[Gluster-users] [Gluster-devel] Memory leak in GlusterFS FUSE client

Vijay Bellur vbellur at redhat.com
Sun Jan 3 18:35:51 UTC 2016


On 01/03/2016 09:23 AM, Oleksandr Natalenko wrote:
> Another Valgrind run.
>
> I did the following:
>
> ===
> valgrind --leak-check=full --show-leak-kinds=all --log-
> file="valgrind_fuse.log" /usr/bin/glusterfs -N --volfile-
> server=some.server.com --volfile-id=somevolume /mnt/volume
> ===
>
> then cd to /mnt/volume and find . -type f. After traversing some part of
> hierarchy I've stopped find and did umount /mnt/volume. Here is
> valgrind_fuse.log file:
>
> https://gist.github.com/7e2679e1e72e48f75a2b
>

Can you please try the same by dropping caches before umount?

echo 3 > /proc/sys/vm/drop_caches

Gluster relies on vfs sending forgets and releases to clean up the 
inodes and the contexts in the inodes maintained by various translators.

Thanks,
Vijay



More information about the Gluster-users mailing list