Hi all,
I have problems with my cluster in heartbeat 2 (the cib.xml is attached to
this message), some times, the monitor of the resources "apache" and
"mysql" fail and the command "crm_mon" shows:
***************************************************
============
Last updated: Tue Jan 26 17:25:47 2010
Current DC: nodo2.example.com
2 Nodes configured.
3 Resources configured.
============
Node: nodo2.example.com : online
Node: nodo1.example.com : online
webip (ocf::heartbeat:IPaddr): Started nodo1.example.com
Master/Slave Set: ms_drbd
drbd0:0 (ocf::heartbeat:drbd):Master nodo1.example.com FAILED
drbd0:1 (ocf::heartbeat:drbd):Slave nodo2.example.com
Resource Group: group_fs
FS_replica (ocf::heartbeat:Filesystem): Started nodo1.example.com
mysql (ocf::heartbeat:mysql): Started nodo1.example.com (unmanaged)
FAILED
apache (ocf::heartbeat:apache): Started nodo1.example.com
(unmanaged) FAILED
Failed actions:
apache_monitor_59000 (node=nodo1.example.com, call=167, rc=-2):
TimedOut
apache_stop_0 (node=nodo1.example.com, call=170, rc=-2): Timed Out
mysql_monitor_59000 (node=nodo1.example.com, call=187, rc=-2): TimedOut
mysql_stop_0 (node=nodo1.example.com, call=190, rc=-2): Timed Out
***************************************************
I need to know how to fix this or, in any case, can I force an automatic
resources migration to another node when it fails.
Thanks a lot.
Carlos Chiriboga Calderon<cib admin_epoch="38" num_updates="38" epoch="38">
<configuration>
<crm_config />
<nodes />
<resources>
<primitive id="webip" class="ocf" type="IPaddr"
provider="heartbeat">
<instance_attributes id="attr_webip1">
<attributes>
<nvpair id="id_ipaddr"
name="ip" value="65.196.156.166"/>
<nvpair id="id_netmask"
name="netmask" value="255.255.255.192"/>
<nvpair id="id_device"
name="nic" value="eth0"/>
<nvpair id="id_start"
name="local_start_script" value="/replica/bin/ifup.sh"/>
<nvpair id="id_stop"
name="local_stop_script" value="/replica/bin/ifdown.sh"/>
</attributes>
</instance_attributes>
</primitive>
<master_slave id="ms_drbd">
<meta_attributes
id="ms_drbd_mysql-meta_attributes">
<attributes>
<nvpair id="ms_drbd_notify"
name="notify" value="yes"/>
<nvpair id="ms_drbd_globa"
name="globally_unique" value="false"/>
<nvpair id="ms_drbd_master_max"
name="master_max" value="1"/>
</attributes>
</meta_attributes>
<primitive id="drbd0" class="ocf"
provider="heartbeat" type="drbd">
<instance_attributes id="ia-r0">
<attributes>
<nvpair id="resource"
name="drbd_resource" value="r0"/>
</attributes>
</instance_attributes>
<operations>
<op id="op-r0-1" name="monitor"
interval="59s" timeout="30s" role="Master"/>
<op id="op-r0-2" name="monitor"
interval="60s" timeout="30s" role="Slave"/>
</operations>
</primitive>
</master_slave>
<group id="group_fs">
<primitive id="FS_replica" class="ocf"
type="Filesystem" provider="heartbeat">
<instance_attributes id="attr_Fs">
<attributes>
<nvpair id="device"
name="device" value="/dev/drbd1"/>
<nvpair id="replica"
name="directory" value="/replica"/>
<nvpair id="fs_type1"
name="fstype" value="ext3"/>
</attributes>
</instance_attributes>
<operations>
<op id="fs_mon" name="monitor"
interval="30s"/>
</operations>
</primitive>
</group>
<primitive id="mysql" class="ocf" type="mysql"
provider="heartbeat">
<instance_attributes id="attr_mysql">
<attributes>
<nvpair id="binary"
name="binary" value="/usr/bin/mysqld_safe"/>
<nvpair id="config"
name="config" value="/replica/etc/my.cnf"/>
<nvpair id="datadir"
name="datadir" value="/replica/var/lib/mysql"/>
<nvpair id="log"
name="log" value="/replica/var/log/mysql.log"/>
<nvpair id="pid"
name="pid" value="/replica/var/lib/mysql/mysql.pid"/>
<nvpair id="socket"
name="socket" value="/replica/var/lib/mysql/mysql.sock"/>
<nvpair id="my_max_con"
name="additional_parameters" value="--max_connections=1000"/>
</attributes>
</instance_attributes>
<operations>
<op id="my_mon" name="monitor"
interval="30s" timeout="59s" on_fail="restart"/>
<op id="my_start" name="start"
timeout="59s" on_fail="restart"/>
<op id="my_stop" name="stop"
timeout="59s" on_fail="restart"/>
</operations>
</primitive>
<primitive id="apache" class="ocf" type="apache"
provider="heartbeat">
<instance_attributes id="attr_apache">
<attributes>
<nvpair id="configfile"
name="configfile" value="/replica/etc/httpd/conf/httpd.conf"/>
<nvpair id="httpd"
name="httpd" value="/usr/sbin/httpd"/>
<nvpair id="statusurl"
name="statusurl"
value="http://127.0.0.1/server-status/index.html"/>
</attributes>
</instance_attributes>
<operations>
<op id="http_mon" name="monitor"
interval="30s" on_fail="restart"/>
<op id="http_start" name="start"
timeout="59s" on_fail="restart"/>
<op id="http_stop" name="stop"
timeout="59s" on_fail="restart"/>
</operations>
</primitive>
</resources>
<constraints>
<rsc_colocation id="loc_ip_groupfs"
from="webip" to="group_fs" score="INFINITY"/>
<rsc_colocation id="loc_mysql_groupfs"
from="mysql" to="webip" score="INFINITY"/>
<rsc_colocation id="loc_apache_groupfs"
from="apache" to="webip" score="INFINITY"/>
<rsc_colocation id="loc_grpFS_r0"
from="group_fs" to="ms_drbd" to_role="Master" score="INFINITY"/>
<rsc_order id="order_r0_webip" from="ms_drbd"
action="start" type="before" to="group_fs"/>
<rsc_order id="order_webip_r0" from="group_fs"
action="start" type="after" to="ms_drbd" to_action="promote"/>
<rsc_order id="order_grpFS_r0" from="webip"
action="start" type="after" to="group_fs"/>
<rsc_order id="order_mysql_grpFS" from="mysql"
action="start" type="after" to="webip"/>
<rsc_order id="order_apache_mysql" from="apache"
action="start" type="after" to="webip"/>
</constraints>
</configuration>
<status />
</cib>
_______________________________________________
Linux-HA mailing list
[email protected]
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
