Huhn Hur Tu
10.03.10, 10:00
Da ich scheinbar etwas durcheinander konfiguriert habe habe ich noch mal von vorn angefangen. Ich ahbe aber das Problem dass Heartbeat mysql nicht startet.
Server 1 eth1 192.168.1.17 Debian Lenny stable
Server 2 eth1 192.168.1.18 Debian Lenny stable
Virtuelle IP 192.168.1.253
/etc/network/interfaces Server1
# The loopback network interface
auto lo
iface lo inet loopback
# The primary network interface
allow-hotplug eth1
iface eth1 inet dhcp
auto eth0
iface eth0 inet static
address 192.168.200.1
network 192.168.200.0
netmask 255.255.255.0
broadcast 192.168.200.255
auto lo:0
iface lo:0 inet static
address 192.168.1.253
netmask 255.255.255.255
pre-up sysctl -p > /dev/null
Server2
# The loopback network interface
auto lo
iface lo inet loopback
# The primary network interface
allow-hotplug eth1
iface eth1 inet dhcp
auto eth0
iface eth0 inet static
address 192.168.200.2
network 192.168.200.0
netmask 255.255.255.0
broadcast 192.168.200.255
auto lo:0
iface lo:0 inet static
address 192.168.1.253
netmask 255.255.255.255
pre-up sysctl -p > /dev/null
Server1
/etc/ha.d/ha.cf
debugfile /var/log/ha-debug
logfile /var/log/ha-log
logfacility local0
bcast eth1
mcast eth1 225.0.0.1 694 1 0
ucast eth1 192.168.1.18
crm yes
keepalive 5
warntime 10
deadtime 120
initdead 120
auto_failback off
node server1
node server2
respawn hacluster /usr/lib/heartbeat/ipfail
apiauth ipfail gid=haclient uid=hacluster
Server1
/etc/ha.d/ha.cf
debugfile /var/log/ha-debug
logfile /var/log/ha-log
logfacility local0
bcast eth1
mcast eth1 225.0.0.1 694 1 0
ucast eth1 192.168.1.18
crm yes
keepalive 5
warntime 10
deadtime 120
initdead 120
auto_failback off
node server1
node server2
respawn hacluster /usr/lib/heartbeat/ipfail
apiauth ipfail gid=haclient uid=hacluster
Server1/2
/etc/ha.d/haresources
muss da als erstes Wort (Server1) nur ein Node stehen? oder der jeweisl andere oder ...
server1 \
IPaddr2::192.168.1.253/24/eth0/192.168.1.255 mysql
/etc/ha.d/authkeys
Server1/2
auth 3
#1 sha1 passworthiereingeben
#2 md5 passworthiereingeben
3 crc
Mit dem Script
/usr/lib/heartbeat/haresources2cib.py /etc/ha.d/haresources
habe ich die haresources in die cib.xml konvertiert, vorher natuerlich die cib.xml und die cib.xml.sig geloescht.
cib.xml
<cib admin_epoch="0" epoch="1" have_quorum="false" ignore_dtd="false" num_peers="2" cib_feature_revision="2.0" generated="false" num_updates="4" cib-last-written="Wed Mar 10 10:55:06 2010">
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<attributes>
<nvpair id="cib-bootstrap-options-symmetric-cluster" name="symmetric-cluster" value="true"/>
<nvpair id="cib-bootstrap-options-no-quorum-policy" name="no-quorum-policy" value="stop"/>
<nvpair id="cib-bootstrap-options-default-resource-stickiness" name="default-resource-stickiness" value="0"/>
<nvpair id="cib-bootstrap-options-default-resource-failure-stickiness" name="default-resource-failure-stickiness" value="0"/>
<nvpair id="cib-bootstrap-options-stonith-enabled" name="stonith-enabled" value="false"/>
<nvpair id="cib-bootstrap-options-stonith-action" name="stonith-action" value="reboot"/>
<nvpair id="cib-bootstrap-options-startup-fencing" name="startup-fencing" value="true"/>
<nvpair id="cib-bootstrap-options-stop-orphan-resources" name="stop-orphan-resources" value="true"/>
<nvpair id="cib-bootstrap-options-stop-orphan-actions" name="stop-orphan-actions" value="true"/>
<nvpair id="cib-bootstrap-options-remove-after-stop" name="remove-after-stop" value="false"/>
<nvpair id="cib-bootstrap-options-short-resource-names" name="short-resource-names" value="true"/>
<nvpair id="cib-bootstrap-options-transition-idle-timeout" name="transition-idle-timeout" value="5min"/>
<nvpair id="cib-bootstrap-options-default-action-timeout" name="default-action-timeout" value="20s"/>
<nvpair id="cib-bootstrap-options-is-managed-default" name="is-managed-default" value="true"/>
<nvpair id="cib-bootstrap-options-cluster-delay" name="cluster-delay" value="60s"/>
<nvpair id="cib-bootstrap-options-pe-error-series-max" name="pe-error-series-max" value="-1"/>
<nvpair id="cib-bootstrap-options-pe-warn-series-max" name="pe-warn-series-max" value="-1"/>
<nvpair id="cib-bootstrap-options-pe-input-series-max" name="pe-input-series-max" value="-1"/>
<nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="2.1.3-node: 552305612591183b1628baa5bc6e903e0f1e26a3"/>
</attributes>
</cluster_property_set>
</crm_config>
<nodes>
<node id="a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0" uname="server2" type="normal"/>
<node id="7d026928-b718-4d28-b3e6-22ee3cd9ab50" uname="server1" type="normal"/>
</nodes>
<resources>
<group id="group_1">
<primitive class="ocf" id="IPaddr2_1" provider="heartbeat" type="IPaddr2">
<operations>
<op id="IPaddr2_1_mon" interval="5s" name="monitor" timeout="5s"/>
</operations>
<instance_attributes id="IPaddr2_1_inst_attr">
<attributes>
<nvpair id="IPaddr2_1_attr_0" name="ip" value="192.168.1.253"/>
<nvpair id="IPaddr2_1_attr_1" name="nic" value="24"/>
<nvpair id="IPaddr2_1_attr_2" name="cidr_netmask" value="eth0"/>
<nvpair id="IPaddr2_1_attr_3" name="broadcast" value="192.168.1.255"/>
</attributes>
</instance_attributes>
</primitive>
<primitive class="ocf" id="mysql_2" provider="heartbeat" type="mysql">
<operations>
<op id="mysql_2_mon" interval="120s" name="monitor" timeout="60s"/>
</operations>
</primitive>
</group>
</resources>
<constraints>
<rsc_location id="rsc_location_group_1" rsc="group_1">
<rule id="prefered_location_group_1" score="100">
<expression attribute="#uname" id="prefered_location_group_1_expr" operation="eq" value="server1"/>
</rule>
</rsc_location>
</constraints>
</configuration>
</cib>
/var/log/messages
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml (digest: /var/lib/heartbeat/crm/cib.xml.sig)
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml.last (digest: /var/lib/heartbeat/crm/cib.xml.sig.last)
Mar 10 10:55:03 server2 crmd: [2393]: info: do_cib_control: CIB connection established
Mar 10 10:55:03 server2 crmd: [2393]: info: register_with_ha: Hostname: server2
Mar 10 10:55:03 server2 cib: [2389]: info: cib_client_status_callback: Status update: Client server2/cib now has status [join]
Mar 10 10:55:03 server2 cib: [2389]: info: cib_client_status_callback: Status update: Client server2/cib now has status [online]
Mar 10 10:55:03 server2 cib: [2389]: info: cib_null_callback: Setting cib_diff_notify callbacks for mgmtd: on
Mar 10 10:55:03 server2 cib: [2389]: info: cib_null_callback: Setting cib_refresh_notify callbacks for crmd: on
Mar 10 10:55:03 server2 cib: [2398]: info: write_cib_contents: Wrote version 0.1.1 of the CIB to disk (digest: 94547266cef61ee87acef8a5225147a3)
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml (digest: /var/lib/heartbeat/crm/cib.xml.sig)
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml.last (digest: /var/lib/heartbeat/crm/cib.xml.sig.last)
Mar 10 10:55:03 server2 crmd: [2393]: info: register_with_ha: UUID: a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0
Mar 10 10:55:03 server2 cib: [2389]: info: cib_client_status_callback: Status update: Client server1/cib now has status [online]
Mar 10 10:55:04 server2 crmd: [2393]: info: populate_cib_nodes: Requesting the list of configured nodes
Mar 10 10:55:05 server2 mgmtd: [2394]: info: Started.
Mar 10 10:55:05 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server2 (uuid: a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0)
Mar 10 10:55:05 server2 ccm: [2388]: info: Break tie for 2 nodes cluster
Mar 10 10:55:05 server2 cib: [2389]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:05 server2 cib: [2389]: info: mem_handle_event: instance=1, nodes=1, new=1, lost=0, n_idx=0, new_idx=0, old_idx=3
Mar 10 10:55:05 server2 cib: [2389]: info: cib_ccm_msg_callback: PEER: server2
Mar 10 10:55:06 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server1 (uuid: 7d026928-b718-4d28-b3e6-22ee3cd9ab50)
Mar 10 10:55:06 server2 crmd: [2393]: info: do_ha_control: Connected to Heartbeat
Mar 10 10:55:06 server2 crmd: [2393]: info: do_ccm_control: CCM connection established... waiting for first callback
Mar 10 10:55:06 server2 crmd: [2393]: info: do_started: Delaying start, CCM (0000000000100000) not connected
Mar 10 10:55:06 server2 crmd: [2393]: info: crmd_init: Starting crmd's mainloop
Mar 10 10:55:06 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server2/crmd now has status [online]
Mar 10 10:55:06 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server2/crmd now has status [online]
Mar 10 10:55:07 server2 heartbeat: [2321]: WARN: 1 lost packet(s) for [server1] [19:21]
Mar 10 10:55:07 server2 heartbeat: [2321]: info: No pkts missing from server1!
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: Got an event OC_EV_MS_INVALID from ccm
Mar 10 10:55:07 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server1/crmd now has status [offline]
Mar 10 10:55:07 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server1/crmd now has status [online]
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: no mbr_track info
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: instance=2, nodes=2, new=1, lost=0, n_idx=0, new_idx=2, old_idx=4
Mar 10 10:55:07 server2 cib: [2389]: info: cib_ccm_msg_callback: PEER: server2
Mar 10 10:55:07 server2 cib: [2389]: info: cib_ccm_msg_callback: PEER: server1
Mar 10 10:55:07 server2 crmd: [2393]: info: do_started: Delaying start, CCM (0000000000100000) not connected
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: instance=1, nodes=1, new=1, lost=0, n_idx=0, new_idx=0, old_idx=3
Mar 10 10:55:07 server2 crmd: [2393]: info: crmd_ccm_msg_callback: Quorum (re)attained after event=NEW MEMBERSHIP (id=1)
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: Got an event OC_EV_MS_INVALID from ccm
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: no mbr_track info
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: instance=2, nodes=2, new=1, lost=0, n_idx=0, new_idx=2, old_idx=4
Mar 10 10:55:07 server2 crmd: [2393]: info: crmd_ccm_msg_callback: Quorum (re)attained after event=NEW MEMBERSHIP (id=2)
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: NEW MEMBERSHIP: trans=2, nodes=2, new=1, lost=0 n_idx=0, new_idx=2, old_idx=4
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011CURRENT: server2 [nodeid=1, born=1]
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011CURRENT: server1 [nodeid=0, born=2]
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011NEW: server1 [nodeid=0, born=2]
Mar 10 10:55:07 server2 crmd: [2393]: info: do_started: The local CRM is operational
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: NEW MEMBERSHIP: trans=1, nodes=1, new=1, lost=0 n_idx=0, new_idx=0, old_idx=3
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011CURRENT: server2 [nodeid=1, born=1]
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011NEW: server2 [nodeid=1, born=1]
Mar 10 10:55:07 server2 crmd: [2393]: info: do_state_transition: State transition S_STARTING -> S_PENDING [ input=I_PENDING cause=C_CCM_CALLBACK origin=do_started ]
Mar 10 10:55:07 server2 heartbeat: [2321]: WARN: 1 lost packet(s) for [server1] [22:24]
Mar 10 10:55:07 server2 heartbeat: [2321]: info: No pkts missing from server1!
Mar 10 10:55:10 server2 attrd: [2392]: info: main: Starting mainloop...
Mar 10 10:57:08 server2 crmd: [2393]: info: crm_timer_popped: Election Trigger (I_DC_TIMEOUT) just popped!
Mar 10 10:57:08 server2 crmd: [2393]: WARN: do_log: [[FSA]] Input I_DC_TIMEOUT from crm_timer_popped() received in state (S_PENDING)
Mar 10 10:57:08 server2 crmd: [2393]: info: do_state_transition: State transition S_PENDING -> S_ELECTION [ input=I_DC_TIMEOUT cause=C_TIMER_POPPED origin=crm_timer_popped ]
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server2 to vote
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: our vote (server2)
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_check: Still waiting on 1 non-votes (2 total)
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server1 to no-vote
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: no-vote from server1
Mar 10 10:57:08 server2 crmd: [2393]: info: do_state_transition: State transition S_ELECTION -> S_INTEGRATION [ input=I_ELECTION_DC cause=C_FSA_INTERNAL origin=do_election_check ]
Mar 10 10:57:08 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "tengine"
Mar 10 10:57:08 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "pengine"
Mar 10 10:57:08 server2 crmd: [2393]: info: do_dc_takeover: Taking over DC status for this partition
Mar 10 10:57:09 server2 cib: [2389]: info: cib_process_readwrite: We are now in R/W mode
Mar 10 10:57:09 server2 crmd: [2393]: info: join_make_offer: Making join offers based on membership 2
Mar 10 10:57:09 server2 crmd: [2393]: info: do_dc_join_offer_all: join-1: Waiting on 2 outstanding join acks
Mar 10 10:57:09 server2 tengine: [2406]: info: G_main_add_SignalHandler: Added signal handler for signal 15
Mar 10 10:57:09 server2 tengine: [2406]: info: G_main_add_TriggerHandler: Added signal manual handler
Mar 10 10:57:09 server2 tengine: [2406]: info: G_main_add_TriggerHandler: Added signal manual handler
Mar 10 10:57:09 server2 tengine: [2406]: info: te_init: Registering TE UUID: 87bd86cf-74fd-4cc0-8b99-7f543e3bccc4
Mar 10 10:57:09 server2 tengine: [2406]: info: set_graph_functions: Setting custom graph functions
Mar 10 10:57:09 server2 tengine: [2406]: info: unpack_graph: Unpacked transition -1: 0 actions in 0 synapses
Mar 10 10:57:09 server2 tengine: [2406]: info: te_init: Starting tengine
Mar 10 10:57:09 server2 tengine: [2406]: info: te_connect_stonith: Attempting connection to fencing daemon...
Mar 10 10:57:09 server2 cib: [2389]: info: cib_null_callback: Setting cib_diff_notify callbacks for tengine: on
Mar 10 10:57:09 server2 pengine: [2407]: info: G_main_add_SignalHandler: Added signal handler for signal 15
Mar 10 10:57:09 server2 pengine: [2407]: info: pe_init: Starting pengine
Mar 10 10:57:09 server2 crmd: [2393]: info: update_dc: Set DC to server2 (2.0)
Mar 10 10:57:10 server2 tengine: [2406]: info: te_connect_stonith: Connected
Mar 10 10:57:10 server2 crmd: [2393]: info: do_state_transition: State transition S_INTEGRATION -> S_FINALIZE_JOIN [ input=I_INTEGRATED cause=C_FSA_INTERNAL origin=check_join_state ]
Mar 10 10:57:10 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes responded to the join offer.
Mar 10 10:57:10 server2 crmd: [2393]: info: do_dc_join_finalize: join-1: Asking server1 for its copy of the CIB
Mar 10 10:57:12 server2 cib: [2389]: info: cib_replace_notify: Replaced: 0.1.3 -> 0.1.4 from <null>
Mar 10 10:57:12 server2 crmd: [2393]: info: populate_cib_nodes: Requesting the list of configured nodes
Mar 10 10:57:12 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server2 (uuid: a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0)
Mar 10 10:57:13 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server1 (uuid: 7d026928-b718-4d28-b3e6-22ee3cd9ab50)
Mar 10 10:57:13 server2 crmd: [2393]: info: update_attrd: Connecting to attrd...
Mar 10 10:57:13 server2 crmd: [2393]: info: do_state_transition: State transition S_FINALIZE_JOIN -> S_ELECTION [ input=I_ELECTION cause=C_FSA_INTERNAL origin=do_cib_replaced ]
Mar 10 10:57:13 server2 crmd: [2393]: info: update_dc: Unset DC server2
Mar 10 10:57:13 server2 attrd: [2392]: info: attrd_local_callback: Sending full refresh
Mar 10 10:57:13 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server2 to vote
Mar 10 10:57:13 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: our vote (server2)
Mar 10 10:57:13 server2 crmd: [2393]: info: do_election_check: Still waiting on 1 non-votes (2 total)
Mar 10 10:57:14 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server1 to no-vote
Mar 10 10:57:14 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: no-vote from server1
Mar 10 10:57:14 server2 crmd: [2393]: info: do_state_transition: State transition S_ELECTION -> S_INTEGRATION [ input=I_ELECTION_DC cause=C_FSA_INTERNAL origin=do_election_check ]
Mar 10 10:57:14 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "tengine"
Mar 10 10:57:14 server2 crmd: [2393]: WARN: start_subsystem: Client tengine already running as pid 2406
Mar 10 10:57:14 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "pengine"
Mar 10 10:57:14 server2 crmd: [2393]: WARN: start_subsystem: Client pengine already running as pid 2407
Mar 10 10:57:14 server2 crmd: [2393]: info: do_dc_takeover: Taking over DC status for this partition
Mar 10 10:57:14 server2 cib: [2389]: info: cib_process_readwrite: We are now in R/O mode
Mar 10 10:57:14 server2 cib: [2389]: info: cib_process_readwrite: We are now in R/W mode
Mar 10 10:57:14 server2 crmd: [2393]: info: do_dc_join_offer_all: join-2: Waiting on 2 outstanding join acks
Mar 10 10:57:15 server2 crmd: [2393]: info: update_dc: Set DC to server2 (2.0)
Mar 10 10:57:16 server2 crmd: [2393]: info: do_state_transition: State transition S_INTEGRATION -> S_FINALIZE_JOIN [ input=I_INTEGRATED cause=C_FSA_INTERNAL origin=check_join_state ]
Mar 10 10:57:16 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes responded to the join offer.
Mar 10 10:57:16 server2 attrd: [2392]: info: attrd_local_callback: Sending full refresh
Mar 10 10:57:16 server2 cib: [2389]: info: sync_our_cib: Syncing CIB to all peers
Mar 10 10:57:16 server2 crmd: [2393]: info: update_dc: Set DC to server2 (2.0)
Mar 10 10:57:17 server2 crmd: [2393]: info: do_dc_join_ack: join-2: Updating node state to member for server2
Mar 10 10:57:18 server2 crmd: [2393]: info: do_dc_join_ack: join-2: Updating node state to member for server1
Mar 10 10:57:18 server2 crmd: [2393]: info: do_state_transition: State transition S_FINALIZE_JOIN -> S_POLICY_ENGINE [ input=I_FINALIZED cause=C_FSA_INTERNAL origin=check_join_state ]
Mar 10 10:57:18 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1000000
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: 'DC Takeover' abort superceeded
Mar 10 10:57:18 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:18 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:18 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:18 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2):#011Stopped
Mar 10 10:57:18 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:18 server2 pengine: [2407]: notice: StartRsc: server1#011Start IPaddr2_1
Mar 10 10:57:18 server2 pengine: [2407]: notice: RecurringOp: server1#011 IPaddr2_1_monitor_5000
Mar 10 10:57:18 server2 pengine: [2407]: notice: StartRsc: server1#011Start mysql_2
Mar 10 10:57:18 server2 pengine: [2407]: notice: RecurringOp: server1#011 mysql_2_monitor_120000
Mar 10 10:57:18 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:18 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 0: 13 actions in 13 synapses
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 3: IPaddr2_1_monitor_0 on server2
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 6: IPaddr2_1_monitor_0 on server1
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 4: mysql_2_monitor_0 on server2
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 7: mysql_2_monitor_0 on server1
Mar 10 10:57:18 server2 crmd: [2393]: info: do_lrm_rsc_op: Performing op=IPaddr2_1_monitor_0 key=3:0:87bd86cf-74fd-4cc0-8b99-7f543e3bccc4)
Mar 10 10:57:18 server2 lrmd: [2390]: info: rsc:IPaddr2_1: monitor
Mar 10 10:57:18 server2 crmd: [2393]: info: do_lrm_rsc_op: Performing op=mysql_2_monitor_0 key=4:0:87bd86cf-74fd-4cc0-8b99-7f543e3bccc4)
Mar 10 10:57:18 server2 lrmd: [2390]: info: rsc:mysql_2: monitor
Mar 10 10:57:18 server2 pengine: [2407]: info: process_pe_message: Transition 0: PEngine Input stored in: /var/lib/heartbeat/pengine/pe-input-11.bz2
Mar 10 10:57:18 server2 crmd: [2393]: info: process_lrm_event: LRM operation mysql_2_monitor_0 (call=3, rc=7) complete
Mar 10 10:57:18 server2 tengine: [2406]: info: match_graph_event: Action mysql_2_monitor_0 (4) confirmed on server2 (rc=0)
Mar 10 10:57:18 server2 lrmd: [2390]: info: RA output: (IPaddr2_1:monitor:stderr) Invalid netmask specification [eth0]#012/usr/lib/heartbeat/findif version 2.1.3 Copyright Alan Robertson#012#012Usage: /usr/lib/heartbeat/findif [-C]#012Options:#012 -C: Output netmask as the number of bits rather than as 4 octets.#012Environment variables:#012OCF_RESKEY_ip#011#011 ip address (mandatory!)#012OCF_RESKEY_cidr_netmask netmask of interface#012OCF_RESKEY_broadcast#011 broadcast address for interface#012OCF_RESKEY_nic#011#011 interface to assign to
Mar 10 10:57:18 server2 crmd: [2393]: info: process_lrm_event: LRM operation IPaddr2_1_monitor_0 (call=2, rc=2) complete
Mar 10 10:57:18 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:18 server2 tengine: [2406]: WARN: status_from_rc: Action monitor on server2 failed (target: 7 vs. rc: 2): Error
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: Abort action 0 superceeded by 2
Mar 10 10:57:18 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_monitor_0 (3) confirmed on server2 (rc=4)
Mar 10 10:57:19 server2 tengine: [2406]: info: match_graph_event: Action mysql_2_monitor_0 (7) confirmed on server1 (rc=0)
Mar 10 10:57:19 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:19 server2 tengine: [2406]: WARN: status_from_rc: Action monitor on server1 failed (target: 7 vs. rc: 2): Error
Mar 10 10:57:19 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_monitor_0 (6) confirmed on server1 (rc=4)
Mar 10 10:57:19 server2 tengine: [2406]: info: run_graph: ================================================== ==
Mar 10 10:57:19 server2 tengine: [2406]: notice: run_graph: Transition 0: (Complete=4, Pending=0, Fired=0, Skipped=7, Incomplete=2)
Mar 10 10:57:19 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_POLICY_ENGINE [ input=I_PE_CALC cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:19 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:19 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:19 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server1: Error
Mar 10 10:57:19 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:19 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server2: Error
Mar 10 10:57:19 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2)
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: #0110 : server1
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: #0111 : server2
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:19 server2 pengine: [2407]: notice: StopRsc: server1#011Stop IPaddr2_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: StopRsc: server2#011Stop IPaddr2_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: StartRsc: server1#011Start IPaddr2_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: RecurringOp: server1#011 IPaddr2_1_monitor_5000
Mar 10 10:57:19 server2 pengine: [2407]: notice: StartRsc: server1#011Start mysql_2
Mar 10 10:57:19 server2 pengine: [2407]: notice: RecurringOp: server1#011 mysql_2_monitor_120000
Mar 10 10:57:19 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:19 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 1: 14 actions in 14 synapses
Mar 10 10:57:19 server2 tengine: [2406]: info: te_pseudo_action: Pseudo action 13 fired and confirmed
Mar 10 10:57:19 server2 tengine: [2406]: info: te_pseudo_action: Pseudo action 16 fired and confirmed
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 4: probe_complete on server2
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 5: probe_complete on server1
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 1: IPaddr2_1_stop_0 on server1
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 2: IPaddr2_1_stop_0 on server2
Mar 10 10:57:19 server2 crmd: [2393]: info: do_lrm_rsc_op: Performing op=IPaddr2_1_stop_0 key=2:1:87bd86cf-74fd-4cc0-8b99-7f543e3bccc4)
Mar 10 10:57:19 server2 lrmd: [2390]: info: rsc:IPaddr2_1: stop
Mar 10 10:57:19 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0
Mar 10 10:57:19 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1000000
Mar 10 10:57:19 server2 tengine: [2406]: info: update_abort_priority: Abort action 0 superceeded by 2
Mar 10 10:57:19 server2 lrmd: [2390]: info: RA output: (IPaddr2_1:stop:stderr) Invalid netmask specification [eth0]
Mar 10 10:57:19 server2 lrmd: [2390]: info: RA output: (IPaddr2_1:stop:stderr) #012/usr/lib/heartbeat/findif version 2.1.3 Copyright Alan Robertson#012#012Usage: /usr/lib/heartbeat/findif [-C]#012Options:#012 -C: Output netmask as the number of bits rather than as 4 octets.#012Environment variables:#012OCF_RESKEY_ip#011#011 ip address (mandatory!)#012OCF_RESKEY_cidr_netmask netmask of interface#012OCF_RESKEY_broadcast#011 broadcast address for interface#012OCF_RESKEY_nic#011#011 interface to assign to
Mar 10 10:57:19 server2 crmd: [2393]: info: process_lrm_event: LRM operation IPaddr2_1_stop_0 (call=4, rc=2) complete
Mar 10 10:57:19 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:19 server2 tengine: [2406]: WARN: status_from_rc: Action stop on server2 failed (target: <null> vs. rc: 2): Error
Mar 10 10:57:19 server2 tengine: [2406]: WARN: update_failcount: Updating failcount for IPaddr2_1 on a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0 after failed stop: rc=2
Mar 10 10:57:19 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_stop_0 (2) confirmed on server2 (rc=4)
Mar 10 10:57:19 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0
Mar 10 10:57:21 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for 7d026928-b718-4d28-b3e6-22ee3cd9ab50
Mar 10 10:57:21 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:21 server2 tengine: [2406]: WARN: status_from_rc: Action stop on server1 failed (target: <null> vs. rc: 2): Error
Mar 10 10:57:21 server2 tengine: [2406]: WARN: update_failcount: Updating failcount for IPaddr2_1 on 7d026928-b718-4d28-b3e6-22ee3cd9ab50 after failed stop: rc=2
Mar 10 10:57:21 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_stop_0 (1) confirmed on server1 (rc=4)
Mar 10 10:57:21 server2 tengine: [2406]: info: run_graph: ================================================== ==
Mar 10 10:57:21 server2 tengine: [2406]: notice: run_graph: Transition 1: (Complete=6, Pending=0, Fired=0, Skipped=8, Incomplete=0)
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_POLICY_ENGINE [ input=I_PE_CALC cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server1
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server2
Mar 10 10:57:21 server2 pengine: [2407]: info: native_add_running: resource IPaddr2_1 isnt managed
Mar 10 10:57:21 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2)
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0110 : server1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0111 : server2
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource IPaddr2_1 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource mysql_2 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 2: 0 actions in 0 synapses
Mar 10 10:57:21 server2 tengine: [2406]: info: run_graph: Transition 2: (Complete=0, Pending=0, Fired=0, Skipped=0, Incomplete=0)
Mar 10 10:57:21 server2 tengine: [2406]: info: notify_crmd: Transition 2 status: te_complete - <null>
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_IDLE [ input=I_TE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 pengine: [2407]: info: process_pe_message: Configuration WARNINGs found during PE processing. Please run "crm_verify -L" to identify issues.
Mar 10 10:57:21 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for 7d026928-b718-4d28-b3e6-22ee3cd9ab50
Mar 10 10:57:21 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1000000
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_IDLE -> S_POLICY_ENGINE [ input=I_PE_CALC cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server1
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server2
Mar 10 10:57:21 server2 pengine: [2407]: info: native_add_running: resource IPaddr2_1 isnt managed
Mar 10 10:57:21 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2)
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0110 : server1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0111 : server2
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource IPaddr2_1 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource mysql_2 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 3: 0 actions in 0 synapses
Mar 10 10:57:21 server2 tengine: [2406]: info: run_graph: Transition 3: (Complete=0, Pending=0, Fired=0, Skipped=0, Incomplete=0)
Mar 10 10:57:21 server2 tengine: [2406]: info: notify_crmd: Transition 3 status: te_complete - <null>
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_IDLE [ input=I_TE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 pengine: [2407]: info: process_pe_message: Configuration WARNINGs found during PE processing. Please run "crm_verify -L" to identify issues.
Was zur Hölle mach ich falsch????
Gruss Stefan
Server 1 eth1 192.168.1.17 Debian Lenny stable
Server 2 eth1 192.168.1.18 Debian Lenny stable
Virtuelle IP 192.168.1.253
/etc/network/interfaces Server1
# The loopback network interface
auto lo
iface lo inet loopback
# The primary network interface
allow-hotplug eth1
iface eth1 inet dhcp
auto eth0
iface eth0 inet static
address 192.168.200.1
network 192.168.200.0
netmask 255.255.255.0
broadcast 192.168.200.255
auto lo:0
iface lo:0 inet static
address 192.168.1.253
netmask 255.255.255.255
pre-up sysctl -p > /dev/null
Server2
# The loopback network interface
auto lo
iface lo inet loopback
# The primary network interface
allow-hotplug eth1
iface eth1 inet dhcp
auto eth0
iface eth0 inet static
address 192.168.200.2
network 192.168.200.0
netmask 255.255.255.0
broadcast 192.168.200.255
auto lo:0
iface lo:0 inet static
address 192.168.1.253
netmask 255.255.255.255
pre-up sysctl -p > /dev/null
Server1
/etc/ha.d/ha.cf
debugfile /var/log/ha-debug
logfile /var/log/ha-log
logfacility local0
bcast eth1
mcast eth1 225.0.0.1 694 1 0
ucast eth1 192.168.1.18
crm yes
keepalive 5
warntime 10
deadtime 120
initdead 120
auto_failback off
node server1
node server2
respawn hacluster /usr/lib/heartbeat/ipfail
apiauth ipfail gid=haclient uid=hacluster
Server1
/etc/ha.d/ha.cf
debugfile /var/log/ha-debug
logfile /var/log/ha-log
logfacility local0
bcast eth1
mcast eth1 225.0.0.1 694 1 0
ucast eth1 192.168.1.18
crm yes
keepalive 5
warntime 10
deadtime 120
initdead 120
auto_failback off
node server1
node server2
respawn hacluster /usr/lib/heartbeat/ipfail
apiauth ipfail gid=haclient uid=hacluster
Server1/2
/etc/ha.d/haresources
muss da als erstes Wort (Server1) nur ein Node stehen? oder der jeweisl andere oder ...
server1 \
IPaddr2::192.168.1.253/24/eth0/192.168.1.255 mysql
/etc/ha.d/authkeys
Server1/2
auth 3
#1 sha1 passworthiereingeben
#2 md5 passworthiereingeben
3 crc
Mit dem Script
/usr/lib/heartbeat/haresources2cib.py /etc/ha.d/haresources
habe ich die haresources in die cib.xml konvertiert, vorher natuerlich die cib.xml und die cib.xml.sig geloescht.
cib.xml
<cib admin_epoch="0" epoch="1" have_quorum="false" ignore_dtd="false" num_peers="2" cib_feature_revision="2.0" generated="false" num_updates="4" cib-last-written="Wed Mar 10 10:55:06 2010">
<configuration>
<crm_config>
<cluster_property_set id="cib-bootstrap-options">
<attributes>
<nvpair id="cib-bootstrap-options-symmetric-cluster" name="symmetric-cluster" value="true"/>
<nvpair id="cib-bootstrap-options-no-quorum-policy" name="no-quorum-policy" value="stop"/>
<nvpair id="cib-bootstrap-options-default-resource-stickiness" name="default-resource-stickiness" value="0"/>
<nvpair id="cib-bootstrap-options-default-resource-failure-stickiness" name="default-resource-failure-stickiness" value="0"/>
<nvpair id="cib-bootstrap-options-stonith-enabled" name="stonith-enabled" value="false"/>
<nvpair id="cib-bootstrap-options-stonith-action" name="stonith-action" value="reboot"/>
<nvpair id="cib-bootstrap-options-startup-fencing" name="startup-fencing" value="true"/>
<nvpair id="cib-bootstrap-options-stop-orphan-resources" name="stop-orphan-resources" value="true"/>
<nvpair id="cib-bootstrap-options-stop-orphan-actions" name="stop-orphan-actions" value="true"/>
<nvpair id="cib-bootstrap-options-remove-after-stop" name="remove-after-stop" value="false"/>
<nvpair id="cib-bootstrap-options-short-resource-names" name="short-resource-names" value="true"/>
<nvpair id="cib-bootstrap-options-transition-idle-timeout" name="transition-idle-timeout" value="5min"/>
<nvpair id="cib-bootstrap-options-default-action-timeout" name="default-action-timeout" value="20s"/>
<nvpair id="cib-bootstrap-options-is-managed-default" name="is-managed-default" value="true"/>
<nvpair id="cib-bootstrap-options-cluster-delay" name="cluster-delay" value="60s"/>
<nvpair id="cib-bootstrap-options-pe-error-series-max" name="pe-error-series-max" value="-1"/>
<nvpair id="cib-bootstrap-options-pe-warn-series-max" name="pe-warn-series-max" value="-1"/>
<nvpair id="cib-bootstrap-options-pe-input-series-max" name="pe-input-series-max" value="-1"/>
<nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="2.1.3-node: 552305612591183b1628baa5bc6e903e0f1e26a3"/>
</attributes>
</cluster_property_set>
</crm_config>
<nodes>
<node id="a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0" uname="server2" type="normal"/>
<node id="7d026928-b718-4d28-b3e6-22ee3cd9ab50" uname="server1" type="normal"/>
</nodes>
<resources>
<group id="group_1">
<primitive class="ocf" id="IPaddr2_1" provider="heartbeat" type="IPaddr2">
<operations>
<op id="IPaddr2_1_mon" interval="5s" name="monitor" timeout="5s"/>
</operations>
<instance_attributes id="IPaddr2_1_inst_attr">
<attributes>
<nvpair id="IPaddr2_1_attr_0" name="ip" value="192.168.1.253"/>
<nvpair id="IPaddr2_1_attr_1" name="nic" value="24"/>
<nvpair id="IPaddr2_1_attr_2" name="cidr_netmask" value="eth0"/>
<nvpair id="IPaddr2_1_attr_3" name="broadcast" value="192.168.1.255"/>
</attributes>
</instance_attributes>
</primitive>
<primitive class="ocf" id="mysql_2" provider="heartbeat" type="mysql">
<operations>
<op id="mysql_2_mon" interval="120s" name="monitor" timeout="60s"/>
</operations>
</primitive>
</group>
</resources>
<constraints>
<rsc_location id="rsc_location_group_1" rsc="group_1">
<rule id="prefered_location_group_1" score="100">
<expression attribute="#uname" id="prefered_location_group_1_expr" operation="eq" value="server1"/>
</rule>
</rsc_location>
</constraints>
</configuration>
</cib>
/var/log/messages
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml (digest: /var/lib/heartbeat/crm/cib.xml.sig)
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml.last (digest: /var/lib/heartbeat/crm/cib.xml.sig.last)
Mar 10 10:55:03 server2 crmd: [2393]: info: do_cib_control: CIB connection established
Mar 10 10:55:03 server2 crmd: [2393]: info: register_with_ha: Hostname: server2
Mar 10 10:55:03 server2 cib: [2389]: info: cib_client_status_callback: Status update: Client server2/cib now has status [join]
Mar 10 10:55:03 server2 cib: [2389]: info: cib_client_status_callback: Status update: Client server2/cib now has status [online]
Mar 10 10:55:03 server2 cib: [2389]: info: cib_null_callback: Setting cib_diff_notify callbacks for mgmtd: on
Mar 10 10:55:03 server2 cib: [2389]: info: cib_null_callback: Setting cib_refresh_notify callbacks for crmd: on
Mar 10 10:55:03 server2 cib: [2398]: info: write_cib_contents: Wrote version 0.1.1 of the CIB to disk (digest: 94547266cef61ee87acef8a5225147a3)
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml (digest: /var/lib/heartbeat/crm/cib.xml.sig)
Mar 10 10:55:03 server2 cib: [2398]: info: retrieveCib: Reading cluster configuration from: /var/lib/heartbeat/crm/cib.xml.last (digest: /var/lib/heartbeat/crm/cib.xml.sig.last)
Mar 10 10:55:03 server2 crmd: [2393]: info: register_with_ha: UUID: a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0
Mar 10 10:55:03 server2 cib: [2389]: info: cib_client_status_callback: Status update: Client server1/cib now has status [online]
Mar 10 10:55:04 server2 crmd: [2393]: info: populate_cib_nodes: Requesting the list of configured nodes
Mar 10 10:55:05 server2 mgmtd: [2394]: info: Started.
Mar 10 10:55:05 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server2 (uuid: a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0)
Mar 10 10:55:05 server2 ccm: [2388]: info: Break tie for 2 nodes cluster
Mar 10 10:55:05 server2 cib: [2389]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:05 server2 cib: [2389]: info: mem_handle_event: instance=1, nodes=1, new=1, lost=0, n_idx=0, new_idx=0, old_idx=3
Mar 10 10:55:05 server2 cib: [2389]: info: cib_ccm_msg_callback: PEER: server2
Mar 10 10:55:06 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server1 (uuid: 7d026928-b718-4d28-b3e6-22ee3cd9ab50)
Mar 10 10:55:06 server2 crmd: [2393]: info: do_ha_control: Connected to Heartbeat
Mar 10 10:55:06 server2 crmd: [2393]: info: do_ccm_control: CCM connection established... waiting for first callback
Mar 10 10:55:06 server2 crmd: [2393]: info: do_started: Delaying start, CCM (0000000000100000) not connected
Mar 10 10:55:06 server2 crmd: [2393]: info: crmd_init: Starting crmd's mainloop
Mar 10 10:55:06 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server2/crmd now has status [online]
Mar 10 10:55:06 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server2/crmd now has status [online]
Mar 10 10:55:07 server2 heartbeat: [2321]: WARN: 1 lost packet(s) for [server1] [19:21]
Mar 10 10:55:07 server2 heartbeat: [2321]: info: No pkts missing from server1!
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: Got an event OC_EV_MS_INVALID from ccm
Mar 10 10:55:07 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server1/crmd now has status [offline]
Mar 10 10:55:07 server2 crmd: [2393]: notice: crmd_client_status_callback: Status update: Client server1/crmd now has status [online]
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: no mbr_track info
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:07 server2 cib: [2389]: info: mem_handle_event: instance=2, nodes=2, new=1, lost=0, n_idx=0, new_idx=2, old_idx=4
Mar 10 10:55:07 server2 cib: [2389]: info: cib_ccm_msg_callback: PEER: server2
Mar 10 10:55:07 server2 cib: [2389]: info: cib_ccm_msg_callback: PEER: server1
Mar 10 10:55:07 server2 crmd: [2393]: info: do_started: Delaying start, CCM (0000000000100000) not connected
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: instance=1, nodes=1, new=1, lost=0, n_idx=0, new_idx=0, old_idx=3
Mar 10 10:55:07 server2 crmd: [2393]: info: crmd_ccm_msg_callback: Quorum (re)attained after event=NEW MEMBERSHIP (id=1)
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: Got an event OC_EV_MS_INVALID from ccm
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: no mbr_track info
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: Got an event OC_EV_MS_NEW_MEMBERSHIP from ccm
Mar 10 10:55:07 server2 crmd: [2393]: info: mem_handle_event: instance=2, nodes=2, new=1, lost=0, n_idx=0, new_idx=2, old_idx=4
Mar 10 10:55:07 server2 crmd: [2393]: info: crmd_ccm_msg_callback: Quorum (re)attained after event=NEW MEMBERSHIP (id=2)
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: NEW MEMBERSHIP: trans=2, nodes=2, new=1, lost=0 n_idx=0, new_idx=2, old_idx=4
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011CURRENT: server2 [nodeid=1, born=1]
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011CURRENT: server1 [nodeid=0, born=2]
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011NEW: server1 [nodeid=0, born=2]
Mar 10 10:55:07 server2 crmd: [2393]: info: do_started: The local CRM is operational
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: NEW MEMBERSHIP: trans=1, nodes=1, new=1, lost=0 n_idx=0, new_idx=0, old_idx=3
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011CURRENT: server2 [nodeid=1, born=1]
Mar 10 10:55:07 server2 crmd: [2393]: info: ccm_event_detail: #011NEW: server2 [nodeid=1, born=1]
Mar 10 10:55:07 server2 crmd: [2393]: info: do_state_transition: State transition S_STARTING -> S_PENDING [ input=I_PENDING cause=C_CCM_CALLBACK origin=do_started ]
Mar 10 10:55:07 server2 heartbeat: [2321]: WARN: 1 lost packet(s) for [server1] [22:24]
Mar 10 10:55:07 server2 heartbeat: [2321]: info: No pkts missing from server1!
Mar 10 10:55:10 server2 attrd: [2392]: info: main: Starting mainloop...
Mar 10 10:57:08 server2 crmd: [2393]: info: crm_timer_popped: Election Trigger (I_DC_TIMEOUT) just popped!
Mar 10 10:57:08 server2 crmd: [2393]: WARN: do_log: [[FSA]] Input I_DC_TIMEOUT from crm_timer_popped() received in state (S_PENDING)
Mar 10 10:57:08 server2 crmd: [2393]: info: do_state_transition: State transition S_PENDING -> S_ELECTION [ input=I_DC_TIMEOUT cause=C_TIMER_POPPED origin=crm_timer_popped ]
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server2 to vote
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: our vote (server2)
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_check: Still waiting on 1 non-votes (2 total)
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server1 to no-vote
Mar 10 10:57:08 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: no-vote from server1
Mar 10 10:57:08 server2 crmd: [2393]: info: do_state_transition: State transition S_ELECTION -> S_INTEGRATION [ input=I_ELECTION_DC cause=C_FSA_INTERNAL origin=do_election_check ]
Mar 10 10:57:08 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "tengine"
Mar 10 10:57:08 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "pengine"
Mar 10 10:57:08 server2 crmd: [2393]: info: do_dc_takeover: Taking over DC status for this partition
Mar 10 10:57:09 server2 cib: [2389]: info: cib_process_readwrite: We are now in R/W mode
Mar 10 10:57:09 server2 crmd: [2393]: info: join_make_offer: Making join offers based on membership 2
Mar 10 10:57:09 server2 crmd: [2393]: info: do_dc_join_offer_all: join-1: Waiting on 2 outstanding join acks
Mar 10 10:57:09 server2 tengine: [2406]: info: G_main_add_SignalHandler: Added signal handler for signal 15
Mar 10 10:57:09 server2 tengine: [2406]: info: G_main_add_TriggerHandler: Added signal manual handler
Mar 10 10:57:09 server2 tengine: [2406]: info: G_main_add_TriggerHandler: Added signal manual handler
Mar 10 10:57:09 server2 tengine: [2406]: info: te_init: Registering TE UUID: 87bd86cf-74fd-4cc0-8b99-7f543e3bccc4
Mar 10 10:57:09 server2 tengine: [2406]: info: set_graph_functions: Setting custom graph functions
Mar 10 10:57:09 server2 tengine: [2406]: info: unpack_graph: Unpacked transition -1: 0 actions in 0 synapses
Mar 10 10:57:09 server2 tengine: [2406]: info: te_init: Starting tengine
Mar 10 10:57:09 server2 tengine: [2406]: info: te_connect_stonith: Attempting connection to fencing daemon...
Mar 10 10:57:09 server2 cib: [2389]: info: cib_null_callback: Setting cib_diff_notify callbacks for tengine: on
Mar 10 10:57:09 server2 pengine: [2407]: info: G_main_add_SignalHandler: Added signal handler for signal 15
Mar 10 10:57:09 server2 pengine: [2407]: info: pe_init: Starting pengine
Mar 10 10:57:09 server2 crmd: [2393]: info: update_dc: Set DC to server2 (2.0)
Mar 10 10:57:10 server2 tengine: [2406]: info: te_connect_stonith: Connected
Mar 10 10:57:10 server2 crmd: [2393]: info: do_state_transition: State transition S_INTEGRATION -> S_FINALIZE_JOIN [ input=I_INTEGRATED cause=C_FSA_INTERNAL origin=check_join_state ]
Mar 10 10:57:10 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes responded to the join offer.
Mar 10 10:57:10 server2 crmd: [2393]: info: do_dc_join_finalize: join-1: Asking server1 for its copy of the CIB
Mar 10 10:57:12 server2 cib: [2389]: info: cib_replace_notify: Replaced: 0.1.3 -> 0.1.4 from <null>
Mar 10 10:57:12 server2 crmd: [2393]: info: populate_cib_nodes: Requesting the list of configured nodes
Mar 10 10:57:12 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server2 (uuid: a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0)
Mar 10 10:57:13 server2 crmd: [2393]: notice: populate_cib_nodes: Node: server1 (uuid: 7d026928-b718-4d28-b3e6-22ee3cd9ab50)
Mar 10 10:57:13 server2 crmd: [2393]: info: update_attrd: Connecting to attrd...
Mar 10 10:57:13 server2 crmd: [2393]: info: do_state_transition: State transition S_FINALIZE_JOIN -> S_ELECTION [ input=I_ELECTION cause=C_FSA_INTERNAL origin=do_cib_replaced ]
Mar 10 10:57:13 server2 crmd: [2393]: info: update_dc: Unset DC server2
Mar 10 10:57:13 server2 attrd: [2392]: info: attrd_local_callback: Sending full refresh
Mar 10 10:57:13 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server2 to vote
Mar 10 10:57:13 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: our vote (server2)
Mar 10 10:57:13 server2 crmd: [2393]: info: do_election_check: Still waiting on 1 non-votes (2 total)
Mar 10 10:57:14 server2 crmd: [2393]: info: do_election_count_vote: Updated voted hash for server1 to no-vote
Mar 10 10:57:14 server2 crmd: [2393]: info: do_election_count_vote: Election ignore: no-vote from server1
Mar 10 10:57:14 server2 crmd: [2393]: info: do_state_transition: State transition S_ELECTION -> S_INTEGRATION [ input=I_ELECTION_DC cause=C_FSA_INTERNAL origin=do_election_check ]
Mar 10 10:57:14 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "tengine"
Mar 10 10:57:14 server2 crmd: [2393]: WARN: start_subsystem: Client tengine already running as pid 2406
Mar 10 10:57:14 server2 crmd: [2393]: info: start_subsystem: Starting sub-system "pengine"
Mar 10 10:57:14 server2 crmd: [2393]: WARN: start_subsystem: Client pengine already running as pid 2407
Mar 10 10:57:14 server2 crmd: [2393]: info: do_dc_takeover: Taking over DC status for this partition
Mar 10 10:57:14 server2 cib: [2389]: info: cib_process_readwrite: We are now in R/O mode
Mar 10 10:57:14 server2 cib: [2389]: info: cib_process_readwrite: We are now in R/W mode
Mar 10 10:57:14 server2 crmd: [2393]: info: do_dc_join_offer_all: join-2: Waiting on 2 outstanding join acks
Mar 10 10:57:15 server2 crmd: [2393]: info: update_dc: Set DC to server2 (2.0)
Mar 10 10:57:16 server2 crmd: [2393]: info: do_state_transition: State transition S_INTEGRATION -> S_FINALIZE_JOIN [ input=I_INTEGRATED cause=C_FSA_INTERNAL origin=check_join_state ]
Mar 10 10:57:16 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes responded to the join offer.
Mar 10 10:57:16 server2 attrd: [2392]: info: attrd_local_callback: Sending full refresh
Mar 10 10:57:16 server2 cib: [2389]: info: sync_our_cib: Syncing CIB to all peers
Mar 10 10:57:16 server2 crmd: [2393]: info: update_dc: Set DC to server2 (2.0)
Mar 10 10:57:17 server2 crmd: [2393]: info: do_dc_join_ack: join-2: Updating node state to member for server2
Mar 10 10:57:18 server2 crmd: [2393]: info: do_dc_join_ack: join-2: Updating node state to member for server1
Mar 10 10:57:18 server2 crmd: [2393]: info: do_state_transition: State transition S_FINALIZE_JOIN -> S_POLICY_ENGINE [ input=I_FINALIZED cause=C_FSA_INTERNAL origin=check_join_state ]
Mar 10 10:57:18 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1000000
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: 'DC Takeover' abort superceeded
Mar 10 10:57:18 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:18 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:18 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:18 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2):#011Stopped
Mar 10 10:57:18 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:18 server2 pengine: [2407]: notice: StartRsc: server1#011Start IPaddr2_1
Mar 10 10:57:18 server2 pengine: [2407]: notice: RecurringOp: server1#011 IPaddr2_1_monitor_5000
Mar 10 10:57:18 server2 pengine: [2407]: notice: StartRsc: server1#011Start mysql_2
Mar 10 10:57:18 server2 pengine: [2407]: notice: RecurringOp: server1#011 mysql_2_monitor_120000
Mar 10 10:57:18 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:18 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 0: 13 actions in 13 synapses
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 3: IPaddr2_1_monitor_0 on server2
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 6: IPaddr2_1_monitor_0 on server1
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 4: mysql_2_monitor_0 on server2
Mar 10 10:57:18 server2 tengine: [2406]: info: send_rsc_command: Initiating action 7: mysql_2_monitor_0 on server1
Mar 10 10:57:18 server2 crmd: [2393]: info: do_lrm_rsc_op: Performing op=IPaddr2_1_monitor_0 key=3:0:87bd86cf-74fd-4cc0-8b99-7f543e3bccc4)
Mar 10 10:57:18 server2 lrmd: [2390]: info: rsc:IPaddr2_1: monitor
Mar 10 10:57:18 server2 crmd: [2393]: info: do_lrm_rsc_op: Performing op=mysql_2_monitor_0 key=4:0:87bd86cf-74fd-4cc0-8b99-7f543e3bccc4)
Mar 10 10:57:18 server2 lrmd: [2390]: info: rsc:mysql_2: monitor
Mar 10 10:57:18 server2 pengine: [2407]: info: process_pe_message: Transition 0: PEngine Input stored in: /var/lib/heartbeat/pengine/pe-input-11.bz2
Mar 10 10:57:18 server2 crmd: [2393]: info: process_lrm_event: LRM operation mysql_2_monitor_0 (call=3, rc=7) complete
Mar 10 10:57:18 server2 tengine: [2406]: info: match_graph_event: Action mysql_2_monitor_0 (4) confirmed on server2 (rc=0)
Mar 10 10:57:18 server2 lrmd: [2390]: info: RA output: (IPaddr2_1:monitor:stderr) Invalid netmask specification [eth0]#012/usr/lib/heartbeat/findif version 2.1.3 Copyright Alan Robertson#012#012Usage: /usr/lib/heartbeat/findif [-C]#012Options:#012 -C: Output netmask as the number of bits rather than as 4 octets.#012Environment variables:#012OCF_RESKEY_ip#011#011 ip address (mandatory!)#012OCF_RESKEY_cidr_netmask netmask of interface#012OCF_RESKEY_broadcast#011 broadcast address for interface#012OCF_RESKEY_nic#011#011 interface to assign to
Mar 10 10:57:18 server2 crmd: [2393]: info: process_lrm_event: LRM operation IPaddr2_1_monitor_0 (call=2, rc=2) complete
Mar 10 10:57:18 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:18 server2 tengine: [2406]: WARN: status_from_rc: Action monitor on server2 failed (target: 7 vs. rc: 2): Error
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1
Mar 10 10:57:18 server2 tengine: [2406]: info: update_abort_priority: Abort action 0 superceeded by 2
Mar 10 10:57:18 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_monitor_0 (3) confirmed on server2 (rc=4)
Mar 10 10:57:19 server2 tengine: [2406]: info: match_graph_event: Action mysql_2_monitor_0 (7) confirmed on server1 (rc=0)
Mar 10 10:57:19 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:19 server2 tengine: [2406]: WARN: status_from_rc: Action monitor on server1 failed (target: 7 vs. rc: 2): Error
Mar 10 10:57:19 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_monitor_0 (6) confirmed on server1 (rc=4)
Mar 10 10:57:19 server2 tengine: [2406]: info: run_graph: ================================================== ==
Mar 10 10:57:19 server2 tengine: [2406]: notice: run_graph: Transition 0: (Complete=4, Pending=0, Fired=0, Skipped=7, Incomplete=2)
Mar 10 10:57:19 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_POLICY_ENGINE [ input=I_PE_CALC cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:19 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:19 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:19 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server1: Error
Mar 10 10:57:19 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:19 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server2: Error
Mar 10 10:57:19 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2)
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: #0110 : server1
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: #0111 : server2
Mar 10 10:57:19 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:19 server2 pengine: [2407]: notice: StopRsc: server1#011Stop IPaddr2_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: StopRsc: server2#011Stop IPaddr2_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: StartRsc: server1#011Start IPaddr2_1
Mar 10 10:57:19 server2 pengine: [2407]: notice: RecurringOp: server1#011 IPaddr2_1_monitor_5000
Mar 10 10:57:19 server2 pengine: [2407]: notice: StartRsc: server1#011Start mysql_2
Mar 10 10:57:19 server2 pengine: [2407]: notice: RecurringOp: server1#011 mysql_2_monitor_120000
Mar 10 10:57:19 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:19 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 1: 14 actions in 14 synapses
Mar 10 10:57:19 server2 tengine: [2406]: info: te_pseudo_action: Pseudo action 13 fired and confirmed
Mar 10 10:57:19 server2 tengine: [2406]: info: te_pseudo_action: Pseudo action 16 fired and confirmed
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 4: probe_complete on server2
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 5: probe_complete on server1
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 1: IPaddr2_1_stop_0 on server1
Mar 10 10:57:19 server2 tengine: [2406]: info: send_rsc_command: Initiating action 2: IPaddr2_1_stop_0 on server2
Mar 10 10:57:19 server2 crmd: [2393]: info: do_lrm_rsc_op: Performing op=IPaddr2_1_stop_0 key=2:1:87bd86cf-74fd-4cc0-8b99-7f543e3bccc4)
Mar 10 10:57:19 server2 lrmd: [2390]: info: rsc:IPaddr2_1: stop
Mar 10 10:57:19 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0
Mar 10 10:57:19 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1000000
Mar 10 10:57:19 server2 tengine: [2406]: info: update_abort_priority: Abort action 0 superceeded by 2
Mar 10 10:57:19 server2 lrmd: [2390]: info: RA output: (IPaddr2_1:stop:stderr) Invalid netmask specification [eth0]
Mar 10 10:57:19 server2 lrmd: [2390]: info: RA output: (IPaddr2_1:stop:stderr) #012/usr/lib/heartbeat/findif version 2.1.3 Copyright Alan Robertson#012#012Usage: /usr/lib/heartbeat/findif [-C]#012Options:#012 -C: Output netmask as the number of bits rather than as 4 octets.#012Environment variables:#012OCF_RESKEY_ip#011#011 ip address (mandatory!)#012OCF_RESKEY_cidr_netmask netmask of interface#012OCF_RESKEY_broadcast#011 broadcast address for interface#012OCF_RESKEY_nic#011#011 interface to assign to
Mar 10 10:57:19 server2 crmd: [2393]: info: process_lrm_event: LRM operation IPaddr2_1_stop_0 (call=4, rc=2) complete
Mar 10 10:57:19 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:19 server2 tengine: [2406]: WARN: status_from_rc: Action stop on server2 failed (target: <null> vs. rc: 2): Error
Mar 10 10:57:19 server2 tengine: [2406]: WARN: update_failcount: Updating failcount for IPaddr2_1 on a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0 after failed stop: rc=2
Mar 10 10:57:19 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_stop_0 (2) confirmed on server2 (rc=4)
Mar 10 10:57:19 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for a8cc6b4a-9b5d-409f-8654-8e2a90cbf1e0
Mar 10 10:57:21 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for 7d026928-b718-4d28-b3e6-22ee3cd9ab50
Mar 10 10:57:21 server2 tengine: [2406]: info: status_from_rc: Re-mapping op status to LRM_OP_ERROR for rc=2
Mar 10 10:57:21 server2 tengine: [2406]: WARN: status_from_rc: Action stop on server1 failed (target: <null> vs. rc: 2): Error
Mar 10 10:57:21 server2 tengine: [2406]: WARN: update_failcount: Updating failcount for IPaddr2_1 on 7d026928-b718-4d28-b3e6-22ee3cd9ab50 after failed stop: rc=2
Mar 10 10:57:21 server2 tengine: [2406]: info: match_graph_event: Action IPaddr2_1_stop_0 (1) confirmed on server1 (rc=4)
Mar 10 10:57:21 server2 tengine: [2406]: info: run_graph: ================================================== ==
Mar 10 10:57:21 server2 tengine: [2406]: notice: run_graph: Transition 1: (Complete=6, Pending=0, Fired=0, Skipped=8, Incomplete=0)
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_POLICY_ENGINE [ input=I_PE_CALC cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server1
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server2
Mar 10 10:57:21 server2 pengine: [2407]: info: native_add_running: resource IPaddr2_1 isnt managed
Mar 10 10:57:21 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2)
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0110 : server1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0111 : server2
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource IPaddr2_1 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource mysql_2 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 2: 0 actions in 0 synapses
Mar 10 10:57:21 server2 tengine: [2406]: info: run_graph: Transition 2: (Complete=0, Pending=0, Fired=0, Skipped=0, Incomplete=0)
Mar 10 10:57:21 server2 tengine: [2406]: info: notify_crmd: Transition 2 status: te_complete - <null>
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_IDLE [ input=I_TE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 pengine: [2407]: info: process_pe_message: Configuration WARNINGs found during PE processing. Please run "crm_verify -L" to identify issues.
Mar 10 10:57:21 server2 tengine: [2406]: info: extract_event: Aborting on transient_attributes changes for 7d026928-b718-4d28-b3e6-22ee3cd9ab50
Mar 10 10:57:21 server2 tengine: [2406]: info: update_abort_priority: Abort priority upgraded to 1000000
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_IDLE -> S_POLICY_ENGINE [ input=I_PE_CALC cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: All 2 cluster nodes are eligible to run resources.
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server1 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server1: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server1
Mar 10 10:57:21 server2 pengine: [2407]: info: determine_online_status: Node server2 is online
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_monitor_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Processing failed op IPaddr2_1_stop_0 on server2: Error
Mar 10 10:57:21 server2 pengine: [2407]: WARN: unpack_rsc_op: Compatability handling for failed op IPaddr2_1_stop_0 on server2
Mar 10 10:57:21 server2 pengine: [2407]: info: native_add_running: resource IPaddr2_1 isnt managed
Mar 10 10:57:21 server2 pengine: [2407]: notice: group_print: Resource Group: group_1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: IPaddr2_1#011(heartbeat::ocf:IPaddr2)
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0110 : server1
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: #0111 : server2
Mar 10 10:57:21 server2 pengine: [2407]: notice: native_print: mysql_2#011(heartbeat::ocf:mysql):#011Stopped
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource IPaddr2_1 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: native_color: Resource mysql_2 cannot run anywhere
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 pengine: [2407]: WARN: custom_action: Action IPaddr2_1_stop_0 (unmanaged)
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_POLICY_ENGINE -> S_TRANSITION_ENGINE [ input=I_PE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 tengine: [2406]: info: unpack_graph: Unpacked transition 3: 0 actions in 0 synapses
Mar 10 10:57:21 server2 tengine: [2406]: info: run_graph: Transition 3: (Complete=0, Pending=0, Fired=0, Skipped=0, Incomplete=0)
Mar 10 10:57:21 server2 tengine: [2406]: info: notify_crmd: Transition 3 status: te_complete - <null>
Mar 10 10:57:21 server2 crmd: [2393]: info: do_state_transition: State transition S_TRANSITION_ENGINE -> S_IDLE [ input=I_TE_SUCCESS cause=C_IPC_MESSAGE origin=route_message ]
Mar 10 10:57:21 server2 pengine: [2407]: info: process_pe_message: Configuration WARNINGs found during PE processing. Please run "crm_verify -L" to identify issues.
Was zur Hölle mach ich falsch????
Gruss Stefan