SLES11 HAE Problem: All nodes for resource dummy1 are unavailable,
unclean or shutting down.

I have setup a 2 node SLES11 SP1 HAE cluster (config see below).
Whenever I ifdown nic0 on node1 followed by ifup on node1, then ifdown
nic0 on node2 followed by ifup on node2, certain resources (e.g. dummy1
which is the built-in classcf/provider:heartbeat/type:dummy resource)
will not be able to start, leaving the following message in
/var/log/messages: "All nodes for resource dummy1 are unavailable,
unclean or shutting down." followed by "Node2 pengine: [27355]: info:
native_color: Resource dummy1 cannot run anywhere".

Any help is greatly appreciated, thanks

Bruno



Versions
======
# rpm -qa '(pacemaker|corosync|resource-agents)'
resource-agents-1.0.3-0.3.2
corosync-1.2.1-0.5.1
pacemaker-1.1.2-0.2.1

/var/log/messages
==============

sfd90211:~ # o /var/log/messages |grep -i 'All nodes for resource'
Oct 18 14:50:13 Node2 pengine: [27355]: debug: native_assign_node: All
nodes for resource dummy1 are unavailable, unclean or shutting down
(Node2: 0, -1000000)
Oct 18 14:50:13 Node2 pengine: [27355]: info: native_color: Resource
dummy1 cannot run anywher


CIB whole Config
============

<cib admin_epoch="0" cib-last-written="Tue Oct 18 14:29:53 2011"
crm_feature_set="3.0.2" dc-uuid="node1" epoch="1285" have-quorum="1"
num_updates="12" validate-with="pacemaker-1.2">
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<nvpair id="cib-bootstrap-options-dc-version" name="dc-version"
value="1.1.2-2e096a41a5f9e184a1c1537c82c6da1093698eb5"/>
<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="1"/>
<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-last-lrm-refresh"
name="last-lrm-refresh" value="1317648808"/>
<nvpair id="cib-bootstrap-options-maintenance-mode"
name="maintenance-mode" value="false"/>
</cluster_property_set>
</crm_config>
<nodes>
<node id="node1" type="normal" uname="node1">
<instance_attributes id="nodes-node1">
<nvpair id="nodes-node1-standby" name="standby"
value="off"/>
</instance_attributes>
</node>
<node id="node2" type="normal" uname="node2">
<instance_attributes id="nodes-node2">
<nvpair id="nodes-node2-standby" name="standby"
value="off"/>
</instance_attributes>
</node>
</nodes>
<resources>
<group id="group_fd">
<meta_attributes id="group_fd-meta_attributes">
<nvpair id="group_fd-meta_attributes-is-managed"
name="is-managed" value="true"/>
<nvpair id="group_fd-meta_attributes-target-role"
name="target-role" value="started"/>
</meta_attributes>
<primitive class="ocf" id="san_disk_fd" provider="heartbeat"
type="Filesystem">
<operations id="san_disk_fd-operations">
<op id="san_disk_fd-monitor-20" interval="20"
name="monitor" timeout="40"/>
</operations>
<instance_attributes id="san_disk_fd-instance_attributes">
<nvpair id="san_disk_fd-instance_attributes-device"
name="device" value="/dev/mapper/vfd90210vol00"/>
<nvpair id="san_disk_fd-instance_attributes-directory"
name="directory" value="/mnt/vfd90210"/>
<nvpair id="san_disk_fd-instance_attributes-fstype"
name="fstype" value="ext3"/>
</instance_attributes>
<meta_attributes id="san_disk_fd-meta_attributes">
<nvpair id="san_disk_fd-meta_attributes-is-managed"
name="is-managed" value="false"/>
<nvpair id="san_disk_fd-meta_attributes-target-role"
name="target-role" value="stopped"/>
</meta_attributes>
</primitive>
<primitive class="ocf" id="clusterip_fd" provider="heartbeat"
type="IPaddr2">
<meta_attributes id="clusterip_fd-meta_attributes">
<nvpair id="clusterip_fd-meta_attributes-target-role"
name="target-role" value="started"/>
<nvpair id="clusterip_fd-meta_attributes-is-managed"
name="is-managed" value="false"/>
</meta_attributes>
<operations id="clusterip_fd-operations">
<op id="clusterip_fd-monitor-10s" interval="10s"
name="monitor" timeout="20s"/>
</operations>
<instance_attributes id="clusterip_fd-instance_attributes">
<nvpair id="clusterip_fd-instance_attributes-ip" name="ip"
value="192.168.0.17"/>
</instance_attributes>
</primitive>
<primitive class="ocf" id="apache_fd" provider="heartbeat"
type="apache">
<operations id="apache_fd-operations">
<op id="apache_fd-monitor-10" interval="10" name="monitor"
timeout="20s"/>
</operations>
<meta_attributes id="apache_fd-meta_attributes">
<nvpair id="apache_fd-meta_attributes-target-role"
name="target-role" value="started"/>
<nvpair id="apache_fd-meta_attributes-is-managed"
name="is-managed" value="false"/>
</meta_attributes>
</primitive>
</group>
<primitive class="ocf" id="clusterip_fd2" provider="heartbeat"
type="IPaddr2">
<meta_attributes id="clusterip_fd2-meta_attributes">
<nvpair id="clusterip_fd2-meta_attributes-target-role"
name="target-role" value="stopped"/>
<nvpair id="clusterip_fd2-meta_attributes-is-managed"
name="is-managed" value="false"/>
</meta_attributes>
<operations id="clusterip_fd2-operations">
<op id="clusterip_fd2-monitor-10s" interval="10s"
name="monitor" timeout="20s"/>
</operations>
<instance_attributes id="clusterip_fd2-instance_attributes">
<nvpair id="clusterip_fd2-instance_attributes-ip" name="ip"
value="192.168.0.17"/>
</instance_attributes>
</primitive>
<group id="my_sandisk_cluster">
<meta_attributes id="my_sandisk_cluster-meta_attributes">
<nvpair id="my_sandisk_cluster-meta_attributes-target-role"
name="target-role" value="started"/>
</meta_attributes>
<primitive class="ocf" id="failover-ip" provider="heartbeat"
type="IPaddr">
<instance_attributes id="failover-ip-instance_attributes">
<nvpair id="failover-ip-instance_attributes-ip" name="ip"
value="192.168.0.17"/>
</instance_attributes>
<operations>
<op id="failover-ip-monitor-10s" interval="10s"
name="monitor"/>
</operations>
<meta_attributes id="failover-ip-meta_attributes">
<nvpair id="failover-ip-meta_attributes-target-role"
name="target-role" value="started"/>
</meta_attributes>
</primitive>
<primitive class="ocf" id="san_disk_fd2" provider="heartbeat"
type="Filesystem">
<operations id="san_disk_fd2-operations">
<op id="san_disk_fd2-monitor-20" interval="20"
name="monitor" timeout="40"/>
</operations>
<instance_attributes id="san_disk_fd2-instance_attributes">
<nvpair id="san_disk_fd2-instance_attributes-device"
name="device" value="/dev/mapper/vfd90210vol00"/>
<nvpair id="san_disk_fd2-instance_attributes-directory"
name="directory" value="/mnt/vfd90210"/>
<nvpair id="san_disk_fd2-instance_attributes-fstype"
name="fstype" value="ext3"/>
</instance_attributes>
<meta_attributes id="san_disk_fd2-meta_attributes">
<nvpair id="san_disk_fd2-meta_attributes-is-managed"
name="is-managed" value="true"/>
</meta_attributes>
</primitive>
</group>
<clone id="pingdclone">
<meta_attributes id="pingdclone-meta_attributes">
<nvpair id="pingdclone-meta_attributes-globally-unique"
name="globally-unique" value="false"/>
</meta_attributes>
<primitive class="ocf" id="pingd" provider="pacemaker"
type="pingd">
<instance_attributes id="pingd-instance_attributes">
<nvpair id="pingd-instance_attributes-host_list"
name="host_list" value="192.168.0.1"/>
<nvpair id="pingd-instance_attributes-multiplier"
name="multiplier" value="100"/>
</instance_attributes>
<operations>
<op id="pingd-monitor-15s" interval="15s" name="monitor"
timeout="5s"/>
</operations>
</primitive>
</clone>
<primitive class="ocf" id="dummy1" provider="heartbeat"
type="Dummy">
<meta_attributes id="dummy1-meta_attributes">
<nvpair id="dummy1-meta_attributes-target-role"
name="target-role" value="started"/>
</meta_attributes>
</primitive>
</resources>
<constraints>
<rsc_location id="my_sandisk_cluster_on_connected_node"
rsc="my_sandisk_cluster">
<rule boolean-op="or"
id="my_sandisk_cluster_on_connected_node-rule" score="-INFINITY">
<expression attribute="pingd"
id="my_sandisk_cluster_on_connected_node-expression"
operation="not_defined"/>
<expression attribute="pingd"
id="my_sandisk_cluster_on_connected_node-expression-0" operation="lte"
value="0"/>
</rule>
</rsc_location>
<rsc_location id="dummy1_on_connected_node" rsc="dummy1">
<rule boolean-op="or" id="dummy1_on_connected_node-rule"
score="-INFINITY">
<expression attribute="pingd"
id="dummy1_on_connected_node-expression" operation="not_defined"/>
<expression attribute="pingd"
id="dummy1_on_connected_node-expression-0" operation="lte" value="0"/>
</rule>
</rsc_location>
</constraints>
<op_defaults>
<meta_attributes id="op_defaults-options">
<nvpair id="op_defaults-options-record-pending"
name="record-pending" value="false"/>
</meta_attributes>
</op_defaults>
<rsc_defaults>
<meta_attributes id="rsc-options">
<nvpair id="rsc-options-resource-stickiness"
name="resource-stickiness" value="1"/>
<nvpair id="rsc-options-failure-timeout" name="failure-timeout"
value="60s"/>
</meta_attributes>
</rsc_defaults>
</configuration>
<status>
<node_state crm-debug-origin="do_update_resource" crmd="online"
expected="member" ha="active" id="node1" in_ccm="true" join="member"
shutdown="0" uname="node1">
<lrm id="node1">
<lrm_resources>
<lrm_resource class="ocf" id="san_disk_fd"
provider="heartbeat" type="Filesystem">
<lrm_rsc_op call-id="2"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="60" id="san_disk_fd_monitor_0" interval="0"
last-rc-change="1318941311" last-run="1318941311"
op-digest="bfadd3a6afb308eb046b879e2070bcb9" op-status="0"
operation="monitor" queue-time="0" rc-code="7"
transition-key="4:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;4:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
<lrm_resource class="ocf" id="clusterip_fd2"
provider="heartbeat" type="IPaddr2">
<lrm_rsc_op call-id="5"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="70" id="clusterip_fd2_monitor_0" interval="0"
last-rc-change="1318941311" last-run="1318941311"
op-digest="199253622b2b5dda4457f146efe66ad1" op-status="0"
operation="monitor" queue-time="0" rc-code="7"
transition-key="7:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;7:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
<lrm_resource class="ocf" id="clusterip_fd"
provider="heartbeat" type="IPaddr2">
<lrm_rsc_op call-id="3"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="80" id="clusterip_fd_monitor_0" interval="0"
last-rc-change="1318941311" last-run="1318941311"
op-digest="199253622b2b5dda4457f146efe66ad1" op-status="0"
operation="monitor" queue-time="0" rc-code="7"
transition-key="5:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;5:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
<lrm_resource class="ocf" id="apache_fd" provider="heartbeat"
type="apache">
<lrm_rsc_op call-id="4"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="100" id="apache_fd_monitor_0" interval="0"
last-rc-change="1318941311" last-run="1318941311"
op-digest="f2317cad3d54cec5d7d7aa7d0bf35cf8" op-status="0"
operation="monitor" queue-time="0" rc-code="7"
transition-key="6:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;6:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
<lrm_resource class="ocf" id="pingd:0" provider="pacemaker"
type="pingd">
<lrm_rsc_op call-id="8"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="30" id="pingd:0_monitor_0" interval="0"
last-rc-change="1318941312" last-run="1318941312"
op-digest="f9e5022a59cac98812bcfea6a34348b4" op-status="0"
operation="monitor" queue-time="1000" rc-code="7"
transition-key="10:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;10:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
<lrm_rsc_op call-id="10"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="20" id="pingd:0_start_0" interval="0"
last-rc-change="1318941312" last-run="1318941312"
op-digest="f9e5022a59cac98812bcfea6a34348b4" op-status="0"
operation="start" queue-time="0" rc-code="0"
transition-key="28:0:0:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:0;28:0:0:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
<lrm_rsc_op call-id="11"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="10" id="pingd:0_monitor_15000" interval="15000"
last-rc-change="1318941312" last-run="1318941312"
op-digest="efd4237723a9695275fd88201a420089" op-status="0"
operation="monitor" queue-time="0" rc-code="0"
transition-key="30:1:0:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:0;30:1:0:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
<lrm_resource class="ocf" id="dummy1" provider="heartbeat"
type="Dummy">
<lrm_rsc_op call-id="9"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="40" id="dummy1_monitor_0" interval="0"
last-rc-change="1318941312" last-run="1318941312"
op-digest="f2317cad3d54cec5d7d7aa7d0bf35cf8" op-status="0"
operation="monitor" queue-time="1000" rc-code="7"
transition-key="11:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;11:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
<lrm_resource class="ocf" id="failover-ip"
provider="heartbeat" type="IPaddr">
<lrm_rsc_op call-id="6"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="40" id="failover-ip_monitor_0" interval="0"
last-rc-change="1318941312" last-run="1318941312"
op-digest="199253622b2b5dda4457f146efe66ad1" op-status="0"
operation="monitor" queue-time="1000" rc-code="7"
transition-key="8:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;8:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
<lrm_resource class="ocf" id="san_disk_fd2"
provider="heartbeat" type="Filesystem">
<lrm_rsc_op call-id="7"
crm-debug-origin="do_update_resource" crm_feature_set="3.0.2"
exec-time="70" id="san_disk_fd2_monitor_0" interval="0"
last-rc-change="1318941312" last-run="1318941312"
op-digest="bfadd3a6afb308eb046b879e2070bcb9" op-status="0"
operation="monitor" queue-time="1000" rc-code="7"
transition-key="9:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"
transition-magic="0:7;9:0:7:5fc58646-b53f-47df-9796-e1764e3f7fd7"/>
</lrm_resource>
</lrm_resources>
</lrm>
<transient_attributes id="node1">
<instance_attributes id="status-node1">
<nvpair id="status-node1-probe_complete"
name="probe_complete" value="true"/>
</instance_attributes>
</transient_attributes>
</node_state>
</status>
</cib>


--
b400bhb
------------------------------------------------------------------------
b400bhb's Profile: http://forums.novell.com/member.php?userid=111651
View this thread: http://forums.novell.com/showthread.php?t=446975