I got regularly core dump: Core was generated by `/usr/sbin/glusterfs -s localhost --volfile-id gluster/glustershd -p /var/run/gl'. Program terminated with signal SIGSEGV, Segmentation fault. #0 afr_selfheal_data (frame=frame@entry=0x7f0af8007268, this=this@entry=0x7f0b0c02a140, fd=0x0) at afr-self-heal-data.c:842 842 inode_t *inode = fd->inode; (gdb) bt #0 afr_selfheal_data (frame=frame@entry=0x7f0af8007268, this=this@entry=0x7f0b0c02a140, fd=0x0) at afr-self-heal-data.c:842 #1 0x00007f0b1a3ac540 in afr_selfheal_do (frame=frame@entry=0x7f0af8007268, this=this@entry=0x7f0b0c02a140, gfid=gfid@entry=0x7f0b08ff8fb0 "U*\b\235>\024B") at afr-self-heal-common.c:2511 #2 0x00007f0b1a3ac665 in afr_selfheal (this=this@entry=0x7f0b0c02a140, gfid=gfid@entry=0x7f0b08ff8fb0 "U*\b\235>\024B") at afr-self-heal-common.c:2560 #3 0x00007f0b1a3b48bc in afr_shd_selfheal (healer=healer@entry=0x7f0b0c036038, child=1, gfid=gfid@entry=0x7f0b08ff8fb0 "U*\b\235>\024B") at afr-self-heald.c:328 #4 0x00007f0b1a3b4aeb in afr_shd_index_heal (subvol=0x7f0b0c024500, entry=<optimized out>, parent=0x7f0b09ff9f90, data=0x7f0b0c036038) at afr-self-heald.c:422 #5 0x00007f0b226cf252 in _dir_scan_job_fn (data=0x7f0afc0091e0) at syncop-utils.c:264 #6 0x00007f0b226ac780 in synctask_wrap () at syncop.c:272 #7 0x00007f0b21a6ffc0 in ?? () from /lib64/libc-2.23.so Checked with 6.3 and 6.5 versions.
This bug is moved to https://github.com/gluster/glusterfs/issues/852, and will be tracked there from now on. Visit GitHub issues URL for further details