Bug 764300 (GLUSTER-2568) - Memory leaks in gNFS
Summary: Memory leaks in gNFS
Keywords:
Status: CLOSED WORKSFORME
Alias: GLUSTER-2568
Product: GlusterFS
Classification: Community
Component: nfs
Version: mainline
Hardware: x86_64
OS: All
medium
medium
Target Milestone: ---
Assignee: Gaurav
QA Contact:
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2011-03-21 10:12 UTC by tcp
Modified: 2015-12-01 16:45 UTC (History)
4 users (show)

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed:
Regression: RTP
Mount Type: nfs
Documentation: DNR
CRM:
Verified Versions:
Embargoed:

Attachments (Terms of Use)
tarball consisting of valgrind report on linux and libumem report on Solaris (150.00 KB, application/x-tar)
2011-03-21 07:12 UTC, tcp 		no flags Details
Valgrind log (11.47 KB, application/octet-stream)
2011-09-08 06:18 UTC, Gaurav 		no flags Details
View All

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.
Note You need to log in before you can comment on or make changes to this bug.