From: Andi Kleen <andi@firstfloor.org>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>,
netdev@vger.kernel.org, davem@davemloft.net,
klassert@mathematik.tu-chemnitz.de
Subject: Re: [RFC PATCH 0/5] IPsec parallelization
Date: Mon, 01 Dec 2008 12:20:22 +0100 [thread overview]
Message-ID: <87hc5o5eh5.fsf@basil.nowhere.org> (raw)
In-Reply-To: <20081201084902.GA19904@gondor.apana.org.au> (Herbert Xu's message of "Mon, 1 Dec 2008 16:49:02 +0800")
Herbert Xu <herbert@gondor.apana.org.au> writes:
>
> I still think that you're much better off doing this in the
> crypto layer. As it stands the only reason why this is attractive
> is because crypto is slow.
>
> Pretty soon processors will start providing crypto support natively
> so this will no longer be the case.
I'm not sure that's a useful argument. When cryptography is not
CPU bound anymore it will be memory bandwidth bound. And in this case
you can still get a win out of parallelization if you parallelize
over multiple sockets with own memory controller or own FSB
because that will give you more bandwidth.
-Andi
--
ak@linux.intel.com
next prev parent reply other threads:[~2008-12-01 11:20 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-12-01 7:16 [RFC PATCH 0/5] IPsec parallelization Steffen Klassert
2008-12-01 7:17 ` [RFC PATCH 1/5] padata: generic interface for parallel processing Steffen Klassert
2008-12-01 7:17 ` [RFC PATCH 2/5] xfrm: add possibility " Steffen Klassert
2008-12-01 7:19 ` [RFC PATCH 3/5] crypto: add possibility to force sync transform Steffen Klassert
2008-12-01 11:22 ` Herbert Xu
2008-12-01 13:19 ` Steffen Klassert
2008-12-01 7:19 ` [RFC PATCH 4/5] crypto: allow allocation of percpu crypto transforms Steffen Klassert
2008-12-01 11:38 ` Herbert Xu
2008-12-01 12:25 ` David Miller
2008-12-01 12:38 ` Herbert Xu
2008-12-01 13:21 ` Steffen Klassert
2008-12-01 7:20 ` [RFC PATCH 5/5] crypto: make struct aead percpu data Steffen Klassert
2008-12-01 11:40 ` Herbert Xu
2008-12-01 13:36 ` Steffen Klassert
2008-12-01 13:44 ` Herbert Xu
2008-12-01 13:47 ` [PATCH 1/6] crypto: hash - Make setkey optional Herbert Xu
2008-12-01 13:47 ` [PATCH 2/6] crypto: null - Switch to shash Herbert Xu
2008-12-01 13:47 ` [PATCH 3/6] crypto: rmd128 " Herbert Xu
2008-12-01 13:47 ` [PATCH 4/6] crypto: rmd160 " Herbert Xu
2008-12-01 13:47 ` [PATCH 5/6] crypto: rmd256 " Herbert Xu
2008-12-01 13:47 ` [PATCH 6/6] crypto: rmd320 " Herbert Xu
2008-12-01 13:51 ` [RFC PATCH 5/5] crypto: make struct aead percpu data Herbert Xu
2008-12-01 13:55 ` Steffen Klassert
2008-12-01 8:49 ` [RFC PATCH 0/5] IPsec parallelization Herbert Xu
2008-12-01 10:29 ` David Miller
2008-12-01 11:15 ` Herbert Xu
2008-12-02 7:58 ` Steffen Klassert
2008-12-02 8:19 ` Herbert Xu
2008-12-02 8:44 ` Steffen Klassert
2008-12-02 8:50 ` Herbert Xu
2008-12-02 9:21 ` Steffen Klassert
2008-12-02 8:53 ` Herbert Xu
2008-12-02 9:39 ` Steffen Klassert
2008-12-02 10:37 ` Herbert Xu
2008-12-01 11:20 ` Andi Kleen [this message]
2008-12-01 13:39 ` Herbert Xu
2008-12-02 8:00 ` Steffen Klassert
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87hc5o5eh5.fsf@basil.nowhere.org \
--to=andi@firstfloor.org \
--cc=davem@davemloft.net \
--cc=herbert@gondor.apana.org.au \
--cc=klassert@mathematik.tu-chemnitz.de \
--cc=netdev@vger.kernel.org \
--cc=steffen.klassert@secunet.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.