[Pacemaker] Help! Simultaneously Mount gfs2 in Pacemaker on RHEL6.1x64 HANGS!
Andrew Beekhof
andrew at beekhof.net
Fri Sep 23 02:41:26 UTC 2011
Perhaps try setting the "ordered" meta attribute to true for the clone.
We had to do something similar for ocfs2 at one stage.
On Thu, Sep 22, 2011 at 11:48 AM, <xin.liang at cs2c.com.cn> wrote:
> hi:
> Hope you everything goes well.
>
> I have problems with DRBD+dlm+gfs in pacemaker.
>
> I follow this
> doc:http://www.clusterlabs.org/doc/en-US/Pacemaker/1.1/html/Clusters_from_Scratch/index.html
> to make a DRBD-GFS2 cluster
>
> When I run DRBD(two primaries)+dlm+gfs+Filesystem, node-c hangs
> and reboot.
>
> Then I run DRBD(two primaries)+dlm+gfs , it does well, running on
> both nodes;
>
> And then, I "mount -t gfs2 /dev/drbd0 /mnt" on node-b, it's ok;
>
> BUT, when I run command "mount -t gfs2 /dev/drbd0 /mnt" on
> node-c, node-c hangs and reboot. No err log on stderr.
>
> Once again, I do this on node-c firstly, it's ok; then on node-b,
> it hangs and reboot!
>
> #################################################################
> $ crm configure show
>
> node ha-b
> node ha-c
> primitive dlm ocf:pacemaker:controld \
> operations $id="dlm-operations" \
> op monitor interval="10" timeout="20" start-delay="0" \
> params args="-L -K -P -q 0 "
> primitive drbd ocf:linbit:drbd \
> operations $id="drbd-operations" \
> op monitor interval="20" role="Slave" timeout="20" \
> op monitor interval="10" role="Master" timeout="20" \
> params drbd_resource="drbd0"
> primitive gfs ocf:pacemaker:controld \
> operations $id="gfs-operations" \
> op monitor interval="10" timeout="20" start-delay="0" \
> params daemon="gfs_controld.pcmk" args="-L -P -g 0"
> group groups dlm gfs
> ms ms-drbd drbd \
> meta master-max="2" notify="true" target-role="Started"
> clone clone-set groups \
> meta interleave="true" target-role="Started"
> colocation clone-on-drbd inf: clone-set:Started ms-drbd:Master
> order clone-after-drbd inf: ms-drbd:promote clone-set:start symmetrical=true
> property $id="cib-bootstrap-options" \
> dc-version="1.1.6-1.el6-9971ebba4494012a93c03b40a2c58ec0eb60f50c" \
> cluster-infrastructure="openais" \
> expected-quorum-votes="2" \
> no-quorum-policy="ignore" \
> stonith-enabled="false"
> ##########################################################################
>
>
> gfs_controld.log on ha-b
> ##########################################################################
> [root at ha-b ~]# cat /var/log/cluster/gfs_controld.log
>
> Sep 22 09:08:13 gfs_controld gfs_controld 3.0.12 started
> Sep 22 09:08:13 gfs_controld Connected as node 3393650954 to cluster 'cs2c'
> Sep 22 09:08:13 gfs_controld logging mode 3 syslog f 160 p 6 logfile p 7
> /var/log/cluster/gfs_controld.log
> Sep 22 09:08:13 gfs_controld group_mode 3 compat 0
> Sep 22 09:08:13 gfs_controld setup_cpg_daemon 11
> Sep 22 09:08:13 gfs_controld gfs:controld conf 1 1 0 memb -901316342 join
> -901316342 left
> Sep 22 09:08:13 gfs_controld set_protocol member_count 1 propose daemon
> 1.1.1 kernel 1.1.1
> Sep 22 09:08:13 gfs_controld run protocol from nodeid -901316342
> Sep 22 09:08:13 gfs_controld daemon run 1.1.1 max 1.1.1 kernel run 1.1.1 max
> 1.1.1
> Sep 22 09:08:14 gfs_controld gfs:controld conf 2 1 0 memb -901316342
> -884539126 join -884539126 left
> Sep 22 09:11:57 gfs_controld client connection 5 fd 14
> Sep 22 09:11:57 gfs_controld join: /mnt gfs2 lock_dlm cs2c:liang rw
> /dev/drbd0
> Sep 22 09:11:57 gfs_controld liang join: cluster name matches: cs2c
> Sep 22 09:11:57 gfs_controld liang process_dlmcontrol register 0
> Sep 22 09:11:57 gfs_controld gfs:mount:liang conf 1 1 0 memb -901316342 join
> -901316342 left
> Sep 22 09:11:57 gfs_controld liang add_change cg 1 joined nodeid -901316342
> Sep 22 09:11:57 gfs_controld liang add_change cg 1 we joined
> Sep 22 09:11:57 gfs_controld liang add_change cg 1 counts member 1 joined 1
> remove 0 failed 0
> Sep 22 09:11:57 gfs_controld liang wait_conditions skip for zero
> started_count
> Sep 22 09:11:57 gfs_controld liang send_start cg 1 id_count 1 om 0 nm 1 oj 0
> nj 0
> Sep 22 09:11:57 gfs_controld liang receive_start -901316342:1 len 92
> Sep 22 09:11:57 gfs_controld liang match_change -901316342:1 matches cg 1
> Sep 22 09:11:57 gfs_controld liang wait_messages cg 1 got all 1
> Sep 22 09:11:57 gfs_controld liang pick_first_recovery_master low -901316342
> old 0
> Sep 22 09:11:57 gfs_controld liang sync_state all_nodes_new
> first_recovery_needed master -901316342
> Sep 22 09:11:57 gfs_controld liang create_old_nodes all new
> Sep 22 09:11:57 gfs_controld liang create_new_nodes -901316342 ro 0 spect 0
> Sep 22 09:11:57 gfs_controld liang create_failed_journals all new
> Sep 22 09:11:57 gfs_controld liang apply_recovery first start_kernel
> Sep 22 09:11:57 gfs_controld liang start_kernel cg 1 member_count 1
> Sep 22 09:11:57 gfs_controld liang set
> /sys/fs/gfs2/cs2c:liang/lock_module/block to 0
> Sep 22 09:11:57 gfs_controld liang set open
> /sys/fs/gfs2/cs2c:liang/lock_module/block error -1 2
> Sep 22 09:11:57 gfs_controld liang client_reply_join_full ci 5 result 0
> hostdata=jid=0:id=915250580:first=1
> Sep 22 09:11:57 gfs_controld client_reply_join liang ci 5 result 0
> Sep 22 09:11:57 gfs_controld uevent add gfs2 /fs/gfs2/cs2c:liang
> Sep 22 09:11:57 gfs_controld liang ping_kernel_mount 0
> Sep 22 09:11:57 gfs_controld uevent change gfs2 /fs/gfs2/cs2c:liang
> Sep 22 09:11:57 gfs_controld liang recovery_uevent jid 0 first recovery done
> 0
> Sep 22 09:11:57 gfs_controld uevent change gfs2 /fs/gfs2/cs2c:liang
> Sep 22 09:11:57 gfs_controld liang recovery_uevent jid 1 first recovery done
> 0
> Sep 22 09:11:57 gfs_controld uevent change gfs2 /fs/gfs2/cs2c:liang
> Sep 22 09:11:57 gfs_controld liang recovery_uevent jid 1 first recovery done
> 0
> Sep 22 09:11:57 gfs_controld liang recovery_uevent first_done
> Sep 22 09:11:57 gfs_controld liang receive_first_recovery_done from
> -901316342 master -901316342 mount_client_notified 1
> Sep 22 09:11:57 gfs_controld liang wait_recoveries done
> Sep 22 09:11:57 gfs_controld uevent online gfs2 /fs/gfs2/cs2c:liang
> Sep 22 09:11:57 gfs_controld liang ping_kernel_mount 0
> Sep 22 09:11:57 gfs_controld mount_done: liang result 0
> Sep 22 09:11:57 gfs_controld connection 5 read error -1
> Sep 22 09:11:57 gfs_controld liang receive_mount_done from -901316342 result
> 0
> Sep 22 09:11:57 gfs_controld liang wait_recoveries done
> Sep 22 09:12:37 gfs_controld uevent remove gfs2 /fs/gfs2/cs2c:liang
> Sep 22 09:12:37 gfs_controld do_leave liang mnterr 0
> Sep 22 09:12:37 gfs_controld gfs:mount:liang conf 0 0 1 memb join left
> -901316342
> Sep 22 09:12:37 gfs_controld liang confchg for our leave
> ##########################################################################
>
>
> gfs_controld.log on ha-c
> ##########################################################################
> [root at ha-c ~]# cat /var/log/cluster/gfs_controld.log
>
> Sep 22 08:52:12 gfs_controld gfs_controld 3.0.12 started
> Sep 22 08:52:12 gfs_controld Connected as node 3410428170 to cluster 'cs2c'
> Sep 22 08:52:12 gfs_controld logging mode 3 syslog f 160 p 6 logfile p 7
> /var/log/cluster/gfs_controld.log
> Sep 22 08:52:12 gfs_controld group_mode 3 compat 0
> Sep 22 08:52:12 gfs_controld setup_cpg_daemon 11
> Sep 22 08:52:12 gfs_controld gfs:controld conf 2 1 0 memb -901316342
> -884539126 join -884539126 left
> Sep 22 08:52:12 gfs_controld run protocol from nodeid -901316342
> Sep 22 08:52:12 gfs_controld daemon run 1.1.1 max 1.1.1 kernel run 1.1.1 max
> 1.1.1
> Sep 22 08:56:52 gfs_controld client connection 5 fd 14
> Sep 22 08:56:52 gfs_controld join: /mnt gfs2 lock_dlm cs2c:liang rw
> /dev/drbd0
> Sep 22 08:56:52 gfs_controld liang join: cluster name matches: cs2c
> Sep 22 08:56:52 gfs_controld liang process_dlmcontrol register 0
> Sep 22 08:56:52 gfs_controld gfs:mount:liang conf 1 1 0 memb -884539126 join
> -884539126 left
> Sep 22 08:56:52 gfs_controld liang add_change cg 1 joined nodeid -884539126
> Sep 22 08:56:52 gfs_controld liang add_change cg 1 we joined
> Sep 22 08:56:52 gfs_controld liang add_change cg 1 counts member 1 joined 1
> remove 0 failed 0
> Sep 22 08:56:52 gfs_controld liang wait_conditions skip for zero
> started_count
> Sep 22 08:56:52 gfs_controld liang send_start cg 1 id_count 1 om 0 nm 1 oj 0
> nj 0
> Sep 22 08:56:52 gfs_controld liang receive_start -884539126:1 len 92
> Sep 22 08:56:52 gfs_controld liang match_change -884539126:1 matches cg 1
> Sep 22 08:56:52 gfs_controld liang wait_messages cg 1 got all 1
> Sep 22 08:56:52 gfs_controld liang pick_first_recovery_master low -884539126
> old 0
> Sep 22 08:56:52 gfs_controld liang sync_state all_nodes_new
> first_recovery_needed master -884539126
> Sep 22 08:56:52 gfs_controld liang create_old_nodes all new
> Sep 22 08:56:52 gfs_controld liang create_new_nodes -884539126 ro 0 spect 0
> Sep 22 08:56:52 gfs_controld liang create_failed_journals all new
> Sep 22 08:56:52 gfs_controld liang apply_recovery first start_kernel
> Sep 22 08:56:52 gfs_controld liang start_kernel cg 1 member_count 1
> Sep 22 08:56:52 gfs_controld liang set
> /sys/fs/gfs2/cs2c:liang/lock_module/block to 0
> Sep 22 08:56:52 gfs_controld liang set open
> /sys/fs/gfs2/cs2c:liang/lock_module/block error -1 2
> Sep 22 08:56:52 gfs_controld liang client_reply_join_full ci 5 result 0
> hostdata=jid=0:id=915250580:first=1
> Sep 22 08:56:52 gfs_controld client_reply_join liang ci 5 result 0
> Sep 22 08:56:53 gfs_controld uevent add gfs2 /fs/gfs2/cs2c:liang
> Sep 22 08:56:53 gfs_controld liang ping_kernel_mount 0
> Sep 22 08:56:53 gfs_controld uevent change gfs2 /fs/gfs2/cs2c:liang
> Sep 22 08:56:53 gfs_controld liang recovery_uevent jid 0 first recovery done
> 0
> Sep 22 08:56:53 gfs_controld uevent change gfs2 /fs/gfs2/cs2c:liang
> Sep 22 08:56:53 gfs_controld liang recovery_uevent jid 1 first recovery done
> 0
> Sep 22 08:56:53 gfs_controld uevent change gfs2 /fs/gfs2/cs2c:liang
> Sep 22 08:56:53 gfs_controld liang recovery_uevent jid 1 first recovery done
> 0
> Sep 22 08:56:53 gfs_controld liang recovery_uevent first_done
> Sep 22 08:56:53 gfs_controld liang receive_first_recovery_done from
> -884539126 master -884539126 mount_client_notified 1
> Sep 22 08:56:53 gfs_controld liang wait_recoveries done
> Sep 22 08:56:53 gfs_controld uevent online gfs2 /fs/gfs2/cs2c:liang
> Sep 22 08:56:53 gfs_controld liang ping_kernel_mount 0
> Sep 22 08:56:53 gfs_controld mount_done: liang result 0
> Sep 22 08:56:53 gfs_controld connection 5 read error -1
> Sep 22 08:56:53 gfs_controld liang receive_mount_done from -884539126 result
> 0
> Sep 22 08:56:53 gfs_controld liang wait_recoveries done
> Sep 22 08:57:17 gfs_controld gfs:mount:liang conf 2 1 0 memb -901316342
> -884539126 join -901316342 left
> Sep 22 08:57:17 gfs_controld liang add_change cg 2 joined nodeid -901316342
> Sep 22 08:57:17 gfs_controld liang add_change cg 2 counts member 2 joined 1
> remove 0 failed 0
> Sep 22 08:57:17 gfs_controld liang wait_conditions skip for zero
> journals_need_recovery
> Sep 22 08:57:17 gfs_controld liang send_start cg 2 id_count 2 om 1 nm 1 oj 0
> nj 0
> Sep 22 08:57:17 gfs_controld liang receive_start -901316342:1 len 104
> Sep 22 08:57:17 gfs_controld liang match_change -901316342:1 matches cg 2
> Sep 22 08:57:17 gfs_controld liang wait_messages cg 2 need 1 of 2
> Sep 22 08:57:17 gfs_controld liang receive_start -884539126:2 len 104
> Sep 22 08:57:17 gfs_controld liang match_change -884539126:2 matches cg 2
> Sep 22 08:57:17 gfs_controld liang wait_messages cg 2 got all 2
> Sep 22 08:57:17 gfs_controld liang sync_state first_recovery_msg
> Sep 22 08:57:17 gfs_controld liang create_new_nodes -901316342 ro 0 spect 0
> Sep 22 08:57:17 gfs_controld liang wait_recoveries done
> Sep 22 08:57:22 gfs_controld gfs:controld conf 1 0 1 memb -884539126 join
> left -901316342
> Sep 22 08:57:22 gfs_controld gfs:mount:liang conf 1 0 1 memb -884539126 join
> left -901316342
> Sep 22 08:57:22 gfs_controld liang add_change cg 3 remove nodeid -901316342
> reason 3
> Sep 22 08:57:22 gfs_controld liang add_change cg 3 counts member 1 joined 0
> remove 1 failed 1
> Sep 22 08:57:22 gfs_controld liang stop_kernel
> Sep 22 08:57:22 gfs_controld liang set
> /sys/fs/gfs2/cs2c:liang/lock_module/block to 1
> Sep 22 08:57:22 gfs_controld liang check_dlm_notify nodeid -901316342 begin
> Sep 22 08:57:22 gfs_controld liang process_dlmcontrol notified nodeid
> -901316342 result 0
> Sep 22 08:57:22 gfs_controld liang check_dlm_notify done
> Sep 22 08:57:22 gfs_controld liang send_start cg 3 id_count 1 om 1 nm 0 oj 0
> nj 0
> Sep 22 08:57:22 gfs_controld liang receive_start -884539126:3 len 92
> Sep 22 08:57:22 gfs_controld liang match_change -884539126:3 matches cg 3
> Sep 22 08:57:22 gfs_controld liang wait_messages cg 3 got all 1
> Sep 22 08:57:22 gfs_controld liang sync_state first_recovery_msg
> Sep 22 08:57:22 gfs_controld liang set_failed_journals no journal for nodeid
> -901316342
> Sep 22 08:57:22 gfs_controld liang wait_recoveries done
> Sep 22 08:57:22 gfs_controld liang apply_recovery start_kernel
> Sep 22 08:57:22 gfs_controld liang start_kernel cg 3 member_count 1
> Sep 22 08:57:22 gfs_controld liang set
> /sys/fs/gfs2/cs2c:liang/lock_module/block to 0
> ##########################################################################
>
> My experimental environment:
>
> 2 PC
> node-b
> node-c
>
> Both OS are RHEL6.1X64
>
> RPMS:
> pacemaker-cli-1.1.6-1.el6.x86_64
> pacemaker-doc-1.1.6-1.el6.x86_64
> pacemaker-libs-1.1.6-1.el6.x86_64
> pacemaker-1.1.6-1.el6.x86_64
> pacemaker-cts-1.1.6-1.el6.x86_64
> pacemaker-libs-devel-1.1.6-1.el6.x86_64
>
> corosynclib-1.4.1-1.x86_64
> corosync-1.4.1-1.x86_64
> corosynclib-devel-1.4.1-1.x86_64
>
> resource-agents-3.9.2-1.x86_64
>
> cluster-glue-libs-devel-1.0.7-1.el6.x86_64
> cluster-glue-libs-1.0.7-1.el6.x86_64
> cluster-glue-1.0.7-1.el6.x86_64
>
> openais-1.1.1-7.el6.x86_64
> openaislib-1.1.1-7.el6.x86_64
>
> dlm-pcmk-3.0.12-23.el6_0.6.x86_64
>
> gfs-pcmk-3.0.12-23.el6_0.6.x86_64
> gfs2-utils-3.0.12-41.el6.x86_64
>
> clusterlib-3.0.12-41.el6.x86_64
>
> drbd-udev-8.4.0-1.el6.x86_64
> drbd-8.4.0-1.el6.x86_64
> drbd-utils-8.4.0-1.el6.x86_64
> drbd-heartbeat-8.4.0-1.el6.x86_64
> drbd-pacemaker-8.4.0-1.el6.x86_64
> drbd-bash-completion-8.4.0-1.el6.x86_64
> drbd-xen-8.4.0-1.el6.x86_64
> drbd-km-2.6.32_131.0.15.el6.x86_64-8.4.0-1.el6.x86_64
> drbd-kernel-8.4.0-1.el6.x86_64
>
> My conf:
> $ cat /etc/corosync/corosync.conf
>
> compatibility: whitetank
>
> totem {
> version: 2
> secauth: off
> threads: 0
> rrp_mode: passive
> interface {
> ringnumber: 0
> bindnetaddr: 10.1.71.0
> mcastaddr: 235.3.4.5
> mcastport: 9876
> }
>
> interface {
> ringnumber: 1
> bindnetaddr: 10.10.10.0
> mcastaddr: 235.3.4.6
> mcastport: 9877
> }
> }
>
> logging {
> fileline: off
> to_stderr: no
> to_logfile: yes
> to_syslog: yes
> logfile: /var/log/cluster/corosync.log
> debug: off
> timestamp: on
> logger_subsys {
> subsys: AMF
> debug: off
> }
> }
>
> amf {
> mode: disabled
> }
>
> service {
> name: pacemaker
> var: 0
> use_logd: yes
> use_mgmtd: yes
> clustername: cs2c
> }
>
>
>
> _______________________________________________
> Pacemaker mailing list: Pacemaker at oss.clusterlabs.org
> http://oss.clusterlabs.org/mailman/listinfo/pacemaker
>
> Project Home: http://www.clusterlabs.org
> Getting started: http://www.clusterlabs.org/doc/Cluster_from_Scratch.pdf
> Bugs:
> http://developerbugs.linux-foundation.org/enter_bug.cgi?product=Pacemaker
>
>
More information about the Pacemaker
mailing list