[Openswan dev] ocf-bench bug & performance :)

[David McCullough]

Jivin Harald Jenny lays it down ...
> On Mon, Dec 20, 2010 at 09:32:20PM +1000, David McCullough wrote:
> > 
> > Jivin Harald Jenny lays it down ...
> > > On Mon, Dec 20, 2010 at 06:05:50AM -0500, Paul Wouters wrote:
> > > > On Mon, 20 Dec 2010, Harald Jenny wrote:
> > > > 
> > > > >>[  460.738971] OCF: 100035 requests of 1488 bytes in 49 jiffies (2430.238 Mbps)
> > > > >
> > > > >Did you use a HW driver or just cryptoapi?
> > > > 
> > > > Just cryptosoft. No HW driver. (no cryptoapi, but ocf)
> > > 
> > > As David said, with hardware OCF uses cryptoapi.
> 
> Sorry I forgot the out in without, was typing to fast ;-).

No problem,  I often miss typing a "not",  which changes the meaning
somewhat :-)

> > Not exactly,  OCF has it's own HW drivers as well,  it doesn't need to use
> > cryptoapi at all.  The software "fallback" driver for OCF is cryptosoft.
> > cryptosoft is an OCF driver that is a wrapper for cryptoapi calls rather
> > than carry a second set of SW algs in the kernel.  
> 
> Which is a good idea
> 
> > 
> > In this example paul is not using any HW accelerators,  just the
> > OCF-to-cryptoapi driver called cryptosoft.
> 
> Yes I just meant that.

Cheers,
Davidm

-- 
David McCullough,      david_mccullough at mcafee.com,  Ph:+61 734352815
McAfee - SnapGear      http://www.mcafee.com         http://www.uCdot.org