On 7/21/17 6:19 AM, Jiffin Tony Thottan wrote:
On 21/07/17 13:11, gui mark wrote:
Hi all (cc maintainers),
We've tried a performance test comparing nfs-ganesha and gNFS from gluster, we
found that gNFS out performs nfs-ganesha by nearly 2 times on OPS.
As I read throught the code FSAL_GLUSTER now adopts sync api from libgfapi, is
there any plan to switch to the *_async ones, so we could possibly gain a
performance boost ?
Which protocol have u tried and which version of ganesha/gluster packages?
Also, my proposed Ganesha V2.6 code has a more async input. Even UDP
should be much faster, as the original TI-RPC code (and previous nTIRPC)
handles them one-at-a-time (using 1 buffer), whereas my code allows many
in parallel.
You'll find that in
https://review.gerrithub.io/#/c/369641/
or
https://github.com/linuxbox2/nfs-ganesha/tree/was26napalm
Besides, I'd appreciate any bug reports....
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
Nfs-ganesha-devel mailing list
Nfs-ganesha-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nfs-ganesha-devel
