check_md_raid

Hi, here's my version that works on my config, i changed some deprecated commands:

#!/bin/bash
#
# Created by Sebastian Grewe, Jammicron Technology
#

# Get count of raid arrays
RAID_DEVICES=$(grep ^md -c /proc/mdstat)

# Get count of degraded arrays
#RAID_STATUS=`grep "\[.*_.*\]" /proc/mdstat -c`
RAID_STATUS=$(grep -E "\[.*(=|>|\.).*\]" /proc/mdstat -c)

# Is an array currently recovering, get percentage of recovery
RAID_RECOVER=$(grep recovery /proc/mdstat | awk '{print $4}')
RAID_RESYNC=$(grep resync /proc/mdstat | awk '{print $4}')
RAID_CHECK=$(grep check /proc/mdstat | awk '{print $4}')

# Check raid status
# RAID recovers --> Warning
if [ -n "${RAID_RECOVER}" ]; then
#if [[ $RAID_RECOVER ]]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, recovering : $RAID_RECOVER"
EXIT=1
elif [ -n "${RAID_RESYNC}" ]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, resync : $RAID_RESYNC"
EXIT=1
elif [ -n "${RAID_CHECK}" ]; then
STATUS="OK - Checked $RAID_DEVICES arrays, check : $RAID_CHECK"
EXIT=0
# RAID ok
elif [ -n "${RAID_STATUS}" = "0" ]; then
STATUS="OK - Checked $RAID_DEVICES arrays."
EXIT=0
# All else critical, better save than sorry
else
EXTEND_RAID_STATUS=$(grep -E "\[.*(=|>|\.|_).*\]" /proc/mdstat | awk '{print $2}' | uniq -c | xargs echo)
STATUS="WARNING- Checked $RAID_DEVICES arrays, $RAID_STATUS have failed check: $EXTEND_RAID_STATUS "
EXIT=1
fi

# Status and quit
echo "$STATUS"
exit $EXIT

Hi,

I added another status for state "check" which is OK (0), and dumps the % complete.

############

[root@stack2 bin]# ./check_md_raid
OK - Checked 1 arrays, check : 0.4%

############

[root@stack2 bin]# more ./check_md_raid
#!/bin/bash
#
# Created by Sebastian Grewe, Jammicron Technology
#

# Get count of raid arrays
RAID_DEVICES=`grep ^md -c /proc/mdstat`

# Get count of degraded arrays
#RAID_STATUS=`grep "\[.*_.*\]" /proc/mdstat -c`
RAID_STATUS=`egrep "\[.*(=|>|\.).*\]" /proc/mdstat -c`

# Is an array currently recovering, get percentage of recovery
RAID_RECOVER=`grep recovery /proc/mdstat | awk '{print $4}'`
RAID_RESYNC=`grep resync /proc/mdstat | awk '{print $4}'`
RAID_CHECK=`grep check /proc/mdstat | awk '{print $4}'`

# Check raid status
# RAID recovers --> Warning
if [[ $RAID_RECOVER ]]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, recovering : $RAID_RECOVER"
EXIT=1
elif [[ $RAID_RESYNC ]]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, resync : $RAID_RESYNC"
EXIT=1
elif [[ $RAID_CHECK ]]; then
STATUS="OK - Checked $RAID_DEVICES arrays, check : $RAID_CHECK"
EXIT=0
# RAID ok
elif [[ $RAID_STATUS == "0" ]]; then
STATUS="OK - Checked $RAID_DEVICES arrays."
EXIT=0
# All else critical, better save than sorry
else
EXTEND_RAID_STATUS=`egrep "\[.*(=|>|\.|_).*\]" /proc/mdstat | awk '{print $2}' | uniq -c | xargs echo`
STATUS="WARNING- Checked $RAID_DEVICES arrays, $RAID_STATUS have failed check: $EXTEND_RAID_STATUS "
EXIT=1
fi

# Status and quit
echo $STATUS
exit $EXIT

Yet I changed some lines, making this script more useful for our environment, from the last review.

Next step would be to parse the raid status, but so far I got the messages listed below, so this is how far my script could go.

Cheers!

[======>..............] check = 34.7% (72921088/209711382) finish=6891.0min speed=330K/sec
[========>............] check = 43.7% (91719680/209711382) finish=480.0min speed=4096K/sec



#!/bin/bash
#
# Created by Sebastian Grewe, Jammicron Technology
#

# Get count of raid arrays
RAID_DEVICES=`grep ^md -c /proc/mdstat`

# Get count of degraded arrays
#RAID_STATUS=`grep "\[.*_.*\]" /proc/mdstat -c`
RAID_STATUS=`egrep "\[.*(=|>|\.).*\]" /proc/mdstat -c`

# Is an array currently recovering, get percentage of recovery
RAID_RECOVER=`grep recovery /proc/mdstat | awk '{print $4}'`
RAID_RESYNC=`grep resync /proc/mdstat | awk '{print $4}'`

# Check raid status
# RAID recovers --> Warning
if [[ $RAID_RECOVER ]]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, recovering : $RAID_RECOVER"
EXIT=1
elif [[ $RAID_RESYNC ]]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, resync : $RAID_RESYNC"
EXIT=1
# RAID ok
elif [[ $RAID_STATUS == "0" ]]; then
STATUS="OK - Checked $RAID_DEVICES arrays."
EXIT=0
# All else critical, better save than sorry
else
EXTEND_RAID_STATUS=`egrep "\[.*(=|>|\.|_).*\]" /proc/mdstat | awk '{print $2}' | uniq -c | xargs echo`
STATUS="WARNING- Checked $RAID_DEVICES arrays, $RAID_STATUS have failed check: $EXTEND_RAID_STATUS "
EXIT=1
fi

# Status and quit
echo $STATUS
exit $EXIT

#!/bin/bash
#
# Created by Sebastian Grewe, Jammicron Technology
#

# Get count of raid arrays
RAID_DEVICES=`grep ^md -c /proc/mdstat`

# Get count of degraded arrays
RAID_STATUS=`grep "\[.*_.*\]" /proc/mdstat -c`

# Is an array currently recovering, get percentage of recovery
RAID_RECOVER=`grep recovery /proc/mdstat | awk '{print $4}'`
RAID_RESYNC=`grep resync /proc/mdstat | awk '{print $4}'`

# Check raid status
# RAID recovers --> Warning
if [[ $RAID_RECOVER ]]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, recovering : $RAID_RECOVER"
EXIT=1
elif [[ $RAID_RESYNC ]]; then
STATUS="WARNING - Checked $RAID_DEVICES arrays, resync : $RAID_RESYNC"
EXIT=1
# RAID ok
elif [[ $RAID_STATUS == "0" ]]; then
STATUS="OK - Checked $RAID_DEVICES arrays."
EXIT=0
# All else critical, better save than sorry
else
STATUS="CRITICAL - Checked $RAID_DEVICES arrays, $RAID_STATUS have FAILED"
EXIT=2
fi

# Status and quit
echo $STATUS
exit $EXIT