From owner-freebsd-current@FreeBSD.ORG Mon Aug 8 03:34:28 2005 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8430516A41F; Mon, 8 Aug 2005 03:34:28 +0000 (GMT) (envelope-from mike@sentex.net) Received: from smarthost1.sentex.ca (smarthost1.sentex.ca [64.7.153.18]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0793E43EF1; Mon, 8 Aug 2005 03:34:27 +0000 (GMT) (envelope-from mike@sentex.net) Received: from pumice3.sentex.ca (pumice3.sentex.ca [64.7.153.26]) by smarthost1.sentex.ca (8.13.3/8.13.3) with ESMTP id j783XXfv026485; Sun, 7 Aug 2005 23:33:33 -0400 (EDT) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by pumice3.sentex.ca (8.13.3/8.13.3) with ESMTP id j783YRpE002099; Sun, 7 Aug 2005 23:34:27 -0400 (EDT) (envelope-from mike@sentex.net) Received: from simian.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.13.3/8.13.3) with ESMTP id j783YPLq022330 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Sun, 7 Aug 2005 23:34:25 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <6.2.1.2.0.20050807233527.06eef730@64.7.153.2> X-Mailer: QUALCOMM Windows Eudora Version 6.2.1.2 Date: Sun, 07 Aug 2005 23:37:02 -0400 To: Pawel Jakub Dawidek From: Mike Tancsa In-Reply-To: <6.2.1.2.0.20050807231805.0449b9c0@64.7.153.2> References: <20050728205413.GB762@darkness.comp.waw.pl> <6.2.1.2.0.20050806205925.0522cad0@64.7.153.2> <20050807065223.GB1002@garage.freebsd.pl> <6.2.1.2.0.20050807091937.040d9e48@64.7.153.2> <20050807160735.GD1002@garage.freebsd.pl> <6.2.1.2.0.20050807231805.0449b9c0@64.7.153.2> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by amavisd-new X-Scanned-By: MIMEDefang 2.51 on 64.7.153.18 X-Scanned-By: MIMEDefang 2.51 on 64.7.153.26 Cc: freebsd-current@freebsd.org Subject: Hifn driver in SMP (was Re: GELI - disk encryption GEOM class committed.) X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 08 Aug 2005 03:34:28 -0000 Actually, it seems I can easily lock up the box with /usr/bin/openssl aes-128-cbc -in big -k pass | ssh -c aes128-cbc mdtancsa@127.0.0.1 "cat - > /home/mdtancsa/targetfile.enc" Is the hifn driver perhaps not fully smp safe ? ---Mike At 11:27 PM 07/08/2005, Mike Tancsa wrote: >At 12:07 PM 07/08/2005, Pawel Jakub Dawidek wrote: >>On Sun, Aug 07, 2005 at 10:07:52AM -0400, Mike Tancsa wrote: >>+> At 02:52 AM 07/08/2005, Pawel Jakub Dawidek wrote: >>+> >>+> >I saw this (I've one hifn here). >>+> >This looks like a bug in hifn(4), it locks up when too many requests are >>+> >sent there. >>+> >Could you try increasing sector size of encrypted provider to eg. 8192? >>+> >(There is '-s' option for 'init' subcommand.) >>+> >>+> No difference. It might even hasten it a little. >>+> >>+> [hippo]# geli init -a 3des -s 8192 -K /var/tmp/da2.key /dev/amrd0s1e >> >>Yes, I'm able to reproduce it easly. >>I made my tests with AES where I see hangs only with small sectorsize - >>AES and 8kB sectorsize works for me. I'm afraid it's hifn(4) issue and >>I'm not sure if I can help here. > >Hmmm, very strange indeed. I just tried with aes and it runs a little >longer, but still eventually locks up. > >[hippo]# geli init -a aes -s 8192 -K /var/tmp/da2.key /dev/amrd0s1e >Enter new passphrase: >Reenter new passphrase: >[hippo]# geli attach -k /var/tmp/da2.key /dev/amrd0s1e >Enter passphrase: >[hippo]# newfs /dev/amrd0s1e.eli >/dev/amrd0s1e.eli: 1024.0MB (2097136 sectors) block size 16384, fragment >size 8192 > using 4 cylinder groups of 256.00MB, 16384 blks, 8192 inodes. >super-block backups (for fsck -b #) at: > 160, 524448, 1048736, 1573024 >[hippo]# mount /dev/amrd0s1e.eli /mnt >[hippo]# bonnie -s 300 -d /mnt/ >File '/mnt//Bonnie.32578', size: 314572800 >Writing with putc()... > > > >[hippo]# iostat -c 1000 > tty amrd0 pass0 cpu > tin tout KB/t tps MB/s KB/t tps MB/s us ni sy in id > 0 0 8.96 2 0.02 0.00 0 0.00 2 0 1 0 97 > 0 179 128.00 18 2.24 0.00 0 0.00 2 0 3 1 94 > 0 61 128.00 16 1.99 0.00 0 0.00 2 0 4 0 93 > 0 61 128.00 18 2.24 0.00 0 0.00 3 0 2 1 94 > 0 61 128.00 18 2.24 0.00 0 0.00 3 0 4 1 93 > 0 61 128.00 18 2.24 0.00 0 0.00 2 0 4 0 94 > 0 61 128.00 17 2.12 0.00 0 0.00 3 0 3 1 94 > 0 61 128.00 18 2.24 0.00 0 0.00 1 0 3 1 94 > 0 61 128.00 17 2.12 0.00 0 0.00 4 0 2 1 93 > 0 61 102.58 24 2.40 0.00 0 0.00 2 0 5 1 92 > 0 61 102.55 22 2.20 0.00 0 0.00 2 0 4 0 94 > 0 61 128.00 17 2.12 0.00 0 0.00 1 0 4 1 94 > 0 61 128.00 18 2.24 0.00 0 0.00 2 0 5 1 91 > 0 61 128.00 17 2.12 0.00 0 0.00 2 0 3 1 95 > 0 61 128.00 17 2.12 0.00 0 0.00 2 0 6 0 92 > 0 61 128.00 18 2.24 0.00 0 0.00 2 0 3 0 95 > 0 61 128.00 17 2.12 0.00 0 0.00 2 0 5 1 93 > 0 61 83.20 25 2.03 0.00 0 0.00 2 0 2 0 96 > 0 60 128.00 17 2.12 0.00 0 0.00 2 0 5 1 92 > 0 61 128.00 18 2.24 0.00 0 0.00 3 0 3 0 94 > tty amrd0 pass0 cpu > tin tout KB/t tps MB/s KB/t tps MB/s us ni sy in id > 0 61 105.52 21 2.16 0.00 0 0.00 2 0 5 1 92 > 0 181 128.00 17 2.12 0.00 0 0.00 2 0 3 0 94 > 0 61 128.00 18 2.24 0.00 0 0.00 3 0 4 0 93 > 0 61 115.11 18 2.02 0.00 0 0.00 2 0 4 0 94 > 0 61 128.00 20 2.49 0.00 0 0.00 1 0 6 1 92 > 0 61 128.00 18 2.24 0.00 0 0.00 3 0 4 1 93 > 0 61 128.00 17 2.12 0.00 0 0.00 2 0 3 0 95 > 0 61 128.00 17 2.12 0.00 0 0.00 3 0 4 1 92 > 0 61 128.00 18 2.24 0.00 0 0.00 2 0 3 1 94 > 0 61 96.73 22 2.07 0.00 0 0.00 2 0 5 0 93 > 0 60 128.00 18 2.24 0.00 0 0.00 1 0 4 1 94