Pradeep,
The patch is to catch FSAL cookie related issues and when got one, it will
ask NFS client to read again.
Will you please provide Ganesha logs & tcpdump for both working (RC2) and
non-working (RC6) cases?
- Sachin.
On Tue, Feb 13, 2018 at 7:05 AM, Pradeep wrote:
Hi Deepak,
There's known knowns and unknown knowns related to nfs-ganesha
performance, including lots of ongoing work.
One of the first things I think we'd like to know is...what version of
the software you're testing.
Matt
On Mon, Feb 12, 2018 at 7:01 PM, Deepak Jagtap
Hello,
I noticed that with large number of directory entries, READDIR does not
return all entries. It happened with RC5; but works fine in RC2. I looked
through the changes and the offending change seems to be this one:
Hey Guys,
I ran few performance tests to compare nfs gansha and nfs kernel server and
noticed significant difference.
Please find my test result:
SSD formated with EXT3 exported using nfs ganesha : ~18K IOPSAvg latency:
~8ms Throughput: ~60MBPS
same directory exported using nfs
Technically you should use atomic fetch to read it , at least on some
archs. Also your assertion might not be hit even if the atomic ops are
working right. In fact, they better be working correctly.
As an example, say it is 1 and both threads check for assertion. Then both
threads decrement and
>From Daniel Gryniewicz :
Daniel Gryniewicz has uploaded this change for review. (
https://review.gerrithub.io/399429
Change subject: Don't leak netconfig entities
..
Don't leak netconfig entities
Change-Id:
The Ceph project also maintains RPMs compatible with RHEL, if you'd
prefer a Ceph-flavored version (also works without Ceph, of course, just
like the Gluster versions).
http://download.ceph.com/nfs-ganesha/rpm-V2.5-stable/luminous/x86_64/
Daniel
On 02/09/2018 02:53 PM, Daniel Gryniewicz