Description of problem: ======================= Same as subject. Not performing inode_forget()s on individual shards also will lead to memory leaks, given that FUSE (possibly GFAPI as well) have no knowledge of inodes associated with individual shards. It is for sharding translator to clean up these resources. Version-Release number of selected component (if applicable): How reproducible: Steps to Reproduce: 1. 2. 3. Actual results: Expected results: Additional info:
In addition to the above, shard translator will also need to regulate memory consumption by inode_t objects for individual shards of different sharded files, so that too many inode_t objects in memory don't result in the client process getting OOM-killed.
http://review.gluster.org/#/c/12254/
This bug is getting closed because a release has been made available that should address the reported issue. In case the problem is still not fixed with glusterfs-3.8.0, please open a new bug report. glusterfs-3.8.0 has been announced on the Gluster mailinglists [1], packages for several distributions should become available in the near future. Keep an eye on the Gluster Users mailinglist [2] and the update infrastructure for your distribution. [1] http://blog.gluster.org/2016/06/glusterfs-3-8-released/ [2] http://thread.gmane.org/gmane.comp.file-systems.gluster.user