Login | Register For Free | Help
Search for: (Advanced)

Mailing List Archive: Linux-HA: Users

DRBD+Hearbeat not working as intended

 

 

Linux-HA users RSS feed   Index | Next | Previous | View Threaded


carlosalexandre at blumar

Mar 12, 2008, 1:29 PM

Post #1 of 3 (400 views)
Permalink
DRBD+Hearbeat not working as intended

Greetings,



I have a drbd+heartbeat setup and I am having a problem.



If the machine which drbd is master shuts down the passive machine does
not change its status to active one and because of that it cant mount
the drbd file system.



Can anyone give me some feedback in this ??





here is my cib.xml



<cib admin_epoch="0" have_quorum="true" ignore_dtd="false" num_peers="2"
cib_feature_revision="2.0" epoch="83" generated="true"
ccm_transition="4" dc_uuid="56ec2257-b0e1-4395-8ca2-ff2f96151b55"
num_updates="1" cib-last-written="Fri Feb 29 08:00:29 2008">

<configuration>

<crm_config>

<cluster_property_set id="cib-bootstrap-options">

<attributes>

<nvpair id="cib-bootstrap-options-dc-version"
name="dc-version" value="2.1.3-node:
552305612591183b1628baa5bc6e903e0f1e26a3"/>

<nvpair id="cib-bootstrap-options-last-lrm-refresh"
name="last-lrm-refresh" value="1204282824"/>

</attributes>

</cluster_property_set>

</crm_config>

<nodes>

<node id="34a67e55-71b1-421f-96cc-519ef05b110b"
uname="pgslave.blumar.com.br" type="normal">

<instance_attributes
id="nodes-34a67e55-71b1-421f-96cc-519ef05b110b">

<attributes>

<nvpair id="standby-34a67e55-71b1-421f-96cc-519ef05b110b"
name="standby" value="off"/>

</attributes>

</instance_attributes>

</node>

<node id="56ec2257-b0e1-4395-8ca2-ff2f96151b55"
uname="pgmaster.blumar.com.br" type="normal"/>

</nodes>

<resources>

<master_slave id="ms-drbd0">

<meta_attributes id="ma-ms-drbd0">

<attributes>

<nvpair id="ma-ms-drbd0-1" name="clone_max" value="2"/>

<nvpair id="ma-ms-drbd0-2" name="clone_node_max"
value="1"/>

<nvpair id="ma-ms-drbd0-3" name="master_max" value="1"/>

<nvpair id="ma-ms-drbd0-4" name="master_node_max"
value="1"/>

<nvpair id="ma-ms-drbd0-5" name="notify" value="yes"/>

<nvpair id="ma-ms-drbd0-6" name="globally_unique"
value="false"/>

<nvpair id="ma-ms-drbd0-7" name="target_role"
value="started"/>

</attributes>

</meta_attributes>

<primitive id="drbd0" class="ocf" provider="heartbeat"
type="drbd">

<instance_attributes id="ia-drbd0">

<attributes>

<nvpair id="ia-drbd0-1" name="drbd_resource"
value="repdata"/>

</attributes>

</instance_attributes>

<meta_attributes id="drbd0:0_meta_attrs">

<attributes/>

</meta_attributes>

</primitive>

</master_slave>

<group id="group_pgsql">

<meta_attributes id="group_pgsql_meta_attrs">

<attributes>

<nvpair id="group_pgsql_metaattr_target_role"
name="target_role" value="stopped"/>

</attributes>

</meta_attributes>

<primitive id="resource_ip" class="ocf" type="IPaddr"
provider="heartbeat">

<instance_attributes id="resource_ip_instance_attrs">

<attributes>

<nvpair id="f294ba51-00f9-4a9b-80c0-43aa7944f474"
name="ip" value="10.3.3.24"/>

</attributes>

</instance_attributes>

<meta_attributes id="resource_ip_meta_attrs">

<attributes>

<nvpair id="resource_ip_metaattr_target_role"
name="target_role" value="started"/>

</attributes>

</meta_attributes>

</primitive>

<primitive id="resource_FS" class="ocf" type="Filesystem"
provider="heartbeat">

<instance_attributes id="resource_FS_instance_attrs">

<attributes>

<nvpair id="d1413b97-4944-4fee-9cba-b4ab3e71f83f"
name="device" value="/dev/drbd0"/>

<nvpair id="baad1fbb-3389-4778-8832-91d5720341a6"
name="directory" value="/repdata"/>

<nvpair id="35e6e951-ace4-4bbf-9d3e-5824219a9809"
name="fstype" value="ext3"/>

</attributes>

</instance_attributes>

<meta_attributes id="resource_FS_meta_attrs">

<attributes>

<nvpair id="resource_FS_metaattr_target_role"
name="target_role" value="started"/>

</attributes>

</meta_attributes>

</primitive>

<primitive id="resource_pgsql" class="ocf" type="pgsql"
provider="heartbeat">

<meta_attributes id="resource_pgsql_meta_attrs">

<attributes>

<nvpair id="resource_pgsql_metaattr_target_role"
name="target_role" value="started"/>

</attributes>

</meta_attributes>

</primitive>

</group>

</resources>

<constraints>

<rsc_colocation id="colocation_" from="group_pgsql"
to="group_pgsql" score="INFINITY"/>

<rsc_location id="location_" rsc="group_pgsql">

<rule id="prefered_location_" score="INFINITY">

<expression attribute="#uname"
id="a7b8a885-27c2-4157-a597-42dd6cafba8c" operation="eq"
value="pgmaster.blumar.com.br"/>

</rule>

</rsc_location>

</constraints>

</configuration>

</cib>



Carlos Alexandre
Analista de Suporte

Direct Phone: + 55 21 2142-9383
www.blumar.com.br <http://www.blumar.com.br>













Av. Borges de Medeiros, 633 - Sala 405 a 408 - Leblon - Rio de janeiro -
Brasil - 22430-041
www.blumar.com.br <http://www.blumar.com.br> phone: +55 21 2142 9300
fax: +55 21 2511 3739
Attachments: image001.gif (3.78 KB)
  image002.gif (2.74 KB)
  image003.gif (6.70 KB)
  image004.gif (0.50 KB)


dk at in-telegence

Mar 13, 2008, 1:45 AM

Post #2 of 3 (370 views)
Permalink
Re: DRBD+Hearbeat not working as intended [In reply to]

Hi

> I have a drbd+heartbeat setup and I am having a problem.
>
>
>
> If the machine which drbd is master shuts down the passive machine does
> not change its status to active one and because of that it cant mount
> the drbd file system.
>
>
>
> Can anyone give me some feedback in this ??
>
>
>
>
>
> here is my cib.xml
>
>
>
> <cib admin_epoch="0" have_quorum="true" ignore_dtd="false" num_peers="2"
> cib_feature_revision="2.0" epoch="83" generated="true"
> ccm_transition="4" dc_uuid="56ec2257-b0e1-4395-8ca2-ff2f96151b55"
> num_updates="1" cib-last-written="Fri Feb 29 08:00:29 2008">
>
> <configuration>
>
> <crm_config>
>
> <cluster_property_set id="cib-bootstrap-options">
>
> <attributes>
>
> <nvpair id="cib-bootstrap-options-dc-version"
> name="dc-version" value="2.1.3-node:
> 552305612591183b1628baa5bc6e903e0f1e26a3"/>
>
> <nvpair id="cib-bootstrap-options-last-lrm-refresh"
> name="last-lrm-refresh" value="1204282824"/>
>
> </attributes>
>
> </cluster_property_set>
>
> </crm_config>
>
> <nodes>
>
> <node id="34a67e55-71b1-421f-96cc-519ef05b110b"
> uname="pgslave.blumar.com.br" type="normal">
>
> <instance_attributes
> id="nodes-34a67e55-71b1-421f-96cc-519ef05b110b">
>
> <attributes>
>
> <nvpair id="standby-34a67e55-71b1-421f-96cc-519ef05b110b"
> name="standby" value="off"/>
>
> </attributes>
>
> </instance_attributes>
>
> </node>
>
> <node id="56ec2257-b0e1-4395-8ca2-ff2f96151b55"
> uname="pgmaster.blumar.com.br" type="normal"/>
>
> </nodes>
>
> <resources>
>
> <master_slave id="ms-drbd0">
>
> <meta_attributes id="ma-ms-drbd0">
>
> <attributes>
>
> <nvpair id="ma-ms-drbd0-1" name="clone_max" value="2"/>
>
> <nvpair id="ma-ms-drbd0-2" name="clone_node_max"
> value="1"/>
>
> <nvpair id="ma-ms-drbd0-3" name="master_max" value="1"/>
>
> <nvpair id="ma-ms-drbd0-4" name="master_node_max"
> value="1"/>
>
> <nvpair id="ma-ms-drbd0-5" name="notify" value="yes"/>
>
> <nvpair id="ma-ms-drbd0-6" name="globally_unique"
> value="false"/>
>
> <nvpair id="ma-ms-drbd0-7" name="target_role"
> value="started"/>
>
> </attributes>
>
> </meta_attributes>
>
> <primitive id="drbd0" class="ocf" provider="heartbeat"
> type="drbd">
>
> <instance_attributes id="ia-drbd0">
>
> <attributes>
>
> <nvpair id="ia-drbd0-1" name="drbd_resource"
> value="repdata"/>
>
> </attributes>
>
> </instance_attributes>
>
> <meta_attributes id="drbd0:0_meta_attrs">
>
> <attributes/>
>
> </meta_attributes>
>
> </primitive>
>
> </master_slave>
>
> <group id="group_pgsql">
>
> <meta_attributes id="group_pgsql_meta_attrs">
>
> <attributes>
>
> <nvpair id="group_pgsql_metaattr_target_role"
> name="target_role" value="stopped"/>

Why stopped here?

> </attributes>
>
> </meta_attributes>
>
> <primitive id="resource_ip" class="ocf" type="IPaddr"
> provider="heartbeat">
>
> <instance_attributes id="resource_ip_instance_attrs">
>
> <attributes>
>
> <nvpair id="f294ba51-00f9-4a9b-80c0-43aa7944f474"
> name="ip" value="10.3.3.24"/>
>
> </attributes>
>
> </instance_attributes>
>
> <meta_attributes id="resource_ip_meta_attrs">
>
> <attributes>
>
> <nvpair id="resource_ip_metaattr_target_role"
> name="target_role" value="started"/>

But started here?

> </attributes>
>
> </meta_attributes>
>
> </primitive>
>
> <primitive id="resource_FS" class="ocf" type="Filesystem"
> provider="heartbeat">
>
> <instance_attributes id="resource_FS_instance_attrs">
>
> <attributes>
>
> <nvpair id="d1413b97-4944-4fee-9cba-b4ab3e71f83f"
> name="device" value="/dev/drbd0"/>
>
> <nvpair id="baad1fbb-3389-4778-8832-91d5720341a6"
> name="directory" value="/repdata"/>
>
> <nvpair id="35e6e951-ace4-4bbf-9d3e-5824219a9809"
> name="fstype" value="ext3"/>
>
> </attributes>
>
> </instance_attributes>
>
> <meta_attributes id="resource_FS_meta_attrs">
>
> <attributes>
>
> <nvpair id="resource_FS_metaattr_target_role"
> name="target_role" value="started"/>

And started here?

> </attributes>
>
> </meta_attributes>
>
> </primitive>
>
> <primitive id="resource_pgsql" class="ocf" type="pgsql"
> provider="heartbeat">
>
> <meta_attributes id="resource_pgsql_meta_attrs">
>
> <attributes>
>
> <nvpair id="resource_pgsql_metaattr_target_role"
> name="target_role" value="started"/>

And started here as well. That does not make sense. It is sufficient to
set the target_role for the group. You do not have to set it for each
resource.

> </attributes>
>
> </meta_attributes>
>
> </primitive>
>
> </group>
>
> </resources>
>
> <constraints>
>
> <rsc_colocation id="colocation_" from="group_pgsql"
> to="group_pgsql" score="INFINITY"/>

This does not make any sense.

> <rsc_location id="location_" rsc="group_pgsql">
>
> <rule id="prefered_location_" score="INFINITY">
>
> <expression attribute="#uname"
> id="a7b8a885-27c2-4157-a597-42dd6cafba8c" operation="eq"
> value="pgmaster.blumar.com.br"/>
>
> </rule>
>
> </rsc_location>


Please read http://www.linux-ha.org/DRBD/HowTov2 and adjust your
constraints.

> </constraints>
>
> </configuration>
>
> </cib>

Regards
Dominik
_______________________________________________
Linux-HA mailing list
Linux-HA [at] lists
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems


florian.schmidt at altroconsult

Mar 13, 2008, 2:23 AM

Post #3 of 3 (368 views)
Permalink
AW: DRBD+Hearbeat not working as intended [In reply to]

Hi,

could you post the logifles from the moment of the switchover?

Does DRBD alone work?
Start DRBD without Heartbeat and try to make nodes primary and secondary
and try to mount the filesystems on it, so you can see if the error is
in DRBD or in Heartbeat.

btw: What a strange constraint is this:

<rsc_colocation id="colocation_" from="group_pgsql" to="group_pgsql"
score="INFINITY"/>

Regards
Florian



> Greetings,
>
>
>
> I have a drbd+heartbeat setup and I am having a problem.
>
>
>
> If the machine which drbd is master shuts down the passive machine
does
> not change its status to active one and because of that it cant mount
> the drbd file system.
>
>
>
> Can anyone give me some feedback in this ??
>
>
>
>
>
> here is my cib.xml
>
>
>
> <cib admin_epoch="0" have_quorum="true" ignore_dtd="false"
num_peers="2"
> cib_feature_revision="2.0" epoch="83" generated="true"
> ccm_transition="4" dc_uuid="56ec2257-b0e1-4395-8ca2-ff2f96151b55"
> num_updates="1" cib-last-written="Fri Feb 29 08:00:29 2008">
>
> <configuration>
>
> <crm_config>
>
> <cluster_property_set id="cib-bootstrap-options">
>
> <attributes>
>
> <nvpair id="cib-bootstrap-options-dc-version"
> name="dc-version" value="2.1.3-node:
> 552305612591183b1628baa5bc6e903e0f1e26a3"/>
>
> <nvpair id="cib-bootstrap-options-last-lrm-refresh"
> name="last-lrm-refresh" value="1204282824"/>
>
> </attributes>
>
> </cluster_property_set>
>
> </crm_config>
>
> <nodes>
>
> <node id="34a67e55-71b1-421f-96cc-519ef05b110b"
> uname="pgslave.blumar.com.br" type="normal">
>
> <instance_attributes
> id="nodes-34a67e55-71b1-421f-96cc-519ef05b110b">
>
> <attributes>
>
> <nvpair id="standby-34a67e55-71b1-421f-96cc-519ef05b110b"
> name="standby" value="off"/>
>
> </attributes>
>
> </instance_attributes>
>
> </node>
>
> <node id="56ec2257-b0e1-4395-8ca2-ff2f96151b55"
> uname="pgmaster.blumar.com.br" type="normal"/>
>
> </nodes>
>
> <resources>
>
> <master_slave id="ms-drbd0">
>
> <meta_attributes id="ma-ms-drbd0">
>
> <attributes>
>
> <nvpair id="ma-ms-drbd0-1" name="clone_max" value="2"/>
>
> <nvpair id="ma-ms-drbd0-2" name="clone_node_max"
> value="1"/>
>
> <nvpair id="ma-ms-drbd0-3" name="master_max" value="1"/>
>
> <nvpair id="ma-ms-drbd0-4" name="master_node_max"
> value="1"/>
>
> <nvpair id="ma-ms-drbd0-5" name="notify" value="yes"/>
>
> <nvpair id="ma-ms-drbd0-6" name="globally_unique"
> value="false"/>
>
> <nvpair id="ma-ms-drbd0-7" name="target_role"
> value="started"/>
>
> </attributes>
>
> </meta_attributes>
>
> <primitive id="drbd0" class="ocf" provider="heartbeat"
> type="drbd">
>
> <instance_attributes id="ia-drbd0">
>
> <attributes>
>
> <nvpair id="ia-drbd0-1" name="drbd_resource"
> value="repdata"/>
>
> </attributes>
>
> </instance_attributes>
>
> <meta_attributes id="drbd0:0_meta_attrs">
>
> <attributes/>
>
> </meta_attributes>
>
> </primitive>
>
> </master_slave>
>
> <group id="group_pgsql">
>
> <meta_attributes id="group_pgsql_meta_attrs">
>
> <attributes>
>
> <nvpair id="group_pgsql_metaattr_target_role"
> name="target_role" value="stopped"/>
>
> </attributes>
>
> </meta_attributes>
>
> <primitive id="resource_ip" class="ocf" type="IPaddr"
> provider="heartbeat">
>
> <instance_attributes id="resource_ip_instance_attrs">
>
> <attributes>
>
> <nvpair id="f294ba51-00f9-4a9b-80c0-43aa7944f474"
> name="ip" value="10.3.3.24"/>
>
> </attributes>
>
> </instance_attributes>
>
> <meta_attributes id="resource_ip_meta_attrs">
>
> <attributes>
>
> <nvpair id="resource_ip_metaattr_target_role"
> name="target_role" value="started"/>
>
> </attributes>
>
> </meta_attributes>
>
> </primitive>
>
> <primitive id="resource_FS" class="ocf" type="Filesystem"
> provider="heartbeat">
>
> <instance_attributes id="resource_FS_instance_attrs">
>
> <attributes>
>
> <nvpair id="d1413b97-4944-4fee-9cba-b4ab3e71f83f"
> name="device" value="/dev/drbd0"/>
>
> <nvpair id="baad1fbb-3389-4778-8832-91d5720341a6"
> name="directory" value="/repdata"/>
>
> <nvpair id="35e6e951-ace4-4bbf-9d3e-5824219a9809"
> name="fstype" value="ext3"/>
>
> </attributes>
>
> </instance_attributes>
>
> <meta_attributes id="resource_FS_meta_attrs">
>
> <attributes>
>
> <nvpair id="resource_FS_metaattr_target_role"
> name="target_role" value="started"/>
>
> </attributes>
>
> </meta_attributes>
>
> </primitive>
>
> <primitive id="resource_pgsql" class="ocf" type="pgsql"
> provider="heartbeat">
>
> <meta_attributes id="resource_pgsql_meta_attrs">
>
> <attributes>
>
> <nvpair id="resource_pgsql_metaattr_target_role"
> name="target_role" value="started"/>
>
> </attributes>
>
> </meta_attributes>
>
> </primitive>
>
> </group>
>
> </resources>
>
> <constraints>
>
> <rsc_colocation id="colocation_" from="group_pgsql"
> to="group_pgsql" score="INFINITY"/>
>
> <rsc_location id="location_" rsc="group_pgsql">
>
> <rule id="prefered_location_" score="INFINITY">
>
> <expression attribute="#uname"
> id="a7b8a885-27c2-4157-a597-42dd6cafba8c" operation="eq"
> value="pgmaster.blumar.com.br"/>
>
> </rule>
>
> </rsc_location>
>
> </constraints>
>
> </configuration>
>
> </cib>
>
>
>
> Carlos Alexandre
> Analista de Suporte
>
> Direct Phone: + 55 21 2142-9383
> www.blumar.com.br <http://www.blumar.com.br>
>
>
>
>
>
>
>
>
>
>
>
>
>
> Av. Borges de Medeiros, 633 - Sala 405 a 408 - Leblon - Rio de janeiro
-
> Brasil - 22430-041
> www.blumar.com.br <http://www.blumar.com.br> phone: +55 21 2142 9300
> fax: +55 21 2511 3739
>
>
>
>

_______________________________________________
Linux-HA mailing list
Linux-HA [at] lists
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems

Linux-HA users RSS feed   Index | Next | Previous | View Threaded
 
 


Interested in having your list archived? Contact Gossamer Threads
 
  Web Applications & Managed Hosting Powered by Gossamer Threads Inc.