>> replicate-0: performing entry selfheal on 94aefa13-9828-49e5-9bac-6f70453c100f > Does this gfid correspond to the same directory path as last time? No, it's one of the "two unrelated directories" that I mentioned in some previous post. Both directories exist on the volume mount and contain files that can be listed. The third gfid is probably a file. > Wonder if you can attach gdb the glustershd process at > the function client4_0_mkdir() Ehum, after 20 years as a linux professional, I still haven't come around to learning to use gdb. I thought OK, I'll give it a shot now, but CentOS hasn't published any gluster debuginfo since gluster v6.0: http://debuginfo.centos.org/7/x86_64/ http://debuginfo.centos.org/8/x86_64/Packages/ I tried strace on glfs_shdheal however, and I get hundreds and hundreds of 22000 futex(0x55c87bb00f7c, FUTEX_WAIT_BITSET_PRIVATE, 4473, {8652954, 543829556}, ffffffff) = -1 ETIMEDOUT (Connection timed out) 22000 <... futex resumed> ) = -1 ETIMEDOUT (Connection timed out) 22000 <... futex resumed> ) = -1 ETIMEDOUT (Connection timed out) All three nodes were connected and could ping each-other, so I don't know what connection kept timing out. ________ Community Meeting Calendar: Schedule - Every 2nd and 4th Tuesday at 14:30 IST / 09:00 UTC Bridge: https://meet.google.com/cpu-eiue-hvk Gluster-users mailing list Gluster-users@xxxxxxxxxxx https://lists.gluster.org/mailman/listinfo/gluster-users
