mirror of
https://github.com/librenms/librenms.git
synced 2024-09-23 11:29:23 +00:00
Merge pull request #409 from f0o/issue-405-check_mk
Updated check_mk_agent
This commit is contained in:
commit
77a5d6b745
@ -6,7 +6,7 @@
|
||||
# | | |___| | | | __/ (__| < | | | | . \ |
|
||||
# | \____|_| |_|\___|\___|_|\_\___|_| |_|_|\_\ |
|
||||
# | |
|
||||
# | Copyright Mathias Kettner 2013 mk@mathias-kettner.de |
|
||||
# | Copyright Mathias Kettner 2014 mk@mathias-kettner.de |
|
||||
# +------------------------------------------------------------------+
|
||||
#
|
||||
# This file is part of Check_MK.
|
||||
@ -29,6 +29,15 @@ unset LANG
|
||||
|
||||
export MK_LIBDIR="/usr/lib/check_mk_agent"
|
||||
export MK_CONFDIR="/etc/check_mk"
|
||||
export MK_VARDIR="/var/lib/check_mk_agent"
|
||||
|
||||
# Provide information about the remote host. That helps when data
|
||||
# is being sent only once to each remote host.
|
||||
if [ "$REMOTE_HOST" ] ; then
|
||||
export REMOTE=$REMOTE_HOST
|
||||
elif [ "$SSH_CLIENT" ] ; then
|
||||
export REMOTE=${SSH_CLIENT%% *}
|
||||
fi
|
||||
|
||||
# Make sure, locally installed binaries are found
|
||||
PATH=$PATH:/usr/local/bin
|
||||
@ -45,8 +54,7 @@ LOCALDIR=$MK_LIBDIR/local
|
||||
|
||||
# All files in SPOOLDIR will simply appended to the agent
|
||||
# output if they are not outdated (see below)
|
||||
SPOOLDIR=$MK_CONFDIR/spool
|
||||
|
||||
SPOOLDIR=$MK_VARDIR/spool
|
||||
|
||||
# close standard input (for security reasons) and stderr
|
||||
if [ "$1" = -d ]
|
||||
@ -58,21 +66,26 @@ fi
|
||||
|
||||
# Runs a command asynchronous by use of a cache file
|
||||
function run_cached () {
|
||||
local section=
|
||||
if [ "$1" = -s ] ; then local section="echo '<<<$2>>>' ; " ; shift ; fi
|
||||
local NAME=$1
|
||||
local MAXAGE=$2
|
||||
shift 2
|
||||
local CMDLINE="$section$@"
|
||||
|
||||
if [ ! -d $MK_CONFDIR/cache ]; then mkdir -p $MK_CONFDIR/cache ; fi
|
||||
CACHEFILE="$MK_CONFDIR/cache/$NAME.cache"
|
||||
if [ ! -d $MK_VARDIR/cache ]; then mkdir -p $MK_VARDIR/cache ; fi
|
||||
CACHEFILE="$MK_VARDIR/cache/$NAME.cache"
|
||||
|
||||
# Check if the creation of the cache takes suspiciously long and return
|
||||
# Check if the creation of the cache takes suspiciously long and return
|
||||
# nothing if the age (access time) of $CACHEFILE.new is twice the MAXAGE
|
||||
local NOW=$(date +%s)
|
||||
if [ -e "$CACHEFILE.new" ] ; then
|
||||
local CF_ATIME=$(stat -c %X "$CACHEFILE.new")
|
||||
if [ $((NOW - CF_ATIME)) -ge $((MAXAGE * 2)) ] ; then
|
||||
if [ $((NOW - CF_ATIME)) -ge $((MAXAGE * 2)) ] ; then
|
||||
# Kill the process still accessing that file in case
|
||||
# it is still running. This avoids overlapping processes!
|
||||
fuser -k -9 "$CACHEFILE.new" >/dev/null 2>&1
|
||||
rm -f "$CACHEFILE.new"
|
||||
return
|
||||
fi
|
||||
fi
|
||||
@ -88,17 +101,21 @@ function run_cached () {
|
||||
|
||||
# Cache file outdated and new job not yet running? Start it
|
||||
if [ -z "$USE_CACHEFILE" -a ! -e "$CACHEFILE.new" ] ; then
|
||||
echo "set -o noclobber ; exec > \"$CACHEFILE.new\" || exit 1 ; $CMDLINE && mv \"$CACHEFILE.new\" \"$CACHEFILE\" || rm -f \"$CACHEFILE\" \"$CACHEFILE.new\"" | nohup bash 2>/dev/null &
|
||||
echo "set -o noclobber ; exec > \"$CACHEFILE.new\" || exit 1 ; $CMDLINE && mv \"$CACHEFILE.new\" \"$CACHEFILE\" || rm -f \"$CACHEFILE\" \"$CACHEFILE.new\"" | nohup bash >/dev/null 2>&1 &
|
||||
fi
|
||||
}
|
||||
|
||||
# Make run_cached available for subshells (plugins, local checks, etc.)
|
||||
export -f run_cached
|
||||
|
||||
echo '<<<check_mk>>>'
|
||||
echo Version: 1.2.4p5
|
||||
echo Version: 1.2.6b5
|
||||
echo AgentOS: linux
|
||||
echo AgentDirectory: $MK_CONFDIR
|
||||
echo DataDirectory: $MK_VARDIR
|
||||
echo SpoolDirectory: $SPOOLDIR
|
||||
echo PluginsDirectory: $PLUGINSDIR
|
||||
echo LocalDirectory: $LOCALDIR
|
||||
echo SpoolDirectory: $SPOOLDIR
|
||||
echo AgentDirectory: $MK_CONFDIR
|
||||
|
||||
# If we are called via xinetd, try to find only_from configuration
|
||||
if [ -n "$REMOTE_HOST" ]
|
||||
@ -117,13 +134,20 @@ fi
|
||||
echo '<<<df>>>'
|
||||
# The exclusion list is getting a bit of a problem. -l should hide any remote FS but seems
|
||||
# to be all but working.
|
||||
excludefs="-x smbfs -x tmpfs -x cifs -x iso9660 -x udf -x nfsv4 -x nfs -x mvfs -x zfs"
|
||||
excludefs="-x smbfs -x cifs -x iso9660 -x udf -x nfsv4 -x nfs -x mvfs -x zfs"
|
||||
df -PTlk $excludefs | sed 1d
|
||||
|
||||
# df inodes information
|
||||
echo '<<<df>>>'
|
||||
echo '[df_inodes_start]'
|
||||
df -PTli $excludefs | sed 1d
|
||||
echo '[df_inodes_end]'
|
||||
|
||||
# Filesystem usage for ZFS
|
||||
if type zfs > /dev/null 2>&1 ; then
|
||||
echo '<<<zfsget>>>'
|
||||
zfs get -Hp name,quota,used,avail,mountpoint,type
|
||||
zfs get -Hp name,quota,used,avail,mountpoint,type -t filesystem,volume || \
|
||||
zfs get -Hp name,quota,used,avail,mountpoint,type
|
||||
echo '[df]'
|
||||
df -PTlk -t zfs | sed 1d
|
||||
fi
|
||||
@ -149,6 +173,20 @@ then
|
||||
printf '\n'|| echo "$MP hanging 0 0 0 0"
|
||||
fi
|
||||
done
|
||||
|
||||
echo '<<<cifsmounts>>>'
|
||||
sed -n '/ cifs\? /s/[^ ]* \([^ ]*\) .*/\1/p' < /proc/mounts |
|
||||
sed 's/\\040/ /g' |
|
||||
while read MP
|
||||
do
|
||||
if [ $STAT_VERSION != $STAT_BROKE ]; then
|
||||
waitmax -s 9 2 stat -f -c "$MP ok %b %f %a %s" "$MP" || \
|
||||
echo "$MP hanging 0 0 0 0"
|
||||
else
|
||||
waitmax -s 9 2 stat -f -c "$MP ok %b %f %a %s" "$MP" && \
|
||||
printf '\n'|| echo "$MP hanging 0 0 0 0"
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
# Check mount options. Filesystems may switch to 'ro' in case
|
||||
@ -158,8 +196,7 @@ grep ^/dev < /proc/mounts
|
||||
|
||||
# processes including username, without kernel processes
|
||||
echo '<<<ps>>>'
|
||||
ps ax -o user,vsz,rss,pcpu,command --columns 10000 | sed -e 1d -e 's/ *\([^ ]*\) *\([^ ]*\) *\([^ ]*\) *\([^ ]*\) */(\1,\2,\3,\4) /'
|
||||
|
||||
ps ax -o user,vsz,rss,cputime,pid,command --columns 10000 | sed -e 1d -e 's/ *\([^ ]*\) *\([^ ]*\) *\([^ ]*\) *\([^ ]*\) *\([^ ]*\) */(\1,\2,\3,\4,\5) /'
|
||||
|
||||
# Memory usage
|
||||
echo '<<<mem>>>'
|
||||
@ -183,7 +220,7 @@ then
|
||||
do
|
||||
echo "[$eth]"
|
||||
ethtool $eth | egrep '(Speed|Duplex|Link detected|Auto-negotiation):'
|
||||
echo -en "\tAddress: " ; cat /sys/class/net/$eth/address
|
||||
echo -en "\tAddress: " ; cat /sys/class/net/$eth/address ; echo
|
||||
done
|
||||
fi
|
||||
|
||||
@ -210,22 +247,12 @@ echo '<<<tcp_conn_stats>>>'
|
||||
# New implementation: netstat is very slow for large TCP tables
|
||||
cat /proc/net/tcp /proc/net/tcp6 2>/dev/null | awk ' /:/ { c[$4]++; } END { for (x in c) { print x, c[x]; } }'
|
||||
|
||||
# Platten- und RAID-Status von LSI-Controlleren, falls vorhanden
|
||||
if type cfggen > /dev/null ; then
|
||||
echo '<<<lsi>>>'
|
||||
cfggen 0 DISPLAY | egrep '(Target ID|State|Volume ID|Status of volume)[[:space:]]*:' | sed -e 's/ *//g' -e 's/:/ /'
|
||||
fi
|
||||
|
||||
# Multipathgeraete
|
||||
# Linux Multipathing
|
||||
if type multipath >/dev/null ; then
|
||||
echo '<<<multipath>>>'
|
||||
multipath -l
|
||||
fi
|
||||
|
||||
# Soft-RAID
|
||||
echo '<<<md>>>'
|
||||
cat /proc/mdstat
|
||||
|
||||
# Performancecounter Platten
|
||||
echo '<<<diskstat>>>'
|
||||
date +%s
|
||||
@ -254,69 +281,81 @@ fi
|
||||
|
||||
# IPMI data via ipmi-sensors (of freeipmi). Please make sure, that if you
|
||||
# have installed freeipmi that IPMI is really support by your hardware.
|
||||
# The agent tries to avoid hanging forever by setting a limit of 300 seconds
|
||||
# for the first run (where the cache is created). If ipmi-sensors runs into
|
||||
# that timeout, it leaves and empty cache file. We skip this check forever
|
||||
# if we find that empty cache file.
|
||||
sdrcache=/var/cache/.freeipmi/sdr-cache/sdr-cache-$(hostname | cut -d. -f1).127.0.0.1
|
||||
if type ipmi-sensors >/dev/null && [ ! -e "$sdrcache" -o -s "$sdrcache" ]
|
||||
if type ipmi-sensors >/dev/null
|
||||
then
|
||||
echo '<<<ipmi_sensors>>>'
|
||||
# No cache file existing? => Impose a high time limit. We do not suffice
|
||||
# in creating the cache we most probably run on a hardware where this tool
|
||||
# is hanging forever. We make sure that we never try again in that case!
|
||||
if [ ! -e "$sdrcache" ]
|
||||
then
|
||||
WAITMAX="waitmax 300"
|
||||
elif tail --bytes 2 < "$sdrcache" | od -t x2 | grep -q 0a0a
|
||||
then
|
||||
WAITMAX="waitmax 3"
|
||||
else
|
||||
# Cache file corrupt. Must end with two linefeeds.
|
||||
rm -f $sdrcache
|
||||
WAITMAX=
|
||||
fi
|
||||
# Newer ipmi-sensors version have new output format; Legacy format can be used
|
||||
if ipmi-sensors --help | grep -q legacy-output; then
|
||||
IPMI_FORMAT="--legacy-output"
|
||||
else
|
||||
IPMI_FORMAT=""
|
||||
fi
|
||||
# Aquire lock with flock in order to avoid multiple runs of ipmi-sensors
|
||||
# in case of parallel or overlapping calls of the agent.
|
||||
(
|
||||
flock -n 200 --wait 60
|
||||
# At least with ipmi-sensoirs 0.7.16 this group is Power_Unit instead of "Power Unit"
|
||||
for class in Temperature Power_Unit Fan
|
||||
do
|
||||
$WAITMAX ipmi-sensors $IPMI_FORMAT --sdr-cache-directory /var/cache -g "$class" | sed -e 's/ /_/g' -e 's/:_\?/ /g' -e 's@ \([^(]*\)_(\([^)]*\))@ \2_\1@'
|
||||
# In case of a timeout immediately leave loop.
|
||||
# At least with ipmi-sensoirs 0.7.16 this group is Power_Unit instead of "Power Unit"
|
||||
run_cached -s ipmi_sensors 300 "for class in Temperature Power_Unit Fan
|
||||
do
|
||||
ipmi-sensors $IPMI_FORMAT --sdr-cache-directory /var/cache -g "$class" | sed -e 's/ /_/g' -e 's/:_\?/ /g' -e 's@ \([^(]*\)_(\([^)]*\))@ \2_\1@'
|
||||
# In case of a timeout immediately leave loop.
|
||||
if [ $? = 255 ] ; then break ; fi
|
||||
WAITMAX="waitmax 3"
|
||||
done
|
||||
) 200>>"$sdrcache"
|
||||
done"
|
||||
fi
|
||||
|
||||
# State of LSI MegaRAID controller via MegaCli. You can download that tool from:
|
||||
# http://www.lsi.com/downloads/Public/MegaRAID%20Common%20Files/8.02.16_MegaCLI.zip
|
||||
# RAID status of Linux software RAID
|
||||
echo '<<<md>>>'
|
||||
cat /proc/mdstat
|
||||
|
||||
# RAID status of Linux RAID via device mapper
|
||||
if type dmraid >/dev/null && DMSTATUS=$(dmraid -r)
|
||||
then
|
||||
echo '<<<dmraid>>>'
|
||||
|
||||
# Output name and status
|
||||
dmraid -s | grep -e ^name -e ^status
|
||||
|
||||
# Output disk names of the RAID disks
|
||||
DISKS=$(echo "$DMSTATUS" | cut -f1 -d\:)
|
||||
|
||||
for disk in $DISKS ; do
|
||||
device=$(cat /sys/block/$(basename $disk)/device/model )
|
||||
status=$(echo "$DMSTATUS" | grep ^${disk})
|
||||
echo "$status Model: $device"
|
||||
done
|
||||
fi
|
||||
|
||||
# RAID status of LSI controllers via cfggen
|
||||
if type cfggen > /dev/null ; then
|
||||
echo '<<<lsi>>>'
|
||||
cfggen 0 DISPLAY | egrep '(Target ID|State|Volume ID|Status of volume)[[:space:]]*:' | sed -e 's/ *//g' -e 's/:/ /'
|
||||
fi
|
||||
|
||||
# RAID status of LSI MegaRAID controller via MegaCli. You can download that tool from:
|
||||
# http://www.lsi.com/downloads/Public/MegaRAID%20Common%20Files/8.02.16_MegaCLI.zip
|
||||
if type MegaCli >/dev/null ; then
|
||||
MegaCli_bin="MegaCli"
|
||||
elif type MegaCli64 >/dev/null ; then
|
||||
MegaCli_bin="MegaCli64"
|
||||
elif type megacli >/dev/null ; then
|
||||
MegaCli_bin="megacli"
|
||||
else
|
||||
MegaCli_bin="unknown"
|
||||
fi
|
||||
|
||||
if [ "$MegaCli_bin" != "unknown" ]; then
|
||||
echo '<<<megaraid_pdisks>>>'
|
||||
for part in $(MegaCli -EncInfo -aALL -NoLog < /dev/null \
|
||||
for part in $($MegaCli_bin -EncInfo -aALL -NoLog < /dev/null \
|
||||
| sed -rn 's/:/ /g; s/[[:space:]]+/ /g; s/^ //; s/ $//; s/Number of enclosures on adapter ([0-9]+).*/adapter \1/g; /^(Enclosure|Device ID|adapter) [0-9]+$/ p'); do
|
||||
[ $part = adapter ] && echo ""
|
||||
[ $part = 'Enclosure' ] && echo -ne "\ndev2enc"
|
||||
echo -n " $part"
|
||||
done
|
||||
echo
|
||||
MegaCli -PDList -aALL -NoLog < /dev/null | egrep 'Enclosure|Raw Size|Slot Number|Device Id|Firmware state|Inquiry|Adapter'
|
||||
$MegaCli_bin -PDList -aALL -NoLog < /dev/null | egrep 'Enclosure|Raw Size|Slot Number|Device Id|Firmware state|Inquiry|Adapter'
|
||||
echo '<<<megaraid_ldisks>>>'
|
||||
MegaCli -LDInfo -Lall -aALL -NoLog < /dev/null | egrep 'Size|State|Number|Adapter|Virtual'
|
||||
$MegaCli_bin -LDInfo -Lall -aALL -NoLog < /dev/null | egrep 'Size|State|Number|Adapter|Virtual'
|
||||
echo '<<<megaraid_bbu>>>'
|
||||
MegaCli -AdpBbuCmd -GetBbuStatus -aALL -NoLog < /dev/null | grep -v Exit
|
||||
$MegaCli_bin -AdpBbuCmd -GetBbuStatus -aALL -NoLog < /dev/null | grep -v Exit
|
||||
fi
|
||||
|
||||
# 3WARE disk controller (by Radoslaw Bak)
|
||||
# RAID status of 3WARE disk controller (by Radoslaw Bak)
|
||||
if type tw_cli > /dev/null ; then
|
||||
for C in $(tw_cli show | awk 'NR < 4 { next } { print $1 }'); do
|
||||
echo '<<<3ware_info>>>'
|
||||
@ -328,11 +367,17 @@ if type tw_cli > /dev/null ; then
|
||||
done
|
||||
fi
|
||||
|
||||
# RAID controllers from areca (Taiwan)
|
||||
# cli64 can be found at ftp://ftp.areca.com.tw/RaidCards/AP_Drivers/Linux/CLI/
|
||||
if type cli64 >/dev/null ; then
|
||||
run_cached -s arc_raid_status 300 "cli64 rsf info | tail -n +3 | head -n -2"
|
||||
fi
|
||||
|
||||
# VirtualBox Guests. Section must always been output. Otherwise the
|
||||
# check would not be executed in case no guest additions are installed.
|
||||
# And that is something the check wants to detect
|
||||
echo '<<<vbox_guest>>>'
|
||||
if type VBoxControl > /dev/null 2>&1 ; then
|
||||
if type VBoxControl >/dev/null 2>&1 ; then
|
||||
VBoxControl -nologo guestproperty enumerate | cut -d, -f1,2
|
||||
[ ${PIPESTATUS[0]} = 0 ] || echo "ERROR"
|
||||
fi
|
||||
@ -341,12 +386,19 @@ fi
|
||||
# /etc/openvpn. We might find a safer way to find the configuration later.
|
||||
if [ -e /etc/openvpn/openvpn-status.log ] ; then
|
||||
echo '<<<openvpn_clients:sep(44)>>>'
|
||||
sed -n -e '/CLIENT LIST/,/ROUTING TABLE/p' < /etc/openvpn/openvpn-status.log | sed -e 1,3d -e '$d'
|
||||
sed -n -e '/CLIENT LIST/,/ROUTING TABLE/p' < /etc/openvpn/openvpn-status.log | sed -e 1,3d -e '$d'
|
||||
fi
|
||||
|
||||
# Time synchronization with NTP
|
||||
if type ntpq > /dev/null 2>&1 ; then
|
||||
# remove heading, make first column space separated
|
||||
run_cached -s ntp 30 "waitmax 5 ntpq -p | sed -e 1,2d -e 's/^\(.\)/\1 /' -e 's/^ /%/'"
|
||||
run_cached -s ntp 30 "waitmax 5 ntpq -np | sed -e 1,2d -e 's/^\(.\)/\1 /' -e 's/^ /%/'"
|
||||
fi
|
||||
|
||||
# Time synchronization with Chrony
|
||||
if type chronyc > /dev/null 2>&1 ; then
|
||||
# Force successful exit code. Otherwise section will be missing if daemon not running
|
||||
run_cached -s chrony 30 "waitmax 5 chronyc tracking || true"
|
||||
fi
|
||||
|
||||
if type nvidia-settings >/dev/null && [ -S /tmp/.X11-unix/X0 ]
|
||||
@ -380,7 +432,7 @@ if type lpstat > /dev/null 2>&1; then
|
||||
echo '---'
|
||||
lpstat -o | while read LINE
|
||||
do
|
||||
PRINTER=$(echo $LINE | awk '{print $2}')
|
||||
PRINTER=${LINE%%-*}
|
||||
if echo "$LOCAL_PRINTERS" | grep -q "$PRINTER"; then
|
||||
echo $LINE
|
||||
fi
|
||||
@ -429,9 +481,17 @@ fi
|
||||
# Only handle the last 6 lines (includes the summary line at the bottom and
|
||||
# the last message in the queue. The last message is not used at the moment
|
||||
# but it could be used to get the timestamp of the last message.
|
||||
if type mailq >/dev/null 2>&1 && [ -x /usr/sbin/postfix ] && getent passwd postfix >/dev/null 2>&1; then
|
||||
if type postconf >/dev/null ; then
|
||||
echo '<<<postfix_mailq>>>'
|
||||
mailq | tail -n 6
|
||||
postfix_queue_dir=$(postconf -h queue_directory)
|
||||
postfix_count=$(find $postfix_queue_dir/deferred -type f | wc -l)
|
||||
postfix_size=$(du -ks $postfix_queue_dir/deferred | awk '{print $1 }')
|
||||
if [ $postfix_count -gt 0 ]
|
||||
then
|
||||
echo -- $postfix_size Kbytes in $postfix_count Requests.
|
||||
else
|
||||
echo Mail queue is empty
|
||||
fi
|
||||
elif [ -x /usr/sbin/ssmtp ] ; then
|
||||
echo '<<<postfix_mailq>>>'
|
||||
mailq 2>&1 | sed 's/^[^:]*: \(.*\)/\1/' | tail -n 6
|
||||
@ -447,7 +507,7 @@ fi
|
||||
# Check status of OMD sites
|
||||
if type omd >/dev/null
|
||||
then
|
||||
run_cached omd_status 60 "echo '<<<omd_status>>>' ; omd status --bare --auto"
|
||||
run_cached -s omd_status 60 "omd status --bare --auto"
|
||||
fi
|
||||
|
||||
|
||||
@ -486,7 +546,7 @@ fi
|
||||
# is a sub directory per user that ran a job. That directory must be
|
||||
# owned by the user so that a symlink or hardlink attack for reading
|
||||
# arbitrary files can be avoided.
|
||||
if pushd /var/lib/check_mk_agent/job >/dev/null; then
|
||||
if pushd $MK_VARDIR/job >/dev/null; then
|
||||
echo '<<<job>>>'
|
||||
for username in *
|
||||
do
|
||||
@ -504,11 +564,18 @@ if ls /sys/class/thermal/thermal_zone* >/dev/null 2>&1; then
|
||||
echo '<<<lnx_thermal>>>'
|
||||
for F in /sys/class/thermal/thermal_zone*; do
|
||||
echo -n "${F##*/} "
|
||||
if [ ! -e $F/mode ] ; then echo -n "- " ; fi
|
||||
cat $F/{mode,type,temp,trip_point_*} | tr \\n " "
|
||||
echo
|
||||
done
|
||||
fi
|
||||
|
||||
# Libelle Business Shadow
|
||||
if type trd >/dev/null; then
|
||||
echo "<<<libelle_business_shadow:sep(58)>>>"
|
||||
trd -s
|
||||
fi
|
||||
|
||||
# MK's Remote Plugin Executor
|
||||
if [ -e "$MK_CONFDIR/mrpe.cfg" ]
|
||||
then
|
||||
|
Loading…
Reference in New Issue
Block a user