[DRBD-user] drbd 8.4.1

Billy Harvey billy.harvey at gmail.com
Fri Jan 20 15:42:29 CET 2012

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.


On Fri, Jan 20, 2012 at 03:09, Rasto Levrinc <rasto.levrinc at gmail.com>wrote:

> On Thu, Jan 19, 2012 at 10:22 PM, Billy Harvey <billy.harvey at gmail.com>
> wrote:
> > Is anyone having success using DRBD 8.4.1 on CentOS 6.2, along with
> > Pacemaker 1.1.6 and Corosync 1.4.1?
> >
> > When I force a failover by putting one node into standby, the other node
> > never brings the DRBD up on its own.
>
> Looks like a common pacemaker misconfiguration. Only if there was a GUI for
> that. :) Anyway you should post your config.
>
> Rasto
>
> > I can bring it up manually by starting the DRBD service, forcing primary,
> > and then get the remainder of my HA configuration with a crm resource
> > cleanup r0 (my resource).
> >
> > Regards,
> > Billy
>

I build the configs during a first-boot process - relevant sections below.
 I was originally trying to use the volume groups that came with DRBD
8.4.0, but after reading of some problems that was having in 8.4.0 (but not
8.4.1 from what I could read here), I commented out that section and tried
using a single drbd device - but still have the described problem.  Here's
the drbd section, and below is the cib.xml.  I'm using stock Centos 6.2
with any updates the base/updates/plus/extras/contrib sections offer, along
with
drbd84-utils-8.4.1-1.el6.elrepo.x86_64.rpm
and kmod-drbd84-8.4.1-1.el6.elrepo.x86_64.rpm.  I create the /dev/csp
logical volumes previous to their use below.

Billy

(
cat << "EOF"
global {
  usage-count  no;
}
common {
  disk {
    fencing      resource-and-stonith;
    on-io-error  detach;
  }
  handlers {
    outdate-peer  "/sbin/kill-other-node.sh";
  }
  net {
    protocol             C;
    after-sb-0pri        discard-zero-changes;
    after-sb-1pri        discard-secondary;
    after-sb-2pri        disconnect;
  }
  startup {
    wfc-timeout           10;
    degr-wfc-timeout      10;
    outdated-wfc-timeout  10;
  }
  syncer {
    rate 1G;
    on-no-data-accessible io-error;
  }
}
EOF
) > /etc/drbd.d/global_common.conf

(
cat << "EOF"
resource r0 {
#  volume 0 {
#    device     /dev/drbd0;
#    disk       /dev/csp/mnt-centos;
#    meta-disk  internal;
#  }
#  volume 1 {
#    device     /dev/drbd1;
#    disk       /dev/csp/mnt-shared;
#    meta-disk  internal;
#  }
#  volume 2 {
#    device     /dev/drbd2;
#    disk       /dev/csp/var-lib-libvirt;
#    meta-disk  internal;
#  }
#  volume 3 {
#    device     /dev/drbd3;
#    disk       /dev/csp/var-www;
#    meta-disk  internal;
#  }
  device     /dev/drbd0;
  disk       /dev/csp/data;
  meta-disk  internal;
  on csp0 {
    address  192.168.11.108:7788;
  }
  on csp1 {
    address  192.168.11.109:7788;
  }
}
EOF
) > /etc/drbd.d/r0.res

(
cat << EOF
compatibility: whitetank

totem {
  version: 2
  secauth: off
  interface {
    member {
      memberaddr: 192.168.11.108
    }
    member {
      memberaddr: 192.168.11.109
    }
    ringnumber: 0
    bindnetaddr: 192.168.11.0
    mcastport: 5678
    ttl: 1
  }
  transport: udpu
}

logging {
  fileline: off
  to_syslog: yes
  debug: on
  timestamp: on
  logger_subsys {
    subsys: AMF
    debug: on
  }
}
EOF
) > /etc/corosync/corosync.conf

(
cat << EOF
service {
  name: pacemaker
  ver:  0
}
EOF
) > /etc/corosync/service.d/pacemaker

(
cat << EOF
<cib admin_epoch="0" crm_feature_set="3.0.5" epoch="1" have-quorum="1"
num_updates="1" validate-with="pacemaker-1.1" dc-uuid="csp0">
  <configuration>
    <crm_config>
      <cluster_property_set id="cib-bootstrap-options">
        <nvpair id="cib-bootstrap-options-no-quorum-policy"
name="no-quorum-policy" value="ignore"/>
        <nvpair id="cib-bootstrap-options-stonith-enabled"
name="stonith-enabled" value="false"/>
        <nvpair id="cib-bootstrap-options-dc-version" name="dc-version"
value="1.1.6-3.el6-a02c0f19a00c1eb2527ad38f146ebc0834814558"/>
        <nvpair id="cib-bootstrap-options-cluster-infrastructure"
name="cluster-infrastructure" value="openais"/>
        <nvpair id="cib-bootstrap-options-expected-quorum-votes"
name="expected-quorum-votes" value="2"/>
        <nvpair id="cib-bootstrap-options-last-lrm-refresh"
name="last-lrm-refresh" value="1326216570"/>
      </cluster_property_set>
    </crm_config>
    <nodes>
      <node id="csp0" type="normal" uname="csp0"/>
      <node id="csp1" type="normal" uname="csp1"/>
    </nodes>
    <resources>
      <master id="ms_0">
        <meta_attributes id="ms_0-meta_attributes">
          <nvpair id="ms_0-meta_attributes-master-max" name="master-max"
value="1"/>
          <nvpair id="ms_0-meta_attributes-master-node-max"
name="master-node-max" value="1"/>
          <nvpair id="ms_0-meta_attributes-clone-max" name="clone-max"
value="2"/>
          <nvpair id="ms_0-meta_attributes-clone-node-max"
name="clone-node-max" value="1"/>
          <nvpair id="ms_0-meta_attributes-notify" name="notify"
value="true"/>
        </meta_attributes>
        <primitive class="ocf" id="ss_drbd" provider="linbit" type="drbd">
          <instance_attributes id="ss_drbd-instance_attributes">
            <nvpair id="ss_drbd-instance_attributes-drbd_resource"
name="drbd_resource" value="r0"/>
          </instance_attributes>
        </primitive>
      </master>
      <primitive class="ocf" id="fs_data" provider="heartbeat"
type="Filesystem">
        <instance_attributes id="fs_data-instance_attributes">
          <nvpair id="fs_data-instance_attributes-device" name="device"
value="/dev/drbd0"/>
          <nvpair id="fs_data-instance_attributes-directory"
name="directory" value="/data"/>
          <nvpair id="fs_data-instance_attributes-fstype" name="fstype"
value="ext4"/>
        </instance_attributes>
      </primitive>
      <primitive class="ocf" id="ap_apache" provider="heartbeat"
type="apache">
        <instance_attributes id="ap_apache-instance_attributes">
          <nvpair id="ap_apache-instance_attributes-configfile"
name="configfile" value="/etc/httpd/conf/httpd.conf"/>
        </instance_attributes>
      </primitive>
      <primitive class="ocf" id="ip_101" provider="heartbeat" type="IPaddr">
        <instance_attributes id="ip_101-instance_attributes">
          <nvpair id="ip_101-instance_attributes-ip" name="ip"
value="192.168.101.101"/>
        </instance_attributes>
      </primitive>
    </resources>
    <constraints>
      <rsc_colocation  id="col-ap_apache"       rsc="ap_apache"
score="INFINITY"  with-rsc="fs_data"/>
      <rsc_colocation  id="col-fs_data"         rsc="fs_data"
score="INFINITY"  with-rsc="ms_0"       with-rsc-role="Master"/>
      <rsc_colocation  id="col-ip_101-ss_drbd"  rsc="ip_101"
 score="INFINITY"  with-rsc="ms_0"       with-rsc-role="Master"/>
      <rsc_order       first="fs_data"          id="ord-ap_apache"
 score="INFINITY"  then="ap_apache"/>
      <rsc_order       first="ms_0"             first-action="promote"
 id="ord-fs_data"  score="INFINITY"      then="fs_data"
 then-action="start"/>
    </constraints>
    <rsc_defaults>
      <meta_attributes id="rsc-options">
        <nvpair id="rsc-options-resource-stickiness"
name="resource-stickiness" value="100"/>
      </meta_attributes>
    </rsc_defaults>
  </configuration>
</cib>
EOF
) > /var/lib/heartbeat/crm/cib.xml
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.linbit.com/pipermail/drbd-user/attachments/20120120/68d54944/attachment.htm>


More information about the drbd-user mailing list