Hi all!
Im trying to setup a new 2 nodes MySQL Cluster with DRBD, Corosync and
Pacemaker.
Everything is fine when corosync is started in both nodes, If I stop
corosync service on one node, resources are migrated as expected to the
other node inmediately.
But if I stop corosync on both nodes, and I start it again at the same time
on both nodes, it does not start the resources until 15 minutes. Same
problem if I only start corosync on one node.
Anybody knows how to solve it?
My configuration:
Centos 6 x86_64
drbd84-utils-8.4.0-2.el6.elrepo.x86_64
kmod-drbd84-8.4.0-2.el6.elrepo.x86_64
corosync-1.2.3-36.el6_1.3.x86_64
pacemaker-1.1.5-5.el6.x86_64
#cat /etc/drbd.conf
include "drbd.d/global_common.conf";
include "drbd.d/*.res";
resource drbd
{
on mysqlcluster1.xxxxxx {
device /dev/drbd1;
disk /dev/sda4;
address sdp 192.168.1.1:7788;
meta-disk internal;
}
on mysqlcluster2.xxxxxx {
device /dev/drbd1;
disk /dev/sda4;
address sdp 192.168.1.2:7788;
meta-disk internal;
}
}
# crm configure show
node mysqlcluster1.xxxxxxx
node mysqlcluster2.xxxxxxx
primitive drbd_mysql ocf:linbit:drbd \
params drbd_resource="drbd" \
op monitor interval="29s" role="Master" \
op monitor interval="31s" role="Slave"
primitive fs_mysql ocf:heartbeat:Filesystem \
params device="/dev/drbd1" directory="/drbd/" fstype="ext4"
primitive ip_mysql ocf:heartbeat:IPaddr2 \
params ip="192.168.0.20" nic="eth1" cidr_netmask="24"
primitive ip_publica ocf:heartbeat:IPaddr2 \
params ip="91.xxx.xxx.xxx" nic="eth0" cidr_netmask="23"
primitive mysqld lsb:mysqld
group mysql fs_mysql ip_mysql ip_publica mysqld
ms ms_drbd_mysql drbd_mysql \
meta master-max="1" master-node-max="1" clone-max="2"
clone-node-max="1" notify="true"
colocation mysql_on_drbd inf: mysql ms_drbd_mysql:Master
order mysql_after_drbd inf: ms_drbd_mysql:promote mysql:start
property $id="cib-bootstrap-options" \
dc-version="1.1.5-5.el6-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
no-quorum-policy="ignore" \
stonith-enabled="false" \
default-resource-stickiness="1000"
rsc_defaults $id="rsc-options" \
resource-stickiness="100"
# cat /etc/corosync/corosync.conf
compatibility: whitetank
totem {
version: 2
secauth: off
threads: 0
interface {
ringnumber: 0
bindnetaddr: 192.168.0.0
mcastaddr: 226.94.1.1
mcastport: 4000
ttl: 1
}
}
logging {
fileline: off
to_stderr: no
to_logfile: yes
to_syslog: yes
logfile: /var/log/cluster/corosync.log
debug: off
timestamp: on
logger_subsys {
subsys: AMF
debug: off
}
}
amf {
mode: disabled
}
aisexec {
user: root
group: root
}
service {
# Load the Pacemaker Cluster Resource Manager
name: pacemaker
ver: 0
}
Log extract:
Dec 21 10:04:39 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:fs_mysql:2:
probe
Dec 21 10:04:39 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:ip_mysql:3:
probe
Dec 21 10:04:39 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:ip_publica:4:
probe
Dec 21 10:04:39 mysqlcluster1.xxxxxx lrmd: [1563]: notice: lrmd_rsc_new():
No lrm_rprovider field in message
Dec 21 10:04:39 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:mysqld:5: probe
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:drbd_mysql:0:6:
probe
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:drbd_mysql:0:7:
start
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: RA output:
(drbd_mysql:0:start:stdout)
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: RA output:
(drbd_mysql:0:start:stdout)
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: RA output:
(drbd_mysql:0:start:stdout)
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: RA output:
(drbd_mysql:0:start:stdout)
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: RA output:
(drbd_mysql:0:start:stdout)
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: RA output:
(drbd_mysql:0:start:stdout)
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:drbd_mysql:0:8:
notify
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: RA output:
(drbd_mysql:0:notify:stdout)
Dec 21 10:04:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: rsc:drbd_mysql:0:9:
monitor
Dec 21 10:19:40 mysqlcluster1.xxxxxx lrmd: [1563]: info: cancel_op:
operation monitor[9] on ocf::drbd::drbd_mysql:0 for client 1566, its
parameters: CRM_meta_clone=[0] CRM_meta_role=[Slave]
CRM_meta_notify_slave_resource=[ ] CRM_met$
Dec 21 10:19:40 mysqlcluster1.xxxxxx lrmd: [1563]: info:
rsc:drbd_mysql:0:10: notify
Dec 21 10:19:40 mysqlcluster1.xxxxxx lrmd: [1563]: info:
rsc:drbd_mysql:0:11: promote
You can see the 15 min delay in the log timestamp.
Any help would be appreciated
Regards,
Javi
_______________________________________________
Linux-HA mailing list
[email protected]
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
