Bug 1471681 - Steadily high CPU usage
Steadily high CPU usage
Status: NEW
Product: nfs-ganesha
Classification: Community
Component: FSAL_GLUSTER (Show other bugs)
devel
x86_64 Linux
unspecified Severity unspecified
: ---
: ---
Assigned To: Kaleb KEITHLEY
:
Depends On:
Blocks:
  Show dependency treegraph
 
Reported: 2017-07-17 05:05 EDT by Jiri Lunacek
Modified: 2017-08-24 10:07 EDT (History)
4 users (show)

See Also:
Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Story Points: ---
Clone Of:
Environment:
Last Closed:
Type: Bug
Regression: ---
Mount Type: ---
Documentation: ---
CRM:
Verified Versions:
Category: ---
oVirt Team: ---
RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: ---


Attachments (Terms of Use)

  None (edit)
Description Jiri Lunacek 2017-07-17 05:05:08 EDT
Description of problem:
Each ganesha export with FSAL_GLUSTER consumes 3-10% CPU.

I have just found these two notions of this issue on the internet with no solution yet.
http://lists.gluster.org/pipermail/gluster-users.old/2016-November/028939.html
https://github.com/nfs-ganesha/nfs-ganesha/issues/124


Version-Release number of selected component (if applicable):
nfs-ganesha-2.3.3-1.el7.x86_64
nfs-ganesha-gluster-2.3.3-1.el7.x86_64
glusterfs-ganesha-3.8.13-1.el7.x86_64


Steps to Reproduce:
1. Create a gluster volume, disable gnfs
2. Create ganesha configuration
3. Start nfs-ganesha service
4. Observe a thread which is consuming CPU

Additional info:
Sample export config:
EXPORT{
	Export_Id= 19 ;
	Path = "/clientmounts/replicated/test";
	FSAL {
		name = GLUSTER;
		hostname="localhost";
		volume="storage-replicated";
		volpath="/clientmounts/test";
	}
	Access_type = RW;
	Disable_ACL = true;
	Squash="No_root_squash";
	Pseudo="/clientmounts/replicated/test";
	Protocols = "3", "4" ;
	Transports = "UDP","TCP";
	SecType = "sys";
}
Comment 3 renaud.fortier 2017-08-24 10:07:45 EDT
We have the same problem with nfs-ganesha 2.5.1

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