[Bugs] [Bug 1593826] Glusterfs being killed due to out of memory situation

bugzilla at redhat.com bugzilla at redhat.com
Mon Jul 9 19:34:14 UTC 2018


https://bugzilla.redhat.com/show_bug.cgi?id=1593826

budic at onholyground.com changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |budic at onholyground.com



--- Comment #6 from budic at onholyground.com ---
I've encountered this memory use issue as well, client side. It's the glusterfs
process mounting gluster volumes that has consumed the memory, seems to be fuse
mounts using it, not glfsapi mounts (it occurred on my Hosted Engine). Probably
began appearing after upgrading to 3.12.9, and is also present in 3.12.11. I
was able to downgrade my hosts and confirmed it's not present in 3.12.8 or
3.12.6. 

Attaching a glusterdump from a processes using a lot of ram before I
restarted/downgraded. As I'm currently back on 3.12.6, I can't do a time
differential set, but if you needed one I can update a node and provide in
fairly short order.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
You are the assignee for the bug.


More information about the Bugs mailing list