[Bugs] [Bug 1269730] New: Sharding - Send inode forgets on _all_ shards if/when the protocol layer (FUSE/Gfapi) at the top sends a forget on the actual file

[bugzilla at redhat.com]

https://bugzilla.redhat.com/show_bug.cgi?id=1269730

            Bug ID: 1269730
           Summary: Sharding - Send inode forgets on _all_ shards if/when
                    the protocol layer (FUSE/Gfapi) at the top sends a
                    forget on the actual file
           Product: GlusterFS
           Version: 3.7.6
         Component: sharding
          Keywords: Triaged
          Severity: high
          Priority: high
          Assignee: kdhananj at redhat.com
          Reporter: kdhananj at redhat.com
        QA Contact: bugs at gluster.org
                CC: bugs at gluster.org
        Depends On: 1252263
            Blocks: 1258386 (Gluster-HC-1)



+++ This bug was initially created as a clone of Bug #1252263 +++

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:

--- Additional comment from Krutika Dhananjay on 2015-09-23 06:02:27 EDT ---

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.

--- Additional comment from Krutika Dhananjay on 2015-09-30 02:35:37 EDT ---

http://review.gluster.org/#/c/12254/


Referenced Bugs:

https://bugzilla.redhat.com/show_bug.cgi?id=1252263
[Bug 1252263] Sharding - Send inode forgets on _all_ shards if/when the
protocol layer (FUSE/Gfapi) at the top sends a forget on the actual file
https://bugzilla.redhat.com/show_bug.cgi?id=1258386
[Bug 1258386] [TRACKER] Gluster Hyperconvergence - Phase 1
-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are on the CC list for the bug.