------------------------
1084 # Checks global status, i.e. both storage and chassis
1086 my $systemStateGlobalSystemStatus = '1.3.6.1.4.1.674.10892.1.200.10.1.2.1';
1087 my $result = $snmp_session->get_request(-varbindlist => [$systemStateGlobalSystemStatus]);
1088 if (!defined $result) {
1089 printf "SNMP ERROR [global]: %s\n", $snmp_error;
1092 $health = $status2nagios{$snmp_status{$result->{$systemStateGlobalSystemStatus}}};
1096 # NB! This does not check storage, only chassis...
1098 foreach (@{ run_command("$omreport $omopt_system -fmt ssv") }) {
1100 next if m/\A SEVERITY;COMPONENT/xms;
1101 if (m/\A (.+?);Main\sSystem(\sChassis)? /xms) {
1102 $health = $status2nagios{$1};
1113 #-----------------------------------------
1114 # STORAGE: Check controllers
1115 #-----------------------------------------
1116 sub check_controllers {
1117 return if blacklisted('ctrl', 'all');
1126 my $firmware = undef;
1128 my $minstdr = undef; # Minimum required Storport driver version
1129 my $stdr = undef; # Storport driver version
1135 '1.3.6.1.4.1.674.10893.1.20.130.1.1.1' => 'controllerNumber',
1136 '1.3.6.1.4.1.674.10893.1.20.130.1.1.2' => 'controllerName',
1137 '1.3.6.1.4.1.674.10893.1.20.130.1.1.5' => 'controllerState',
1138 '1.3.6.1.4.1.674.10893.1.20.130.1.1.8' => 'controllerFWVersion',
1139 '1.3.6.1.4.1.674.10893.1.20.130.1.1.38' => 'controllerComponentStatus',
1140 '1.3.6.1.4.1.674.10893.1.20.130.1.1.39' => 'controllerNexusID',
1141 '1.3.6.1.4.1.674.10893.1.20.130.1.1.41' => 'controllerDriverVersion',
1142 '1.3.6.1.4.1.674.10893.1.20.130.1.1.44' => 'controllerMinFWVersion',
1143 '1.3.6.1.4.1.674.10893.1.20.130.1.1.45' => 'controllerMinDriverVersion',
1144 '1.3.6.1.4.1.674.10893.1.20.130.1.1.55' => 'controllerStorportDriverVersion',
1145 '1.3.6.1.4.1.674.10893.1.20.130.1.1.56' => 'controllerMinRequiredStorportVer',
1148 # We use get_table() here for the odd case where a server has
1149 # two or more controllers, and where some OIDs are missing on
1150 # one of the controllers.
1151 my $controllerTable = '1.3.6.1.4.1.674.10893.1.20.130.1';
1152 my $result = $snmp_session->get_table(-baseoid => $controllerTable);
1154 # No controllers is OK
1155 return if !defined $result;
1157 @output = @{ get_snmp_output($result, \%ctrl_oid) };
1160 @output = @{ run_omreport('storage controller') };
1174 foreach my $out (@output) {
1176 # $id = $out->{controllerNumber} - 1;
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;
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 = $out->{arrayDiskSmartAlertIndication} == 2 ? 1 : 0;
1423 $nexus = convert_nexus($out->{arrayDiskNexusID});
1424 $vendor = $out->{arrayDiskVendor};
1425 $product = $out->{arrayDiskProductID};
1426 $spare = get_hashval($out->{arrayDiskSpareState}, \%spare_state);
1427 $bus = exists $out->{arrayDiskBusType}
1428 ? get_hashval($out->{arrayDiskBusType}, \%bus_type) : undef;
1429 $media = exists $out->{arrayDiskMediaType}
1430 ? get_hashval($out->{arrayDiskMediaType}, \%media_type) : undef;
1431 $capacity = $out->{arrayDiskLengthInMB} * 1024**2;
1432 if (exists $out->{arrayDiskEnclosureConnectionControllerNumber}) {
1433 $ctrl = $snmp_controller{$out->{arrayDiskEnclosureConnectionControllerNumber}};
1435 elsif (exists $out->{arrayDiskChannelConnectionControllerNumber}) {
1436 $ctrl = $snmp_controller{$out->{arrayDiskChannelConnectionControllerNumber}};
1439 # last resort... use the nexus id
1441 $ctrl =~ s{\A (\d+) : .* \z}{$1}xms;
1446 $name = $out->{'Name'};
1447 $state = $out->{'State'};
1448 $status = $out->{'Status'};
1449 $fpred = lc($out->{'Failure Predicted'}) eq 'yes' ? 1 : 0;
1450 $progr = ' [' . $out->{'Progress'} . ']';
1451 $ctrl = $out->{'ctrl'};
1452 $nexus = join q{:}, $out->{ctrl}, $id;
1453 $vendor = $out->{'Vendor ID'};
1454 $product = $out->{'Product ID'};
1455 $media = $out->{'Media'};
1456 $spare = $out->{'Hot Spare'};
1457 $bus = $out->{'Bus Protocol'};
1458 $capacity = $out->{'Capacity'};
1459 $capacity =~ s{\A .*? \((\d+) \s bytes\) \z}{$1}xms;
1462 next PDISK if blacklisted('pdisk', $nexus);
1465 $vendor =~ s{\s+\z}{}xms; # remove trailing whitespace
1466 $product =~ s{\s+\z}{}xms; # remove trailing whitespace
1469 if ($spare eq 'Global') { $spare = 'Global HS'; }
1470 elsif ($spare eq 'Dedicated') { $spare = 'Dedicated HS'; }
1471 elsif ($spare !~ m{\A Global|Dedicated}xms) { $spare = undef; }
1473 # Calculate human readable capacity
1474 $capacity = ceil($capacity / 1000**3) >= 1000
1475 ? sprintf '%.1fTB', ($capacity / 1000**4)
1476 : sprintf '%.0fGB', ($capacity / 1000**3);
1477 $capacity = '450GB' if $capacity eq '449GB'; # quick fix for 450GB disks
1478 $capacity = '300GB' if $capacity eq '299GB'; # quick fix for 300GB disks
1479 $capacity = '146GB' if $capacity eq '147GB'; # quick fix for 146GB disks
1480 $capacity = '100GB' if $capacity eq '99GB'; # quick fix for 100GB disks
1482 # Capitalize only the first letter of the vendor name
1483 $vendor = (substr $vendor, 0, 1) . lc (substr $vendor, 1, length $vendor);
1485 # Remove unnecessary trademark rubbish from vendor name
1486 $vendor =~ s{\(tm\)\z}{}xms;
1488 # bus and media aren't always defined
1490 if (defined $bus && defined $media) { $busmedia = "$bus-$media "; }
1491 elsif (defined $bus && ! defined $media) { $busmedia = "$bus "; }
1492 elsif (! defined $bus && defined $media) { $busmedia = "$media "; }
1494 # Special case: Failure predicted
1496 my $msg = sprintf '%s [%s %s, %s] on ctrl %d needs attention: Failure Predicted',
1497 $name, $vendor, $product, $capacity, $ctrl;
1498 $msg .= " ($state)" if $state ne 'Predictive failure';
1499 report('storage', $msg,
1500 ($status2nagios{$status} == $E_CRITICAL ? $E_CRITICAL : $E_WARNING), $nexus);
1502 # Special case: Rebuilding / Replacing
1503 elsif ($state =~ m{\A Rebuilding|Replacing \z}xms) {
1504 my $msg = sprintf '%s [%s %s, %s] on ctrl %d is %s%s',
1505 $name, $vendor, $product, $capacity, $ctrl, $state, $progr;
1506 report('storage', $msg, $E_WARNING, $nexus);
1509 elsif ($status ne 'Ok') {
1510 my $msg = sprintf '%s [%s %s, %s] on ctrl %d needs attention: %s',
1511 $name, $vendor, $product, $capacity, $ctrl, $state;
1512 report('storage', $msg, $status2nagios{$status}, $nexus);
1516 my $msg = sprintf '%s [%s%s] on ctrl %d is %s',
1517 $name, $busmedia, $capacity, $ctrl, $state;
1518 if (defined $spare) { $msg .= " ($spare)"; }
1519 report('storage', $msg, $E_OK, $nexus);
1526 #-----------------------------------------
1527 # STORAGE: Check logical drives
1528 #-----------------------------------------
1529 sub check_virtual_disks {
1530 return if $#controllers == -1;
1531 return if blacklisted('vdisk', 'all');
1548 '1.3.6.1.4.1.674.10893.1.20.140.1.1.3' => 'virtualDiskDeviceName',
1549 '1.3.6.1.4.1.674.10893.1.20.140.1.1.4' => 'virtualDiskState',
1550 '1.3.6.1.4.1.674.10893.1.20.140.1.1.6' => 'virtualDiskLengthInMB',
1551 '1.3.6.1.4.1.674.10893.1.20.140.1.1.13' => 'virtualDiskLayout',
1552 '1.3.6.1.4.1.674.10893.1.20.140.1.1.17' => 'virtualDiskTargetID',
1553 '1.3.6.1.4.1.674.10893.1.20.140.1.1.20' => 'virtualDiskComponentStatus',
1554 '1.3.6.1.4.1.674.10893.1.20.140.1.1.21' => 'virtualDiskNexusID',
1557 if ($opt{use_get_table}) {
1558 my $virtualDiskTable = '1.3.6.1.4.1.674.10893.1.20.140.1';
1559 $result = $snmp_session->get_table(-baseoid => $virtualDiskTable);
1562 $result = $snmp_session->get_entries(-columns => [keys %vdisk_oid]);
1565 # No logical drives is OK
1566 return if !defined $result;
1568 @output = @{ get_snmp_output($result, \%vdisk_oid) };
1571 foreach my $c (@controllers) {
1572 push @output, @{ run_omreport("storage vdisk controller=$c") };
1573 map_item('ctrl', $c, \@output);
1586 16 => 'Regenerating',
1589 32 => 'Reconstructing',
1590 35 => 'Initializing',
1591 36 => 'Background Initialization',
1592 38 => 'Resynching Paused',
1593 52 => 'Permanently Degraded',
1594 54 => 'Degraded Redundancy',
1599 1 => 'Concatenated',
1606 19 => 'Concatenated RAID-1',
1610 # Check virtual disks on each of the controllers
1612 foreach my $out (@output) {
1614 $id = $out->{virtualDiskTargetID};
1615 $dev = $out->{virtualDiskDeviceName};
1616 $state = get_hashval($out->{virtualDiskState}, \%vdisk_state);
1617 $layout = get_hashval($out->{virtualDiskLayout}, \%vdisk_layout);
1618 $status = $snmp_status{$out->{virtualDiskComponentStatus}};
1619 $size = sprintf '%.2f GB', $out->{virtualDiskLengthInMB} / 1024;
1620 $progr = q{}; # can't get this from SNMP(?)
1621 $nexus = convert_nexus($out->{virtualDiskNexusID});
1625 $dev = $out->{'Device Name'};
1626 $state = $out->{State};
1627 $status = $out->{Status};
1628 $layout = $out->{Layout};
1629 $size = $out->{Size};
1630 $progr = ' [' . $out->{Progress} . ']';
1631 $size =~ s{\A (.*GB).* \z}{$1}xms;
1632 $nexus = join q{:}, $out->{ctrl}, $id;
1633 $ctrl = $out->{ctrl};
1636 next VDISK if blacklisted('vdisk', $nexus);
1639 # The device name is undefined sometimes
1640 $dev = q{} if !defined $dev;
1642 # Special case: Regenerating
1643 if ($state eq 'Regenerating') {
1644 my $msg = sprintf q{Logical Drive '%s' [%s, %s] is %s%s},
1645 $dev, $layout, $size, $state, $progr;
1646 report('storage', $msg, $E_WARNING, $nexus);
1649 elsif ($status ne 'Ok') {
1650 my $msg = sprintf q{Logical Drive '%s' [%s, %s] needs attention: %s},
1651 $dev, $layout, $size, $state;
1652 report('storage', $msg, $status2nagios{$status}, $nexus);
1656 my $msg = sprintf q{Logical Drive '%s' [%s, %s] is %s},
1657 $dev, $layout, $size, $state;
1658 report('storage', $msg, $E_OK, $nexus);
1665 #-----------------------------------------
1666 # STORAGE: Check cache batteries
1667 #-----------------------------------------
1668 sub check_cache_battery {
1669 return if $#controllers == -1;
1670 return if blacklisted('bat', 'all');
1677 my $learn = undef; # learn state
1678 my $pred = undef; # battery's ability to be charged
1684 '1.3.6.1.4.1.674.10893.1.20.130.15.1.4' => 'batteryState',
1685 '1.3.6.1.4.1.674.10893.1.20.130.15.1.6' => 'batteryComponentStatus',
1686 '1.3.6.1.4.1.674.10893.1.20.130.15.1.9' => 'batteryNexusID',
1687 '1.3.6.1.4.1.674.10893.1.20.130.15.1.10' => 'batteryPredictedCapacity',
1688 '1.3.6.1.4.1.674.10893.1.20.130.15.1.12' => 'batteryLearnState',
1689 '1.3.6.1.4.1.674.10893.1.20.130.16.1.5' => 'batteryConnectionControllerNumber',
1692 if ($opt{use_get_table}) {
1693 my $batteryTable = '1.3.6.1.4.1.674.10893.1.20.130.15';
1694 my $batteryConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.16';
1696 $result = $snmp_session->get_table(-baseoid => $batteryTable);
1697 my $ext = $snmp_session->get_table(-baseoid => $batteryConnectionTable);
1699 if (defined $result) {
1700 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
1704 $result = $snmp_session->get_entries(-columns => [keys %bat_oid]);
1707 # No cache battery is OK
1708 return if !defined $result;
1710 @output = @{ get_snmp_output($result, \%bat_oid) };
1713 foreach my $c (@controllers) {
1714 push @output, @{ run_omreport("storage battery controller=$c") };
1715 map_item('ctrl', $c, \@output);
1725 7 => 'Reconditioning',
1733 # Specifies the learn state activity of the battery
1743 # This property displays the battery's ability to be charged
1746 1 => 'Failed', # The battery cannot be charged and needs to be replaced
1747 2 => 'Ready', # The battery can be charged to full capacity
1748 4 => 'Unknown', # The battery is completing a Learn cycle. The charge capacity of the
1749 # battery cannot be determined until the Learn cycle is complete
1752 # Check battery on each of the controllers
1754 foreach my $out (@output) {
1756 $status = $snmp_status{$out->{batteryComponentStatus}};
1757 $state = get_hashval($out->{batteryState}, \%bat_state);
1758 $learn = get_hashval($out->{batteryLearnState}, \%bat_learn_state);
1759 $pred = get_hashval($out->{batteryPredictedCapacity}, \%bat_pred_cap);
1760 $ctrl = $out->{batteryConnectionControllerNumber} - 1;
1761 $nexus = convert_nexus($out->{batteryNexusID});
1763 $id =~ s{\A \d+:(\d+) \z}{$1}xms;
1767 $state = $out->{'State'};
1768 $status = $out->{'Status'};
1769 $learn = $out->{'Learn State'};
1770 $pred = $out->{'Predicted Capacity Status'};
1771 $ctrl = $out->{'ctrl'};
1772 $nexus = join q{:}, $out->{ctrl}, $id;
1775 next BATTERY if blacklisted('bat', $nexus);
1777 # Special case: Charging
1778 if ($state eq 'Charging') {
1779 if ($pred eq 'Failed') {
1780 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [replace battery]',
1781 $id, $ctrl, $state, $pred;
1782 report('storage', $msg, $E_CRITICAL, $nexus);
1785 next BATTERY if blacklisted('bat_charge', $nexus);
1786 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [probably harmless]',
1787 $id, $ctrl, $state, $pred;
1788 report('storage', $msg, $E_WARNING, $nexus);
1791 # Special case: Learning (battery learns its capacity)
1792 elsif ($state eq 'Learning') {
1793 if ($learn eq 'Failed') {
1794 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s)',
1795 $id, $ctrl, $state, $learn;
1796 report('storage', $msg, $E_CRITICAL, $nexus);
1799 next BATTERY if blacklisted('bat_charge', $nexus);
1800 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [probably harmless]',
1801 $id, $ctrl, $state, $learn;
1802 report('storage', $msg, $E_WARNING, $nexus);
1805 # Special case: Power Low (first part of recharge cycle)
1806 elsif ($state eq 'Power Low') {
1807 next BATTERY if blacklisted('bat_charge', $nexus);
1808 my $msg = sprintf 'Cache Battery %d in controller %d is %s [probably harmless]',
1810 report('storage', $msg, $E_WARNING, $nexus);
1812 # Special case: Degraded and Non-Critical (usually part of recharge cycle)
1813 elsif ($state eq 'Degraded' && $status eq 'Non-Critical') {
1814 next BATTERY if blacklisted('bat_charge', $nexus);
1815 my $msg = sprintf 'Cache Battery %d in controller %d is %s (%s) [probably harmless]',
1816 $id, $ctrl, $state, $status;
1817 report('storage', $msg, $E_WARNING, $nexus);
1820 elsif ($status ne 'Ok') {
1821 my $msg = sprintf 'Cache Battery %d in controller %d needs attention: %s (%s)',
1822 $id, $ctrl, $state, $status;
1823 report('storage', $msg, $status2nagios{$status}, $nexus);
1827 my $msg = sprintf 'Cache Battery %d in controller %d is %s',
1829 report('storage', $msg, $E_OK, $nexus);
1836 #-----------------------------------------
1837 # STORAGE: Check connectors (channels)
1838 #-----------------------------------------
1839 sub check_connectors {
1840 return if $#controllers == -1;
1841 return if blacklisted('conn', 'all');
1855 '1.3.6.1.4.1.674.10893.1.20.130.2.1.1' => 'channelNumber',
1856 '1.3.6.1.4.1.674.10893.1.20.130.2.1.2' => 'channelName',
1857 '1.3.6.1.4.1.674.10893.1.20.130.2.1.3' => 'channelState',
1858 '1.3.6.1.4.1.674.10893.1.20.130.2.1.8' => 'channelComponentStatus',
1859 '1.3.6.1.4.1.674.10893.1.20.130.2.1.9' => 'channelNexusID',
1860 '1.3.6.1.4.1.674.10893.1.20.130.2.1.11' => 'channelBusType',
1863 if ($opt{use_get_table}) {
1864 my $channelTable = '1.3.6.1.4.1.674.10893.1.20.130.2';
1865 $result = $snmp_session->get_table(-baseoid => $channelTable);
1868 $result = $snmp_session->get_entries(-columns => [keys %conn_oid]);
1871 if (!defined $result) {
1872 printf "SNMP ERROR [storage / channel]: %s.\n", $snmp_session->error;
1873 $snmp_session->close;
1877 @output = @{ get_snmp_output($result, \%conn_oid) };
1880 foreach my $c (@controllers) {
1881 push @output, @{ run_omreport("storage connector controller=$c") };
1882 map_item('ctrl', $c, \@output);
1900 3 => 'Fibre Channel',
1907 # Check connectors on each of the controllers
1909 foreach my $out (@output) {
1911 $id = $out->{channelNumber} - 1;
1912 $name = $out->{channelName};
1913 $status = $snmp_status{$out->{channelComponentStatus}};
1914 $state = get_hashval($out->{channelState}, \%conn_state);
1915 $type = get_hashval($out->{channelBusType}, \%conn_bustype);
1916 $nexus = convert_nexus($out->{channelNexusID});
1918 $ctrl =~ s{(\d+):\d+}{$1}xms;
1922 $name = $out->{'Name'};
1923 $state = $out->{'State'};
1924 $status = $out->{'Status'};
1925 $type = $out->{'Connector Type'};
1926 $ctrl = $out->{ctrl};
1927 $nexus = join q{:}, $out->{ctrl}, $id;
1930 next CHANNEL if blacklisted('conn', $nexus);
1932 my $msg = sprintf '%s [%s] on controller %d is %s',
1933 $name, $type, $ctrl, $state;
1934 report('storage', $msg, $status2nagios{$status}, $nexus);
1940 #-----------------------------------------
1941 # STORAGE: Check enclosures
1942 #-----------------------------------------
1943 sub check_enclosures {
1944 return if blacklisted('encl', 'all');
1951 my $firmware = undef;
1953 my $occupied_slots = undef; # number of occupied slots
1954 my $total_slots = undef; # number of total slots
1960 '1.3.6.1.4.1.674.10893.1.20.130.3.1.1' => 'enclosureNumber',
1961 '1.3.6.1.4.1.674.10893.1.20.130.3.1.2' => 'enclosureName',
1962 '1.3.6.1.4.1.674.10893.1.20.130.3.1.4' => 'enclosureState',
1963 '1.3.6.1.4.1.674.10893.1.20.130.3.1.19' => 'enclosureChannelNumber',
1964 '1.3.6.1.4.1.674.10893.1.20.130.3.1.24' => 'enclosureComponentStatus',
1965 '1.3.6.1.4.1.674.10893.1.20.130.3.1.25' => 'enclosureNexusID',
1966 '1.3.6.1.4.1.674.10893.1.20.130.3.1.26' => 'enclosureFirmwareVersion',
1967 '1.3.6.1.4.1.674.10893.1.20.130.3.1.31' => 'enclosureOccupiedSlotCount', # new in OMSA 6.3.0
1968 '1.3.6.1.4.1.674.10893.1.20.130.3.1.32' => 'enclosureTotalSlots', # new in OMSA 6.3.0
1971 if ($opt{use_get_table}) {
1972 my $enclosureTable = '1.3.6.1.4.1.674.10893.1.20.130.3';
1973 $result = $snmp_session->get_table(-baseoid => $enclosureTable);
1976 $result = $snmp_session->get_entries(-columns => [keys %encl_oid]);
1979 # No enclosures is OK
1980 return if !defined $result;
1982 @output = @{ get_snmp_output($result, \%encl_oid) };
1985 foreach my $c (@controllers) {
1986 push @output, @{ run_omreport("storage enclosure controller=$c") };
1987 map_item('ctrl', $c, \@output);
2002 foreach my $out (@output) {
2004 $id = $out->{enclosureNumber} - 1;
2005 $name = $out->{enclosureName};
2006 $state = get_hashval($out->{enclosureState}, \%encl_state);
2007 $status = $snmp_status{$out->{enclosureComponentStatus}};
2008 $firmware = exists $out->{enclosureFirmwareVersion}
2009 ? $out->{enclosureFirmwareVersion} : 'N/A';
2010 $nexus = convert_nexus($out->{enclosureNexusID});
2012 $ctrl =~ s{\A (\d+):.* \z}{$1}xms;
2013 # for the next two, a value of 9999 means feature not available
2014 $occupied_slots = exists $out->{enclosureOccupiedSlotCount}
2015 && $out->{enclosureOccupiedSlotCount} != 9999
2016 ? $out->{enclosureOccupiedSlotCount} : undef;
2017 $total_slots = exists $out->{enclosureTotalSlots}
2018 && $out->{enclosureTotalSlots} != 9999
2019 ? $out->{enclosureTotalSlots} : undef;
2023 $name = $out->{Name};
2024 $state = $out->{State};
2025 $status = $out->{Status};
2026 $firmware = $out->{'Firmware Version'} ne 'Not Applicable'
2027 ? $out->{'Firmware Version'} : 'N/A';
2028 $nexus = join q{:}, $out->{ctrl}, $id;
2029 $ctrl = $out->{ctrl};
2032 $name =~ s{\s+\z}{}xms; # remove trailing whitespace
2033 $firmware =~ s{\s+\z}{}xms; # remove trailing whitespace
2035 # store enclosure data for future use
2037 $snmp_enclosure{$out->{enclosureNumber}}{id} = $id;
2038 $snmp_enclosure{$out->{enclosureNumber}}{name} = $name;
2039 $snmp_enclosure{$out->{enclosureNumber}}{nexus} = $nexus;
2042 push @enclosures, { 'id' => $id,
2043 'ctrl' => $out->{ctrl},
2047 # Collecting some storage info
2048 $sysinfo{'enclosure'}{$nexus}{'id'} = $nexus;
2049 $sysinfo{'enclosure'}{$nexus}{'name'} = $name;
2050 $sysinfo{'enclosure'}{$nexus}{'firmware'} = $firmware;
2052 next ENCLOSURE if blacklisted('encl', $nexus);
2055 if (defined $occupied_slots && defined $total_slots) {
2056 $msg = sprintf 'Enclosure %s [%s, %d/%d slots occupied] on ctrl %d is %s',
2057 $nexus, $name, $occupied_slots, $total_slots, $ctrl, $state;
2060 $msg = sprintf 'Enclosure %s [%s] on controller %d is %s',
2061 $nexus, $name, $ctrl, $state;
2063 report('storage', $msg, $status2nagios{$status}, $nexus);
2069 #-----------------------------------------
2070 # STORAGE: Check enclosure fans
2071 #-----------------------------------------
2072 sub check_enclosure_fans {
2073 return if $#controllers == -1;
2074 return if blacklisted('encl_fan', 'all');
2082 my $encl_id = undef;
2083 my $encl_name = undef;
2089 '1.3.6.1.4.1.674.10893.1.20.130.7.1.1' => 'fanNumber',
2090 '1.3.6.1.4.1.674.10893.1.20.130.7.1.2' => 'fanName',
2091 '1.3.6.1.4.1.674.10893.1.20.130.7.1.4' => 'fanState',
2092 '1.3.6.1.4.1.674.10893.1.20.130.7.1.11' => 'fanProbeCurrValue',
2093 '1.3.6.1.4.1.674.10893.1.20.130.7.1.15' => 'fanComponentStatus',
2094 '1.3.6.1.4.1.674.10893.1.20.130.7.1.16' => 'fanNexusID',
2095 '1.3.6.1.4.1.674.10893.1.20.130.8.1.4' => 'fanConnectionEnclosureName',
2096 '1.3.6.1.4.1.674.10893.1.20.130.8.1.5' => 'fanConnectionEnclosureNumber',
2099 if ($opt{use_get_table}) {
2100 my $fanTable = '1.3.6.1.4.1.674.10893.1.20.130.7';
2101 my $fanConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.8';
2103 $result = $snmp_session->get_table(-baseoid => $fanTable);
2104 my $ext = $snmp_session->get_table(-baseoid => $fanConnectionTable);
2106 if (defined $result) {
2107 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2111 $result = $snmp_session->get_entries(-columns => [keys %fan_oid]);
2114 # No enclosure fans is OK
2115 return if !defined $result;
2117 @output = @{ get_snmp_output($result, \%fan_oid) };
2120 foreach my $enc (@enclosures) {
2121 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=fans") };
2122 map_item('ctrl', $enc->{ctrl}, \@output);
2123 map_item('encl_id', $enc->{id}, \@output);
2124 map_item('encl_name', $enc->{name}, \@output);
2139 # Check fans on each of the enclosures
2141 foreach my $out (@output) {
2143 $id = $out->{fanNumber} - 1;
2144 $name = $out->{fanName};
2145 $state = get_hashval($out->{fanState}, \%fan_state);
2146 $status = $snmp_status{$out->{fanComponentStatus}};
2147 $speed = $out->{fanProbeCurrValue};
2148 #$encl_id = $out->{fanConnectionEnclosureNumber} - 1;
2149 $encl_name = $out->{fanConnectionEnclosureName};
2151 $encl_id = $snmp_enclosure{$out->{fanConnectionEnclosureNumber}}{nexus};
2154 # foreach my $e (@enclosures) {
2155 # print $e->{nexus}, "\n";
2156 # if ($e->{id} == $out->{fanConnectionEnclosureNumber} - 1) {
2157 # $encl_id = $e->{nexus};
2162 $nexus = convert_nexus($out->{fanNexusID});
2166 $name = $out->{'Name'};
2167 $state = $out->{'State'};
2168 $status = $out->{'Status'};
2169 $speed = $out->{'Speed'};
2170 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2171 $encl_name = $out->{encl_name};
2172 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2175 next FAN if blacklisted('encl_fan', $nexus);
2178 if ($status ne 'Ok') {
2179 my $msg = sprintf '%s in enclosure %s [%s] needs attention: %s',
2180 $name, $encl_id, $encl_name, $state;
2181 report('storage', $msg, $status2nagios{$status}, $nexus);
2185 my $msg = sprintf '%s in enclosure %s [%s] is %s (speed=%s)',
2186 $name, $encl_id, $encl_name, $state, $speed;
2187 report('storage', $msg, $E_OK, $nexus);
2194 #-----------------------------------------
2195 # STORAGE: Check enclosure power supplies
2196 #-----------------------------------------
2197 sub check_enclosure_pwr {
2198 return if $#controllers == -1;
2199 return if blacklisted('encl_ps', 'all');
2206 my $encl_id = undef;
2207 my $encl_name = undef;
2213 '1.3.6.1.4.1.674.10893.1.20.130.9.1.1' => 'powerSupplyNumber',
2214 '1.3.6.1.4.1.674.10893.1.20.130.9.1.2' => 'powerSupplyName',
2215 '1.3.6.1.4.1.674.10893.1.20.130.9.1.4' => 'powerSupplyState',
2216 '1.3.6.1.4.1.674.10893.1.20.130.9.1.9' => 'powerSupplyComponentStatus',
2217 '1.3.6.1.4.1.674.10893.1.20.130.9.1.10' => 'powerSupplyNexusID',
2218 '1.3.6.1.4.1.674.10893.1.20.130.10.1.4' => 'powerSupplyConnectionEnclosureName',
2219 '1.3.6.1.4.1.674.10893.1.20.130.10.1.5' => 'powerSupplyConnectionEnclosureNumber',
2222 if ($opt{use_get_table}) {
2223 my $powerSupplyTable = '1.3.6.1.4.1.674.10893.1.20.130.9';
2224 my $powerSupplyConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.10';
2226 $result = $snmp_session->get_table(-baseoid => $powerSupplyTable);
2227 my $ext = $snmp_session->get_table(-baseoid => $powerSupplyConnectionTable);
2229 if (defined $result) {
2230 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2234 $result = $snmp_session->get_entries(-columns => [keys %ps_oid]);
2237 # No enclosure power supplies is OK
2238 return if !defined $result;
2240 @output = @{ get_snmp_output($result, \%ps_oid) };
2243 foreach my $enc (@enclosures) {
2244 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=pwrsupplies") };
2245 map_item('ctrl', $enc->{ctrl}, \@output);
2246 map_item('encl_id', $enc->{id}, \@output);
2247 map_item('encl_name', $enc->{name}, \@output);
2256 5 => 'Not Installed',
2262 # Check power supplies on each of the enclosures
2264 foreach my $out (@output) {
2266 $id = $out->{powerSupplyNumber};
2267 $name = $out->{powerSupplyName};
2268 $state = get_hashval($out->{powerSupplyState}, \%ps_state);
2269 $status = $snmp_status{$out->{powerSupplyComponentStatus}};
2270 #$encl_id = $out->{powerSupplyConnectionEnclosureNumber} - 1;
2271 $encl_id = $snmp_enclosure{$out->{powerSupplyConnectionEnclosureNumber}}{nexus};
2272 $encl_name = $out->{powerSupplyConnectionEnclosureName};
2273 $nexus = convert_nexus($out->{powerSupplyNexusID});
2277 $name = $out->{'Name'};
2278 $state = $out->{'State'};
2279 $status = $out->{'Status'};
2280 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2281 $encl_name = $out->{encl_name};
2282 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2285 next PS if blacklisted('encl_ps', $nexus);
2288 if ($status ne 'Ok') {
2289 my $msg = sprintf '%s in enclosure %s [%s] needs attention: %s',
2290 $name, $encl_id, $encl_name, $state;
2291 report('storage', $msg, $status2nagios{$status}, $nexus);
2295 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2296 $name, $encl_id, $encl_name, $state;
2297 report('storage', $msg, $E_OK, $nexus);
2304 #-----------------------------------------
2305 # STORAGE: Check enclosure temperatures
2306 #-----------------------------------------
2307 sub check_enclosure_temp {
2308 return if $#controllers == -1;
2309 return if blacklisted('encl_temp', 'all');
2316 my $reading = undef;
2318 my $max_warn = undef;
2319 my $max_crit = undef;
2320 my $min_warn = undef;
2321 my $min_crit = undef;
2322 my $encl_id = undef;
2323 my $encl_name = undef;
2329 '1.3.6.1.4.1.674.10893.1.20.130.11.1.1' => 'temperatureProbeNumber',
2330 '1.3.6.1.4.1.674.10893.1.20.130.11.1.2' => 'temperatureProbeName',
2331 '1.3.6.1.4.1.674.10893.1.20.130.11.1.4' => 'temperatureProbeState',
2332 '1.3.6.1.4.1.674.10893.1.20.130.11.1.6' => 'temperatureProbeUnit',
2333 '1.3.6.1.4.1.674.10893.1.20.130.11.1.7' => 'temperatureProbeMinWarning',
2334 '1.3.6.1.4.1.674.10893.1.20.130.11.1.8' => 'temperatureProbeMinCritical',
2335 '1.3.6.1.4.1.674.10893.1.20.130.11.1.9' => 'temperatureProbeMaxWarning',
2336 '1.3.6.1.4.1.674.10893.1.20.130.11.1.10' => 'temperatureProbeMaxCritical',
2337 '1.3.6.1.4.1.674.10893.1.20.130.11.1.11' => 'temperatureProbeCurValue',
2338 '1.3.6.1.4.1.674.10893.1.20.130.11.1.13' => 'temperatureProbeComponentStatus',
2339 '1.3.6.1.4.1.674.10893.1.20.130.11.1.14' => 'temperatureProbeNexusID',
2340 '1.3.6.1.4.1.674.10893.1.20.130.12.1.4' => 'temperatureConnectionEnclosureName',
2341 '1.3.6.1.4.1.674.10893.1.20.130.12.1.5' => 'temperatureConnectionEnclosureNumber',
2344 if ($opt{use_get_table}) {
2345 my $temperatureProbeTable = '1.3.6.1.4.1.674.10893.1.20.130.11';
2346 my $temperatureConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.12';
2348 $result = $snmp_session->get_table(-baseoid => $temperatureProbeTable);
2349 my $ext = $snmp_session->get_table(-baseoid => $temperatureConnectionTable);
2351 if (defined $result) {
2352 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2356 $result = $snmp_session->get_entries(-columns => [keys %temp_oid]);
2359 # No enclosure temperature probes is OK
2360 return if !defined $result;
2362 @output = @{ get_snmp_output($result, \%temp_oid) };
2365 foreach my $enc (@enclosures) {
2366 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=temps") };
2367 map_item('ctrl', $enc->{ctrl}, \@output);
2368 map_item('encl_id', $enc->{id}, \@output);
2369 map_item('encl_name', $enc->{name}, \@output);
2384 # Check temperature probes on each of the enclosures
2386 foreach my $out (@output) {
2388 $id = $out->{temperatureProbeNumber} - 1;
2389 $name = $out->{temperatureProbeName};
2390 $state = get_hashval($out->{temperatureProbeState}, \%temp_state);
2391 $status = $snmp_status{$out->{temperatureProbeComponentStatus}};
2392 $unit = $out->{temperatureProbeUnit};
2393 $reading = exists $out->{temperatureProbeCurValue}
2394 ? $out->{temperatureProbeCurValue} : '[N/A]';
2395 $max_warn = exists $out->{temperatureProbeMaxWarning}
2396 ? $out->{temperatureProbeMaxWarning} : '[N/A]';
2397 $max_crit = exists $out->{temperatureProbeMaxCritical}
2398 ? $out->{temperatureProbeMaxCritical} : '[N/A]';
2399 $min_warn = exists $out->{temperatureProbeMinWarning}
2400 ? $out->{temperatureProbeMinWarning} : '[N/A]';
2401 $min_crit = exists $out->{temperatureProbeMinCritical}
2402 ? $out->{temperatureProbeMinCritical} : '[N/A]';
2403 #$encl_id = $out->{temperatureConnectionEnclosureNumber} - 1;
2404 $encl_id = $snmp_enclosure{$out->{temperatureConnectionEnclosureNumber}}{nexus};
2405 $encl_name = $out->{temperatureConnectionEnclosureName};
2406 $nexus = convert_nexus($out->{temperatureProbeNexusID});
2410 $name = $out->{'Name'};
2411 $state = $out->{'State'};
2412 $status = $out->{'Status'};
2414 $reading = $out->{'Reading'};
2415 $max_warn = $out->{'Maximum Warning Threshold'};
2416 $max_crit = $out->{'Maximum Failure Threshold'};
2417 $min_warn = $out->{'Minimum Warning Threshold'};
2418 $min_crit = $out->{'Minimum Failure Threshold'};
2419 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2420 $encl_name = $out->{encl_name};
2421 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2424 next TEMP if blacklisted('encl_temp', $nexus);
2426 # Make sure these values are integers
2427 $reading =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $reading = '[N/A]';
2428 $max_warn =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $max_warn = '[N/A]';
2429 $max_crit =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $max_crit = '[N/A]';
2430 $min_warn =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $min_warn = '[N/A]';
2431 $min_crit =~ s{\A \s* (-?\d+) \s* C? \s* \z}{$1}xms or $min_crit = '[N/A]';
2433 # Inactive temp probes
2434 if ($status eq 'Unknown' and $state eq 'Inactive') {
2435 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2436 $name, $encl_id, $encl_name, $state;
2437 report('storage', $msg, $E_OK, $nexus);
2439 elsif ($status ne 'Ok' and $max_crit ne '[N/A]' and $reading > $max_crit) {
2440 my $msg = sprintf '%s in enclosure %s [%s] is critically high at %d C',
2441 $name, $encl_id, $encl_name, $reading;
2442 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2443 report('chassis', $msg, $err, $nexus);
2445 elsif ($status ne 'Ok' and $max_warn ne '[N/A]' and $reading > $max_warn) {
2446 my $msg = sprintf '%s in enclosure %s [%s] is too high at %d C',
2447 $name, $encl_id, $encl_name, $reading;
2448 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2449 report('chassis', $msg, $err, $nexus);
2451 elsif ($status ne 'Ok' and $min_crit ne '[N/A]' and $reading < $min_crit) {
2452 my $msg = sprintf '%s in enclosure %s [%s] is critically low at %d C',
2453 $name, $encl_id, $encl_name, $reading;
2454 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2455 report('chassis', $msg, $err, $nexus);
2457 elsif ($status ne 'Ok' and $min_warn ne '[N/A]' and $reading < $min_warn) {
2458 my $msg = sprintf '%s in enclosure %s [%s] is too low at %d C',
2459 $name, $encl_id, $encl_name, $reading;
2460 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2461 report('chassis', $msg, $err, $nexus);
2464 elsif ($status ne 'Ok') {
2465 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2466 $name, $encl_id, $encl_name, $state;
2467 if (defined $reading && $reading =~ m{\A -?\d+ \z}xms) {
2468 # take into account that with certain states the
2469 # reading doesn't exist or is not an integer
2470 $msg .= sprintf ' at %s C', $reading;
2471 if ($min_warn eq '[N/A]' or $min_crit eq '[N/A]') {
2472 $msg .= sprintf ' (max=%s/%s)', $max_warn, $max_crit;
2475 $msg .= sprintf ' (min=%s/%s, max=%s/%s)',
2476 $min_warn, $min_crit, $max_warn, $max_crit;
2479 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2480 report('storage', $msg, $err, $nexus);
2484 my $msg = sprintf '%s in enclosure %s [%s]',
2485 $name, $encl_id, $encl_name;
2486 if (defined $reading && $reading ne '[N/A]') {
2487 # take into account that with certain states the
2488 # reading doesn't exist or is not an integer
2489 $msg .= sprintf ' reads %d C', $reading;
2490 if ($min_warn eq '[N/A]' or $min_crit eq '[N/A]') {
2491 $msg .= sprintf ' (max=%s/%s)', $max_warn, $max_crit;
2494 $msg .= sprintf ' (min=%s/%s, max=%s/%s)',
2495 $min_warn, $min_crit, $max_warn, $max_crit;
2499 $msg .= sprintf ' is %s', $state;
2501 report('storage', $msg, $E_OK, $nexus);
2504 # Collect performance data
2505 if (defined $opt{perfdata} && $reading ne '[N/A]') {
2506 $name =~ s{\A Temperature\sProbe\s(\d+) \z}{temp_$1}gxms;
2507 my $label = "enclosure_${encl_id}_${name}";
2509 $mini =~ s{enclosure_(.+?)_temp_(.+?)}{e$1t$2}xms;
2523 #-----------------------------------------
2524 # STORAGE: Check enclosure management modules (EMM)
2525 #-----------------------------------------
2526 sub check_enclosure_emms {
2527 return if $#controllers == -1;
2528 return if blacklisted('encl_emm', 'all');
2535 my $encl_id = undef;
2536 my $encl_name = undef;
2542 '1.3.6.1.4.1.674.10893.1.20.130.13.1.1' => 'enclosureManagementModuleNumber',
2543 '1.3.6.1.4.1.674.10893.1.20.130.13.1.2' => 'enclosureManagementModuleName',
2544 '1.3.6.1.4.1.674.10893.1.20.130.13.1.4' => 'enclosureManagementModuleState',
2545 '1.3.6.1.4.1.674.10893.1.20.130.13.1.11' => 'enclosureManagementModuleComponentStatus',
2546 '1.3.6.1.4.1.674.10893.1.20.130.13.1.12' => 'enclosureManagementModuleNexusID',
2547 '1.3.6.1.4.1.674.10893.1.20.130.14.1.4' => 'enclosureManagementModuleConnectionEnclosureName',
2548 '1.3.6.1.4.1.674.10893.1.20.130.14.1.5' => 'enclosureManagementModuleConnectionEnclosureNumber',
2551 if ($opt{use_get_table}) {
2552 my $enclosureManagementModuleTable = '1.3.6.1.4.1.674.10893.1.20.130.13';
2553 my $enclosureManagementModuleConnectionTable = '1.3.6.1.4.1.674.10893.1.20.130.14';
2555 $result = $snmp_session->get_table(-baseoid => $enclosureManagementModuleTable);
2556 my $ext = $snmp_session->get_table(-baseoid => $enclosureManagementModuleConnectionTable);
2558 if (defined $result) {
2559 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
2563 $result = $snmp_session->get_entries(-columns => [keys %emms_oid]);
2566 # No enclosure EMMs is OK
2567 return if !defined $result;
2569 @output = @{ get_snmp_output($result, \%emms_oid) };
2572 foreach my $enc (@enclosures) {
2573 push @output, @{ run_omreport("storage enclosure controller=$enc->{ctrl} enclosure=$enc->{id} info=emms") };
2574 map_item('ctrl', $enc->{ctrl}, \@output);
2575 map_item('encl_id', $enc->{id}, \@output);
2576 map_item('encl_name', $enc->{name}, \@output);
2587 5 => 'Not Installed',
2592 # Check EMMs on each of the enclosures
2594 foreach my $out (@output) {
2596 $id = $out->{enclosureManagementModuleNumber} - 1;
2597 $name = $out->{enclosureManagementModuleName};
2598 $state = get_hashval($out->{enclosureManagementModuleState}, \%emms_state);
2599 $status = $snmp_status{$out->{enclosureManagementModuleComponentStatus}};
2600 #$encl_id = $out->{enclosureManagementModuleConnectionEnclosureNumber} - 1;
2601 $encl_id = $snmp_enclosure{$out->{enclosureManagementModuleConnectionEnclosureNumber}}{nexus};
2602 $encl_name = $out->{enclosureManagementModuleConnectionEnclosureName};
2603 $nexus = convert_nexus($out->{enclosureManagementModuleNexusID});
2607 $name = $out->{'Name'};
2608 $state = $out->{'State'};
2609 $status = $out->{'Status'};
2610 $encl_id = join q{:}, $out->{ctrl}, $out->{'encl_id'};
2611 $encl_name = $out->{encl_name};
2612 $nexus = join q{:}, $out->{ctrl}, $out->{'encl_id'}, $id;
2615 next EMM if blacklisted('encl_emm', $nexus);
2618 if ($status =~ m{\A Other|Unknown \z}xms and $state eq 'Not Installed') {
2619 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2620 $name, $encl_id, $encl_name, $state;
2621 report('storage', $msg, $E_OK, $nexus);
2624 elsif ($status ne 'Ok') {
2625 my $msg = sprintf '%s in enclosure %s [%s] needs attention: %s',
2626 $name, $encl_id, $encl_name, $state;
2627 report('storage', $msg, $status2nagios{$status}, $nexus);
2631 my $msg = sprintf '%s in enclosure %s [%s] is %s',
2632 $name, $encl_id, $encl_name, $state;
2633 report('storage', $msg, $E_OK, $nexus);
2640 #-----------------------------------------
2641 # CHASSIS: Check memory modules
2642 #-----------------------------------------
2644 return if blacklisted('dimm', 'all');
2648 my $location = undef;
2657 '1.3.6.1.4.1.674.10892.1.1100.50.1.2.1' => 'memoryDeviceIndex',
2658 '1.3.6.1.4.1.674.10892.1.1100.50.1.5.1' => 'memoryDeviceStatus',
2659 '1.3.6.1.4.1.674.10892.1.1100.50.1.8.1' => 'memoryDeviceLocationName',
2660 '1.3.6.1.4.1.674.10892.1.1100.50.1.14.1' => 'memoryDeviceSize',
2661 '1.3.6.1.4.1.674.10892.1.1100.50.1.20.1' => 'memoryDeviceFailureModes',
2664 if ($opt{use_get_table}) {
2665 my $memoryDeviceTable = '1.3.6.1.4.1.674.10892.1.1100.50.1';
2666 $result = $snmp_session->get_table(-baseoid => $memoryDeviceTable);
2669 $result = $snmp_session->get_entries(-columns => [keys %dimm_oid]);
2672 if (!defined $result) {
2673 printf "SNMP ERROR [memory]: %s.\n", $snmp_session->error;
2674 $snmp_session->close;
2678 @output = @{ get_snmp_output($result, \%dimm_oid) };
2681 @output = @{ run_omreport("$omopt_chassis memory") };
2684 # Note: These values are bit masks, so combination values are
2685 # possible. If value is 0 (zero), memory device has no faults.
2688 1 => 'ECC single bit correction warning rate exceeded',
2689 2 => 'ECC single bit correction failure rate exceeded',
2690 4 => 'ECC multibit fault encountered',
2691 8 => 'ECC single bit correction logging disabled',
2692 16 => 'device disabled because of spare activation',
2696 foreach my $out (@output) {
2697 @failures = (); # Initialize
2699 $index = $out->{memoryDeviceIndex};
2700 $status = $snmp_status{$out->{memoryDeviceStatus}};
2701 $location = $out->{memoryDeviceLocationName};
2702 $size = sprintf '%d MB', $out->{memoryDeviceSize}/1024;
2703 $modes = $out->{memoryDeviceFailureModes};
2705 foreach my $mask (sort keys %failure_mode) {
2706 if (($modes & $mask) != 0) { push @failures, $failure_mode{$mask}; }
2711 $index = $out->{'Type'} eq '[Not Occupied]' ? undef : $out->{'Index'};
2712 $status = $out->{'Status'};
2713 $location = $out->{'Connector Name'};
2714 $size = $out->{'Size'};
2715 if (defined $size) {
2716 $size =~ s{\s\s}{ }gxms;
2718 # Run 'omreport chassis memory index=X' to get the failures
2719 if ($status ne 'Ok' && defined $index) {
2720 foreach (@{ run_command("$omreport $omopt_chassis memory index=$index -fmt ssv") }) {
2721 if (m/\A Failures; (.+?) \z/xms) {
2722 chop(my $fail = $1);
2723 push @failures, split m{\.}xms, $fail;
2728 $location =~ s{\A \s*(.*?)\s* \z}{$1}xms;
2730 # calculate total memory
2731 my $msize = defined $size ? $size : 0;
2732 $msize =~ s{\A (\d+) \s MB}{$1}xms;
2733 $count{mem} += $msize;
2735 next DIMM if blacklisted('dimm', $index);
2737 # Ignore empty memory slots
2738 next DIMM if !defined $index;
2741 if ($status ne 'Ok') {
2743 if (scalar @failures == 0) {
2744 $msg = sprintf 'Memory module %d [%s, %s] needs attention (%s)',
2745 $index, $location, $size, $status;
2748 $msg = sprintf 'Memory module %d [%s, %s] needs attention: %s',
2749 $index, $location, $size, (join q{, }, @failures);
2752 report('chassis', $msg, $status2nagios{$status}, $index);
2756 my $msg = sprintf 'Memory module %d [%s, %s] is %s',
2757 $index, $location, $size, $status;
2758 report('chassis', $msg, $E_OK, $index);
2765 #-----------------------------------------
2766 # CHASSIS: Check fans
2767 #-----------------------------------------
2769 return if blacklisted('fan', 'all');
2773 my $reading = undef;
2774 my $location = undef;
2775 my $max_crit = undef;
2776 my $max_warn = undef;
2782 '1.3.6.1.4.1.674.10892.1.700.12.1.2.1' => 'coolingDeviceIndex',
2783 '1.3.6.1.4.1.674.10892.1.700.12.1.5.1' => 'coolingDeviceStatus',
2784 '1.3.6.1.4.1.674.10892.1.700.12.1.6.1' => 'coolingDeviceReading',
2785 '1.3.6.1.4.1.674.10892.1.700.12.1.8.1' => 'coolingDeviceLocationName',
2786 '1.3.6.1.4.1.674.10892.1.700.12.1.10.1' => 'coolingDeviceUpperCriticalThreshold',
2787 '1.3.6.1.4.1.674.10892.1.700.12.1.11.1' => 'coolingDeviceUpperNonCriticalThreshold',
2790 if ($opt{use_get_table}) {
2791 my $coolingDeviceTable = '1.3.6.1.4.1.674.10892.1.700.12.1';
2792 $result = $snmp_session->get_table(-baseoid => $coolingDeviceTable);
2795 $result = $snmp_session->get_entries(-columns => [keys %cool_oid]);
2798 if ($blade && !defined $result) {
2801 elsif (!$blade && !defined $result) {
2802 printf "SNMP ERROR [cooling]: %s.\n", $snmp_session->error;
2803 $snmp_session->close;
2807 @output = @{ get_snmp_output($result, \%cool_oid) };
2810 @output = @{ run_omreport("$omopt_chassis fans") };
2814 foreach my $out (@output) {
2816 $index = $out->{coolingDeviceIndex};
2817 $status = $snmp_probestatus{$out->{coolingDeviceStatus}};
2818 $reading = $out->{coolingDeviceReading};
2819 $location = $out->{coolingDeviceLocationName};
2820 $max_crit = exists $out->{coolingDeviceUpperCriticalThreshold}
2821 ? $out->{coolingDeviceUpperCriticalThreshold} : 0;
2822 $max_warn = exists $out->{coolingDeviceUpperNonCriticalThreshold}
2823 ? $out->{coolingDeviceUpperNonCriticalThreshold} : 0;
2826 $index = $out->{'Index'};
2827 $status = $out->{'Status'};
2828 $reading = $out->{'Reading'};
2829 $location = $out->{'Probe Name'};
2830 $max_crit = $out->{'Maximum Failure Threshold'} ne '[N/A]'
2831 ? $out->{'Maximum Failure Threshold'} : 0;
2832 $max_warn = $out->{'Maximum Warning Threshold'} ne '[N/A]'
2833 ? $out->{'Maximum Warning Threshold'} : 0;
2834 $reading =~ s{\A (\d+).* \z}{$1}xms;
2835 $max_warn =~ s{\A (\d+).* \z}{$1}xms;
2836 $max_crit =~ s{\A (\d+).* \z}{$1}xms;
2839 next FAN if blacklisted('fan', $index);
2842 if ($status ne 'Ok') {
2843 my $msg = sprintf 'Chassis fan %d [%s] needs attention: %s',
2844 $index, $location, $status;
2845 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
2846 report('chassis', $msg, $err, $index);
2849 my $msg = sprintf 'Chassis fan %d [%s]: %s',
2850 $index, $location, $reading;
2851 report('chassis', $msg, $E_OK, $index);
2854 # Collect performance data
2855 if (defined $opt{perfdata}) {
2856 my $pname = lc $location;
2857 $pname =~ s{\s}{_}gxms;
2858 $pname =~ s{proc_}{cpu#}xms;
2860 label => "fan_${index}_${pname}",
2872 #-----------------------------------------
2873 # CHASSIS: Check power supplies
2874 #-----------------------------------------
2875 sub check_powersupplies {
2876 return if blacklisted('ps', 'all');
2881 my $err_type = undef;
2889 '1.3.6.1.4.1.674.10892.1.600.12.1.2.1' => 'powerSupplyIndex',
2890 '1.3.6.1.4.1.674.10892.1.600.12.1.5.1' => 'powerSupplyStatus',
2891 '1.3.6.1.4.1.674.10892.1.600.12.1.7.1' => 'powerSupplyType',
2892 '1.3.6.1.4.1.674.10892.1.600.12.1.11.1' => 'powerSupplySensorState',
2893 '1.3.6.1.4.1.674.10892.1.600.12.1.12.1' => 'powerSupplyConfigurationErrorType',
2896 if ($opt{use_get_table}) {
2897 my $powerDeviceTable = '1.3.6.1.4.1.674.10892.1.600.12.1';
2898 $result = $snmp_session->get_table(-baseoid => $powerDeviceTable);
2901 $result = $snmp_session->get_entries(-columns => [keys %ps_oid]);
2904 # No instrumented PSU is OK (blades, low-end servers)
2905 return 0 if !defined $result;
2907 @output = @{ get_snmp_output($result, \%ps_oid) };
2910 @output = @{ run_omreport("$omopt_chassis pwrsupplies") };
2920 6 => 'Uninterruptible Power Supply',
2930 1 => 'Presence detected',
2931 2 => 'Failure detected',
2932 4 => 'Predictive Failure',
2934 16 => 'AC lost or out-of-range',
2935 32 => 'AC out-of-range but present',
2936 64 => 'Configuration error',
2939 my %ps_config_error_type
2941 1 => 'Vendor mismatch',
2942 2 => 'Revision mismatch',
2943 3 => 'Processor missing',
2947 foreach my $out (@output) {
2949 @states = (); # contains states for the PS
2951 $index = $out->{powerSupplyIndex} - 1;
2952 $status = $snmp_status{$out->{powerSupplyStatus}};
2953 $type = get_hashval($out->{powerSupplyType}, \%ps_type);
2954 $err_type = defined $out->{powerSupplyConfigurationErrorType}
2955 ? $ps_config_error_type{$out->{powerSupplyConfigurationErrorType}} : undef;
2957 # get the combined state from the StatusReading OID
2958 foreach my $mask (sort keys %ps_state) {
2959 if (($out->{powerSupplySensorState} & $mask) != 0) {
2960 push @states, $ps_state{$mask};
2964 # If configuration error, also include the error type
2965 if (defined $err_type) {
2966 push @states, $err_type;
2969 # Finally, construct the state string
2970 $state = join q{, }, @states;
2973 $index = $out->{'Index'};
2974 $status = $out->{'Status'};
2975 $type = $out->{'Type'};
2976 $state = $out->{'Online Status'};
2979 next PS if blacklisted('ps', $index);
2982 if ($status ne 'Ok') {
2983 my $msg = sprintf 'Power Supply %d [%s] needs attention: %s',
2984 $index, $type, $state;
2985 report('chassis', $msg, $status2nagios{$status}, $index);
2988 my $msg = sprintf 'Power Supply %d [%s]: %s',
2989 $index, $type, $state;
2990 report('chassis', $msg, $E_OK, $index);
2997 #-----------------------------------------
2998 # CHASSIS: Check temperatures
2999 #-----------------------------------------
3000 sub check_temperatures {
3001 return if blacklisted('temp', 'all');
3005 my $reading = undef;
3006 my $location = undef;
3007 my $max_crit = undef;
3008 my $max_warn = undef;
3009 my $min_warn = undef;
3010 my $min_crit = undef;
3012 my $discrete = undef;
3015 # Getting custom temperature thresholds (user option)
3016 my %warn_threshold = %{ custom_temperature_thresholds('w') };
3017 my %crit_threshold = %{ custom_temperature_thresholds('c') };
3022 '1.3.6.1.4.1.674.10892.1.700.20.1.2.1' => 'temperatureProbeIndex',
3023 '1.3.6.1.4.1.674.10892.1.700.20.1.5.1' => 'temperatureProbeStatus',
3024 '1.3.6.1.4.1.674.10892.1.700.20.1.6.1' => 'temperatureProbeReading',
3025 '1.3.6.1.4.1.674.10892.1.700.20.1.7.1' => 'temperatureProbeType',
3026 '1.3.6.1.4.1.674.10892.1.700.20.1.8.1' => 'temperatureProbeLocationName',
3027 '1.3.6.1.4.1.674.10892.1.700.20.1.10.1' => 'temperatureProbeUpperCriticalThreshold',
3028 '1.3.6.1.4.1.674.10892.1.700.20.1.11.1' => 'temperatureProbeUpperNonCriticalThreshold',
3029 '1.3.6.1.4.1.674.10892.1.700.20.1.12.1' => 'temperatureProbeLowerNonCriticalThreshold',
3030 '1.3.6.1.4.1.674.10892.1.700.20.1.13.1' => 'temperatureProbeLowerCriticalThreshold',
3031 '1.3.6.1.4.1.674.10892.1.700.20.1.16.1' => 'temperatureProbeDiscreteReading',
3033 # this didn't work well for some reason
3034 #my $result = $snmp_session->get_entries(-columns => [keys %temp_oid]);
3036 # Getting values using the table
3037 my $temperatureProbeTable = '1.3.6.1.4.1.674.10892.1.700.20';
3038 my $result = $snmp_session->get_table(-baseoid => $temperatureProbeTable);
3040 if (!defined $result) {
3041 printf "SNMP ERROR [temperatures]: %s.\n", $snmp_session->error;
3042 $snmp_session->close;
3046 @output = @{ get_snmp_output($result, \%temp_oid) };
3049 @output = @{ run_omreport("$omopt_chassis temps") };
3054 1 => 'Other', # type is other than following values
3055 2 => 'Unknown', # type is unknown
3056 3 => 'AmbientESM', # type is Ambient Embedded Systems Management temperature probe
3057 16 => 'Discrete', # type is temperature probe with discrete reading
3061 foreach my $out (@output) {
3063 $index = $out->{temperatureProbeIndex} - 1;
3064 $status = $snmp_probestatus{$out->{temperatureProbeStatus}};
3065 $location = $out->{temperatureProbeLocationName};
3066 $reading = exists $out->{temperatureProbeReading}
3067 ? $out->{temperatureProbeReading} / 10 : '[N/A]';
3068 $max_crit = exists $out->{temperatureProbeUpperCriticalThreshold}
3069 ? $out->{temperatureProbeUpperCriticalThreshold} / 10 : '[N/A]';
3070 $max_warn = exists $out->{temperatureProbeUpperNonCriticalThreshold}
3071 ? $out->{temperatureProbeUpperNonCriticalThreshold} / 10 : '[N/A]';
3072 $min_crit = exists $out->{temperatureProbeLowerCriticalThreshold}
3073 ? $out->{temperatureProbeLowerCriticalThreshold} / 10 : '[N/A]';
3074 $min_warn = exists $out->{temperatureProbeLowerNonCriticalThreshold}
3075 ? $out->{temperatureProbeLowerNonCriticalThreshold} / 10 : '[N/A]';
3076 $type = get_hashval($out->{temperatureProbeType}, \%probe_type);
3077 $discrete = exists $out->{temperatureProbeDiscreteReading}
3078 ? $out->{temperatureProbeDiscreteReading} : '[N/A]';
3079 # workaround for bad temp probes
3080 if ($type eq 'AmbientESM' and $reading !~ m{\A \d+(\.\d+)? \z}xms) {
3085 $index = $out->{'Index'};
3086 $status = $out->{'Status'};
3087 $reading = $out->{'Reading'}; $reading =~ s{\.0\s+C}{}xms;
3088 $location = $out->{'Probe Name'};
3089 $max_crit = $out->{'Maximum Failure Threshold'}; $max_crit =~ s{\.0\s+C}{}xms;
3090 $max_warn = $out->{'Maximum Warning Threshold'}; $max_warn =~ s{\.0\s+C}{}xms;
3091 $min_crit = $out->{'Minimum Failure Threshold'}; $min_crit =~ s{\.0\s+C}{}xms;
3092 $min_warn = $out->{'Minimum Warning Threshold'}; $min_warn =~ s{\.0\s+C}{}xms;
3093 $type = $reading =~ m{\A\d+\z}xms ? 'AmbientESM' : 'Discrete';
3094 $discrete = $reading;
3097 next TEMP if blacklisted('temp', $index);
3100 if ($type eq 'Discrete') {
3101 my $msg = sprintf 'Temperature probe %d [%s] is %s',
3102 $index, $location, $discrete;
3103 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3104 report('chassis', $msg, $err, $index);
3107 # First check according to custom thresholds
3108 if (exists $crit_threshold{$index}{max} and $reading > $crit_threshold{$index}{max}) {
3109 # Custom critical MAX
3110 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom max=%d)',
3111 $index, $location, $reading, $crit_threshold{$index}{max};
3112 report('chassis', $msg, $E_CRITICAL, $index);
3114 elsif (exists $warn_threshold{$index}{max} and $reading > $warn_threshold{$index}{max}) {
3115 # Custom warning MAX
3116 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom max=%d)',
3117 $index, $location, $reading, $warn_threshold{$index}{max};
3118 report('chassis', $msg, $E_WARNING, $index);
3120 elsif (exists $crit_threshold{$index}{min} and $reading < $crit_threshold{$index}{min}) {
3121 # Custom critical MIN
3122 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom min=%d)',
3123 $index, $location, $reading, $crit_threshold{$index}{min};
3124 report('chassis', $msg, $E_CRITICAL, $index);
3126 elsif (exists $warn_threshold{$index}{min} and $reading < $warn_threshold{$index}{min}) {
3127 # Custom warning MIN
3128 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C (custom min=%d)',
3129 $index, $location, $reading, $warn_threshold{$index}{min};
3130 report('chassis', $msg, $E_WARNING, $index);
3132 elsif ($status ne 'Ok' and $max_crit ne '[N/A]' and $reading > $max_crit) {
3133 my $msg = sprintf 'Temperature Probe %d [%s] is critically high at %d C',
3134 $index, $location, $reading;
3135 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3136 report('chassis', $msg, $err, $index);
3138 elsif ($status ne 'Ok' and $max_warn ne '[N/A]' and $reading > $max_warn) {
3139 my $msg = sprintf 'Temperature Probe %d [%s] is too high at %d C',
3140 $index, $location, $reading;
3141 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3142 report('chassis', $msg, $err, $index);
3144 elsif ($status ne 'Ok' and $min_crit ne '[N/A]' and $reading < $min_crit) {
3145 my $msg = sprintf 'Temperature Probe %d [%s] is critically low at %d C',
3146 $index, $location, $reading;
3147 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3148 report('chassis', $msg, $err, $index);
3150 elsif ($status ne 'Ok' and $min_warn ne '[N/A]' and $reading < $min_warn) {
3151 my $msg = sprintf 'Temperature Probe %d [%s] is too low at %d C',
3152 $index, $location, $reading;
3153 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3154 report('chassis', $msg, $err, $index);
3158 my $msg = sprintf 'Temperature Probe %d [%s] reads %d C',
3159 $index, $location, $reading;
3160 if ($min_warn eq '[N/A]' and $min_crit eq '[N/A]') {
3161 $msg .= sprintf ' (max=%s/%s)', $max_warn, $max_crit;
3164 $msg .= sprintf ' (min=%s/%s, max=%s/%s)',
3165 $min_warn, $min_crit, $max_warn, $max_crit;
3167 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3168 report('chassis', $msg, $err, $index);
3171 # Collect performance data
3172 if (defined $opt{perfdata}) {
3173 my $pname = lc $location;
3174 $pname =~ s{\s}{_}gxms;
3175 $pname =~ s{_temp\z}{}xms;
3176 $pname =~ s{proc_}{cpu#}xms;
3178 label => "temp_${index}_${pname}",
3191 #-----------------------------------------
3192 # CHASSIS: Check processors
3193 #-----------------------------------------
3194 sub check_processors {
3195 return if blacklisted('cpu', 'all');
3208 # NOTE: For some reason, older models don't have the
3209 # "Processor Device Status" OIDs. We check both the newer
3210 # (preferred) OIDs and the old ones.
3214 '1.3.6.1.4.1.674.10892.1.1100.30.1.2.1' => 'processorDeviceIndex',
3215 '1.3.6.1.4.1.674.10892.1.1100.30.1.5.1' => 'processorDeviceStatus',
3216 '1.3.6.1.4.1.674.10892.1.1100.30.1.8.1' => 'processorDeviceManufacturerName',
3217 '1.3.6.1.4.1.674.10892.1.1100.30.1.9.1' => 'processorDeviceStatusState',
3218 '1.3.6.1.4.1.674.10892.1.1100.30.1.10.1' => 'processorDeviceFamily',
3219 '1.3.6.1.4.1.674.10892.1.1100.30.1.12.1' => 'processorDeviceCurrentSpeed',
3220 '1.3.6.1.4.1.674.10892.1.1100.30.1.23.1' => 'processorDeviceBrandName',
3221 '1.3.6.1.4.1.674.10892.1.1100.32.1.2.1' => 'processorDeviceStatusIndex',
3222 '1.3.6.1.4.1.674.10892.1.1100.32.1.5.1' => 'processorDeviceStatusStatus',
3223 '1.3.6.1.4.1.674.10892.1.1100.32.1.6.1' => 'processorDeviceStatusReading',
3226 if ($opt{use_get_table}) {
3227 my $processorDeviceTable = '1.3.6.1.4.1.674.10892.1.1100.30.1';
3228 my $processorDeviceStatusTable = '1.3.6.1.4.1.674.10892.1.1100.32.1';
3230 $result = $snmp_session->get_table(-baseoid => $processorDeviceTable);
3231 my $ext = $snmp_session->get_table(-baseoid => $processorDeviceStatusTable);
3233 defined $ext && map { $$result{$_} = $$ext{$_} } keys %{ $ext };
3236 $result = $snmp_session->get_entries(-columns => [keys %cpu_oid]);
3239 if (!defined $result) {
3240 printf "SNMP ERROR [processors]: %s.\n", $snmp_session->error;
3241 $snmp_session->close;
3245 @output = @{ get_snmp_output($result, \%cpu_oid) };
3248 @output = @{ run_omreport("$omopt_chassis processors") };
3253 1 => 'Other', # other than following values
3254 2 => 'Unknown', # unknown
3255 3 => 'Enabled', # enabled
3256 4 => 'User Disabled', # disabled by user via BIOS setup
3257 5 => 'BIOS Disabled', # disabled by BIOS (POST error)
3263 1 => 'Internal Error', # Internal Error
3264 2 => 'Thermal Trip', # Thermal Trip
3265 32 => 'Configuration Error', # Configuration Error
3266 128 => 'Present', # Processor Present
3267 256 => 'Disabled', # Processor Disabled
3268 512 => 'Terminator Present', # Terminator Present
3269 1024 => 'Throttled', # Processor Throttled
3272 # Mapping between family numbers from SNMP and actual CPU family
3275 1 => 'Other', 2 => 'Unknown',
3276 3 => '8086', 4 => '80286',
3277 5 => '386', 6 => '486',
3278 7 => '8087', 8 => '80287',
3279 9 => '80387', 10 => '80487',
3280 11 => 'Pentium', 12 => 'Pentium Pro',
3281 13 => 'Pentium II', 14 => 'Pentium with MMX',
3282 15 => 'Celeron', 16 => 'Pentium II Xeon',
3283 17 => 'Pentium III', 18 => 'Pentium III Xeon',
3284 19 => 'Pentium III', 20 => 'Itanium',
3285 21 => 'Xeon', 22 => 'Pentium 4',
3286 23 => 'Xeon MP', 24 => 'Itanium 2',
3287 25 => 'K5', 26 => 'K6',
3288 27 => 'K6-2', 28 => 'K6-3',
3289 29 => 'Athlon', 30 => 'AMD2900',
3290 31 => 'K6-2+', 32 => 'Power PC',
3291 33 => 'Power PC 601', 34 => 'Power PC 603',
3292 35 => 'Power PC 603+', 36 => 'Power PC 604',
3293 37 => 'Power PC 620', 38 => 'Power PC x704',
3294 39 => 'Power PC 750', 40 => 'Core Duo',
3295 41 => 'Core Duo mobile', 42 => 'Core Solo mobile',
3296 43 => 'Intel Atom', 44 => undef,
3297 45 => undef, 46 => undef,
3298 47 => undef, 48 => 'Alpha',
3299 49 => 'Alpha 21064', 50 => 'Alpha 21066',
3300 51 => 'Alpha 21164', 52 => 'Alpha 21164PC',
3301 53 => 'Alpha 21164a', 54 => 'Alpha 21264',
3302 55 => 'Alpha 21364', 56 => 'Turion II Ultra Dual-Core Mobile M',
3303 57 => 'Turion II Dual-Core Mobile M', 58 => 'Athlon II Dual-Core Mobile M ',
3304 59 => 'Opteron 6100', 60 => 'Opteron 4100',
3305 61 => undef, 62 => undef,
3306 63 => undef, 64 => 'MIPS',
3307 65 => 'MIPS R4000', 66 => 'MIPS R4200',
3308 67 => 'MIPS R4400', 68 => 'MIPS R4600',
3309 69 => 'MIPS R10000', 70 => undef,
3310 71 => undef, 72 => undef,
3311 73 => undef, 74 => undef,
3312 75 => undef, 76 => undef,
3313 77 => undef, 78 => undef,
3314 79 => undef, 80 => 'SPARC',
3315 81 => 'SuperSPARC', 82 => 'microSPARC II',
3316 83 => 'microSPARC IIep', 84 => 'UltraSPARC',
3317 85 => 'UltraSPARC II', 86 => 'UltraSPARC IIi',
3318 87 => 'UltraSPARC III', 88 => 'UltraSPARC IIIi',
3319 89 => undef, 90 => undef,
3320 91 => undef, 92 => undef,
3321 93 => undef, 94 => undef,
3322 95 => undef, 96 => '68040',
3323 97 => '68xxx', 98 => '68000',
3324 99 => '68010', 100 => '68020',
3325 101 => '68030', 102 => undef,
3326 103 => undef, 104 => undef,
3327 105 => undef, 106 => undef,
3328 107 => undef, 108 => undef,
3329 109 => undef, 110 => undef,
3330 111 => undef, 112 => 'Hobbit',
3331 113 => undef, 114 => undef,
3332 115 => undef, 116 => undef,
3333 117 => undef, 118 => undef,
3334 119 => undef, 120 => 'Crusoe TM5000',
3335 121 => 'Crusoe TM3000', 122 => 'Efficeon TM8000',
3336 123 => undef, 124 => undef,
3337 125 => undef, 126 => undef,
3338 127 => undef, 128 => 'Weitek',
3339 129 => undef, 130 => 'Celeron M',
3340 131 => 'Athlon 64', 132 => 'Opteron',
3341 133 => 'Sempron', 134 => 'Turion 64 Mobile',
3342 135 => 'Dual-Core Opteron', 136 => 'Athlon 64 X2 DC',
3343 137 => 'Turion 64 X2 M', 138 => 'Quad-Core Opteron',
3344 139 => '3rd gen Opteron', 140 => 'AMD Phenom FX Quad-Core',
3345 141 => 'AMD Phenom X4 Quad-Core', 142 => 'AMD Phenom X2 Dual-Core',
3346 143 => 'AMD Athlon X2 Dual-Core', 144 => 'PA-RISC',
3347 145 => 'PA-RISC 8500', 146 => 'PA-RISC 8000',
3348 147 => 'PA-RISC 7300LC', 148 => 'PA-RISC 7200',
3349 149 => 'PA-RISC 7100LC', 150 => 'PA-RISC 7100',
3350 151 => undef, 152 => undef,
3351 153 => undef, 154 => undef,
3352 155 => undef, 156 => undef,
3353 157 => undef, 158 => undef,
3354 159 => undef, 160 => 'V30',
3355 161 => 'Quad-Core Xeon 3200', 162 => 'Dual-Core Xeon 3000',
3356 163 => 'Quad-Core Xeon 5300', 164 => 'Dual-Core Xeon 5100',
3357 165 => 'Dual-Core Xeon 5000', 166 => 'Dual-Core Xeon LV',
3358 167 => 'Dual-Core Xeon ULV', 168 => 'Dual-Core Xeon 7100',
3359 169 => 'Quad-Core Xeon 5400', 170 => 'Quad-Core Xeon',
3360 171 => 'Dual-Core Xeon 5200', 172 => 'Dual-Core Xeon 7200',
3361 173 => 'Quad-Core Xeon 7300', 174 => 'Quad-Core Xeon 7400',
3362 175 => 'Multi-Core Xeon 7400', 176 => 'M1',
3363 177 => 'M2', 178 => undef,
3364 179 => 'Pentium 4 HT', 180 => 'AS400',
3365 181 => undef, 182 => 'Athlon XP',
3366 183 => 'Athlon MP', 184 => 'Duron',
3367 185 => 'Pentium M', 186 => 'Celeron D',
3368 187 => 'Pentium D', 188 => 'Pentium Extreme',
3369 189 => 'Core Solo', 190 => 'Core2',
3370 191 => 'Core2 Duo', 192 => 'Core2 Solo',
3371 193 => 'Core2 Extreme', 194 => 'Core2 Quad',
3372 195 => 'Core2 Extreme mobile', 196 => 'Core2 Duo mobile',
3373 197 => 'Core2 Solo mobile', 198 => 'Core i7',
3374 199 => 'Dual-Core Celeron', 200 => 'IBM390',
3375 201 => 'G4', 202 => 'G5',
3376 203 => 'ESA/390 G6', 204 => 'z/Architectur',
3377 205 => 'Core i5', 206 => 'Core i3',
3378 207 => undef, 208 => undef,
3379 209 => undef, 210 => 'C7-M',
3380 211 => 'C7-D', 212 => 'C7',
3381 213 => 'Eden', 214 => 'Multi-Core Xeon',
3382 215 => 'Dual-Core Xeon 3xxx', 216 => 'Quad-Core Xeon 3xxx',
3383 217 => 'VIA Nano', 218 => 'Dual-Core Xeon 5xxx',
3384 219 => 'Quad-Core Xeon 5xxx', 220 => undef,
3385 221 => 'Dual-Core Xeon 7xxx', 222 => 'Quad-Core Xeon 7xxx',
3386 223 => 'Multi-Core Xeon 7xxx', 224 => 'Multi-Core Xeon 3400',
3387 225 => undef, 226 => undef,
3388 227 => undef, 228 => undef,
3389 229 => undef, 230 => 'Embedded AMD Opteron Quad-Core',
3390 231 => 'AMD Phenom Triple-Core', 232 => 'AMD Turion Ultra Dual-Core Mobile',
3391 233 => 'AMD Turion Dual-Core Mobile', 234 => 'AMD Athlon Dual-Core',
3392 235 => 'AMD Sempron SI', 236 => 'AMD Phenom II',
3393 237 => 'AMD Athlon II', 238 => 'Six-Core AMD Opteron',
3394 239 => 'AMD Sempron M', 240 => undef,
3395 241 => undef, 242 => undef,
3396 243 => undef, 244 => undef,
3397 245 => undef, 246 => undef,
3398 247 => undef, 248 => undef,
3399 249 => undef, 250 => 'i860',
3404 foreach my $out (@output) {
3406 $index = exists $out->{processorDeviceStatusIndex}
3407 ? $out->{processorDeviceStatusIndex} - 1
3408 : $out->{processorDeviceIndex} - 1;
3409 $status = exists $out->{processorDeviceStatusStatus}
3410 ? $snmp_status{$out->{processorDeviceStatusStatus}}
3411 : $snmp_status{$out->{processorDeviceStatus}};
3412 if (exists $out->{processorDeviceStatusReading}) {
3413 my @states = (); # contains states for the CPU
3415 # get the combined state from the StatusReading OID
3416 foreach my $mask (sort keys %cpu_reading) {
3417 if (($out->{processorDeviceStatusReading} & $mask) != 0) {
3418 push @states, $cpu_reading{$mask};
3422 # Finally, create the state string
3423 $state = join q{, }, @states;
3426 $state = get_hashval($out->{processorDeviceStatusState}, \%cpu_state);
3428 $man = $out->{processorDeviceManufacturerName};
3429 $family = (exists $out->{processorDeviceFamily}
3430 and exists $cpu_family{$out->{processorDeviceFamily}})
3431 ? $cpu_family{$out->{processorDeviceFamily}} : undef;
3432 $speed = $out->{processorDeviceCurrentSpeed};
3433 $brand = $out->{processorDeviceBrandName};
3436 $index = $out->{'Index'};
3437 $status = $out->{'Status'};
3438 $state = $out->{'State'};
3439 $brand = exists $out->{'Processor Brand'} ? $out->{'Processor Brand'} : undef;
3440 $family = exists $out->{'Processor Family'} ? $out->{'Processor Family'} : undef;
3441 $man = exists $out->{'Processor Manufacturer'} ? $out->{'Processor Manufacturer'} : undef;
3442 $speed = exists $out->{'Current Speed'} ? $out->{'Current Speed'} : undef;
3445 next CPU if blacklisted('cpu', $index);
3447 # Ignore unoccupied CPU slots (omreport)
3448 next CPU if (defined $out->{'Processor Manufacturer'}
3449 and $out->{'Processor Manufacturer'} eq '[Not Occupied]')
3450 or (defined $out->{'Processor Brand'} and $out->{'Processor Brand'} eq '[Not Occupied]');
3452 # Ignore unoccupied CPU slots (snmp)
3453 if ($snmp and exists $out->{processorDeviceStatusReading}
3454 and $out->{processorDeviceStatusReading} == 0) {
3460 if (defined $brand) {
3461 $brand =~ s{\s\s+}{ }gxms;
3462 $brand =~ s{\((R|tm)\)}{}gxms;
3463 $brand =~ s{\s(CPU|Processor)}{}xms;
3464 $brand =~ s{\s\@}{}xms;
3466 elsif (defined $family and defined $man and defined $speed) {
3467 $speed =~ s{\A (\d+) .*}{$1}xms;
3468 $brand = sprintf '%s %s %.2fGHz', $man, $family, $speed / 1000;
3475 if ($status ne 'Ok') {
3476 my $msg = sprintf 'Processor %d [%s] needs attention: %s',
3477 $index, $brand, $state;
3478 report('chassis', $msg, $status2nagios{$status}, $index);
3482 my $msg = sprintf 'Processor %d [%s] is %s',
3483 $index, $brand, $state;
3484 report('chassis', $msg, $E_OK, $index);
3491 #-----------------------------------------
3492 # CHASSIS: Check voltage probes
3493 #-----------------------------------------
3495 return if blacklisted('volt', 'all');
3499 my $reading = undef;
3500 my $location = undef;
3506 '1.3.6.1.4.1.674.10892.1.600.20.1.2.1' => 'voltageProbeIndex',
3507 '1.3.6.1.4.1.674.10892.1.600.20.1.5.1' => 'voltageProbeStatus',
3508 '1.3.6.1.4.1.674.10892.1.600.20.1.6.1' => 'voltageProbeReading',
3509 '1.3.6.1.4.1.674.10892.1.600.20.1.8.1' => 'voltageProbeLocationName',
3510 '1.3.6.1.4.1.674.10892.1.600.20.1.16.1' => 'voltageProbeDiscreteReading',
3513 my $voltageProbeTable = '1.3.6.1.4.1.674.10892.1.600.20.1';
3514 my $result = $snmp_session->get_table(-baseoid => $voltageProbeTable);
3516 if (!defined $result) {
3517 printf "SNMP ERROR [voltage]: %s.\n", $snmp_session->error;
3518 $snmp_session->close;
3522 @output = @{ get_snmp_output($result, \%volt_oid) };
3525 @output = @{ run_omreport("$omopt_chassis volts") };
3528 my %volt_discrete_reading
3535 foreach my $out (@output) {
3537 $index = $out->{voltageProbeIndex} - 1;
3538 $status = $snmp_probestatus{$out->{voltageProbeStatus}};
3539 $reading = exists $out->{voltageProbeReading}
3540 ? sprintf('%.3f V', $out->{voltageProbeReading}/1000)
3541 : get_hashval($out->{voltageProbeDiscreteReading}, \%volt_discrete_reading);
3542 $location = $out->{voltageProbeLocationName};
3545 $index = $out->{'Index'};
3546 $status = $out->{'Status'};
3547 $reading = $out->{'Reading'};
3548 $location = $out->{'Probe Name'};
3551 next VOLT if blacklisted('volt', $index);
3554 my $msg = sprintf 'Voltage sensor %d [%s] is %s',
3555 $index, $location, $reading;
3556 my $err = $snmp ? $probestatus2nagios{$status} : $status2nagios{$status};
3557 report('chassis', $msg, $err, $index);
3563 #-----------------------------------------
3564 # CHASSIS: Check batteries
3565 #-----------------------------------------
3566 sub check_batteries {
3567 return if blacklisted('bp', 'all');
3571 my $reading = undef;
3572 my $location = undef;
3578 '1.3.6.1.4.1.674.10892.1.600.50.1.2.1' => 'batteryIndex',
3579 '1.3.6.1.4.1.674.10892.1.600.50.1.5.1' => 'batteryStatus',
3580 '1.3.6.1.4.1.674.10892.1.600.50.1.6.1' => 'batteryReading',
3581 '1.3.6.1.4.1.674.10892.1.600.50.1.7.1' => 'batteryLocationName',
3584 if ($opt{use_get_table}) {
3585 my $batteryTable = '1.3.6.1.4.1.674.10892.1.600.50.1';
3586 $result = $snmp_session->get_table(-baseoid => $batteryTable);
3589 $result = $snmp_session->get_entries(-columns => [keys %bat_oid]);
3592 # No batteries is OK
3593 return 0 if !defined $result;
3595 @output = @{ get_snmp_output($result, \%bat_oid) };
3598 @output = @{ run_omreport("$omopt_chassis batteries") };
3603 1 => 'Predictive Failure',
3605 4 => 'Presence Detected',
3609 foreach my $out (@output) {
3611 $index = $out->{batteryIndex} - 1;
3612 $status = $snmp_status{$out->{batteryStatus}};
3613 $reading = get_hashval($out->{batteryReading}, \%bat_reading);
3614 $location = $out->{batteryLocationName};
3617 $index = $out->{'Index'};
3618 $status = $out->{'Status'};
3619 $reading = $out->{'Reading'};
3620 $location = $out->{'Probe Name'};
3623 next BATTERY if blacklisted('bp', $index);
3626 my $msg = sprintf 'Battery probe %d [%s] is %s',
3627 $index, $location, $reading;
3628 report('chassis', $msg, $status2nagios{$status}, $index);
3634 #-----------------------------------------
3635 # CHASSIS: Check amperage probes (power monitoring)
3636 #-----------------------------------------
3637 sub check_pwrmonitoring {
3638 return if blacklisted('amp', 'all');
3642 my $reading = undef;
3643 my $location = undef;
3644 my $max_crit = undef;
3645 my $max_warn = undef;
3653 '1.3.6.1.4.1.674.10892.1.600.30.1.2.1' => 'amperageProbeIndex',
3654 '1.3.6.1.4.1.674.10892.1.600.30.1.5.1' => 'amperageProbeStatus',
3655 '1.3.6.1.4.1.674.10892.1.600.30.1.6.1' => 'amperageProbeReading',
3656 '1.3.6.1.4.1.674.10892.1.600.30.1.7.1' => 'amperageProbeType',
3657 '1.3.6.1.4.1.674.10892.1.600.30.1.8.1' => 'amperageProbeLocationName',
3658 '1.3.6.1.4.1.674.10892.1.600.30.1.10.1' => 'amperageProbeUpperCriticalThreshold',
3659 '1.3.6.1.4.1.674.10892.1.600.30.1.11.1' => 'amperageProbeUpperNonCriticalThreshold',
3660 '1.3.6.1.4.1.674.10892.1.600.30.1.16.1' => 'amperageProbeDiscreteReading',
3663 if ($opt{use_get_table}) {
3664 my $amperageProbeTable = '1.3.6.1.4.1.674.10892.1.600.30.1';
3665 $result = $snmp_session->get_table(-baseoid => $amperageProbeTable);
3668 $result = $snmp_session->get_entries(-columns => [keys %amp_oid]);
3671 # No pwrmonitoring is OK
3672 return 0 if !defined $result;
3674 @output = @{ get_snmp_output($result, \%amp_oid) };
3677 @output = @{ run_omreport("$omopt_chassis pwrmonitoring") };
3680 my %amp_type # Amperage probe types
3682 1 => 'amperageProbeTypeIsOther', # other than following values
3683 2 => 'amperageProbeTypeIsUnknown', # unknown
3684 3 => 'amperageProbeTypeIs1Point5Volt', # 1.5 amperage probe
3685 4 => 'amperageProbeTypeIs3Point3volt', # 3.3 amperage probe
3686 5 => 'amperageProbeTypeIs5Volt', # 5 amperage probe
3687 6 => 'amperageProbeTypeIsMinus5Volt', # -5 amperage probe
3688 7 => 'amperageProbeTypeIs12Volt', # 12 amperage probe
3689 8 => 'amperageProbeTypeIsMinus12Volt', # -12 amperage probe
3690 9 => 'amperageProbeTypeIsIO', # I/O probe
3691 10 => 'amperageProbeTypeIsCore', # Core probe
3692 11 => 'amperageProbeTypeIsFLEA', # FLEA (standby) probe
3693 12 => 'amperageProbeTypeIsBattery', # Battery probe
3694 13 => 'amperageProbeTypeIsTerminator', # SCSI Termination probe
3695 14 => 'amperageProbeTypeIs2Point5Volt', # 2.5 amperage probe
3696 15 => 'amperageProbeTypeIsGTL', # GTL (ground termination logic) probe
3697 16 => 'amperageProbeTypeIsDiscrete', # amperage probe with discrete reading
3698 23 => 'amperageProbeTypeIsPowerSupplyAmps', # Power Supply probe with reading in Amps
3699 24 => 'amperageProbeTypeIsPowerSupplyWatts', # Power Supply probe with reading in Watts
3700 25 => 'amperageProbeTypeIsSystemAmps', # System probe with reading in Amps
3701 26 => 'amperageProbeTypeIsSystemWatts', # System probe with reading in Watts
3712 'amperageProbeTypeIsPowerSupplyAmps' => 'hA', # tenths of Amps
3713 'amperageProbeTypeIsSystemAmps' => 'hA', # tenths of Amps
3714 'amperageProbeTypeIsPowerSupplyWatts' => 'W', # Watts
3715 'amperageProbeTypeIsSystemWatts' => 'W', # Watts
3716 'amperageProbeTypeIsDiscrete' => q{}, # discrete reading, no unit
3720 foreach my $out (@output) {
3722 $index = $out->{amperageProbeIndex} - 1;
3723 $status = $snmp_status{$out->{amperageProbeStatus}};
3724 $type = get_hashval($out->{amperageProbeType}, \%amp_type);
3725 $reading = $type eq 'amperageProbeTypeIsDiscrete'
3726 ? get_hashval($out->{amperageProbeDiscreteReading}, \%amp_discrete)
3727 : $out->{amperageProbeReading};
3728 $location = $out->{amperageProbeLocationName};
3729 $max_crit = exists $out->{amperageProbeUpperCriticalThreshold}
3730 ? $out->{amperageProbeUpperCriticalThreshold} : 0;
3731 $max_warn = exists $out->{amperageProbeUpperNonCriticalThreshold}
3732 ? $out->{amperageProbeUpperNonCriticalThreshold} : 0;
3733 $unit = exists $amp_unit{$amp_type{$out->{amperageProbeType}}}
3734 ? $amp_unit{$amp_type{$out->{amperageProbeType}}} : 'mA';
3736 # workaround for broken probes
3737 if (!defined $reading) {
3738 $type = 'amperageProbeTypeIsDiscrete';
3743 # calculate proper values and set unit for ampere probes
3744 if ($unit eq 'hA' and $type ne 'amperageProbeTypeIsDiscrete') {
3752 $index = $out->{'Index'};
3753 next AMP if (!defined $index || $index !~ m/^\d+$/x);
3754 $status = $out->{'Status'};
3755 $reading = $out->{'Reading'};
3756 $location = $out->{'Probe Name'};
3757 $max_crit = $out->{'Failure Threshold'} ne '[N/A]'
3758 ? $out->{'Failure Threshold'} : 0;
3759 $max_warn = $out->{'Warning Threshold'} ne '[N/A]'
3760 ? $out->{'Warning Threshold'} : 0;
3761 $reading =~ s{\A (\d+.*?)\s+([a-zA-Z]+) \s*\z}{$1}xms;
3763 $max_warn =~ s{\A (\d+.*?)\s+[a-zA-Z]+ \s*\z}{$1}xms;
3764 $max_crit =~ s{\A (\d+.*?)\s+[a-zA-Z]+ \s*\z}{$1}xms;
3767 next AMP if blacklisted('amp', $index);
3768 next AMP if $index !~ m{\A \d+ \z}xms;
3771 if (defined $type and $type eq 'amperageProbeTypeIsDiscrete') {
3772 my $msg = sprintf 'Amperage probe %d [%s] is %s',
3773 $index, $location, $reading;
3774 report('chassis', $msg, $status2nagios{$status}, $index);
3777 my $msg = sprintf 'Amperage probe %d [%s] reads %s %s',
3778 $index, $location, $reading, $unit;
3779 report('chassis', $msg, $status2nagios{$status}, $index);
3782 # Collect performance data
3783 if (defined $opt{perfdata}) {
3784 next AMP if $reading !~ m{\A \d+(\.\d+)? \z}xms; # discrete reading (not number)
3785 #next AMP if $type eq 'amperageProbeTypeIsDiscrete';
3786 my $label = join q{_}, 'pwr_mon', $index, lc $location;
3787 $label =~ s{\s}{_}gxms;
3790 mini => "p${index}" . lc $unit,
3798 # Collect EXTRA performance data not found at first run. This is a
3800 if (defined $opt{perfdata} && !$snmp) {
3806 foreach (@perfdata) {
3807 if ($_->{label} =~ m/\A pwr_mon_(\d+)/xms) {
3813 foreach my $line (@{ run_command("$omreport $omopt_chassis pwrmonitoring -fmt ssv") }) {
3815 if ($line eq 'Location;Reading') {
3823 if ($found and $line =~ m/\A ([^;]+?) ; (\d*\.\d+) \s [AW] \z/xms) {
3826 $aname =~ s{\s}{_}gxms;
3828 # don't use an existing index
3829 while (exists $used{$index}) { ++$index; }
3832 label => "pwr_mon_${index}_${aname}",
3833 mini => "p${index}a",
3847 #-----------------------------------------
3848 # CHASSIS: Check intrusion
3849 #-----------------------------------------
3850 sub check_intrusion {
3851 return if blacklisted('intr', 'all');
3855 my $reading = undef;
3861 '1.3.6.1.4.1.674.10892.1.300.70.1.2.1' => 'intrusionIndex',
3862 '1.3.6.1.4.1.674.10892.1.300.70.1.5.1' => 'intrusionStatus',
3863 '1.3.6.1.4.1.674.10892.1.300.70.1.6.1' => 'intrusionReading',
3866 if ($opt{use_get_table}) {
3867 my $intrusionTable = '1.3.6.1.4.1.674.10892.1.300.70.1';
3868 $result = $snmp_session->get_table(-baseoid => $intrusionTable);
3871 $result = $snmp_session->get_entries(-columns => [keys %int_oid]);
3874 # No intrusion is OK
3875 return 0 if !defined $result;
3877 @output = @{ get_snmp_output($result, \%int_oid) };
3880 @output = @{ run_omreport("$omopt_chassis intrusion") };
3885 1 => 'Not Breached', # chassis not breached and no uncleared breaches
3886 2 => 'Breached', # chassis currently breached
3887 3 => 'Breached Prior', # chassis breached prior to boot and has not been cleared
3888 4 => 'Breach Sensor Failure', # intrusion sensor has failed
3892 foreach my $out (@output) {
3894 $index = $out->{intrusionIndex} - 1;
3895 $status = $snmp_status{$out->{intrusionStatus}};
3896 $reading = get_hashval($out->{intrusionReading}, \%int_reading);
3899 $index = $out->{'Index'};
3900 $status = $out->{'Status'};
3901 $reading = $out->{'State'};
3904 next INTRUSION if blacklisted('intr', $index);
3907 if ($status ne 'Ok') {
3908 my $msg = sprintf 'Chassis intrusion %d detected: %s',
3910 report('chassis', $msg, $E_WARNING, $index);
3914 my $msg = sprintf 'Chassis intrusion %d detection: %s (%s)',
3915 $index, $status, $reading;
3916 report('chassis', $msg, $E_OK, $index);
3923 #-----------------------------------------
3924 # CHASSIS: Check alert log
3925 #-----------------------------------------
3926 sub check_alertlog {
3927 return if $snmp; # Not supported with SNMP
3929 my @output = @{ run_omreport("$omopt_system alertlog") };
3930 foreach my $out (@output) {
3931 ++$count{alert}{$out->{Severity}};
3934 # Create error messages and set exit value if appropriate
3936 if ($count{alert}{'Critical'} > 0) { $err = $E_CRITICAL; }
3937 elsif ($count{alert}{'Non-Critical'} > 0) { $err = $E_WARNING; }
3939 my $msg = sprintf 'Alert log content: %d critical, %d non-critical, %d ok',
3940 $count{alert}{'Critical'}, $count{alert}{'Non-Critical'}, $count{alert}{'Ok'};
3941 report('other', $msg, $err);
3946 #-----------------------------------------
3947 # CHASSIS: Check ESM log overall health
3948 #-----------------------------------------
3949 sub check_esmlog_health {
3953 my $systemStateEventLogStatus = '1.3.6.1.4.1.674.10892.1.200.10.1.41.1';
3954 my $result = $snmp_session->get_request(-varbindlist => [$systemStateEventLogStatus]);
3955 if (!defined $result) {
3956 my $msg = sprintf 'SNMP ERROR [esmhealth]: %s',
3957 $snmp_session->error;
3958 report('other', $msg, $E_UNKNOWN);
3960 $health = $snmp_status{$result->{$systemStateEventLogStatus}};
3963 foreach (@{ run_command("$omreport $omopt_system esmlog -fmt ssv") }) {
3964 if (m/\A Health;(.+) \z/xms) {
3972 # If the overall health of the ESM log is other than "Ok", the
3973 # fill grade of the log is more than 80% and the log should be
3975 if ($health eq 'Ok') {
3976 my $msg = sprintf 'ESM log health is Ok (less than 80%% full)';
3977 report('other', $msg, $E_OK);
3979 elsif ($health eq 'Critical') {
3980 my $msg = sprintf 'ESM log is 100%% full';
3981 report('other', $msg, $status2nagios{$health});
3984 my $msg = sprintf 'ESM log is more than 80%% full';
3985 report('other', $msg, $status2nagios{$health});
3991 #-----------------------------------------
3992 # CHASSIS: Check ESM log
3993 #-----------------------------------------
4000 '1.3.6.1.4.1.674.10892.1.300.40.1.7.1' => 'eventLogSeverityStatus',
4002 my $result = $snmp_session->get_entries(-columns => [keys %esm_oid]);
4005 return if !defined $result;
4007 @output = @{ get_snmp_output($result, \%esm_oid) };
4008 foreach my $out (@output) {
4009 ++$count{esm}{$snmp_status{$out->{eventLogSeverityStatus}}};
4013 @output = @{ run_omreport("$omopt_system esmlog") };
4014 foreach my $out (@output) {
4015 ++$count{esm}{$out->{Severity}};
4019 # Create error messages and set exit value if appropriate
4021 if ($count{esm}{'Critical'} > 0) { $err = $E_CRITICAL; }
4022 elsif ($count{esm}{'Non-Critical'} > 0) { $err = $E_WARNING; }
4024 my $msg = sprintf 'ESM log content: %d critical, %d non-critical, %d ok',
4025 $count{esm}{'Critical'}, $count{esm}{'Non-Critical'}, $count{esm}{'Ok'};
4026 report('other', $msg, $err);
4032 # Handy function for checking all storage components
4035 check_controllers();
4036 check_physical_disks();
4037 check_virtual_disks();
4038 check_cache_battery();
4041 check_enclosure_fans();
4042 check_enclosure_pwr();
4043 check_enclosure_temp();
4044 check_enclosure_emms();
4050 #---------------------------------------------------------------------
4052 #---------------------------------------------------------------------
4055 # Fetch output from 'omreport chassis info', put in sysinfo hash
4057 sub get_omreport_chassis_info {
4058 if (open my $INFO, '-|', "$omreport $omopt_chassis info -fmt ssv") {
4059 my @lines = <$INFO>;
4062 next if !m/\A (Chassis\sModel|Chassis\sService\sTag|Model|Service\sTag)/xms;
4063 my ($key, $val) = split /;/xms;
4064 $key =~ s{\s+\z}{}xms; # remove trailing whitespace
4065 $val =~ s{\s+\z}{}xms; # remove trailing whitespace
4066 if ($key eq 'Chassis Model' or $key eq 'Model') {
4067 $sysinfo{model} = $val;
4069 if ($key eq 'Chassis Service Tag' or $key eq 'Service Tag') {
4070 $sysinfo{serial} = $val;
4078 # Fetch output from 'omreport chassis bios', put in sysinfo hash
4080 sub get_omreport_chassis_bios {
4081 if (open my $BIOS, '-|', "$omreport $omopt_chassis bios -fmt ssv") {
4082 my @lines = <$BIOS>;
4086 my ($key, $val) = split /;/xms;
4087 $key =~ s{\s+\z}{}xms; # remove trailing whitespace
4088 $val =~ s{\s+\z}{}xms; # remove trailing whitespace
4089 $sysinfo{bios} = $val if $key eq 'Version';
4090 $sysinfo{biosdate} = $val if $key eq 'Release Date';
4097 # Fetch output from 'omreport system operatingsystem', put in sysinfo hash
4099 sub get_omreport_system_operatingsystem {
4100 if (open my $VER, '-|', "$omreport $omopt_system operatingsystem -fmt ssv") {
4105 my ($key, $val) = split /;/xms;
4106 $key =~ s{\s+\z}{}xms; # remove trailing whitespace
4107 $val =~ s{\s+\z}{}xms; # remove trailing whitespace
4108 if ($key eq 'Operating System') {
4109 $sysinfo{osname} = $val;
4111 elsif ($key eq 'Operating System Version') {
4112 $sysinfo{osver} = $val;
4120 # Fetch output from 'omreport about', put in sysinfo hash
4122 sub get_omreport_about {
4123 if (open my $OM, '-|', "$omreport about -fmt ssv") {
4127 if (m/\A Version;(.+) \z/xms) {
4137 # Fetch chassis info via SNMP, put in sysinfo hash
4139 sub get_snmp_chassis_info {
4142 '1.3.6.1.4.1.674.10892.1.300.10.1.9.1' => 'chassisModelName',
4143 '1.3.6.1.4.1.674.10892.1.300.10.1.11.1' => 'chassisServiceTagName',
4146 my $chassisInformationTable = '1.3.6.1.4.1.674.10892.1.300.10.1';
4147 my $result = $snmp_session->get_table(-baseoid => $chassisInformationTable);
4149 if (defined $result) {
4150 foreach my $oid (keys %{ $result }) {
4151 if (exists $chassis_oid{$oid} and $chassis_oid{$oid} eq 'chassisModelName') {
4152 $sysinfo{model} = $result->{$oid};
4153 $sysinfo{model} =~ s{\s+\z}{}xms; # remove trailing whitespace
4155 elsif (exists $chassis_oid{$oid} and $chassis_oid{$oid} eq 'chassisServiceTagName') {
4156 $sysinfo{serial} = $result->{$oid};
4161 my $msg = sprintf 'SNMP ERROR getting chassis info: %s',
4162 $snmp_session->error;
4163 report('other', $msg, $E_UNKNOWN);
4169 # Fetch BIOS info via SNMP, put in sysinfo hash
4171 sub get_snmp_chassis_bios {
4174 '1.3.6.1.4.1.674.10892.1.300.50.1.7.1.1' => 'systemBIOSReleaseDateName',
4175 '1.3.6.1.4.1.674.10892.1.300.50.1.8.1.1' => 'systemBIOSVersionName',
4178 my $systemBIOSTable = '1.3.6.1.4.1.674.10892.1.300.50.1';
4179 my $result = $snmp_session->get_table(-baseoid => $systemBIOSTable);
4181 if (defined $result) {
4182 foreach my $oid (keys %{ $result }) {
4183 if (exists $bios_oid{$oid} and $bios_oid{$oid} eq 'systemBIOSReleaseDateName') {
4184 $sysinfo{biosdate} = $result->{$oid};
4185 $sysinfo{biosdate} =~ s{\A (\d{4})(\d{2})(\d{2}).*}{$2/$3/$1}xms;
4187 elsif (exists $bios_oid{$oid} and $bios_oid{$oid} eq 'systemBIOSVersionName') {
4188 $sysinfo{bios} = $result->{$oid};
4193 my $msg = sprintf 'SNMP ERROR getting BIOS info: %s',
4194 $snmp_session->error;
4195 report('other', $msg, $E_UNKNOWN);
4201 # Fetch OS info via SNMP, put in sysinfo hash
4203 sub get_snmp_system_operatingsystem {
4206 '1.3.6.1.4.1.674.10892.1.400.10.1.6.1' => 'operatingSystemOperatingSystemName',
4207 '1.3.6.1.4.1.674.10892.1.400.10.1.7.1' => 'operatingSystemOperatingSystemVersionName',
4210 my $operatingSystemTable = '1.3.6.1.4.1.674.10892.1.400.10.1';
4211 my $result = $snmp_session->get_table(-baseoid => $operatingSystemTable);
4213 if (defined $result) {
4214 foreach my $oid (keys %{ $result }) {
4215 if (exists $os_oid{$oid} and $os_oid{$oid} eq 'operatingSystemOperatingSystemName') {
4216 $sysinfo{osname} = ($result->{$oid});
4218 elsif (exists $os_oid{$oid} and $os_oid{$oid} eq 'operatingSystemOperatingSystemVersionName') {
4219 $sysinfo{osver} = $result->{$oid};
4224 my $msg = sprintf 'SNMP ERROR getting OS info: %s',
4225 $snmp_session->error;
4226 report('other', $msg, $E_UNKNOWN);
4232 # Fetch OMSA version via SNMP, put in sysinfo hash
4234 sub get_snmp_about {
4235 # systemManagementSoftwareGlobalVersionName
4236 my $oid = '1.3.6.1.4.1.674.10892.1.100.10.0';
4237 my $result = $snmp_session->get_request(-varbindlist => [$oid]);
4239 if (defined $result) {
4240 $sysinfo{om} = exists $result->{$oid} && $result->{$oid} ne q{}
4241 ? $result->{$oid} : 'unknown';
4244 my $msg = sprintf 'SNMP ERROR: Getting OMSA version failed: %s', $snmp_session->error;
4245 report('other', $msg, $E_UNKNOWN);
4251 # Collects some information about the system
4255 # Get system model and serial number
4256 $snmp ? get_snmp_chassis_info() : get_omreport_chassis_info();
4258 # Get BIOS information. Only if needed
4259 if ( $opt{okinfo} >= 1
4261 or (defined $opt{postmsg} and $opt{postmsg} =~ m/[%][bd]/xms) ) {
4262 $snmp ? get_snmp_chassis_bios() : get_omreport_chassis_bios();
4265 # Get OMSA information. Only if needed
4266 if ($opt{okinfo} >= 3 or $opt{debug}) {
4267 $snmp ? get_snmp_about() : get_omreport_about();
4270 # Return now if debug
4271 return if $opt{debug};
4273 # Get OS information. Only if needed
4274 if (defined $opt{postmsg} and $opt{postmsg} =~ m/[%][or]/xms) {
4275 $snmp ? get_snmp_system_operatingsystem() : get_omreport_system_operatingsystem();
4282 # Helper function for running omreport when the results are strictly
4284 sub run_omreport_info {
4285 my $command = shift;
4289 # Run omreport and fetch output
4290 my $rawtext = slurp_command("$omreport $command -fmt ssv 2>&1");
4292 # Parse output, store in array
4293 for ((split /\n/xms, $rawtext)) {
4294 if (m/\A Error/xms) {
4295 my $msg = "Problem running 'omreport $command': $_";
4296 report('other', $msg, $E_UNKNOWN);
4298 next if !m/;/xms; # ignore lines with less than two fields
4299 my @vals = split m/;/xms;
4300 $output{$vals[0]} = $vals[1];
4303 # Finally, return the collected information
4307 # Get various firmware information (BMC, RAC)
4308 sub get_firmware_info {
4309 my @snmp_output = ();
4310 my %nrpe_output = ();
4315 '1.3.6.1.4.1.674.10892.1.300.60.1.7.1' => 'firmwareType',
4316 '1.3.6.1.4.1.674.10892.1.300.60.1.8.1' => 'firmwareTypeName',
4317 '1.3.6.1.4.1.674.10892.1.300.60.1.11.1' => 'firmwareVersionName',
4320 my $firmwareTable = '1.3.6.1.4.1.674.10892.1.300.60.1';
4321 my $result = $snmp_session->get_table(-baseoid => $firmwareTable);
4323 # Some don't have this OID, this is ok
4324 if (!defined $result) {
4328 @snmp_output = @{ get_snmp_output($result, \%fw_oid) };
4331 %nrpe_output = %{ run_omreport_info("$omopt_chassis info") };
4334 my %fw_type # Firmware types
4336 1 => 'other', # other than following values
4337 2 => 'unknown', # unknown
4338 3 => 'systemBIOS', # System BIOS
4339 4 => 'embeddedSystemManagementController', # Embedded System Management Controller
4340 5 => 'powerSupplyParallelingBoard', # Power Supply Paralleling Board
4341 6 => 'systemBackPlane', # System (Primary) Backplane
4342 7 => 'powerVault2XXSKernel', # PowerVault 2XXS Kernel
4343 8 => 'powerVault2XXSApplication', # PowerVault 2XXS Application
4344 9 => 'frontPanel', # Front Panel Controller
4345 10 => 'baseboardManagementController', # Baseboard Management Controller
4346 11 => 'hotPlugPCI', # Hot Plug PCI Controller
4347 12 => 'sensorData', # Sensor Data Records
4348 13 => 'peripheralBay', # Peripheral Bay Backplane
4349 14 => 'secondaryBackPlane', # Secondary Backplane for ESM 2 systems
4350 15 => 'secondaryBackPlaneESM3And4', # Secondary Backplane for ESM 3 and 4 systems
4351 16 => 'rac', # Remote Access Controller
4352 17 => 'imc' # Integrated Management Controller
4357 foreach my $out (@snmp_output) {
4358 if ($fw_type{$out->{firmwareType}} eq 'baseboardManagementController') {
4359 $sysinfo{'bmc'} = 1;
4360 $sysinfo{'bmc_fw'} = $out->{firmwareVersionName};
4362 elsif ($fw_type{$out->{firmwareType}} =~ m{\A rac|imc \z}xms) {
4363 my $name = $out->{firmwareTypeName}; $name =~ s/\s//gxms;
4364 $sysinfo{'rac'} = 1;
4365 $sysinfo{'rac_name'} = $name;
4366 $sysinfo{'rac_fw'} = $out->{firmwareVersionName};
4371 foreach my $key (keys %nrpe_output) {
4372 next if !defined $nrpe_output{$key};
4373 if ($key eq 'BMC Version' or $key eq 'Baseboard Management Controller Version') {
4374 $sysinfo{'bmc'} = 1;
4375 $sysinfo{'bmc_fw'} = $nrpe_output{$key};
4377 elsif ($key =~ m{\A (i?DRAC)\s*(\d?)\s+Version}xms) {
4379 $sysinfo{'rac'} = 1;
4380 $sysinfo{'rac_fw'} = $nrpe_output{$key};
4381 $sysinfo{'rac_name'} = $name;
4391 #=====================================================================
4393 #=====================================================================
4395 # Here we do the actual checking of components
4396 # Check global status if applicable
4398 $globalstatus = check_global();
4401 # Do multiple selected checks
4402 if ($check{storage}) { check_storage(); }
4403 if ($check{memory}) { check_memory(); }
4404 if ($check{fans}) { check_fans(); }
4405 if ($check{power}) { check_powersupplies(); }
4406 if ($check{temp}) { check_temperatures(); }
4407 if ($check{cpu}) { check_processors(); }
4408 if ($check{voltage}) { check_volts(); }
4409 if ($check{batteries}) { check_batteries(); }
4410 if ($check{amperage}) { check_pwrmonitoring(); }
4411 if ($check{intrusion}) { check_intrusion(); }
4412 if ($check{alertlog}) { check_alertlog(); }
4413 if ($check{esmlog}) { check_esmlog(); }
4414 if ($check{esmhealth}) { check_esmlog_health(); }
4417 #---------------------------------------------------------------------
4419 #---------------------------------------------------------------------
4430 # Get system information
4433 # Get firmware info if requested via option
4434 if ($opt{okinfo} >= 1) {
4435 get_firmware_info();
4438 # Close SNMP session
4440 $snmp_session->close;
4445 print " System: $sysinfo{model}\n";
4446 print " ServiceTag: $sysinfo{serial}";
4447 print q{ } x (25 - length $sysinfo{serial}), "OMSA version: $sysinfo{om}\n";
4448 print " BIOS/date: $sysinfo{bios} $sysinfo{biosdate}";
4449 print q{ } x (25 - length "$sysinfo{bios} $sysinfo{biosdate}"), "Plugin version: $VERSION\n";
4450 if ($#report_storage >= 0) {
4451 print "-----------------------------------------------------------------------------\n";
4452 print " Storage Components \n";
4453 print "=============================================================================\n";
4454 print " STATE | ID | MESSAGE TEXT \n";
4455 print "---------+----------+--------------------------------------------------------\n";
4456 foreach (@report_storage) {
4457 my ($msg, $level, $nexus) = @{$_};
4458 print q{ } x (8 - length $reverse_exitcode{$level}) . "$reverse_exitcode{$level} | "
4459 . q{ } x (8 - length $nexus) . "$nexus | $msg\n";
4460 $nagios_alert_count{$reverse_exitcode{$level}}++;
4463 if ($#report_chassis >= 0) {
4464 print "-----------------------------------------------------------------------------\n";
4465 print " Chassis Components \n";
4466 print "=============================================================================\n";
4467 print " STATE | ID | MESSAGE TEXT \n";
4468 print "---------+------+------------------------------------------------------------\n";
4469 foreach (@report_chassis) {
4470 my ($msg, $level, $nexus) = @{$_};
4471 print q{ } x (8 - length $reverse_exitcode{$level}) . "$reverse_exitcode{$level} | "
4472 . q{ } x (4 - length $nexus) . "$nexus | $msg\n";
4473 $nagios_alert_count{$reverse_exitcode{$level}}++;
4476 if ($#report_other >= 0) {
4477 print "-----------------------------------------------------------------------------\n";
4478 print " Other messages \n";
4479 print "=============================================================================\n";
4480 print " STATE | MESSAGE TEXT \n";
4481 print "---------+-------------------------------------------------------------------\n";
4482 foreach (@report_other) {
4483 my ($msg, $level, $nexus) = @{$_};
4484 print q{ } x (8 - length $reverse_exitcode{$level}) . "$reverse_exitcode{$level} | $msg\n";
4485 $nagios_alert_count{$reverse_exitcode{$level}}++;
4490 my $c = 0; # counter to determine linebreaks
4492 # Run through each message, sorted by severity level
4494 foreach (sort {$a->[1] < $b->[1]} (@report_storage, @report_chassis, @report_other)) {
4495 my ($msg, $level, $nexus) = @{ $_ };
4496 next ALERT if $level == $E_OK;
4498 if (defined $opt{only}) {
4499 # If user wants only critical alerts
4500 next ALERT if ($opt{only} eq 'critical' and $level == $E_WARNING);
4502 # If user wants only warning alerts
4503 next ALERT if ($opt{only} eq 'warning' and $level == $E_CRITICAL);
4506 # Prefix with service tag if specified with option '-i|--info'
4508 if (defined $opt{htmlinfo}) {
4509 $msg = '[<a href="' . warranty_url($sysinfo{serial})
4510 . "\">$sysinfo{serial}</a>] " . $msg;
4513 $msg = "[$sysinfo{serial}] " . $msg;
4517 # Prefix with nagios level if specified with option '--state'
4518 $msg = $reverse_exitcode{$level} . ": $msg" if $opt{state};
4520 # Prefix with one-letter nagios level if specified with option '--short-state'
4521 $msg = (substr $reverse_exitcode{$level}, 0, 1) . ": $msg" if $opt{shortstate};
4523 ($c++ == 0) ? print $msg : print $linebreak, $msg;
4525 $nagios_alert_count{$reverse_exitcode{$level}}++;
4529 # Determine our exit code
4531 $exit_code = $E_UNKNOWN if $nagios_alert_count{'UNKNOWN'} > 0;
4532 $exit_code = $E_WARNING if $nagios_alert_count{'WARNING'} > 0;
4533 $exit_code = $E_CRITICAL if $nagios_alert_count{'CRITICAL'} > 0;
4535 # Global status via SNMP.. extra safety check
4536 if ($globalstatus != $E_OK && $exit_code == $E_OK && !defined $opt{only}) {
4537 print "OOPS! Something is wrong with this server, but I don't know what. ";
4538 print "The global system health status is $reverse_exitcode{$globalstatus}, ";
4539 print "but every component check is OK. This may be a bug in the Nagios plugin, ";
4540 print "please file a bug report.\n";
4545 if ($exit_code == $E_OK && defined $opt{only} && $opt{only} !~ m{\A critical|warning|chassis \z}xms && !$opt{debug}) {
4547 = ( 'storage' => "STORAGE OK - $count{pdisk} physical drives, $count{vdisk} logical drives",
4548 'fans' => $count{fan} == 0 && $blade ? 'OK - blade system with no fan probes' : "FANS OK - $count{fan} fan probes checked",
4549 'temp' => "TEMPERATURES OK - $count{temp} temperature probes checked",
4550 'memory' => "MEMORY OK - $count{dimm} memory modules, $count{mem} MB total memory",
4551 'power' => $count{power} == 0 ? 'OK - no instrumented power supplies found' : "POWER OK - $count{power} power supplies checked",
4552 'cpu' => "PROCESSORS OK - $count{cpu} processors checked",
4553 'voltage' => "VOLTAGE OK - $count{volt} voltage probes checked",
4554 'batteries' => $count{bat} == 0 ? 'OK - no batteries found' : "BATTERIES OK - $count{bat} batteries checked",
4555 'amperage' => $count{amp} == 0 ? 'OK - no power monitoring probes found' : "AMPERAGE OK - $count{amp} amperage (power monitoring) probes checked",
4556 'intrusion' => $count{intr} == 0 ? 'OK - no intrusion detection probes found' : "INTRUSION OK - $count{intr} intrusion detection probes checked",
4557 '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",
4558 'esmlog' => "OK - ESM Log content: $count{esm}{Ok} ok, $count{esm}{'Non-Critical'} warning and $count{esm}{Critical} critical",
4559 'esmhealth' => "ESM LOG OK - less than 80% used",
4562 print $okmsg{$opt{only}};
4564 elsif ($exit_code == $E_OK && !$opt{debug}) {
4565 if (defined $opt{htmlinfo}) {
4566 printf q{OK - System: '<a href="%s">%s</a>', SN: '<a href="%s">%s</a>'},
4567 documentation_url($sysinfo{model}), $sysinfo{model},
4568 warranty_url($sysinfo{serial}), $sysinfo{serial};
4571 printf q{OK - System: '%s', SN: '%s'},
4572 $sysinfo{model}, $sysinfo{serial};
4575 if ($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 $opt{htmlinfo}) {
4642 printf '------ SYSTEM: <a href="%s">%s</a>, SN: <a href="%s">%s</a>',
4643 documentation_url($sysinfo{model}), $sysinfo{model},
4644 warranty_url($sysinfo{serial}), $sysinfo{serial};
4647 printf '------ SYSTEM: %s, SN: %s',
4648 $sysinfo{model}, $sysinfo{serial};
4651 if (defined $opt{postmsg}) {
4653 if (-f $opt{postmsg}) {
4654 open my $POST, '<', $opt{postmsg}
4655 or ( print $linebreak
4656 and print "ERROR: Couldn't open post message file $opt{postmsg}: $!\n"
4657 and exit $E_UNKNOWN );
4663 $post = $opt{postmsg};
4665 if (defined $post) {
4667 $post =~ s{[%]s}{$sysinfo{serial}}gxms;
4668 $post =~ s{[%]m}{$sysinfo{model}}gxms;
4669 $post =~ s{[%]b}{$sysinfo{bios}}gxms;
4670 $post =~ s{[%]d}{$sysinfo{biosdate}}gxms;
4671 $post =~ s{[%]o}{$sysinfo{osname}}gxms;
4672 $post =~ s{[%]r}{$sysinfo{osver}}gxms;
4673 $post =~ s{[%]p}{$count{pdisk}}gxms;
4674 $post =~ s{[%]l}{$count{vdisk}}gxms;
4675 $post =~ s{[%]n}{$linebreak}gxms;
4676 $post =~ s{[%]{2}}{%}gxms;
4682 # Reset the WARN signal
4683 $SIG{__WARN__} = 'DEFAULT';
4685 # Print any perl warnings that have occured
4686 if (@perl_warnings) {
4687 foreach (@perl_warnings) {
4689 print "${linebreak}INTERNAL ERROR: @$_";
4691 $exit_code = $E_UNKNOWN;
4694 # Print performance data
4695 if (defined $opt{perfdata} && !$opt{debug} && @perfdata) {
4696 my $lb = $opt{perfdata} eq 'multiline' ? "\n" : q{ }; # line break for perfdata
4699 # Sort routine for performance data
4701 my %order = ( fan => 0, pwr => 1, tem => 2, enc => 3, );
4702 return ($order{(substr $a->{label}, 0, 3)} cmp $order{(substr $b->{label}, 0, 3)}) ||
4703 $a->{label} cmp $b->{label};
4706 # Print performance data sorted
4707 my $type = $opt{perfdata} eq 'minimal' ? 'mini' : 'label';
4708 print join $lb, map { "$_->{$type}=$_->{value};$_->{warn};$_->{crit}" } sort perfsort @perfdata;
4711 # Print a linebreak at the end
4712 print "\n" if !$opt{debug};
4714 # Exit with proper exit code