lkml.org 
[lkml]   [2000]   [Nov]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: 2.2.18Pre Lan Performance Rocks!
Date
From
Jesse Pollard <pollard@cats-chateau.net> said:
> On Tue, 31 Oct 2000, Horst von Brand wrote:
> >Jesse Pollard <pollard@tomcat.admin.navo.hpc.mil> said:
> >
> >[...]
> >
> >> Also pay attention to the security aspects of a true "zero copy" TCP stack.
> >> It means that SOMETIMES a user buffer will recieve data that is destined
> >> for a different process.

> >Why? AFAIKS, given proper handling of the issues involved, this can't
> >happen (sure can get tricky, but can be done in principle. Or am I
> >off-base?)

> As I understand the current implementation, this can't. One of the
> optimization s I had read about (for a linux test) used zero copy to/from
> user buffer as well as zero copy in the kernel. I believe the DMA went
> directly to the users memory.

Right. This means you have to ensure (somehow blocking the process(es) with
access to the buffer(s) involved) that nobody can see half-filled buffers.
Tricky, but not impossible, at least not in principle. Or play VM games and
switch the areas underneath atomically. The VM games we have been told are
costlier than the average copy on "typical" machines (PCs, presumably ;-),
plus you'd have to either ensure aligned buffers (how?) or keep two copies
of whatever surrounds them (where is the advantage then?).
--
Horst von Brand vonbrand@sleipnir.valparaiso.cl
Casilla 9G, Vin~a del Mar, Chile +56 32 672616

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 12:45    [W:0.037 / U:17.696 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site