#!/bin/bash
#
# Shell script for checking for raid problems
# by Kent Ziebell 10-April-2001
#
# raid.cron.script
#
#
# Example cron entry:
#
# check the raid out
#
#56 3,9,16 * * * /usr/local/src/raid/raid.cron.script > /dev/null 2>&1
#
#
#
# ======> Preliminary setup work starts here
# Before placing this script into cron, be sure to "seed" the check so that
#   you have a permanent copy of what your raid config should look like if
#   all is well.  Do that by issuing the following:
#
#   cd /usr/local/src/raid   (or where ever you want this stuff to live)
#
#   now use your favorite editor to create a file called "raid.commands" with
#      the following six commands (without leading # character, of course):
#
#      open afa0
#      logfile start raid.current.config
#      container list
#      disk list
#      logfile end
#      exit
#
#   /usr/sbin/afacli < raid.commands
#   mv raid.current.config raid.production.config
#
#   Dale Blount reports that you may need leading whitespace before
#   the commands if running this out of crond, else the commands get
#   munged together somehow.
#
#
# End of preliminary setup.
#
#
# Who's watching - whom to send the notification
#
# =====> Change the following line to whom should be notified
#

mailwatch=support@logic.cz
host=`hostname`

#  CHECK 1
#
cd /usr/local/src/raid
rm raid.current.config
/usr/sbin/afacli < raid.commands

curdiff=`/usr/bin/diff raid.current.config raid.production.config`
raiderr=`/bin/cat raid.current.config`

if [ "$curdiff" != "" ] ; then
   /usr/sbin/sendmail -f root@$host -t << RedCatSun
   To: $mailwatch
   From: root@$host
   Subject: Raid may be broken on $host
   Raid may be broken on $host.

   ====> A diff between production and current is:

   $curdiff

   ====> The current container list and disk list is:

   $raiderr

   RedCatSun
fi


#  CHECK 2
#
#  The next check is just looking for AAC: messages in /var/log/messages
#
#  Raid error messages look something like the following:
#
#  AAC:ID(0:02:0); Selection Timeout [command:0x28]
#  AAC:Drive 0:2:0 returning error
#  AAC:ID(0:02:0) - drive failure (retries exhausted)
#  AAC:RAID5 Container 0 Drive 0:2:0 Failure
#  AAC:ID(0:02:0) [DC_Ioctl] DiskSpinControl: Drive spindown failure
#  AAC:RAID5 Failover Container 0 No Failover Assigned
#  AAC:Drive 0:2:0 offline on container 0:
#  AAC:RAID5 Failover Container 0 No Failover Assigned
AACerr=`/usr/bin/egrep "(AAC|aacraid):" /var/log/messages`

if [ "$AACerr" != "" ] ; then
   /usr/sbin/sendmail -f devnull@$host -t << RedDogSun
   To: $mailwatch
   From: root@$host
   Subject: Raid may be broken on $host
   Raid 5 may be broken on $host.

   ====> A grep for ACC: in /var/log/messages:

   $AACerr

   RedDogSun
fi

exit 0