[Date Prev][Date Next] [Thread Prev][Thread Next]
[Thread Index]
[Date Index]
[Author Index]
Re: [dm-devel] [PATCH] DM-CRYPT: Scale to multiple CPUs
- From: Herbert Xu <herbert gondor hengli com au>
- To: Mikulas Patocka <mpatocka redhat com>
- Cc: device-mapper development <dm-devel redhat com>, ak linux intel com, linux-kernel vger kernel org, agk redhat com
- Subject: Re: [dm-devel] [PATCH] DM-CRYPT: Scale to multiple CPUs
- Date: Wed, 2 Jun 2010 16:07:02 +1000
On Wed, Jun 02, 2010 at 01:25:11AM -0400, Mikulas Patocka wrote:
>
> Are you sure that you know what you're talking about? pcrypt_alloc
> contains this:
> switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) {
> case CRYPTO_ALG_TYPE_AEAD:
> return pcrypt_alloc_aead(tb);
> }
>
> return ERR_PTR(-EINVAL);
> --- so for anything other byt AEAD it returns -EINVAL.
So someone needs to write the ablkcipher plugins for pcrypt.
This is the whole point of pcrypt, to implement parallelisation
exactly once, in the crypto layer.
> For what? For avoiding cache bounces? But the encrypting is
> order-of-magnitude slower than memory speed.
Have you benchmarked the Nehalem AES performance lately?
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert gondor apana org au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
[Date Prev][Date Next] [Thread Prev][Thread Next]
[Thread Index]
[Date Index]
[Author Index]