| I’m not seeing any leaks myself, been on 3.12.13 for about 38 hours now, still small.
You did restart that node, or at least put it into maintenance (if it’s ovirt) to be sure you restarted the glusterfs processes after updating? That’s a lot of run time unless it’s really busy, so figured I’d check.
Subject: Re: gluster 3.12.8 fuse consume huge memory
Date: August 30, 2018 at 10:02:31 PM CDT
To: Darrell Budic
Cc: gluster-users@xxxxxxxxxxx
Thanks for your reply, I also test gluster 3.12.13 and found the client also consumes huge memory:
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 180095 root 20 0 4752256 4.091g 4084 S 43.5 1.6 17:54.70 glusterfs
I read and write some files on the gluster fuse client, the client consume 4g memory and it keeps arising.
Does it really fixed in 3.12.13?
![]() | huting3 | ![]() | huting3@xxxxxxxxxxxxxxxx |
It’s probably https://bugzilla.redhat.com/show_bug.cgi?id=1593826, although I did not encounter it in 3.12.8, only 3.12.9 - 12.
It’s fixed in 3.12.13.
Subject: gluster 3.12.8 fuse consume huge memory
Date: August 30, 2018 at 2:02:01 AM CDT
To: gluster-users@xxxxxxxxxxx
The version of glusterfs I installed is 3.12.8, and I find it`s client also consume huge memory.
I dumped the statedump file, and I found the size of a variable is extreamly huge like below:
[mount/fuse.fuse - usage-type gf_fuse_mt_iov_base memusage] 49805 size=4250821416 49806 num_allocs=1 49807 max_size=4294960048 49808 max_num_allocs=3 49809 total_allocs=12330719
Is it means a memory leak exist in glusterfs client?
![]() | huting3 | ![]() | huting3@xxxxxxxxxxxxxxxx |
|
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
https://lists.gluster.org/mailman/listinfo/gluster-users
