From mboxrd@z Thu Jan  1 00:00:00 1970
From: olivier arsac <oliv@arsac.org>
Date: Mon, 13 Aug 2007 09:49:23 +0000
Subject: Re: [LARTC] How to check an inactive slave in a bond?
Message-Id: <46C02923.1010904@arsac.org>
List-Id: <lartc.vger.kernel.org>
References: <469F6422.5060303@arsac.org>
In-Reply-To: <469F6422.5060303@arsac.org>
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
To: lartc@vger.kernel.org

Thank you for this very complete answer.

- Assuming I really have to implement some sort of inactive slave-link 
check.
- Assuming it is acceptable to remove the inactive slave from the bound 
for the duration of the check.

Could you help me check my script? It works well for me but as I'm about 
to deploy it for production purpose I'd rather have a double check from 
you guys.
(Note: I'm not reliable when it comes to (among other things) routing 
and network related topics)

Thx.

       Olivier

---------------------------------------------------------------------------------------
#!/bin/bash

# Check all nics enslaved in a bond.
# This is a way to check that all nics (including inactive ones) are 
working properly.
#

# Authors:
#   OA: Olivier Arsac
# History:
#   19/04/2007: OA scratch
#   31/06/2007: OA better handling of "free" IPs used during test
# TODO:
#   remove all TODOs from the script

#set -x

# try to be robust -> exit if a variable is not set (probably something 
went wrong)
set -o nounset

trap clean INT TERM

PATH=/exploit/local/sbin:/exploit/local/bin:/usr/kerberos/sbin:/usr/kerberos/bin:/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin:/exploit/unix/prod/bin

com=`basename "$0"`
fullcom="$*"

usage() {
    echo "Usage: $com [-q] [-i ip] [-t target] [bond]"
    echo "  Check all nics enslaved to a bond."
    echo "  This is a way to check that all nics (including inactive 
ones) are working properly. You should check that periodicaly to avoid 
nasty surprises when your active nic stops working and you have to 
fallback to your (unchecked) slave one."
    echo "  exit 0 if all is OK (or if no bond is present)."
    echo "  -q: quiet (no verbose message for human operator)."
    echo "  -i: ip to use during check of inactive slaves."
    echo "  -t: target ip to ping during checks."
    echo "eg: $com"
    echo "  check all nics from all bonds."
    echo "eg: $com -q bond0"
    echo "  check silently all nics from bond0."
}

quiet=0
ip=""
target=""
while getopts "qi:t:" option
do
  case $option in
    q) quiet=1;;
    i) ip=$OPTARG;;
    t) target=$OPTARG;;
    *) usage; exit 1;;
  esac
done

# drop what has been parsed by getopts
shift `expr $OPTIND - 1`

# get args
if [ "$#" -ne 0 ]
then
  bonds="$@"
  for bond in $bonds; do
    if [ ! -f /proc/net/bonding/$bond ]; then
      echoe "Error: $bond is not a valid bond."
      exit 6
    fi
  done
else
  bonds=`ls /proc/net/bonding/ 2>/dev/null`
fi

#match a MAC address
re_mac="([a-zA-Z0-9][a-zA-Z0-9]:){5}[a-zA-Z0-9][a-zA-Z0-9]"
re_ip="(([0-9]{3}[.]){3}[0-9]{3}"

function echoe(){
  echo "$@" >/dev/stderr
}

function echoq(){
  if [ $quiet -eq 0 ] ; then echo "$@"; fi
}

# set a valid mac to a nic
# (must get a mac from the slaves in bond but one that is not currently 
in use by the bond)
get_free_mac_ret=""
function get_free_mac(){
  bond=$1
  nic=$2
  free_mac=""
  macs=`grep "Permanent HW addr:" /proc/net/bonding/$bond | egrep -o 
$re_mac| tr 'a-z' 'A-Z'`
  bond_mac=`ifconfig $bond | grep HWaddr | egrep -o $re_mac`
  for mac in $macs; do
    if [ "$mac" != "$bond_mac" ]; then
      free_mac=$mac
    fi
  done
  get_free_mac_ret=$free_mac
}

# ping a target using a specified nic to test for IP connectivity
check_nic_ret=0
function check_nic(){
   target=$1
   if [ $# -ge 2 ]; then
     nic=$2
     ping -n -c 3 -I $nic $target 1>/dev/null 2>/dev/null
   else
     ping -n -c 3 $target 1>/dev/null 2>/dev/null
   fi
   if [ $? -ne 0 ]; then
     ma=""
     if [ $# -ge 3 ]; then
       ma="(using $3 as ip)"
     fi 
     echoq "      [ERROR]"
     echo "$nic interface on $host is not working properly! $ma" > 
/dev/stderr
     check_nic_ret=1
   else
     echoq "      [OK]"
     check_nic_ret=0
   fi
}

# arping a target using a specified nic to test for IP connectivity
function exercise_nic_arp(){
   target=$1
   nic=$2
   src_ip=$3
   arping -c 3 -s "$src_ip" -I "$nic" "$target" 1>/dev/null 2>/dev/null
}

# reset a properly configured bond if someone interrupts the script
clean_bond=""
clean_nic=""
function clean(){
  echoq
  echoq "Script interrupted, restoring bond."
  if [ ! -z $clean_bond ] && [ ! -z $clean_nic ]; then
    ifenslave $clean_bond $clean_nic 2>/dev/null
  fi
  exit 2
}

host=`hostname -s`
table 0

if [ ! -d /proc/net/bonding ]; then
  echoe "Warning: Module bonding not loaded. Obviously no bond to check."
  #trying to check a bond on a server where none is present is probably 
not realy an error -> exit 0 with a warning message
  exit 0
fi


if [ -z $target ]; then
  # no target given as parameter -> auto-detect
  # get the default gateway as a ping target
  target=`route -n | grep UG | awk '{print $2}'`
  if [ -z $target ]; then
    echoe "Error: Unable to auto-detect the target to use during test 
(use -t?)."
    exit 3
  fi
fi


if [ -z "$ip" ]; then
  # no ip given as parameter -> auto-detect
  ip_b1=`host "${host}-bond-t1" | grep -o "$re_ip"`
  ip_b2=`host "${host}-bond-t2" | grep -o "$re_ip"`
  if [ -z "$ip_b1" ] && [ -z "$ip_b2" ]; then
    echoe "Error: Unable to auto-detect an ip to use during test (use -i?)."
    exit 4
  fi
fi

error_nb=0
for bond in $bonds
do
  bond=`basename $bond`
  echoq "checking bond $bond"
  active=`grep  "Active Slave" /proc/net/bonding/$bond |cut -d':' -f2`
  echoq -n "  active slave   :$active"
  check_nic $target
  error_nb=$(($error_nb + $check_nic_ret))
  slaves=`grep "Slave Interface:" /proc/net/bonding/$bond |cut -d':' -f2`
  slave_nb=0
  for slave in $slaves
  do
    if [ $slave != $active ]; then
      # this nic is enslaved but not active. we want to check if it is 
ready to work (no cable or VPN trouble that will bite us only when the 
active slave will change)
      echoq -n "  inactive slave : $slave"
      # search for a free mac in this bond (ie a real phy MAC that is 
not the one used by the bond)
      get_free_mac $bond $slave
      free_mac=$get_free_mac_ret
      # store the bond/nic we are going to un-enslave (to be able de 
re-enslave it in case of interrupt)
      clean_bond=$bond
      clean_nic=$slave
      if [ -z "$ip" ]; then
        ip="$ip_b1" # TODO: use a clever way to match slave and free ip
      fi
      # free this nic from the bond
      ifenslave -d $bond $slave
      # set it up with a "free" mac
      ifconfig $slave hw ether $free_mac
      # set it up with a temp IP
      ifconfig $slave $ip netmask 255.255.255.255
      # it seems we need a small temporisation here or the rest may fail
      sleep 2
      exercise_nic_arp $target $slave $ip
      check_nic $target $slave $ip
      error_nb=$(($error_nb + $check_nic_ret))
      # clean this temporary ip/route
      ifconfig $slave down
      # re-enslave this nic to the bond
      ifenslave $bond $slave
      clean_bond=""; clean_nic=""
      slave_nb=$(($slave_nb + 1))
    fi
  done
  echoq -n "  bond           : $bond"
  check_nic $target $bond
  error_nb=$(($error_nb + $check_nic_ret))
  if [ $slave_nb -eq 0 ]; then
    echoe "Error: No inactive slave in $bond."
    exit 5
  fi
done

if [ $error_nb -ne 0 ]; then
  exit $((10 + $error_nb))
fi
exit 0



---------------------------------------------------------------------------------------






_______________________________________________
LARTC mailing list
LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/cgi-bin/mailman/listinfo/lartc