Greetings,

 

Something is very wrong with my drbd. Whenever my master machine goes
down and it comes back, I get something like this when the service is
started and the node is promoted by heartbeat.

 

[EMAIL PROTECTED] ~]# cat /proc/drbd

version: 8.0.11 (api:86/proto:86)

GIT-hash: b3fe2bdfd3b9f7c2f923186883eb9e2a0d3a5b1b build by
[EMAIL PROTECTED], 2008-03-09 10:26:55

 0: cs:WFConnection st:Primary/Unknown ds:UpToDate/DUnknown C r---

    ns:0 nr:0 dw:0 dr:0 al:0 bm:0 lo:0 pe:0 ua:0 ap:0

        resync: used:0/31 hits:0 misses:0 starving:0 dirty:0 changed:0

        act_log: used:0/127 hits:0 misses:0 starving:0 dirty:0 changed:0

[EMAIL PROTECTED] ~]#

 

 

And when this happens, the nodes does not sync anymore, looks like one
can't see the other one. The problem gets fixed if I recreated the meta
disks but if I have to do this then I dont have a reliable fail over
solution.

 

Does anyone have any advice to give me about this ??

 

My drbd.conf and cib.xml are posted below.

 

global { usage-count no; }

resource repdata {

  protocol C;

  startup { wfc-timeout 0; degr-wfc-timeout     120; }

  disk { on-io-error detach; } # or panic, ...

  net {  cram-hmac-alg "sha1"; shared-secret "C4c4b4sh1"; } # don't
forget to choose a secret for auth !

  syncer { rate 10M; }

  on pgmaster.blumar.com.br {

    device /dev/drbd0;

    disk /dev/sda6;

    address 30.30.30.30:7788;

    meta-disk /dev/sda7[0];

  }

  on pgslave.blumar.com.br {

    device /dev/drbd0;

    disk /dev/hda3;

    address 30.30.30.29:7788;

    meta-disk /dev/hda4[0];

  }

}

 

 

<cib generated="true" admin_epoch="0" have_quorum="true"
ignore_dtd="false" num_peers="2" cib_feature_revision="2.0"
ccm_transition="5" dc_uuid="56ec2257-b0e1-4395-8ca2-ff2f96151b55"
epoch="100" num_updates="1" cib-last-written="Fri Mar 28 17:33:41 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 name="last-lrm-refresh"
id="cib-bootstrap-options-last-lrm-refresh" value="1206725922"/>

         </attributes>

       </cluster_property_set>

     </crm_config>

     <nodes>

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

       <node id="fb01ec99-1ece-40ed-a737-f3816e69368c"
uname="pgmaster.blumar.com.br" type="normal"/>

     </nodes>

     <resources>

       <master_slave id="array_drbd">

         <meta_attributes id="array_drbd_meta_attrs">

           <attributes>

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

             <nvpair id="array_drbd_metaattr_clone_max" name="clone_max"
value="2"/>

             <nvpair id="array_drbd_metaattr_clone_node_max"
name="clone_node_max" value="1"/>

             <nvpair id="array_drbd_metaattr_master_max"
name="master_max" value="1"/>

             <nvpair id="array_drbd_metaattr_master_node_max"
name="master_node_max" value="1"/>

             <nvpair id="array_drbd_metaattr_notify" name="notify"
value="true"/>

             <nvpair id="array_drbd_metaattr_globally_unique"
name="globally_unique" value="false"/>

           </attributes>

         </meta_attributes>

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

           <instance_attributes id="resource_drbd_instance_attrs">

             <attributes>

               <nvpair id="19b32757-d764-410b-8892-376598313f94"
name="drbd_resource" value="repdata"/>

             </attributes>

           </instance_attributes>

         </primitive>

       </master_slave>

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

         <meta_attributes id="resource_fs_meta_attrs">

           <attributes>

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

           </attributes>

         </meta_attributes>

         <instance_attributes id="resource_fs_instance_attrs">

           <attributes>

             <nvpair id="edf7c582-3d98-4605-bbca-a176f0b8ec0d"
name="device" value="/dev/drbd0"/>

             <nvpair id="a71f6fa0-2be3-485a-8467-cfb92e54bf08"
name="directory" value="/repdata"/>

             <nvpair id="73af8c10-3244-44d9-b883-43c4c5e87685"
name="fstype" value="ext3"/>

           </attributes>

         </instance_attributes>

       </primitive>

       <primitive class="ocf" type="IPaddr2" provider="heartbeat"
id="ip_postgres">

         <meta_attributes id="ip_postgres_meta_attrs">

           <attributes>

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

           </attributes>

         </meta_attributes>

         <instance_attributes id="ip_postgres_instance_attrs">

           <attributes>

             <nvpair id="e1e0d015-aafa-49fb-aab1-877ecb54b4b7" name="ip"
value="10.3.3.1"/>

           </attributes>

         </instance_attributes>

       </primitive>

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

         <meta_attributes id="resource_postgres_meta_attrs">

           <attributes>

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

           </attributes>

         </meta_attributes>

         <instance_attributes id="resource_postgres_instance_attrs">

           <attributes>

             <nvpair id="9b48a9af-cea7-4758-b392-072e8eb68634"
name="pgdata" value="/repdata/pg"/>

           </attributes>

         </instance_attributes>

       </primitive>

     </resources>

     <constraints>

       <rsc_order id="drbd_antes_fs" from="resource_fs" action="start"
to="array_drbd" to_action="promote"/>

       <rsc_colocation id="fs_com_drbd" to="array_drbd" to_role="master"
from="resource_fs" score="INFINITY"/>

       <rsc_colocation id="ip_com_fs" from="ip_postgres"
to="resource_fs" score="INFINITY"/>

       <rsc_order id="ip_antes_pg" from="ip_postgres" type="before"
to="resource_postgres"/>

       <rsc_location id="drbd_pgmaster" rsc="array_drbd">

         <rule id="prefered_drbd_pgmaster" score="100">

           <expression attribute="#uname"
id="68a231b9-57e0-4bcb-840c-bce74e429a4c" operation="eq"
value="pgmaster.blumar.com.br"/>

         </rule>

       </rsc_location>

       <rsc_colocation id="postgres_com_ip" from="resource_postgres"
to="ip_postgres" score="INFINITY"/>

     </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 

 

 

<<image001.gif>>

<<image002.gif>>

<<image003.gif>>

<<image004.gif>>

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

Reply via email to