From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.saout.de ([127.0.0.1]) by localhost (mail.saout.de [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id MkuxC5Zd_Gbv for ; Mon, 23 Jul 2012 08:07:40 +0200 (CEST) Received: from molly.corsac.net (molly.corsac.net [IPv6:2002:4ec0:442e::1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.saout.de (Postfix) with ESMTPS for ; Mon, 23 Jul 2012 08:07:39 +0200 (CEST) Message-ID: <1343023657.26887.6.camel@scapa> From: Yves-Alexis Perez Date: Mon, 23 Jul 2012 08:07:37 +0200 In-Reply-To: <20120722214757.GA16793@tansi.org> References: <20120722190757.GB10089@merlins.org> <20120722202213.GA7306@fancy-poultry.org> <20120722190757.GB10089@merlins.org> <1342986452.26887.3.camel@scapa> <20120722203929.GB3925@merlins.org> <20120722214757.GA16793@tansi.org> Content-Type: multipart/signed; micalg="pgp-sha256"; protocol="application/pgp-signature"; boundary="=-Luj+SDLFKJeA2ZbusMG7" Mime-Version: 1.0 Subject: Re: [dm-crypt] aes-xts-plain with aes_x86_64 makes my SSD 5x slower than my encrypted HD List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Arno Wagner Cc: dm-crypt@saout.de --=-Luj+SDLFKJeA2ZbusMG7 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On dim., 2012-07-22 at 23:47 +0200, Arno Wagner wrote: > On Sun, Jul 22, 2012 at 01:39:29PM -0700, Marc MERLIN wrote: > > On Sun, Jul 22, 2012 at 09:47:32PM +0200, Yves-Alexis Perez wrote: > > > > Any suggestions would be appreciated.=20 > > >=20 > > > I'm using Debian sid (so still at 3.2 kernel), currently using a 256G > > > Samsung SSD. What I get is: >=20 > SID? That would be "unstable", whit possible assorted problems. *I* am running SID, not the original reporter. And I have pretty decent speed, thank you :) >=20 > [...] > > gandalfthegreat:~# dd if=3D/dev/mapper/ssdcrypt of=3D/dev/null bs=3D1M = count=3D1024=20 > > 1073741824 bytes (1.1 GB) copied, 44.3302 s, 24.2 MB/s > >=20 > > atop shows dd isn't really pegging a single core: > > THR SYSCPU USRCPU RDDSK WRDSK ST EXC S CPUNR CPU C= MD=20 > > 1 0.60s 0.01s 226.2M 0K -- - D 3 6% d= d >=20 > It would not, as AES-NI (AFAIK) does need very little CPU > assistance. AES-NI may be the problem though. Can you try with > the normal AES module? I think unloading the AES-NI module=20 > may be enough for that, but I am not sure.=20 >=20 > Maybe AES-NI needs very long for something it needs to do each=20 > sector. Google("aes-ni slow") found at least some indications that > aes-ni may still have problems. And I do use aes-ni too. --=20 Yves-Alexis --=-Luj+SDLFKJeA2ZbusMG7 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQIcBAABCAAGBQJQDOopAAoJEDBVD3hx7wuo1cYP/3fl/Wiw82C77eW3fg/0eRGA OQy+gKVSkOwh4vdbH1ECQuEX/RlxGpJA9UdcONCG+yf7jgUU3V5eQKVTbTsUH5QX 2H8Vhdwa+3Y2Ri+uwZW17u63A9W7kTrxV8pHWW/MWt0pxtYfOuwKManuC6z4LvHq q511CvCOqAWcrtIGSq3FyMLCffinnNSzFQhT7cSlNHq8jzI7PfuqELz0WLfp8Wc1 Dn5RUeNi+1jsdvJvfvVFJ7+0E2FX+JKiWtQbXvslyvdSxVHyL+wIOMidu8dpqeQB o+9q7iWjOVl/sF5XwI84OaI4Dbc9aqEFPSZRpIMH2CrnRX07mzdRrW8u2C9UMJqD 7SQe2FNUHCMvz9jV6K49t517m3giJrRIud1au7uJIbHJQ4d93109Jf8q2/GvIUz7 ziwNpyqNZl9Dv3018D/0AwfGLuZXTpxe2FTVrsdChUy4/A4+/n+XRRiNhsbV6bDK 9MTi3yTAiNX/z0XLAWuBsILQwHjGR7kE8Q1ElgkZYHKV05Hs4AbzXwRDlD+Wjko2 VfsQAMftadTpxWtNJBZegoaUpwG+ZJr2ghmYiCxsotmp8ryQ4AX/4qEtd+jE7oZ3 TY7RcOtpwa2AZ31EyZvXUGGq7mpwx/BOroFGaNWYgpToVZPezghzqchaS/8dAeXq LtlMEX2P6RUBm8OgpAIr =4zB0 -----END PGP SIGNATURE----- --=-Luj+SDLFKJeA2ZbusMG7--