Heartbeat 与DRBD 配置过程

164次阅读

没有评论

共计 3682 个字符，预计需要花费 10 分钟才能阅读完成。

我的 PC 机都只有 1 个网卡，所以我用串口使双机通讯；

192.168.119.1 是我的路由器的 IP，作为一个域外的服务器，检测域内服务器是否正常；

首先配置 host 文件：

127.0.0.1 localhost
127.0.1.1 Ubuntu-Bing

192.168.119.102 ubuntu-Bing
192.168.119.103 Lab-Server

拷贝配置文件：

cp /usr/local/ha/share/doc/authkeys /usr/local/ha/etc/ha.d
cp /usr/local/ha/share/doc/ha.cf /usr/local/ha/etc/ha.d
cp /usr/local/ha/share/doc/haresources /usr/local/ha/etc/ha.d

ha.d 文件：

debugfile /var/log/ha-debug
logfile /var/log/ha-log
logfacility local0
keepalive 2
deadtime 30
warntime 10
initdead 120
baud 19200
serial /dev/ttyS0 # Linux
auto_failback on
node ubuntu-Bing
node Lab-Server
ping 192.168.119.1
respawn hacluster /usr/lib/ocf/resource.d/heartbeat/pingd -m 100 -d 5s
apiauth pingd gid=haclient uid=hacluster

compression bz2
compression_threshold 2

resource.d 目录下 drbddisk 脚本

#!/bin/bash
#
# This script is intended to be used as resource script by heartbeat
#
# Copright 2003-2008 LINBIT Information Technologies
# Philipp Reisner, Lars Ellenberg
#
###

DEFAULTFILE=”/etc/default/drbd”
DRBDADM=”/sbin/drbdadm”

if [-f $DEFAULTFILE]; then
. $DEFAULTFILE
fi

if [“$#” -eq 2]; then
RES=”$1″
CMD=”$2″
else
RES=”all”
CMD=”$1″
fi

## EXIT CODES
# since this is a “legacy heartbeat R1 resource agent” script,
# exit codes actually do not matter that much as long as we conform to
# http://wiki.linux-ha.org/HeartbeatResourceAgent
# but it does not hurt to conform to lsb init-script exit codes,
# where we can.
# http://refspecs.linux-foundation.org/LSB_3.1.0/
#LSB-Core-generic/LSB-Core-generic/iniscrptact.html
####

drbd_set_role_from_proc_drbd()
{
local out
if ! test -e /proc/drbd; then
ROLE=”Unconfigured”
return
fi

dev=$($DRBDADM sh-dev $RES)
minor=${dev#/dev/drbd}
if [[$minor = *[!0-9]* ]] ; then
# sh-minor is only supported since drbd 8.3.1
minor=$($DRBDADM sh-minor $RES)
fi
if [[-z $minor]] || [[$minor = *[!0-9]* ]] ; then
ROLE=Unknown
return
fi

if out=$(sed -ne “/^ *$minor: cs:/ { s/:/ /g; p; q;}” /proc/drbd); then
set — $out
ROLE=${5%/**}
: ${ROLE:=Unconfigured} # if it does not show up
else
ROLE=Unknown
fi
}

case “$CMD” in
start)
# try several times, in case heartbeat deadtime
# was smaller than drbd ping time
try=6
while true; do
$DRBDADM primary $RES && break
let “–try” || exit 1 # LSB generic error
sleep 1
done
;;
stop)
# heartbeat (haresources mode) will retry failed stop
# for a number of times in addition to this internal retry.
try=3
while true; do
$DRBDADM secondary $RES && break
# We used to lie here, and pretend success for anything != 11,
# to avoid the reboot on failed stop recovery for “simple
# config errors” and such. But that is incorrect.
# Don’t lie to your cluster manager.
# And don’t do config errors…
let –try || exit 1 # LSB generic error
sleep 1
done
;;
status)
if [“$RES” = “all”]; then
echo “A resource name is required for status inquiries.”
exit 10
fi
ST=$($DRBDADM role $RES)
ROLE=${ST%/**}
case $ROLE in
Primary|Secondary|Unconfigured)
# expected
;;
*)
# unexpected. whatever…
# If we are unsure about the state of a resource, we need to
# report it as possibly running, so heartbeat can, after failed
# stop, do a recovery by reboot.
# drbdsetup may fail for obscure reasons, e.g. if /var/lock/ is
# suddenly readonly. So we retry by parsing /proc/drbd.
drbd_set_role_from_proc_drbd
esac
case $ROLE in
Primary)
echo “running (Primary)”
exit 0 # LSB status “service is OK”
;;
Secondary|Unconfigured)
echo “stopped ($ROLE)”
exit 3 # LSB status “service is not running”
;;
*)
# NOTE the “running” in below message.
# this is a “heartbeat” resource script,
# the exit code is _ignored_.
echo “cannot determine status, may be running ($ROLE)”
exit 4 # LSB status “service status is unknown”
;;
esac
;;
*)
echo “Usage: drbddisk [resource] {start|stop|status}”
exit 1
;;
esac