Bug 764300 (GLUSTER-2568)

Summary: Memory leaks in gNFS
Product: [Community] GlusterFS Reporter: tcp
Component: nfsAssignee: Gaurav <ggangalw>
Status: CLOSED WORKSFORME QA Contact:
Severity: medium Docs Contact:
Priority: medium    
Version: mainlineCC: gluster-bugs, sgowda, vbellur, vijay
Target Milestone: ---   
Target Release: ---   
Hardware: x86_64   
OS: All   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: RTP Mount Type: nfs
Documentation: DNR CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Attachments:
Description Flags
tarball consisting of valgrind report on linux and libumem report on Solaris
none
Valgrind log none

Description tcp 2011-03-21 10:12:29 UTC 
The gNFS server leaks memory under I/O. Particularly, the file operation sequence - (Open, Read, Close) of a large number of files results in the memory footprint of the gNFS process to grow quickly. The memory usage does not reduce even after successfully unmounting all the clients.

Find attached the following:

* valgrind report on Linux (courtesy Shishir)
* libumem report from Solaris
Comment 1 Shehjar Tikoo 2011-05-25 05:55:51 UTC 
Assigning to Gaurav for further investigation.
Comment 2 Gaurav 2011-09-08 06:18:33 UTC 
Created attachment 653
Comment 3 Gaurav 2011-09-08 06:20:46 UTC 
Attaching the valgrind log for gNFS, i did file operation sequence (Open, Read, Close) of a large number of files (1000 files each of size 2k). Not seeing any memory leak.