Benchmark results
Jeremy Allison
jallison at cthulhu.engr.sgi.com
Wed Feb 3 20:09:24 GMT 1999
David Collier-Brown wrote:
>
>
> Methinks this benchmark allows lots of server-side caching (;-))
> Anyone care to comment on the method(ology)?
>
No - it's actually client side caching (the oplocks, see).
What NetBench actually measures in a large part is the
speed of the client memory cache :-) :-) :-).
This is why we beat up ZDNet at the last CIFS conference.
NetApp's proposed CIFSbench isn't any better as it's a
proprietary Win32 based app.
The only reasonable benchmark would be one based on
open code that generated the CIFS calls via direct
socket calls - not going through a Windows redirector
(which is broken in *so many* subtle and not-so-subtle
ways :-). The smbtorture code would be a good start
here.
It still doesn't stop me trumpeting the Samba Netbench
figures when I get good ones though - that's called
"marketing" :-) :-) :-).
Cheers,
Jeremy.
--
--------------------------------------------------------
Buying an operating system without source is like buying
a self-assembly Space Shuttle with no instructions.
--------------------------------------------------------
More information about the samba-technical
mailing list