> -----Original Message-----
> From: Geoff Thorpe [mailto:[EMAIL PROTECTED]]
> Sent: 12 February 2001 20:05
> To: [EMAIL PROTECTED]
> Subject: RE: Rainbow Cryptoswift cards - information
snipped
>
> > However, it wouldn't be so much of an issue if IE didn't exist!
>
> ?? Didn't follow that sorry.
>
What I meant is that SSL is CPU intensive for IE users, since probably all
of us on this list know about the fact that it doesn't support keep-alives.
I have logs full of IE SSL re-negotiations. <hide microsoft criticism
/hide>.
I see no problem at present in offloading CPU processing for SSL, as it's
exactly the same concept as using a graphics card to offload graphics
processing. Until we have on-chip support for SSL, it's probably the best we
can do.
I take your point about Apache not being multi-threaded (and I guess the
Apache group do too, since I believe that's one of the motivations for the
Apache 2.0 project). The issue of latency is thankfully something I haven't
had to face yet. I imagine however that the latency of off-loading SSL
processing is nothing like the latency of back-end database queries.
However, I'm not bold enough to say whether on-chip CPU processing of SSL or
separate cards is the way ahead.
-
John Airey
Internet Systems Support Officer, ITCSD, Royal National Institute for the
Blind,
Bakewell Road, Peterborough PE2 6XU,
Tel.: +44 (0) 1733 375299 Fax: +44 (0) 1733 370848 [EMAIL PROTECTED]
______________________________________________________________________
Apache Interface to OpenSSL (mod_ssl) www.modssl.org
User Support Mailing List [EMAIL PROTECTED]
Automated List Manager [EMAIL PROTECTED]
