This is my cluster.conf
-------------
<?xml version="1.0"?>
<cluster config_version="24" name="FON_DB_Cluster">
<fence_daemon post_fail_delay="0" post_join_delay="30"/>
<clusternodes>
<clusternode name="fonessql01" votes="1">
<fence>
<method name="1">
<device name="iLO-SQL01"/>
</method>
</fence>
</clusternode>
<clusternode name="fonessql02" votes="1">
<fence>
<method name="1">
<device name="iLO-SQL02"/>
</method>
</fence>
</clusternode>
<clusternode name="fonessql03" votes="1">
<fence>
<method name="1">
<device name="iLO-SQL03"/>
</method>
</fence>
</clusternode>
<clusternode name="fonessql04" votes="1">
<fence>
<method name="1">
<device name="iLO-SQL04"/>
</method>
</fence>
</clusternode>
</clusternodes>
<cman/>
<fencedevices>
<fencedevice agent="fence_ilo" hostname="fonessql01-ilo"
login="Administrator" name="iLO-SQL01" passwd="sadsa"/>
<fencedevice agent="fence_ilo" hostname="fonessql02-ilo"
login="Administrator" name="iLO-SQL02" passwd="asdad"/>
<fencedevice agent="fence_ilo" hostname="fonessql03-ilo"
login="Administrator" name="iLO-SQL03" passwd="adsas"/>
<fencedevice agent="fence_ilo" hostname="fonessql04-ilo"
login="Administrator" name="iLO-SQL04" passwd="adasd"/>
</fencedevices>
<rm>
<failoverdomains>
<failoverdomain name="Radius-Failover-domain"
ordered="1" restricted="1">
<failoverdomainnode name="fonessql01"
priority="1"/>
<failoverdomainnode name="fonessql02"
priority="2"/>
</failoverdomain>
<failoverdomain name="eShop-Failover-Domain"
ordered="1" restricted="1">
<failoverdomainnode name="fonessql02"
priority="1"/>
<failoverdomainnode name="fonessql01"
priority="2"/>
</failoverdomain>
<failoverdomain name="WebDB-Failover-Domain"
ordered="1" restricted="1">
<failoverdomainnode name="fonessql03"
priority="1"/>
<failoverdomainnode name="fonessql04"
priority="2"/>
</failoverdomain>
<failoverdomain name="Billing-Failover-Domain"
ordered="1" restricted="1">
<failoverdomainnode name="fonessql04"
priority="1"/>
<failoverdomainnode name="fonessql03"
priority="2"/>
</failoverdomain>
</failoverdomains>
<resources>
<fs device="/dev/sql01" force_fsck="0"
force_unmount="0" fsid="01" fstype="ext3" mountpoint="/mnt/sql01"
name="disco-sql01" options="
sync" self_fence="1"/>
<fs device="/dev/sql02" force_fsck="0"
force_unmount="0" fsid="02" fstype="ext3" mountpoint="/mnt/sql02"
name="disco-sql02" options="
sync" self_fence="1"/>
<fs device="/dev/sql03" force_fsck="0"
force_unmount="0" fsid="03" fstype="ext3" mountpoint="/mnt/sql03"
name="disco-sql03" options="
sync" self_fence="1"/>
<fs device="/dev/sql04" force_fsck="0"
force_unmount="0" fsid="04" fstype="ext3" mountpoint="/mnt/sql04"
name="disco-sql04" options="
sync" self_fence="1"/>
<ip address="172.17.0.168" monitor_link="1"/>
<ip address="172.17.0.169" monitor_link="1"/>
<ip address="172.17.0.170" monitor_link="1"/>
<ip address="172.17.0.171" monitor_link="1"/>
<script file="/etc/init.d/mysql01" name="mysql01"/>
<script file="/etc/init.d/mysql02" name="mysql02"/>
<script file="/etc/init.d/mysql03" name="mysql03"/>
<script file="/etc/init.d/mysql04" name="mysql04"/>
</resources>
<service autostart="1" domain="Radius-Failover-domain"
name="mysql01-Radius" recovery="restart">
<fs ref="disco-sql01"/>
<ip ref="172.17.0.168"/>
<script ref="mysql01"/>
</service>
<service autostart="1" domain="eShop-Failover-Domain"
name="mysql02-eShop-varios" recovery="restart">
<fs ref="disco-sql02"/>
<ip ref="172.17.0.169"/>
<script ref="mysql02"/>
</service>
<service autostart="1" domain="WebDB-Failover-Domain"
name="mysql03-WebDB" recovery="restart">
<fs ref="disco-sql03"/>
<ip ref="172.17.0.170"/>
<script ref="mysql03"/>
</service>
<service autostart="1" domain="Billing-Failover-Domain"
name="mysql04-Billing" recovery="restart">
<fs ref="disco-sql04"/>
<ip ref="172.17.0.171"/>
<script ref="mysql04"/>
</service>
</rm>
</cluster>
----------------
and my /etc/hosts
.........................
127.0.0.1 localhost
# Red de Backend
172.17.0.232 fonessql01.es.fon.srv fonessql01
172.17.0.233 fonessql02.es.fon.srv fonessql02
172.17.0.234 fonessql03.es.fon.srv fonessql03
172.17.0.235 fonessql04.es.fon.srv fonessql04
172.17.0.168 vipsql01.es.fon.srv vipsql01
172.17.0.169 vipsql02.es.fon.srv vipsql02
172.17.0.170 vipsql03.es.fon.srv vipsql03
172.17.0.171 vipsql04.es.fon.srv vipsql04
# Red de Almacenamiento VLAN 10 (stg)
172.17.4.232 fonessql01.es.fon.stg fonessql01-stg
172.17.4.233 fonessql02.es.fon.stg fonessql02-stg
172.17.4.234 fonessql03.es.fon.stg fonessql03-stg
172.17.4.235 fonessql04.es.fon.stg fonessql04-stg
172.17.4.244 fonesnas01.es.fon.stg fonesnas01-stg
172.17.4.245 fonesnas02.es.fon.stg fonesnas02-stg
----- Original Message -----
From: "Robert Peterson" <rpeterso@xxxxxxxxxx>
To: "linux clustering" <linux-cluster@xxxxxxxxxx>
Sent: Thursday, June 22, 2006 6:03 PM
Subject: Re: MySQL + RH Cluster Suite + GFS
Eloy Acosta Toscano wrote:
The problem is that when I power off one node ( I mean disable its power
supply totally ) to test it, the fencing does not work, on the log I get:
fenced: fencing node "nodename"
fenced: fence "nodename" failed
This will show forerer and the cluster will hang, until the other node
join the cluster again.
The problem is that, the fenced daemon waits (forever) until the iLO of
the dead node back to life.
So my cluster is node reboot/reset fault tolerant, but not totally power
off tolerant.
Do you know what I mean?
Can anybody helps me to workaround the problem?
thak U very much
Hi Eloy,
Sounds like maybe there's something wrong in your cluster.conf file.
Perhaps you can post it plus the names of the systems in your cluster
and what kind of fencing you have, and I'll see what I can do.
Regards,
Bob Peterson
Red Hat Cluster Suite
--
Linux-cluster@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/linux-cluster
--
Linux-cluster@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/linux-cluster
