Created attachment 545692 [details]
logs of all bricks and clients.

Description of problem:

Core was generated by `/usr/local/sbin/glusterfsd -s localhost --volfile-id vol.dagobah.data-export6 -'.
Program terminated with signal 11, Segmentation fault.
#0  0x00007ff72d4cbb5d in malloc_consolidate (av=0x7ff71c000020) at malloc.c:5169
5169	malloc.c: No such file or directory.
	in malloc.c
(gdb) bt
#0  0x00007ff72d4cbb5d in malloc_consolidate (av=0x7ff71c000020) at malloc.c:5169
#1  0x00007ff72d4cc528 in _int_free (av=0x7ff71c000020, p=0x7ff71c09ef00) at malloc.c:5034
#2  0x00007ff72d4d08e3 in __libc_free (mem=<value optimized out>) at malloc.c:3738
#3  0x00007ff72d4fd39d in __closedir (dirp=<value optimized out>) at ../sysdeps/unix/closedir.c:52
#4  0x00007ff72a1daac7 in posix_janitor_thread_proc (data=0x1278ab0) at ../../../../../xlators/storage/posix/src/posix-helpers.c:775
#5  0x00007ff72d7eed8c in start_thread (arg=0x7ff72915a700) at pthread_create.c:304
#6  0x00007ff72d53a04d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:112
#7  0x0000000000000000 in ?? ()
(gdb) f 4
#4  0x00007ff72a1daac7 in posix_janitor_thread_proc (data=0x1278ab0) at ../../../../../xlators/storage/posix/src/posix-helpers.c:775
775	                                closedir (pfd->dir);
(gdb) p *pfd
$1 = {fd = 42, flags = 0, path = 0x7ff71c02ec70 "/data/export6/clients/client8/~dmtmp", dir = 0x7ff71c09ef10, flushwrites = 0, list = {next = 0xbabebabe, 
    prev = 0xcafecafe}}
(gdb) p *pfd->dir
$2 = {fd = 42, lock = 0, allocation = 32768, size = 0, offset = 0, filepos = 2147483647, data = 0x7ff71c09ef10 "*"}

I got a lot setxattrs failed on the dbench files and then this crash happened.

Version-Release number of selected component (if applicable):


How reproducible:
Hit it only once. Trying to reproduce again.

Steps to Reproduce:
Though not exact steps, this is how i got the crash. 
1. Created a distributed replicate volume 3x2.
2. enabled geo-rep & quota
3. made numerous graph changes by doing stat-prefetch on/off
4. when the crash happened stat-prefetch was off.
5. ran dbench -s -F -S --stat-check 10
  
Actual results:
glusterfsd crash

Expected results:
dbench should have run successfully.

Additional info: