LOG NODE1 Feb 3 17:48:03 wsguardian1 kernel: e1000e: eth4 NIC Link is Down Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: PingAck did not arrive in time. Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: peer( Primary -> Unknown ) conn( Connected -> NetworkFailure ) pdsk( UpToDate -> DUnknown ) susp( 0 -> 1 ) Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: asender terminated Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: Terminating asender thread Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: Connection closed Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: conn( NetworkFailure -> Unconnected ) Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: receiver terminated Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: Restarting receiver thread Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: receiver (re)started Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: conn( Unconnected -> WFConnection ) Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_db: helper command: /sbin/drbdadm fence-peer wsg_db Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: PingAck did not arrive in time. Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: peer( Primary -> Unknown ) conn( Connected -> NetworkFailure ) pdsk( UpToDate -> DUnknown ) susp( 0 -> 1 ) Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: asender terminated Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: Terminating asender thread Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: Connection closed Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: conn( NetworkFailure -> Unconnected ) Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: receiver terminated Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: Restarting receiver thread Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: receiver (re)started Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: conn( Unconnected -> WFConnection ) Feb 3 17:48:13 wsguardian1 kernel: d-con wsg_config: helper command: /sbin/drbdadm fence-peer wsg_config Feb 3 17:48:13 wsguardian1 rhcs_fence: 125; DEBUG: Checking if: [uname] is at: [/bin/uname] Feb 3 17:48:13 wsguardian1 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian1 rhcs_fence: 125; DEBUG: Checking if: [fence_node] is at: [/usr/sbin/fence_node] Feb 3 17:48:13 wsguardian1 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian1 rhcs_fence: 125; DEBUG: Checking if: [cman_tool] is at: [/usr/sbin/cman_tool] Feb 3 17:48:13 wsguardian1 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian1 rhcs_fence: 74; Attempting to fence peer using RHCS from DRBD... Feb 3 17:48:13 wsguardian1 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_RESOURCE] == [wsg_config] Feb 3 17:48:13 wsguardian1 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_MINOR] == [1] Feb 3 17:48:13 wsguardian1 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_PEERS] == [wsguardian2] Feb 3 17:48:13 wsguardian1 rhcs_fence: 454; DEBUG: shell call: [/usr/sbin/cman_tool status] Feb 3 17:48:13 wsguardian1 rhcs_fence: 125; DEBUG: Checking if: [uname] is at: [/bin/uname] Feb 3 17:48:13 wsguardian1 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian1 rhcs_fence: 125; DEBUG: Checking if: [fence_node] is at: [/usr/sbin/fence_node] Feb 3 17:48:13 wsguardian1 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian1 rhcs_fence: 125; DEBUG: Checking if: [cman_tool] is at: [/usr/sbin/cman_tool] Feb 3 17:48:13 wsguardian1 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian1 rhcs_fence: 74; Attempting to fence peer using RHCS from DRBD... Feb 3 17:48:13 wsguardian1 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_RESOURCE] == [wsg_db] Feb 3 17:48:13 wsguardian1 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_MINOR] == [0] Feb 3 17:48:13 wsguardian1 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_PEERS] == [wsguardian2] Feb 3 17:48:13 wsguardian1 rhcs_fence: 454; DEBUG: shell call: [/usr/sbin/cman_tool status] Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Version: 6.2.0 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Config Version: 2 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Name: WSGClust Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Id: 30485 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Member: Yes Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Generation: 28 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Membership state: Cluster-Member Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Nodes: 2 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Expected votes: 1 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Total votes: 2 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Version: 6.2.0 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Node votes: 1 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Config Version: 2 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Quorum: 1 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Active subsystems: 7 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Name: WSGClust Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Flags: 2node Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Id: 30485 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Ports Bound: 0 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Member: Yes Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Node name: wsguardian1 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Cluster Generation: 28 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Membership state: Cluster-Member Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Nodes: 2 Feb 3 17:48:13 wsguardian1 rhcs_fence: 469; DEBUG: Attempt to get local node name via 'cman_tool status' exited with: [0] Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Expected votes: 1 Feb 3 17:48:13 wsguardian1 rhcs_fence: 471; DEBUG: I am: [wsguardian1] Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Total votes: 2 Feb 3 17:48:13 wsguardian1 rhcs_fence: 403; DEBUG: Checking the state of resource with minor number: [1] Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Node votes: 1 Feb 3 17:48:13 wsguardian1 rhcs_fence: 409; DEBUG: minor: [1] Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Quorum: 1 Feb 3 17:48:13 wsguardian1 rhcs_fence: 460; DEBUG: output: Active subsystems: 7 Feb 3 17:48:13 wsguardian1 rhcs_fence: 412; DEBUG: shell call: [ Unknown ) conn( Connected -> NetworkFailure ) pdsk( UpToDate -> DUnknown ) susp( 0 -> 1 ) Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: asender terminated Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: Terminating asender thread Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: Connection closed Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: conn( NetworkFailure -> Unconnected ) Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: receiver terminated Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: Restarting receiver thread Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: receiver (re)started Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: conn( Unconnected -> WFConnection ) Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_db: helper command: /sbin/drbdadm fence-peer wsg_db Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: PingAck did not arrive in time. Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: peer( Primary -> Unknown ) conn( Connected -> NetworkFailure ) pdsk( UpToDate -> DUnknown ) susp( 0 -> 1 ) Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: asender terminated Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: Terminating asender thread Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: Connection closed Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: conn( NetworkFailure -> Unconnected ) Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: receiver terminated Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: Restarting receiver thread Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: receiver (re)started Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: conn( Unconnected -> WFConnection ) Feb 3 17:48:13 wsguardian2 kernel: d-con wsg_config: helper command: /sbin/drbdadm fence-peer wsg_config Feb 3 17:48:13 wsguardian2 rhcs_fence: 125; DEBUG: Checking if: [uname] is at: [/bin/uname] Feb 3 17:48:13 wsguardian2 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian2 rhcs_fence: 125; DEBUG: Checking if: [fence_node] is at: [/usr/sbin/fence_node] Feb 3 17:48:13 wsguardian2 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian2 rhcs_fence: 125; DEBUG: Checking if: [cman_tool] is at: [/usr/sbin/cman_tool] Feb 3 17:48:13 wsguardian2 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian2 rhcs_fence: 74; Attempting to fence peer using RHCS from DRBD... Feb 3 17:48:13 wsguardian2 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_RESOURCE] == [wsg_config] Feb 3 17:48:13 wsguardian2 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_MINOR] == [1] Feb 3 17:48:13 wsguardian2 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_PEERS] == [wsguardian1] Feb 3 17:48:13 wsguardian2 rhcs_fence: 454; DEBUG: shell call: [/usr/sbin/cman_tool status] Feb 3 17:48:13 wsguardian2 rhcs_fence: 125; DEBUG: Checking if: [uname] is at: [/bin/uname] Feb 3 17:48:13 wsguardian2 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian2 rhcs_fence: 125; DEBUG: Checking if: [fence_node] is at: [/usr/sbin/fence_node] Feb 3 17:48:13 wsguardian2 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian2 rhcs_fence: 125; DEBUG: Checking if: [cman_tool] is at: [/usr/sbin/cman_tool] Feb 3 17:48:13 wsguardian2 rhcs_fence: 156; DEBUG: Found! Feb 3 17:48:13 wsguardian2 rhcs_fence: 74; Attempting to fence peer using RHCS from DRBD... Feb 3 17:48:13 wsguardian2 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_RESOURCE] == [wsg_db] Feb 3 17:48:13 wsguardian2 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_MINOR] == [0] Feb 3 17:48:13 wsguardian2 rhcs_fence: 80; DEBUG: Environment variable: [DRBD_PEERS] == [wsguardian1] Feb 3 17:48:13 wsguardian2 rhcs_fence: 454; DEBUG: shell call: [/usr/sbin/cman_tool status] Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Version: 6.2.0 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Config Version: 2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Name: WSGClust Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Id: 30485 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Member: Yes Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Generation: 28 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Membership state: Cluster-Member Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Nodes: 2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Version: 6.2.0 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Expected votes: 1 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Total votes: 2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Config Version: 2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Node votes: 1 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Name: WSGClust Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Quorum: 1 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Id: 30485 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Active subsystems: 7 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Member: Yes Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Flags: 2node Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Cluster Generation: 28 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Membership state: Cluster-Member Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Ports Bound: 0 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Nodes: 2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Node name: wsguardian2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Expected votes: 1 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Total votes: 2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 469; DEBUG: Attempt to get local node name via 'cman_tool status' exited with: [0] Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Node votes: 1 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Quorum: 1 Feb 3 17:48:13 wsguardian2 rhcs_fence: 471; DEBUG: I am: [wsguardian2] Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Active subsystems: 7 Feb 3 17:48:13 wsguardian2 rhcs_fence: 403; DEBUG: Checking the state of resource with minor number: [1] Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Flags: 2node Feb 3 17:48:13 wsguardian2 rhcs_fence: 409; DEBUG: minor: [1] Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Ports Bound: 0 Feb 3 17:48:13 wsguardian2 rhcs_fence: 460; DEBUG: output: Node name: wsguardian2 Feb 3 17:48:13 wsguardian2 rhcs_fence: 469; DEBUG: Attempt to get local node name via 'cman_tool status' exited with: [0] Feb 3 17:48:13 wsguardian2 rhcs_fence: 412; DEBUG: shell call: [ drbd.conf global { usage-count no; } common { protocol C; syncer { rate 100M; al-extents 3389; } # This tells DRBD what policy to use when a fence is required. disk { fencing resource-and-stonith; } handlers { #outdate-peer "/sbin/obliterate-peer.sh"; outdate-peer "/usr/sbin/rhcs_fence"; split-brain "/usr/lib/drbd/notify-split-brain.sh kortux@gmail.com"; } net { sndbuf-size 1024k; # Tell DRBD to allow dual-primary. allow-two-primaries; # Set the recover policy for split-brain recover when no device # in the resource was primary. after-sb-0pri discard-zero-changes; # Now if one device was primary. after-sb-1pri discard-secondary; # Finally, set the policy when both nodes were Primary. The # only viable option is 'disconnect', which tells DRBD to # simply tear-down the DRBD resource right away and wait for # the administrator to manually invalidate one side of the # resource. after-sb-2pri disconnect; } startup { become-primary-on both; } } resource wsg_db { device /dev/drbd0; meta-disk internal; on wsguardian1 { address 192.168.253.1:7788; disk /dev/rootvg/wsg_data_lv; } on wsguardian2 { address 192.168.253.2:7788; disk /dev/rootvg/wsg_data_lv; } } resource wsg_config { device /dev/drbd1; meta-disk internal; on wsguardian1 { address 192.168.253.1:7789; disk /dev/rootvg/wsg_config_lv; } on wsguardian2 { address 192.168.253.2:7789; disk /dev/rootvg/wsg_config_lv; } }