This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
storage:svc_scripts [2024/11/13 00:28] manu [Check quorum] |
storage:svc_scripts [2025/02/28 14:36] (current) manu |
||
---|---|---|---|
Line 2: | Line 2: | ||
===== Monitoring SVC nagios ===== | ===== Monitoring SVC nagios ===== | ||
+ | |||
+ | ==== Check paths ==== | ||
+ | |||
+ | <cli prompt='#'> | ||
+ | [root@aix001]/usr/local/nagios/libexec# cat check_paths.sh | ||
+ | </cli> | ||
+ | <code> | ||
+ | #!/bin/sh | ||
+ | #@(#) v1.0 Count number of paths per disk | ||
+ | # v1.1 add sudo linux | ||
+ | # v1.2 change for VSCSI | ||
+ | # v1.3 add verbose (-v), improvements linux | ||
+ | |||
+ | # number of path per type of disk | ||
+ | pathviosfc=4 | ||
+ | pathviosscsi=2 | ||
+ | pathviossas=1 | ||
+ | pathlparfc=8 | ||
+ | pathlparscsi=2 | ||
+ | pathlparsas=1 | ||
+ | |||
+ | |||
+ | STATUS=0 | ||
+ | |||
+ | STATE_OK=0 | ||
+ | STATE_WARNING=1 | ||
+ | STATE_CRITICAL=2 | ||
+ | STATE_UNKNOWN=3 | ||
+ | |||
+ | MSG="" | ||
+ | verbose="" | ||
+ | |||
+ | # specified value for nb paths | ||
+ | if [ "$npath" == "" ] | ||
+ | then | ||
+ | nbpath=$pathlparfc | ||
+ | fi | ||
+ | |||
+ | os=$(uname -a | awk '{print $1}') | ||
+ | |||
+ | grepp() { [ $# -eq 1 ] && perl -00ne "print if /$1/i" || perl -00ne "print if /$1/i" < "$2";} | ||
+ | |||
+ | #--------------------- | ||
+ | count_linux_path() | ||
+ | { | ||
+ | tempfile=/tmp/multipath.txt | ||
+ | |||
+ | if [ ! -x /usr/sbin/multipath ] || [ $(lsscsi -s | grep -q VMware; echo $?) -eq 0 ] | ||
+ | then | ||
+ | MSG="OK: no multipathing" | ||
+ | verbose="$MSG" | ||
+ | STATUS=$STATE_OK | ||
+ | else | ||
+ | if [ $(timeout 30 sudo /usr/sbin/multipath -ll | grep -v "policy=" | grep -v "size=" | tr -s ' ' | sed 's/\ /;/g' | sed '/^mpath/i \\n' > $tempfile ; echo $?) -ne "0" ] | ||
+ | then | ||
+ | MSG="$MSG Maybe error on sudo config" | ||
+ | verbose="$MSG" | ||
+ | STATUS=$STATE_UNKNOWN | ||
+ | else | ||
+ | for i in $(cat $tempfile | grep '^mpath' | awk -F';' '{print $1}') | ||
+ | do | ||
+ | pathok=$(cat $tempfile | grepp "^$i;" | grep -v "policy=" | grep -v "size=" | grep -v '^mpath' | grep active | wc -l | awk '{print $1}') | ||
+ | pathok_pct=$(echo "scale=1;100*$pathok/$nbpath" | bc | cut -d '.' -f1) | ||
+ | verbose="$verbose $i;$pathok/$nbpath" # verbose message | ||
+ | if [ "$pathok_pct" -lt "50" ] | ||
+ | then | ||
+ | MSG="$MSG $i;$pathok/$nbpath" | ||
+ | if [ $STATUS -lt $STATE_CRITICAL ] | ||
+ | then | ||
+ | STATUS=$STATE_CRITICAL | ||
+ | fi | ||
+ | else | ||
+ | if [ "$pathok_pct" -ne "100" ] | ||
+ | then | ||
+ | MSG="$MSG $i;$pathok/$nbpath" | ||
+ | if [ $STATUS -lt $STATE_CRITICAL ] | ||
+ | then | ||
+ | STATUS=$STATE_WARNING | ||
+ | fi | ||
+ | fi | ||
+ | fi | ||
+ | done | ||
+ | fi | ||
+ | fi | ||
+ | |||
+ | rm -f $tempfile 2>/dev/null | ||
+ | } | ||
+ | |||
+ | #--------------------- | ||
+ | count_aix_path() | ||
+ | { | ||
+ | # check not available disks | ||
+ | nbdisknok=$(lsdev -Cc disk | grep -v Available | wc -l | awk '{print $1}') | ||
+ | if [ "$nbdisknok" -ne "0" ] | ||
+ | then | ||
+ | MSG="$MSG WARNING: $nbdisknok disks defined" | ||
+ | verbose="$MSG" | ||
+ | STATUS=$STATE_WARNING | ||
+ | else | ||
+ | STATUS=$STATE_OK | ||
+ | fi | ||
+ | |||
+ | for line in $(lsdev -Cc disk | tr -s ' ' | sed 's/\ /:/' | sed 's/\ /:/' | sed 's/\ /,/g') | ||
+ | do | ||
+ | hdisk=$(echo $line | awk -F':' '{print $1}') | ||
+ | if [ "$(echo $line | cut -d':' -f3- | tr 'A-Z' 'a-z' | grep -q mpio; echo $?)" -eq "0" ] | ||
+ | then | ||
+ | if [ ! -e /usr/ios/cli/ioscli ] | ||
+ | then | ||
+ | # type LPAR FC | ||
+ | nbpath=$pathlparfc | ||
+ | else | ||
+ | # type VIOS FC | ||
+ | nbpath=$pathviosfc | ||
+ | fi | ||
+ | else | ||
+ | if [ "$(echo $line | cut -d':' -f3- | tr 'A-Z' 'a-z' | grep -q scsi; echo $?)" -eq "0" ] | ||
+ | then | ||
+ | if [ ! -e /usr/ios/cli/ioscli ] | ||
+ | then | ||
+ | # type LPAR SCSI | ||
+ | nbpath=$pathlparscsi | ||
+ | else | ||
+ | # type VIOS SCSI | ||
+ | nbpath=$pathviosscsi | ||
+ | fi | ||
+ | else | ||
+ | if [ "$(echo $line | cut -d':' -f3- | tr 'A-Z' 'a-z' | grep -q sas; echo $?)" -eq "0" ] | ||
+ | then | ||
+ | if [ ! -e /usr/ios/cli/ioscli ] | ||
+ | then | ||
+ | # type LPAR SAS | ||
+ | nbpath=$pathlparsas | ||
+ | else | ||
+ | # type VIOS SAS | ||
+ | nbpath=$pathviossas | ||
+ | fi | ||
+ | fi | ||
+ | fi | ||
+ | fi | ||
+ | |||
+ | pathok=$(lspath -l $hdisk | grep Enabled | wc -l | awk '{print $1}') | ||
+ | pathok_pct=$(echo "scale=1;100*$pathok/$nbpath" | bc | cut -d '.' -f1) | ||
+ | verbose="$verbose $hdisk;$pathok/$nbpath" | ||
+ | if [ "$pathok_pct" -lt "50" ] | ||
+ | then | ||
+ | MSG="$MSG $hdisk;$pathok/$nbpath" | ||
+ | if [ $STATUS -lt $STATE_CRITICAL ] | ||
+ | then | ||
+ | STATUS=$STATE_CRITICAL | ||
+ | fi | ||
+ | else | ||
+ | if [ "$pathok_pct" -ne "100" ] | ||
+ | then | ||
+ | MSG="$MSG $hdisk;$pathok/$nbpath" | ||
+ | if [ $STATUS -lt $STATE_CRITICAL ] | ||
+ | then | ||
+ | STATUS=$STATE_WARNING | ||
+ | fi | ||
+ | fi | ||
+ | fi | ||
+ | done | ||
+ | } | ||
+ | |||
+ | ###################### | ||
+ | if [ "$os" = "Linux" ] | ||
+ | then | ||
+ | count_linux_path | ||
+ | else | ||
+ | if [ "$os" = "AIX" ] | ||
+ | then | ||
+ | count_aix_path | ||
+ | else | ||
+ | echo "########## Unknown OS" | ||
+ | STATUS=$STATE_UNKNOWN | ||
+ | fi | ||
+ | fi | ||
+ | |||
+ | if [ $STATUS -eq $STATE_OK ] | ||
+ | then | ||
+ | echo "OK" | ||
+ | else | ||
+ | echo "$MSG" | ||
+ | fi | ||
+ | |||
+ | # For debug | ||
+ | if [ "$1" = "-v" ] | ||
+ | then | ||
+ | echo "$verbose" | tr ' ' '\n' | ||
+ | fi | ||
+ | |||
+ | exit $STATUS | ||
+ | </code> | ||
==== Check quorum ==== | ==== Check quorum ==== | ||
Line 27: | Line 220: | ||
user="nagios" | user="nagios" | ||
- | quorumsrv="witness01.ad.police.etat.lu" | + | quorumsrv="witness01.ad.com" |
- | if [[ $(ssh $user@$cluster 'lsquorum -delim :' | grep ':online:' | grep ':device:' | grep ":${quorumsrv}" | wc -l | awk '{print $1}') == "1" ]] | + | output=$(ssh $user@$cluster 'lsquorum -delim :') |
+ | |||
+ | STATUS=0 | ||
+ | MSG="" | ||
+ | if [[ $(echo $output | tr ' ' '\n' | grep ':online:' | grep ':device:' | grep ":${quorumsrv}" | wc -l | awk '{print $1}') -ge "1" ]] | ||
then | then | ||
- | STATUS=$STATE_OK | + | (( STATUS = STATUS + 0 )) |
MSG="IP quorum: $quorumsrv OK" | MSG="IP quorum: $quorumsrv OK" | ||
else | else | ||
- | STATUS=$STATE_CRITICAL | + | (( STATUS = STATUS + 1 )) |
MSG="IP quorum: $quorumsrv down!!!" | MSG="IP quorum: $quorumsrv down!!!" | ||
+ | fi | ||
+ | |||
+ | if [[ $(echo $output | tr ' ' '\n' | grep ':online:' | grep -v ':device:' | wc -l | awk '{print $1}') -ge "2" ]] | ||
+ | then | ||
+ | (( STATUS = STATUS + 0 )) | ||
+ | MSG=$(echo "$MSG | nb quorum OK") | ||
+ | else | ||
+ | (( STATUS = STATUS + 1 )) | ||
+ | MSG=$(echo "$MSG | bad number of quorum !!") | ||
fi | fi | ||
Line 41: | Line 247: | ||
exit $STATUS | exit $STATUS | ||
</code> | </code> | ||
+ | |||
==== Check paths ==== | ==== Check paths ==== | ||
- | + | <cli prompt='#'> | |
- | ==== Check v7000/SVC ==== | + | [root@lnxb080 plugins]# cat check_storage_host_paths.sh |
- | + | </cli> | |
- | https://exchange.nagios.org/directory/Plugins/Hardware/Storage-Systems/SAN-and-NAS/IBM-San-Volume-Controller/IBM-StorWize-V3700--2F-V7000-check/details | + | |
<code> | <code> | ||
- | [root@nagios plugins]# cat check_ibm_storwize.pl | + | #!/bin/sh |
- | #!/usr/bin/perl | + | #set -x |
- | # | + | ################################################## |
- | # check_ibm_v7000_svc Nagios check | + | #@(#) check host paths on SVC |
- | # you need to configure a ssh key without passphrase for logins to your V7000 storage array. | + | ################################################## |
- | # IBM SVC.pm Perl Module is required and available here: | + | # version: 1.0 02-2022 Manu |
- | # https://www14.software.ibm.com/webapp/iwm/web/preLogin.do?source=AW-0NK | + | ################################################## |
- | # http://www.alphaworks.ibm.com/tech/svctools | + | |
- | # | + | |
- | # Martin Leucht <mleucht@ipb.de> 09.01.2013 | + | |
- | # Version 1.1 | + | |
- | # | + | |
- | # fixed version 1.2 03.04.2014 | + | |
- | # | + | |
- | # Usage: check_ibm_v7000_svc.pl -cluster=[IP or hostname] -check=[check] [ -exclude=[listofitems] ] | + | |
- | # | + | |
- | # this script can check the following things of your IBM V7000 SVC | + | |
- | # | + | |
- | # lsarray -> state of array MDisks | + | |
- | # lshost -> state of attached hosts | + | |
- | # lsdrive -> state of drives | + | |
- | # lsmdiskgrp -> state of svc managed disk groups | + | |
- | # lsmdisk -> state of external managed disks | + | |
- | # lunonline / lsvdisk -> state of volumes (lun's/vdisk's) | + | |
- | # lsenclosure -> state of enclosures | + | |
- | # lsenclosurebattery -> state of batteries | + | |
- | # lsnodebattery -> for SVC | + | |
- | # lsenclosurecanister -> state of canister/nodes | + | |
- | # lsnode -> for SVC | + | |
- | # lsenclosurepsu -> state of psu's | + | |
- | # lsenclosureslot -> state of port enclosure slots | + | |
- | # luninsync / lsrcrelationship -> state of syncs of your volumes (if you have more than one machine and mirroring) | + | |
- | # lsenclosureslotx -> state of enclosure slot port | + | |
- | # | + | |
- | # TODO: ISCSI port check (BUG in Perl module - lsportip state is not provided via IBM::SVC) | + | |
- | # | + | |
- | # example nagios command definition | + | |
- | # | + | |
- | # define command { | + | |
- | # command_name check_ibm_v7000_svc | + | |
- | # command_line $USER1$/check_ibm_v7000_svc.pl -cluster=$HOSTADDRESS$ -check=$ARG1$ -v | + | |
- | # } | + | |
- | # | + | |
- | # example command excluding some items | + | |
- | # | + | |
- | # define command { | + | |
- | # command_name check_ibm_v7000_svc_exclude | + | |
- | # command_line $USER1$/check_ibm_v7000_svc.pl -cluster=$HOSTADDRESS$ -check=$ARG1$ -exclude=$ARG2$ -v | + | |
- | # } | + | |
- | # | + | |
- | # ... and service definition | + | |
- | # | + | |
- | # define service { | + | |
- | # use severity2,noperf | + | |
- | # service_description check_lunsonline | + | |
- | # host_name storwize01,storwize02 | + | |
- | # check_command check_ibm_v7000_svc!lunonline!'lun1,lun2' | + | |
- | # } | + | |
- | use strict; | + | STATUS=0 |
- | use IBM::SVC1; | + | |
- | use Getopt::Long; | + | |
- | #use Data::Dumper; | + | |
- | my ($cluster, $ssh, $verbose, $user, $check, $help, $exclude); | + | STATE_OK=0 |
- | $ssh="ssh"; | + | STATE_WARNING=1 |
- | $user="nagios"; | + | STATE_CRITICAL=2 |
- | my $state=""; | + | STATE_UNKNOWN=3 |
- | my $message=""; | + | |
- | my $params={}; | + | |
- | my $svc_command=""; | + | |
- | my $item=""; | + | |
- | my $item_name=""; | + | |
- | my $item_state=""; | + | |
- | my $msg=""; | + | |
- | my @exclude=""; | + | |
- | my $x=0; | + | |
- | my %excl=(); | + | |
- | GetOptions ( | + | cluster=$(echo $1 | sed 's/\-cluster=//') |
- | "cluster=s" => \$cluster, | + | user="nagios" |
- | "verbose|v" => \$verbose, | + | SSH="ssh -o ConnectTimeout=30 ${user}@" |
- | "ssh=s" => \$ssh, | + | list="svc01" |
- | "check=s" => \$check, | + | |
- | "help|h" => \$help, | + | |
- | "exclude=s" => \$exclude, | + | |
- | "user=s" => \$user | + | |
- | ); | + | |
- | if ( !$cluster || !$check || $help) { | + | MSG="" |
- | print_usage(); | + | exclude=':none:' |
- | exit(0); | + | |
- | } | + | |
- | # Nagios exit states | + | |
- | our %states = ( | + | |
- | OK => 0, | + | |
- | WARNING => 1, | + | |
- | CRITICAL => 2, | + | |
- | UNKNOWN => 3 | + | |
- | ); | + | |
- | # Nagios state names | + | |
- | our %state_names = ( | + | |
- | 0 => 'OK', | + | |
- | 1 => 'WARNING', | + | |
- | 2 => 'CRITICAL', | + | |
- | 3 => 'UNKNOWN' | + | |
- | ); | + | |
- | # get excluded items | + | |
- | if ($exclude ne "") { | + | |
- | if ($check eq "lunonline" || $check eq "luninsync" || $check eq "lshost") { | + | |
- | @exclude = split(",",$exclude); | + | |
- | foreach (@exclude) { | + | |
- | $x++; | + | |
- | $excl{$_} = $x; | + | |
- | } | + | |
- | } else { | + | |
- | print "excluding is only available for lunonline, luninsync and lshost check!\n"; | + | |
- | exit(0); | + | |
- | } | + | |
- | } | + | word="$1" |
- | # return states SVC/V7000 (see on console by typing svc_command -h | + | case "$word" in |
- | # generic_states for lunonline, lsenclosure,lsmdiskgrp,lsmdisk | + | "esx" ) count=2 |
- | # lsenclosurecanister, lsenclosurepsu, lsenclosureslot checks | + | exclude=':none:' ;; |
+ | "aix" ) count=4 | ||
+ | exclude="aixv" ;; | ||
+ | "lnx" ) count=4 | ||
+ | exclude=':none:' ;; | ||
+ | "vio" ) count=2 | ||
+ | word=aixv | ||
+ | exclude=':none:' ;; | ||
+ | "win" ) count=2 | ||
+ | word='win|mssql' | ||
+ | exclude=':none:' ;; | ||
+ | "other" ) count=4 | ||
+ | word='svc01' | ||
+ | exclude='esx|aix|lnx|win|mssql' ;; | ||
+ | "*" ) MSG="wrong parameter" ;; | ||
+ | esac | ||
- | my %generic_states = ( | ||
- | 'online' => 'OK', | ||
- | 'offline' => 'CRITICAL', | ||
- | 'degraded' => 'CRITICAL', ); | ||
- | my %luninsync_states = ( | ||
- | 'consistent_synchronized' => 'OK', | ||
- | 'consistent_copying' => 'OK', | ||
- | 'inconsistent_stopped' => 'CRITICAL', | ||
- | 'consistent_stopped' => 'WARNING', | ||
- | 'idling' => 'WARNING', | ||
- | 'consistent_disconnected' => 'CRITICAL', | ||
- | 'inconsistent_copying' => 'CRITICAL', | ||
- | 'idling_disconnected' => 'CRITICAL', | ||
- | 'inconsistent_disconnected' => 'CRITICAL', ); | ||
- | my %lsdrive_states = ( | ||
- | 'online' => 'OK', | ||
- | 'offline' => 'CRITICAL', | ||
- | 'degraded' => 'CRITICAL', ); | ||
- | my %lsmdisk_states = ( | ||
- | 'offline' => 'CRITICAL', | ||
- | 'degraded' => 'CRITICAL', | ||
- | 'syncing' => 'WARNING', | ||
- | 'initting' => 'OK', | ||
- | 'online' => 'OK', ); | ||
- | my %lsiogrp_states = ( | ||
- | '2' => 'OK', | ||
- | '1' => 'CRITICAL',); | ||
- | my %lsenclosureslot_states = ( | ||
- | 'online' => 'OK', | ||
- | 'excluded_by_drive' => 'WARNING', | ||
- | 'excluded_by_enclosure' => 'WARNING', | ||
- | 'excluded_by_system' => 'WARNING',); | ||
- | my %lshost_states = ( | ||
- | 'online' => 'OK', | ||
- | 'offline' => 'CRITICAL', | ||
- | 'degraded' => 'WARNING', ); | ||
- | # do not edit anything below this | ||
- | sub print_usage { | + | for storage in $(echo ${list}) |
- | print <<EOU; | + | do |
+ | cmd='lshost -delim : -nohdr' | ||
+ | for node in $(${SSH}${storage} $cmd | cut -d':' -f2) | ||
+ | do | ||
+ | cmd="lshost -delim : $node" | ||
+ | MSG1=$(echo "$storage:$node:$(${SSH}${storage} $cmd | grep -c "state:active")" | grep -v ':0$' | egrep -i "${word}" | grep -v ":${count}$" | egrep -vi "${exclude}") | ||
+ | if [ "$MSG1" != "" ] | ||
+ | then | ||
+ | MSG=$(echo "${MSG};${MSG1}") | ||
+ | fi | ||
+ | done | ||
+ | done | ||
- | Usage: $0 -cluster=[IP or hostname] -check=[check] -v | + | if [ "$MSG" == "" ] |
+ | then | ||
+ | RC=0 | ||
+ | else | ||
+ | RC=2 | ||
+ | echo $MSG | ||
+ | fi | ||
- | -cluster Hostname or IP address of V7000 SVC (*required*) | + | exit $RC |
- | -check Checktype (*required*) | + | </code> |
- | Possible values are: | + | |
- | * lunonline|luninsync | + | |
- | * lsmdisk|lsdrive|lsenclosure|lsenclosurebattery | + | |
- | * lsenclosurecanister|lsenclosurepsu|lsenclosureslotx | + | |
- | ( lsenclosureslotx = lsenclosureslot1 ... lsenclosureslotx ) | + | |
- | -user Username which is configured on your v7000 (default nagios) | + | ==== Check v7000/SVC ==== |
- | -ssh ssh method - the ssh command to use. Possible values are: | + | |
- | * "ssh" (default) | + | |
- | * "plink" (PUTTY) | + | |
- | -exclude comma separated list of excluded vdisknames (lunonline check) | + | |
- | or consistency group names (luninsync check) | + | |
- | -h -help Print this help | + | |
- | -v -verbose verbose output (OK items are listed) | + | |
- | EOU | + | https://exchange.nagios.org/directory/Plugins/Hardware/Storage-Systems/SAN-and-NAS/IBM-San-Volume-Controller/IBM-StorWize-V3700--2F-V7000-check/details |
- | exit (0); | + | |
- | } | + | |
- | # Set parameters for svc connection | + | <cli prompt='#'> |
- | $params->{'cluster_name'} = $cluster if $cluster; | + | [root@centreon01 plugins]# cat check_ibm_v7000.sh |
- | $params->{'user'} = $user if $user; | + | </cli> |
- | $params->{'ssh_method'} = $ssh if $ssh; | + | <code> |
- | #$params->{'keyfile'} = $keyfile if $keyfile; | + | #!/usr/bin/bash |
+ | #set -x | ||
+ | ############################################# | ||
+ | #@(#) Nagios-Centreon check for IBM storage | ||
+ | ############################################# | ||
+ | # version 1.0 01-2025 | ||
- | # Create the connection with the parameters set above. | + | ssh='/usr/bin/ssh -q' |
- | my $svc = IBM::SVC->new($params); | + | exitCode=1 |
- | if ($check eq "lunonline") { | + | while getopts 'M:U:Q:d:h' OPT; do |
- | $svc_command = "lsvdisk"; | + | case $OPT in |
- | $item = "vdisks (luns)"; | + | M) storage=$OPTARG ;; |
- | $item_name = "name"; | + | U) user=$OPTARG ;; |
- | $item_state = "status"; | + | Q) query=$OPTARG ;; |
- | &itemcheck(\%generic_states,\%excl) | + | h) help="yes" ;; |
+ | *) unknown="yes" ;; | ||
+ | esac | ||
+ | done | ||
- | } elsif ($check eq "luninsync") { | + | #storage="psnsvccl01" |
- | # * consistent_synchronized | + | #user=centreon |
- | # * consistent_copying | + | outputMess="" |
- | # * inconsistent_stopped | + | |
- | # * consistent_stopped | + | |
- | # * idling | + | |
- | # * consistent_disconnected' | + | |
- | # * inconsistent_copying | + | |
- | # * idling_disconnected | + | |
- | # * inconsistent_disconnected | + | |
- | $svc_command = "lsrcrelationship"; | + | |
- | $item = "consistency groups"; | + | |
- | $item_name = "consistency_group_name"; | + | |
- | $item_state = "state"; | + | |
- | &itemcheck(\%luninsync_states,\%excl) | + | |
- | } elsif ($check eq "lsmdisk") { | + | # usage |
- | # * offline - the array is offline on all nodes | + | HELP=" |
- | # * degraded - the array has deconfigured or offline members; the array is not fully redundant | + | Check IBM Storwize v7000 throght ssh (GPL licence) |
- | # * syncing - array members are all online, the array is syncing parity or mirrors to achieve redundancy | + | |
- | # * initting - array members are all online, the array is initializing; the array is fully redundant | + | |
- | # * online - array members are all online, and the array is fully redundant | + | |
- | $svc_command = "lsmdisk"; | + | |
- | $item = "mdisk"; | + | |
- | $item_name = "name"; | + | |
- | $item_state = "status"; | + | |
- | &itemcheck(\%lsmdisk_states) | + | |
- | } elsif ($check eq "lsiogrp") { | + | usage: $0 [ -M value -U value -Q command -h ] |
- | # * 2 - the array is operating normally | + | |
- | # * 1 - the array has deconfigured or offline nodes; the array is not fully redundant | + | |
- | $svc_command = "lsiogrp"; | + | |
- | $item = "iogrp"; | + | |
- | $item_name = "name"; | + | |
- | $item_state = "node_count"; | + | |
- | &itemcheck(\%lsiogrp_states) | + | |
- | } elsif ($check eq "lshost") { | + | syntax: |
- | # * 2 - the array is operating normally | + | |
- | # * 1 - the array has deconfigured or offline nodes; the array is not fully redundant | + | |
- | $svc_command = "lshost"; | + | |
- | $item = "host"; | + | |
- | $item_name = "name"; | + | |
- | $item_state = "status"; | + | |
- | &itemcheck(\%lshost_states,\%excl) | + | |
- | } elsif ($check eq "lsmdiskgrp") { | + | -M --> IP Address |
- | # * offline - the array is offline on all nodes | + | -U --> user |
- | # * degraded - the array has deconfigured or offline members; the array is not fully redundant | + | -Q --> query to storage |
- | # * syncing - array members are all online, the array is syncing parity or mirrors to achieve redundancy | + | lsdrive |
- | # * initting - array members are all online, the array is initializing; the array is fully redundant | + | lsarray |
- | # * online - array members are all online, and the array is fully redundant | + | lsmdisk |
- | $svc_command = "lsmdiskgrp"; | + | lsmdiskgrp |
- | $item = "mdiskgrp"; | + | lsvdisk |
- | $item_name = "name"; | + | lsenclosure |
- | $item_state = "status"; | + | lsenclosurecanister |
- | &itemcheck(\%generic_states) | + | lsenclosurepsu |
+ | lsenclosurebattery | ||
+ | lsnode --> SVC only | ||
+ | lsnodebattery --> SVC only | ||
+ | -h --> Print This Help Screen | ||
- | } elsif ($check eq "lsdrive") { | + | Note : |
- | # * online: blank | + | This check use ssh protocoll. |
- | # * degraded: populated if associated with an error | + | " |
- | # * offline: must be populated | + | |
- | $svc_command = "lsdrive"; | + | |
- | $item = "mdisk member"; | + | |
- | $item_name = "id"; | + | |
- | #$item_state = "error_sequence_number"; | + | |
- | $item_state = "status"; | + | |
- | &itemcheck(\%lsdrive_states) | + | |
- | } elsif ($check eq "lsenclosure") { | + | if [ "$hlp" = "yes" -o $# -lt 1 ]; then |
- | # Indicates if an enclosure is visible to the SAS network: | + | echo "$HELP" |
- | $svc_command = "lsenclosure"; | + | exit 0 |
- | $item = "enclosure(s)"; | + | fi |
- | $item_name = "id"; | + | |
- | $item_state = "status"; | + | |
- | &itemcheck(\%generic_states) | + | |
- | + | ||
- | } elsif ($check eq "lsenclosurebattery") { | + | |
- | # The status of the battery: | + | |
- | $svc_command = "lsenclosurebattery"; | + | |
- | $item = "enclosurebatteries"; | + | |
- | $item_name = "battery_id"; | + | |
- | $item_state = "status"; | + | |
- | &itemcheck(\%generic_states) | + | |
- | + | ||
- | } elsif ($check eq "lsnodebattery") { | + | |
- | # The status of the battery: | + | |
- | $svc_command = "lsnodebattery"; | + | |
- | $item = "enclosurebatteries"; | + | |
- | $item_name = "battery_id"; | + | |
- | $item_state = "status"; | + | |
- | &itemcheck(\%generic_states) | + | |
- | } elsif ($check eq "lsenclosurecanister") { | + | case $query in |
- | # The status of the canister: | + | lsdrive) |
- | $svc_command = "lsenclosurecanister"; | + | word_online=':online:' |
- | $item = "enclosurecanister(s)"; | + | num=1 |
- | $item_name = "node_name"; | + | device='Drives' |
- | $item_state = "status"; | + | ;; |
- | &itemcheck(\%generic_states) | + | lsarray) |
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Array' | ||
+ | ;; | ||
+ | lsmdisk) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Mdisks' | ||
+ | ;; | ||
+ | lsmdiskgrp) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Pools' | ||
+ | ;; | ||
+ | lsvdisk) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Volumes' | ||
+ | ;; | ||
+ | lsenclosure) | ||
+ | word_online=':online:' | ||
+ | num=1 | ||
+ | device='Enclosures' | ||
+ | ;; | ||
+ | lsenclosurecanister) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Nodes' | ||
+ | ;; | ||
+ | lsenclosurepsu) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='PowerSupply' | ||
+ | ;; | ||
+ | lsenclosurebattery) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Battery' | ||
+ | ;; | ||
+ | lsnode) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Nodes' | ||
+ | ;; | ||
+ | lsnodebattery) | ||
+ | word_online=':online:' | ||
+ | num=2 | ||
+ | device='Battery' | ||
+ | ;; | ||
+ | *) | ||
+ | echo -ne "Command not found. \n" | ||
+ | exitCode=3 | ||
+ | exit $exitCode | ||
+ | ;; | ||
+ | esac | ||
- | } elsif ($check eq "lsnode") { | + | output=$($ssh $user@$storage $query -delim : 2>/dev/null) |
- | # The status of the canister: | + | |
- | $svc_command = "lsnode"; | + | |
- | $item = "enclosurecanister(s)"; | + | |
- | $item_name = "name"; | + | |
- | $item_state = "status"; | + | |
- | &itemcheck(\%generic_states) | + | |
- | } elsif ($check eq "lsenclosurepsu") { | + | if [ "$output" == "" ] |
- | # The status of the psu(s) | + | then |
- | $svc_command = "lsenclosurepsu"; | + | outputMess="$outputMess UNKNOWN: Improper command" |
- | $item = "enclosurepsu(s)"; | + | exitCode=3 |
- | $item_name = "PSU_id"; | + | else |
- | $item_state = "status"; | + | nbline=$(echo $output | tr ' ' '\n' | sed '1d' | grep -cv "${word_online}") |
- | &itemcheck(\%generic_states) | + | if [ "$nbline" -ne "0" ] |
- | + | then | |
- | } elsif ($check =~ m/^lsenclosureslot(\d+)$/ ) { | + | value=$(echo $output | tr ' ' '\n' | sed '1d' | grep -v "${word_online}" | cut -d':' -f$num | tr '\n' ';' | sed 's/;$//') |
- | # The status of enclosure slot port x. If the port is bypassed for multiple reasons, only one is shown. | + | outputMess="$outputMess CRITICAL: $device OFFLINE $value \n" |
- | # In order of priority, they are: | + | exitCode=2 |
- | # * online: enclosure slot port x is online | + | else |
- | # * excluded_by_drive: the drive excluded the port | + | value=$(echo $output | tr ' ' '\n' | sed '1d' | grep "${word_online}" | cut -d':' -f$num | tr '\n' ';' | sed 's/;$//') |
- | # * excluded_by_enclosure: the enclosure excluded the port | + | outputMess="$outputMess OK: $device $value \n" |
- | # * excluded_by_system: the clustered system (system) has excluded the port | + | exitCode=0 |
- | + | fi | |
- | $svc_command = "lsenclosureslot"; | + | fi |
- | $item = "enclosureslots port" . $1; | + | |
- | $item_name = "slot_id"; | + | |
- | $item_state = "port_" . $1 . "_status"; | + | |
- | &itemcheck(\%lsenclosureslot_states) | + | |
- | + | ||
- | } else { | + | |
- | $state = 'UNKNOWN'; | + | |
- | $message = "the check you provided does not exist"; | + | |
- | } | + | |
- | # main check subroutine | + | |
- | sub itemcheck { | + | |
- | # get hash reference(s) from subroutine call | + | |
- | my $v7000_states=shift; | + | |
- | my $excluded=shift; | + | |
- | + | ||
- | my @critical_items = ""; | + | |
- | my @warn_items = ""; | + | |
- | my @ok_items = ""; | + | |
- | my @all_items = ""; | + | |
- | my $criticalcount = 0; | + | |
- | my $warncount = 0; | + | |
- | my $okcount = 0; | + | |
- | my ($items_desc, $item_desc, $final_item_state); | + | |
- | + | ||
- | # query storage cluster | + | |
- | my ($rc,$all_items_ref) = $svc->svcinfo($svc_command,{}); | + | |
- | + | ||
- | if ($rc == 0) { | + | |
- | @all_items = @$all_items_ref; | + | |
- | if (scalar(@all_items) == 0) { | + | |
- | $state = 'WARNING'; | + | |
- | $message = "Could not find any entry for $item"; | + | |
- | } else { | + | |
- | foreach my $items_params (@all_items) { | + | |
- | $item_desc = "$items_params->{$item_name}"; | + | |
- | chomp($item_desc); | + | |
- | #print Dumper($items_params); | + | |
- | # ommit excluded and blank items | + | |
- | next if $excluded->{$item_desc} || $item_desc =~ m/^s*$/g; | + | |
- | $final_item_state = "$items_params->{$item_state}"; | + | |
- | if ($v7000_states->{$final_item_state} eq 'OK' ) { | + | |
- | $okcount++; | + | |
- | push (@ok_items, $item_desc); | + | |
- | } elsif ($v7000_states->{$final_item_state} eq 'WARNING' ) { | + | |
- | $warncount++; | + | |
- | $msg = "$item_desc ($final_item_state) "; | + | |
- | push (@warn_items, $msg); | + | |
- | } elsif ($v7000_states->{$final_item_state} eq 'CRITICAL' ) { | + | |
- | $criticalcount++; | + | |
- | $msg = "$item_desc ($final_item_state) "; | + | |
- | push (@critical_items, $msg); | + | |
- | + | ||
- | } | + | |
- | + | ||
- | } | + | |
- | } | + | |
- | } else { | + | |
- | print "Cannot connect to cluster $cluster\n"; | + | |
- | exit $states{'CRITICAL'}; | + | |
- | } | + | |
- | + | ||
- | if ( $warncount == 0 && $criticalcount == 0 && $okcount > 0 ) { | + | |
- | $state = 'OK'; | + | |
- | if ($verbose) { | + | |
- | $message = "$state: all $item $final_item_state [" . join(" ",@ok_items) . " ]"; | + | |
- | } else { | + | |
- | $message = "$state: all $item $final_item_state"; | + | |
- | } | + | |
- | } elsif ( $warncount > 0 && $criticalcount == 0 ) { | + | |
- | $state = 'WARNING'; | + | |
- | $message = "$state:" . join(" ",@warn_items) ; | + | |
- | } elsif ( ( $warncount > 0 && $criticalcount > 0 ) || ( $warncount == 0 && $criticalcount > 0 ) ) { | + | |
- | $state = 'CRITICAL'; | + | |
- | $message = "$state:" . join(" ",@critical_items) . " " . join(" ",@warn_items) ; | + | |
- | } else { | + | |
- | $state = 'UNKNOWN'; | + | |
- | $message = "$state: Could not find status information or items" ; | + | |
- | } | + | |
- | } | + | |
- | print $message."\n"; | + | echo -ne "$outputMess\n" |
- | exit $states{$state}; | + | exit $exitCode |
</code> | </code> | ||
Line 766: | Line 777: | ||
</code> | </code> | ||
+ | ==== template ==== | ||
+ | |||
+ | **check_ibm_v7000.sh** | ||
+ | <code> | ||
+ | #!/bin/bash | ||
+ | # Author: Lazzarin Alberto | ||
+ | # Date: 10-04-2013 | ||
+ | # Version 1.4 | ||
+ | # | ||
+ | # This plugin check the HW status of IBM Storwize v7000. | ||
+ | # To use this script you need to create a linux user with his ssh certificate. | ||
+ | # Create the same user on the v7000, member of monitor group and upload the public ssh key. | ||
+ | # Try to log from linux machine to the v7000 without password, if it function you can use the plugin. | ||
+ | # I use the 'nagios' user to check the remote system. | ||
+ | # The help is included into the script. | ||
+ | # | ||
+ | # | ||
+ | # | ||
+ | # CHANGELOG | ||
+ | # | ||
+ | # 1.4 Made by Andrea Tedesco [andrea85 . tedesco @ gmail . com] | ||
+ | # Add check of v7000 Unified | ||
+ | # 1.3 Made by Ivan Bergantin [ivan . bergantin @ gmail . com] suggested by Leandro Freitas [leandro @ nodeps . com . br] | ||
+ | # Add short output in "Service Status Details For Host" view, and detailed output in "Service Information"view | ||
+ | # | ||
+ | # 1.2 Made by Feilong | ||
+ | # Add check of mirror status between two volumes on two IBM V7000. | ||
+ | # It check the number of mirrors, the numbers of consitent and synchronized mirrors. If they are differents, the status returned is critical. | ||
+ | # | ||
+ | # 1.1 | ||
+ | # Change login method from from 'plink' to ssh. | ||
+ | # Add "OK" and "ATTENTION" in the output. | ||
+ | # | ||
+ | # 1.0 | ||
+ | # First release. | ||
+ | # | ||
+ | |||
+ | ssh=/usr/bin/ssh | ||
+ | exitCode=0 | ||
+ | |||
+ | while getopts 'M:U:Q:d:h' OPT; do | ||
+ | case $OPT in | ||
+ | M) storage=$OPTARG;; | ||
+ | U) user=$OPTARG;; | ||
+ | Q) query=$OPTARG;; | ||
+ | h) hlp="yes";; | ||
+ | *) unknown="yes";; | ||
+ | esac | ||
+ | done | ||
+ | |||
+ | # usage | ||
+ | HELP=" | ||
+ | Check IBM Storwize v7000 throght ssh (GPL licence) | ||
+ | |||
+ | usage: $0 [ -M value -U value -Q command -h ] | ||
+ | |||
+ | syntax: | ||
+ | |||
+ | -M --> IP Address | ||
+ | -U --> user | ||
+ | -Q --> query to storage | ||
+ | lsarray | ||
+ | lsdrive | ||
+ | lsvdisk | ||
+ | lsenclosure | ||
+ | lsenclosurebattery | ||
+ | lsenclosurecanister | ||
+ | lsenclosurepsu | ||
+ | lsenclosureslot | ||
+ | lsrcrelationship | ||
+ | unified | ||
+ | -h --> Print This Help Screen | ||
+ | |||
+ | Note : | ||
+ | This check use ssh protocoll. | ||
+ | " | ||
+ | |||
+ | if [ "$hlp" = "yes" -o $# -lt 1 ]; then | ||
+ | echo "$HELP" | ||
+ | exit 0 | ||
+ | fi | ||
+ | |||
+ | tmp_file=/tmp/v7000_$storage_$query.tmp | ||
+ | tmp_file_OK=/tmp/v7000_OK.tmp | ||
+ | outputMess="" | ||
+ | |||
+ | #echo -ne "IBM Storwize v7000 Health Check\n" | ||
+ | |||
+ | case $query in | ||
+ | lsarray) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $3}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: MDisk OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: MDisks \n" | ||
+ | fi | ||
+ | |||
+ | while read line | ||
+ | do | ||
+ | mdisk_name=$(echo "${line}" | awk '{printf $2}') | ||
+ | mdisk_status=$(echo "${line}" | awk '{printf $3}') | ||
+ | |||
+ | if [ $mdisk_status = "online" ]; then | ||
+ | outputMess="$outputMess OK: MDisks $mdisk_name status: $mdisk_status \n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: MDisks $mdisk_name status: $mdisk_status \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | ;; | ||
+ | |||
+ | lsdrive) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $2}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: Disk OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: Drive \n" | ||
+ | fi | ||
+ | |||
+ | drive_total=$(/bin/cat $tmp_file |/usr/bin/wc -l) | ||
+ | while read line | ||
+ | do | ||
+ | drive_n=$(echo "${line}" | awk '{printf $1}') | ||
+ | drive_status=$(echo "${line}" | awk '{printf $2}') | ||
+ | drive_role=$(echo "${line}" | awk '{printf $4}') | ||
+ | drive_type=$(echo "${line}" | awk '{printf $5}') | ||
+ | drive_capacity=$(echo "${line}" | awk '{printf $6}') | ||
+ | drive_enclosure=$(echo "${line}" | awk '{printf $10}') | ||
+ | drive_slot=$(echo "${line}" | awk '{printf $11}') | ||
+ | |||
+ | if [ $drive_status = "online" ]; then | ||
+ | outputMess="$outputMess OK: Drive $drive_n is online \n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: Disk $drive_n \nstatus: $disk_status \nrole: $drive_role \ntype: $drive_type \ncapacity: $drive_capacity \nenclosure: $drive_enclosure \nslot: $drive_slot " | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | |||
+ | ;; | ||
+ | |||
+ | lsvdisk) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $5}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: VDisk OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: VDisk \n" | ||
+ | fi | ||
+ | |||
+ | while read line | ||
+ | do | ||
+ | vdisk_name=$(echo "${line}" | awk '{printf $2}') | ||
+ | vdisk_status=$(echo "${line}" | awk '{printf $5}') | ||
+ | |||
+ | if [ $vdisk_status = "online" ]; then | ||
+ | outputMess="$outputMess OK: VDisks $vdisk_name status: $vdisk_status \n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: VDisks $mdisk_name status: $vdisk_status \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | ;; | ||
+ | |||
+ | lsenclosure) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $2}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: Enclosure OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: Enclosure \n" | ||
+ | fi | ||
+ | |||
+ | while read line | ||
+ | do | ||
+ | enc_n=$(echo "${line}" | awk '{printf $1}') | ||
+ | enc_status=$(echo "${line}" | awk '{printf $2}') | ||
+ | enc_pn=$(echo "${line}" | awk '{printf $7}') | ||
+ | enc_sn=$(echo "${line}" | awk '{printf $8}') | ||
+ | |||
+ | |||
+ | if [ $enc_status = "online" ]; then | ||
+ | outputMess="$outputMess OK: Enclosure $enc_n status: $enc_status \n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: Enclosure $enc_n status: $enc_status sn: $enc_sn pn: $enc_pn \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | ;; | ||
+ | |||
+ | lsenclosurebattery) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $3}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: Battery OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: Battery \n" | ||
+ | fi | ||
+ | |||
+ | while read line | ||
+ | do | ||
+ | batt_n=$(echo "${line}" | awk '{printf $2}') | ||
+ | batt_status=$(echo "${line}" | awk '{printf $3}') | ||
+ | batt_charge=$(echo "${line}" | awk '{printf $4}') | ||
+ | batt_rec=$(echo "${line}" | awk '{printf $5}') | ||
+ | batt_charge=$(echo "${line}" | awk '{printf $6}') | ||
+ | batt_eol=$(echo "${line}" | awk '{printf $7}') | ||
+ | |||
+ | |||
+ | if [ $batt_status = "online" -a $batt_rec = "no" -a $batt_charge = "100" -a $batt_eol = "no" ]; then | ||
+ | outputMess="$outputMess OK: Battery $batt_n status: $batt_status \n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: Battery $batt_n status: $batt_statusn recharge: $batt_rec charged: $batt_charge eol: $batt_eol \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | ;; | ||
+ | |||
+ | lsenclosurecanister) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $3}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: Canister OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: Canister \n" | ||
+ | fi | ||
+ | |||
+ | while read line | ||
+ | do | ||
+ | can_id=$(echo "${line}" | awk '{printf $2}') | ||
+ | can_enc_id=$(echo "${line}" | awk '{printf $1}') | ||
+ | can_stat=$(echo "${line}" | awk '{printf $3}') | ||
+ | can_type=$(echo "${line}" | awk '{printf $4}') | ||
+ | |||
+ | if [ $can_stat = "online" ]; then | ||
+ | outputMess="$outputMess OK: Canister $can_id enclosure: $can_enc_id status: $can_stat \n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: Canister $can_id enclosure: $can_enc_id status: $can_stat type: $can_type \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | ;; | ||
+ | |||
+ | lsenclosurepsu) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $3}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: PSU OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: PSU \n" | ||
+ | fi | ||
+ | |||
+ | while read line | ||
+ | do | ||
+ | psu_id=$(echo "${line}" | awk '{printf $2}') | ||
+ | psu_enc_id=$(echo "${line}" | awk '{printf $1}') | ||
+ | psu_stat=$(echo "${line}" | awk '{printf $3}') | ||
+ | |||
+ | if [ $psu_stat = "online" ]; then | ||
+ | outputMess="$outputMess OK: PSU $psu_id enclosure: $psu_enc_id status: $psu_stat \n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: PSU $psu_id enclosure: $psu_enc_id status: $psu_stat \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | ;; | ||
+ | |||
+ | lsenclosureslot) | ||
+ | $ssh $user@$storage $query |sed '1d' > $tmp_file | ||
+ | |||
+ | cat $tmp_file |awk '{printf $3, $4}' |grep -i offline | ||
+ | if [ "$?" -eq "0" ]; then | ||
+ | outputMess="$outputMess CRITICAL: EnclosureSlot OFFLINE \n" | ||
+ | else | ||
+ | outputMess="$outputMess OK: EnclosureSlot \n" | ||
+ | fi | ||
+ | |||
+ | while read line | ||
+ | do | ||
+ | slt_enc_id=$(echo "${line}" | awk '{printf $1}') | ||
+ | slt_id=$(echo "${line}" | awk '{printf $2}') | ||
+ | slt_prt1_stat=$(echo "${line}" | awk '{printf $3}') | ||
+ | slt_prt2_stat=$(echo "${line}" | awk '{printf $4}') | ||
+ | slt_drv=$(echo "${line}" | awk '{printf $5}') | ||
+ | drv_id=$(echo "${line}" | awk '{printf $6}') | ||
+ | |||
+ | if [ $slt_prt1_stat = "online" -a $slt_prt2_stat = "online" -a $slt_drv = "yes" ]; then | ||
+ | outputMess="$outputMess OK: Drive-$drv_id enclosure-$slt_enc_id slot-$slt_id port1-$slt_prt1_stat port2-$slt_prt2_stat\n" | ||
+ | else | ||
+ | outputMess="$outputMess ATTENTION: Drive-$drv_id enclosure-$slt_enc_id slot-$slt_id port1-$slt_prt1_stat port2-$slt_prt2_stat \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | done < $tmp_file | ||
+ | ;; | ||
+ | |||
+ | lsrcrelationship) | ||
+ | volume_mirror_prod=$($ssh $user@$storage $query | grep -c "rcrel*") | ||
+ | volume_mirror_sync=$($ssh $user@$storage $query | grep -c "consistent_synchronized") | ||
+ | |||
+ | if [ $volume_mirror_prod = $volume_mirror_sync ]; then | ||
+ | outputMess="$outputMess OK: $volume_mirror_prod mirors are consistent and synchronized \n" | ||
+ | else | ||
+ | outputMess="$outputMess CRITICAL: sur les $volume_mirror_prod volumes, only $volume_mirror_sync are consistent and synchronized \n" | ||
+ | exitCode=2 | ||
+ | fi | ||
+ | |||
+ | ;; | ||
+ | |||
+ | unified) | ||
+ | # Execute remote command | ||
+ | $ssh $user@$storage lshealth -Y > $tmp_file | ||
+ | |||
+ | # Parse remote command output | ||
+ | while read line | ||
+ | do | ||
+ | case $(echo "$line" | cut -d : -f 9) in | ||
+ | OK) # Sensor OK state -> do nothing | ||
+ | outputMess="${outputMess}`echo $line | cut -d : -f 7,9 >> $tmp_file_OK`" | ||
+ | ;; | ||
+ | WARNING) # Sensor WARNING state | ||
+ | if [ "$exitCode" -lt 1 ]; then | ||
+ | exitCode=1; | ||
+ | fi | ||
+ | # Append sensor message to output | ||
+ | if [ -n "$outputMess" ]; then | ||
+ | outputMess="$outputMess +++ "; | ||
+ | fi | ||
+ | outputMess="${outputMess}STATE WARNING - [`echo $line | cut -d : -f 7`:`echo $line | cut -d : -f 8`] `echo $line | cut -d : -f 10`" | ||
+ | ;; | ||
+ | ERROR) # Sensor ERROR state | ||
+ | if [ "$exitCode" -lt 2 ]; then | ||
+ | exitCode=2; | ||
+ | fi | ||
+ | # Append sensor message to output | ||
+ | if [ -n "$outputMess" ]; then | ||
+ | outputMess="$outputMess +++ "; | ||
+ | fi | ||
+ | outputMess="${outputMess}STATE CRITICAL - [`echo $line | cut -d : -f 7`:`echo $line | cut -d : -f 8`] `echo $line | cut -d : -f 10`" | ||
+ | ;; | ||
+ | esac | ||
+ | done < $tmp_file | ||
+ | |||
+ | # No warnings/errors detected | ||
+ | if [ "$exitCode" -eq 0 ]; then | ||
+ | outputMess=`uniq "$tmp_file_OK"`; | ||
+ | fi | ||
+ | ;; | ||
+ | *) | ||
+ | echo -ne "Command not found. \n" | ||
+ | exit 3 | ||
+ | ;; | ||
+ | esac | ||
+ | |||
+ | rm $tmp_file | ||
+ | rm $tmp_file_OK | ||
+ | echo -ne "$outputMess\n" | ||
+ | exit $exitCode | ||
+ | </code> | ||
+ | |||
+ | $ssh $user@$storage $query -delim : | ||
+ | <code> | ||
+ | ######### lsarray | ||
+ | mdisk_id:mdisk_name:status:mdisk_grp_id:mdisk_grp_name:capacity:raid_status:raid_level:redundancy:strip_size:tier:encrypt:distributed | ||
+ | 0:MDisk1:online:0:Pool01_SiteA:694.9TB:online:raid6:2:256:tier0_flash:yes:yes | ||
+ | ######### lshost | ||
+ | id:name:port_count:iogrp_count:status:site_id:site_name:host_cluster_id:host_cluster_name:protocol:owner_id:owner_name:portset_id:portset_name:partition_id:partition_name:draft_partition_id:draft_partition_name:ungrouped_volume_mapping:location_system_name | ||
+ | 0:svc01:2:4:online:::0:svccl01:scsi:::64:portset64:::::yes: | ||
+ | 1:svc02:2:4:online:::0:svccl01:scsi:::64:portset64:::::yes: | ||
+ | ######### lsdrive | ||
+ | id:status:error_sequence_number:use:tech_type:capacity:mdisk_id:mdisk_name:member_id:enclosure_id:slot_id:node_id:node_name:auto_manage:drive_class_id | ||
+ | 0:online::member:tier0_flash:52.4TB:0:MDisk1:0:1:19:::inactive:0 | ||
+ | 1:online::member:tier0_flash:52.4TB:0:MDisk1:1:1:5:::inactive:0 | ||
+ | 2:online::member:tier0_flash:52.4TB:0:MDisk1:2:1:11:::inactive:0 | ||
+ | 3:online::member:tier0_flash:52.4TB:0:MDisk1:3:1:15:::inactive:0 | ||
+ | 4:online::member:tier0_flash:52.4TB:0:MDisk1:4:1:7:::inactive:0 | ||
+ | 5:online::member:tier0_flash:52.4TB:0:MDisk1:5:1:16:::inactive:0 | ||
+ | 6:online::member:tier0_flash:52.4TB:0:MDisk1:6:1:13:::inactive:0 | ||
+ | 7:online::member:tier0_flash:52.4TB:0:MDisk1:7:1:17:::inactive:0 | ||
+ | 8:online::member:tier0_flash:52.4TB:0:MDisk1:8:1:20:::inactive:0 | ||
+ | 9:online::member:tier0_flash:52.4TB:0:MDisk1:9:1:21:::inactive:0 | ||
+ | 10:online::member:tier0_flash:52.4TB:0:MDisk1:10:1:12:::inactive:0 | ||
+ | 11:online::member:tier0_flash:52.4TB:0:MDisk1:11:1:18:::inactive:0 | ||
+ | 12:online::member:tier0_flash:52.4TB:0:MDisk1:12:1:10:::inactive:0 | ||
+ | 13:online::member:tier0_flash:52.4TB:0:MDisk1:13:1:8:::inactive:0 | ||
+ | 14:online::member:tier0_flash:52.4TB:0:MDisk1:14:1:9:::inactive:0 | ||
+ | 15:online::member:tier0_flash:52.4TB:0:MDisk1:15:1:14:::inactive:0 | ||
+ | 16:online::member:tier0_flash:52.4TB:0:MDisk1:16:1:6:::inactive:0 | ||
+ | ######### lsmdiskgrp | ||
+ | id:name:status:mdisk_count:vdisk_count:capacity:extent_size:free_capacity:virtual_capacity:used_capacity:real_capacity:overallocation:warning:easy_tier:easy_tier_status:compression_active:compression_virtual_capacity:compression_compressed_capacity:compression_uncompressed_capacity:parent_mdisk_grp_id:parent_mdisk_grp_name:child_mdisk_grp_count:child_mdisk_grp_capacity:type:encrypt:owner_type:owner_id:owner_name:site_id:site_name:data_reduction:used_capacity_before_reduction:used_capacity_after_reduction:overhead_capacity:deduplication_capacity_saving:reclaimable_capacity:easy_tier_fcm_over_allocation_max:provisioning_policy_id:provisioning_policy_name:replication_pool_link_uid | ||
+ | 0:Pool01_SiteA:online:1:13:694.22TB:2048:654.21TB:40.00TB:40.00TB:40.00TB:5:80:auto:balanced:no:0.00MB:0.00MB:0.00MB:0:Pool01_SiteA:0:0.00MB:parent:yes:none:::::no:0.00MB:0.00MB:0.00MB:0.00MB:0.00MB:100%:::7D97EF5B263D688Exxxxxxxxxxxxxxxxxxxx | ||
+ | ######### lsmdisk | ||
+ | id:name:status:mode:mdisk_grp_id:mdisk_grp_name:capacity:ctrl_LUN_#:controller_name:UID:tier:encrypt:site_id:site_name:distributed:dedupe:over_provisioned:supports_unmap | ||
+ | 0:MDisk1:online:array:0:Pool01_SiteA:694.9TB::::tier0_flash:yes:::yes:no:yes:yes | ||
+ | ######### lsvdisk | ||
+ | id:name:IO_group_id:IO_group_name:status:mdisk_grp_id:mdisk_grp_name:capacity:type:FC_id:FC_name:RC_id:RC_name:vdisk_UID:fc_map_count:copy_count:fast_write_state:se_copy_count:RC_change:compressed_copy_count:parent_mdisk_grp_id:parent_mdisk_grp_name:owner_id:owner_name:formatting:encrypt:volume_id:volume_name:function:volume_group_id:volume_group_name:protocol:is_snapshot:snapshot_count:volume_type:replication_mode:is_safeguarded_snapshot:safeguarded_snapshot_count:restore_in_progress | ||
+ | 0:vol_siteA_001:0:io_grp0:online:0:Pool01_SiteA:4.00TB:striped:::::60050xxxxxxxxxx10000000000000000:0:1:not_empty:0:no:0:0:Pool01_SiteA:::yes:yes:0:vol_siteA_001::::scsi:no:0:::no:0:no | ||
+ | 1:vol_siteA_002:0:io_grp0:online:0:Pool01_SiteA:4.00TB:striped:::::60050xxxxxxxxxx10000000000000001:0:1:not_empty:0:no:0:0:Pool01_SiteA:::yes:yes:1:vol_siteA_002::::scsi:no:0:::no:0:no | ||
+ | 2:vol_siteA_003:0:io_grp0:online:0:Pool01_SiteA:4.00TB:striped:::::60050xxxxxxxxxx10000000000000002:0:1:not_empty:0:no:0:0:Pool01_SiteA:::yes:yes:2:vol_siteA_003::::scsi:no:0:::no:0:no | ||
+ | ######### lsenclosure | ||
+ | id:status:type:managed:IO_group_id:IO_group_name:product_MTM:serial_number:total_canisters:online_canisters:total_PSUs:online_PSUs:drive_slots:total_fan_modules:online_fan_modules:total_sems:online_sems | ||
+ | 1:online:control:yes:0:io_grp0:4657-924:78xxxxx:2:2:2:2:24:0:0:0:0 | ||
+ | ######### lsenclosurebattery | ||
+ | enclosure_id:battery_id:status:charging_status:recondition_needed:percent_charged:end_of_life_warning:canister_id:battery_slot | ||
+ | 1:1:online:idle:no:100:no:1:1 | ||
+ | 1:2:online:idle:no:100:no:2:1 | ||
+ | ######### lsenclosurecanister | ||
+ | enclosure_id:canister_id:status:type:node_id:node_name | ||
+ | 1:1:online:node:2:node2 | ||
+ | 1:2:online:node:1:node1 | ||
+ | ######### lsenclosurepsu | ||
+ | enclosure_id:PSU_id:status:input_power | ||
+ | 1:1:online:ac | ||
+ | 1:2:online:ac | ||
+ | ######### lsenclosureslot | ||
+ | enclosure_id:slot_id:port_1_status:port_2_status:drive_present:drive_id:row:column | ||
+ | 1:1:::no::: | ||
+ | 1:2:::no::: | ||
+ | 1:3:::no::: | ||
+ | 1:4:::no::: | ||
+ | 1:5:::yes:1:: | ||
+ | 1:6:::yes:16:: | ||
+ | 1:7:::yes:4:: | ||
+ | 1:8:::yes:13:: | ||
+ | ... | ||
+ | </code> | ||
+ | |||
+ | On SVC | ||
+ | <code> | ||
+ | ######### lsnode | ||
+ | id:name:UPS_serial_number:WWNN:status:IO_group_id:IO_group_name:config_node:UPS_unique_id:hardware:iscsi_name:iscsi_alias:panel_name:enclosure_id:canister_id:enclosure_serial_number:site_id:site_name | ||
+ | 1:svcaxx01::50050xxxx000yyD:online:0:io_grp0:yes::SA2:iqn.xxxxxxx.com.ibm:2145.svccl01.svcaxx01::78xxxxD::1::1:siteA | ||
+ | 6:svcbxx01::50050xxxx000yyA4:online:0:io_grp0:no::SA2:iqn.xxxxxxx.com.ibm:2145.svccl01.svcbxx01::78xxxxC::1::2:siteB | ||
+ | 3:svcaxx02::50050xxxx000yy5F:online:1:io_grp1:no::SA2:iqn.xxxxxxx.com.ibm:2145.svccl01.svcaxx02::78xxxxL::1::1:siteA | ||
+ | 4:svcbxx02::50050xxxx000yy5D:online:1:io_grp1:no::SA2:iqn.xxxxxxx.com.ibm:2145.svccl01.svcbxx02::78xxxxN::1::2:siteB | ||
+ | ######### lsnodebattery | ||
+ | node_id:node_name:battery_id:status:charging_status:recondition_needed:node_percentage_charge:end_of_life_warning | ||
+ | 1:svcaxx01:1:online:idle:no:100:no | ||
+ | 6:svcbxx01:1:online:idle:no:100:no | ||
+ | 3:svcaxx02:1:online:idle:no:100:no | ||
+ | 4:svcbxx02:1:online:idle:no:100:no | ||
+ | </code> |