I am also experiencing this issue, would be interesting to find the cause or if this can be accepted and worked.

Cluster details

Percona XtraDB galera cluster x3 nodes each node 30gb RAM

Our rpm list
| <email address hidden>:/rootdba -> rpm -qa | grep Percona
Percona-Server-shared-51-5.1.73-rel14.12.624.rhel6.x86_64
Percona-XtraDB-Cluster-client-56-5.6.24-25.11.1.el6.x86_64
Percona-XtraDB-Cluster-galera-3-3.11-1.rhel6.x86_64
Percona-XtraDB-Cluster-server-56-5.6.24-25.11.1.el6.x86_64
Percona-XtraDB-Cluster-shared-56-5.6.24-25.11.1.el6.x86_64

OS Version: CentOS release 6.6 (Final)

Crash appears to be random but consistent, needs manual start to recover.
So far the whole cluster has not entirely crashed, the other 2 nodes have continued and allows rejoin after the crashed node is manually started, sometimes the first start attempt fails and a 2nd "service mysql start" command is needed, which then detects the stale sst file and re-initializes things.


Mysql error Log snapshot
----------------
2015-06-18 18:26:13 18275 [Warning] WSREP: BF applier failed to open_and_lock_tables: 1615, fatal: 0 wsrep = (exec_mode: 1 conflict_state: 5 seqno: 1704468)
2015-06-18 18:26:13 18275 [Warning] WSREP: RBR event 3 Update_rows apply warning: 1615, 1704468
2015-06-18 18:26:13 18275 [Warning] WSREP: Failed to apply app buffer: seqno: 1704468, status: 1
at galera/src/trx_handle.cpp:apply():351
Retrying 2th time
2015-06-18 18:26:13 18275 [Warning] WSREP: BF applier failed to open_and_lock_tables: 1615, fatal: 0 wsrep = (exec_mode: 1 conflict_state: 5 seqno: 1704468)
2015-06-18 18:26:13 18275 [Warning] WSREP: RBR event 3 Update_rows apply warning: 1615, 1704468
2015-06-18 18:26:13 18275 [Warning] WSREP: Failed to apply app buffer: seqno: 1704468, status: 1
at galera/src/trx_handle.cpp:apply():351
Retrying 3th time
2015-06-18 18:26:13 18275 [Warning] WSREP: BF applier failed to open_and_lock_tables: 1615, fatal: 0 wsrep = (exec_mode: 1 conflict_state: 5 seqno: 1704468)
2015-06-18 18:26:13 18275 [Warning] WSREP: RBR event 3 Update_rows apply warning: 1615, 1704468
2015-06-18 18:26:13 18275 [Warning] WSREP: Failed to apply app buffer: seqno: 1704468, status: 1
at galera/src/trx_handle.cpp:apply():351
Retrying 4th time
2015-06-18 18:26:13 18275 [Warning] WSREP: BF applier failed to open_and_lock_tables: 1615, fatal: 0 wsrep = (exec_mode: 1 conflict_state: 5 seqno: 1704468)
2015-06-18 18:26:13 18275 [Warning] WSREP: RBR event 3 Update_rows apply warning: 1615, 1704468
2015-06-18 18:26:13 18275 [Warning] WSREP: failed to replay trx: source: 401397a7-15b4-11e5-8b99-87d715e86d59 version: 3 local: 1 state: REPLAYING flags: 1 con
n_id: 11318 trx_id: 16121482 seqnos (l: 18306, g: 1704468, s: 1704466, d: 1704467, ts: 3186938643214857)
2015-06-18 18:26:13 18275 [Warning] WSREP: Failed to apply trx 1704468 4 times
2015-06-18 18:26:13 18275 [ERROR] WSREP: trx_replay failed for: 6, query: void
2015-06-18 18:26:13 18275 [ERROR] Aborting

2015-06-18 18:26:15 18275 [Note] WSREP: Closing send monitor...
2015-06-18 18:26:15 18275 [Note] WSREP: Closed send monitor.
2015-06-18 18:26:15 18275 [Note] WSREP: gcomm: terminating thread
2015-06-18 18:26:15 18275 [Note] WSREP: gcomm: joining thread
2015-06-18 18:26:15 18275 [Note] WSREP: gcomm: closing backend
2015-06-18 18:26:15 18275 [Note] WSREP: view(view_id(NON_PRIM,157a25f2,289) memb {
401397a7,0
} joined {
} left {
} partitioned {
157a25f2,0
c48d73a9,0
})
2015-06-18 18:26:15 18275 [Note] WSREP: New COMPONENT: primary = no, bootstrap = no, my_idx = 0, memb_num = 1
2015-06-18 18:26:15 18275 [Note] WSREP: view((empty))
2015-06-18 18:26:15 18275 [Note] WSREP: gcomm: closed
2015-06-18 18:26:15 18275 [Note] WSREP: Flow-control interval: [16, 16]
2015-06-18 18:26:15 18275 [Note] WSREP: Received NON-PRIMARY.
2015-06-18 18:26:15 18275 [Note] WSREP: Shifting SYNCED -> OPEN (TO: 1704469)
2015-06-18 18:26:15 18275 [Note] WSREP: Received self-leave message.
2015-06-18 18:26:15 18275 [Note] WSREP: Flow-control interval: [0, 0]
2015-06-18 18:26:15 18275 [Note] WSREP: Received SELF-LEAVE. Closing connection.
2015-06-18 18:26:15 18275 [Note] WSREP: Shifting OPEN -> CLOSED (TO: 1704469)
2015-06-18 18:26:15 18275 [Note] WSREP: RECV thread exiting 0: Success
2015-06-18 18:26:15 18275 [Note] WSREP: recv_thread() joined.
2015-06-18 18:26:15 18275 [Note] WSREP: Closing replication queue.
2015-06-18 18:26:15 18275 [Note] WSREP: Closing slave action queue.
2015-06-18 18:26:15 18275 [Note] WSREP: Service disconnected.
2015-06-18 18:26:15 18275 [Note] WSREP: rollbacker thread exiting
2015-06-18 18:26:16 18275 [Note] WSREP: Some threads may fail to exit.
2015-06-18 18:26:16 18275 [Note] Binlog end
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'partition'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'ARCHIVE'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'BLACKHOLE'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'PERFORMANCE_SCHEMA'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_CHANGED_PAGES'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_DATAFILES'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_TABLESPACES'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_FOREIGN_COLS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_FOREIGN'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_FIELDS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_COLUMNS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_INDEXES'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_TABLESTATS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_SYS_TABLES'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_FT_INDEX_TABLE'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_FT_INDEX_CACHE'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_FT_CONFIG'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_FT_BEING_DELETED'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_FT_DELETED'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_FT_DEFAULT_STOPWORD'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_METRICS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_BUFFER_POOL_STATS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_BUFFER_PAGE_LRU'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_BUFFER_PAGE'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_CMP_PER_INDEX_RESET'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_CMP_PER_INDEX'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_CMPMEM_RESET'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_CMPMEM'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_CMP_RESET'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_CMP'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_LOCK_WAITS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_LOCKS'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'INNODB_TRX'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'XTRADB_RSEG'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'XTRADB_INTERNAL_HASH_TABLES'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'XTRADB_READ_VIEW'
2015-06-18 18:26:16 18275 [Note] Shutting down plugin 'InnoDB'
2015-06-18 18:26:16 18275 [Note] InnoDB: FTS optimize thread exiting.
2015-06-18 18:26:16 18275 [Note] InnoDB: Starting shutdown...
18:26:16 UTC - mysqld got signal 11 ;
This could be because you hit a bug. It is also possible that this binary
or one of the libraries it was linked against is corrupt, improperly built,
or misconfigured. This error can also be caused by malfunctioning hardware.
We will try our best to scrape up some info that will hopefully help
diagnose the problem, but since we have already crashed,
something is definitely wrong and this may fail.
Please help us make Percona XtraDB Cluster better by reporting any
bugs at https://bugs.launchpad.net/percona-xtradb-cluster

key_buffer_size=8388608
read_buffer_size=131072
max_used_connections=3
max_threads=5002
thread_count=3
connection_count=2
It is possible that mysqld could use up to
key_buffer_size + (read_buffer_size + sort_buffer_size)*max_threads = 2005108 K bytes of memory
Hope that's ok; if not, decrease some variables in the equation.

Thread pointer: 0x1b351690
Attempting backtrace. You can use the following information to find out
where mysqld died. If you see no messages after this, something went
terribly wrong...
stack_bottom = 7fa17a357d38 thread_stack 0x40000
/usr/sbin/mysqld(my_print_stacktrace+0x35)[0x8fa965]
/usr/sbin/mysqld(handle_fatal_signal+0x4b4)[0x665644]
/lib64/libpthread.so.0[0x33d7c0f710]
/usr/sbin/mysqld(_Z14ip_to_hostnameP16sockaddr_storagePKcPPc Pj+0xd5)[0x5ad9a5]
/usr/sbin/mysqld[0x6bb14c]
/usr/sbin/mysqld(_Z16login_connectionP3THD+0x4d)[0x6bb2ad]
/usr/sbin/mysqld(_Z22thd_prepare_connectionP3THD+0x24)[0x6bb4a4]
/usr/sbin/mysqld(_Z24do_handle_one_connectionP3THD+0x152)[0x6bc502]
/usr/sbin/mysqld(handle_one_connection+0x47)[0x6bc717]
/usr/sbin/mysqld(pfs_spawn_thread+0x12a)[0xaf611a]
/lib64/libpthread.so.0[0x33d7c079d1]
/lib64/libc.so.6(clone+0x6d)[0x33d78e88fd]

Trying to get some variables.
Some pointers may be invalid and cause the dump to abort.
Query (0): is an invalid pointer
Connection ID (thread ID): 11320
Status: NOT_KILLED

You may download the Percona XtraDB Cluster operations manual by visiting
http://www.percona.com/software/percona-xtradb-cluster/. You may find information
in the manual which will help you identify the cause of the crash.
150618 18:26:17 mysqld_safe Number of processes running now: 0
150618 18:26:17 mysqld_safe WSREP: not restarting wsrep node automatically
150618 18:26:17 mysqld_safe mysqld from pid file /var/lib/mysql/db.local.pid ended
150618 18:32:26 mysqld_safe Starting mysqld daemon with databases from /var/lib/mysql
150618 18:32:26 mysqld_safe WSREP: Running position recovery with --log_error='/var/lib/mysql/wsrep_recovery.xmMS4A' --pid-file='/var/lib/mysql/db.local-recover.pid'
2015-06-18 18:32:27 0 [Warning] TIMESTAMP with implicit DEFAULT value is deprecated. Please use --explicit_defaults_for_timestamp server option (see documentation for more details).
150618 18:32:33 mysqld_safe WSREP: Recovered position 16b1acf5-ed01-11e4-8ad4-dfefd145c7ec:1704467
Log of wsrep recovery (--wsrep-recover):
2015-06-18 18:32:27 32035 [Note] Plugin 'FEDERATED' is disabled.
2015-06-18 18:32:27 32035 [Note] InnoDB: Using atomics to ref count buffer pool pages
2015-06-18 18:32:27 32035 [Note] InnoDB: The InnoDB memory heap is disabled
2015-06-18 18:32:27 32035 [Note] InnoDB: Mutexes and rw_locks use GCC atomic builtins
2015-06-18 18:32:27 32035 [Note] InnoDB: Memory barrier is not used
2015-06-18 18:32:27 32035 [Note] InnoDB: Compressed tables use zlib 1.2.3
2015-06-18 18:32:27 32035 [Note] InnoDB: Using Linux native AIO
2015-06-18 18:32:27 32035 [Note] InnoDB: Using CPU crc32 instructions
2015-06-18 18:32:27 32035 [Note] InnoDB: Initializing buffer pool, size = 14.0G
2015-06-18 18:32:29 32035 [Note] InnoDB: Completed initialization of buffer pool
2015-06-18 18:32:29 32035 [Note] InnoDB: Highest supported file format is Barracuda.
2015-06-18 18:32:29 32035 [Note] InnoDB: The log sequence numbers 23909010087 and 23909010087 in ibdata files do not match the log sequence number 23950849320 in the ib_logfiles!
2015-06-18 18:32:29 32035 [Note] InnoDB: Database was not shutdown normally!
2015-06-18 18:32:29 32035 [Note] InnoDB: Starting crash recovery.
2015-06-18 18:32:29 32035 [Note] InnoDB: Reading tablespace information from the .ibd files...
2015-06-18 18:32:29 32035 [Note] InnoDB: Restoring possible half-written data pages 
2015-06-18 18:32:29 32035 [Note] InnoDB: from the doublewrite buffer...
InnoDB: 1 transaction(s) which must be rolled back or cleaned up
InnoDB: in total 1 row operations to undo
InnoDB: Trx id counter is 16121856
InnoDB: Last MySQL binlog file position 0 15334897, file name mysql-bin.000001
2015-06-18 18:32:30 32035 [Note] InnoDB: 128 rollback segment(s) are active.
InnoDB: Starting in background the rollback of uncommitted transactions
2015-06-18 18:32:30 7f61db6ab700  InnoDB: Rolling back trx with id 16121486, 1 rows to undo
2015-06-18 18:32:30 32035 [Note] InnoDB: Waiting for purge to start
2015-06-18 18:32:30 32035 [Note] InnoDB: Rollback of trx with id 16121486 completed
2015-06-18 18:32:30 7f61db6ab700  InnoDB: Rollback of non-prepared transactions completed
2015-06-18 18:32:30 32035 [Note] InnoDB:  Percona XtraDB (http://www.percona.com) 5.6.22-72.0 started; log sequence number 23950849320
2015-06-18 18:32:30 32035 [Warning] InnoDB: Skipping buffer pool dump/restore during wsrep recovery.
2015-06-18 18:32:30 32035 [Note] WSREP: Recovered position: 16b1acf5-ed01-11e4-8ad4-dfefd145c7ec:1704467
2015-06-18 18:32:30 32035 [Note] Binlog end
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'partition'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'ARCHIVE'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'BLACKHOLE'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'PERFORMANCE_SCHEMA'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_CHANGED_PAGES'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_DATAFILES'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_TABLESPACES'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_FOREIGN_COLS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_FOREIGN'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_FIELDS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_COLUMNS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_INDEXES'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_TABLESTATS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_SYS_TABLES'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_FT_INDEX_TABLE'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_FT_INDEX_CACHE'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_FT_CONFIG'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_FT_BEING_DELETED'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_FT_DELETED'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_FT_DEFAULT_STOPWORD'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_METRICS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_BUFFER_POOL_STATS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_BUFFER_PAGE_LRU'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_BUFFER_PAGE'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_CMP_PER_INDEX_RESET'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_CMP_PER_INDEX'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_CMPMEM_RESET'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_CMPMEM'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_CMP_RESET'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_CMP'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_LOCK_WAITS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_LOCKS'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'INNODB_TRX'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'XTRADB_RSEG'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'XTRADB_INTERNAL_HASH_TABLES'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'XTRADB_READ_VIEW'
2015-06-18 18:32:30 32035 [Note] Shutting down plugin 'InnoDB'
2015-06-18 18:32:30 32035 [Note] InnoDB: FTS optimize thread exiting.
2015-06-18 18:32:30 32035 [Note] InnoDB: Starting shutdown...
2015-06-18 18:32:33 32035 [Note] InnoDB: Shutdown completed; log sequence number 23950855349
2015-06-18 18:32:33 32035 [Note] Shutting down plugin 'CSV'
2015-06-18 18:32:33 32035 [Note] Shutting down plugin 'MyISAM'
2015-06-18 18:32:33 32035 [Note] Shutting down plugin 'MRG_MYISAM'
2015-06-18 18:32:33 32035 [Note] Shutting down plugin 'MEMORY'
2015-06-18 18:32:33 32035 [Note] Shutting down plugin 'sha256_password'