From: Herbert Xu Subject: Re: comparison of the AF_ALG interface with the /dev/crypto Date: Thu, 1 Sep 2011 22:59:02 +0800 Message-ID: <20110901145902.GA31834@gondor.apana.org.au> References: <20110901133952.GB14522@orbit.nwl.cc> <20110901141445.GA31447@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Phil Sutter , cryptodev-linux-devel@gna.org, linux-crypto@vger.kernel.org, linux-kernel@vger.kernel.org To: Nikos Mavrogiannopoulos Return-path: Received: from helcar.apana.org.au ([209.40.204.226]:41907 "EHLO fornost.hengli.com.au" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932252Ab1IAO7M (ORCPT ); Thu, 1 Sep 2011 10:59:12 -0400 Content-Disposition: inline In-Reply-To: Sender: linux-crypto-owner@vger.kernel.org List-ID: On Thu, Sep 01, 2011 at 04:56:56PM +0200, Nikos Mavrogiannopoulos wrote: > On Thu, Sep 1, 2011 at 4:14 PM, Herbert Xu wrote: > > > Are you maxing out your submission CPU? If not then you're testing > > the latency of the interface, as opposed to the throughput. > > I think it is obvious that a benchmark of throughput measures > throughput. If however, you think that AF_ALG is in disadvantage in > this benchmark, because it is a high latency interface, you're free to > propose and perform another one. I haven't seen anywhere how is this > interface was supposed to be used, nor about its qualities (high > latency, maybe(?) high throughput or so). Thus, I designed this > benchmark with a use-case in mind, i.e., a TLS or DTLS tunnel > executing in a system with such an accelerator. There might be other > benchmarks with other use cases in mind, but I haven't seen any. Putting TLS data-path in user-space is always going to be less than optimal, especially with hardware crypto offload, since you'll be crossing the user-space/kernel boundary multiple times. The data-path should reside in the kernel so as to avoid that. Cheers, -- Email: Herbert Xu Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt