From owner-freebsd-hackers@FreeBSD.ORG Sun Jan 20 00:11:04 2013 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.freebsd.org (mx1.FreeBSD.org [8.8.178.115]) by hub.freebsd.org (Postfix) with ESMTP id 0046B25D for ; Sun, 20 Jan 2013 00:11:03 +0000 (UTC) (envelope-from scott4long@yahoo.com) Received: from nm15-vm4.bullet.mail.ne1.yahoo.com (nm15-vm4.bullet.mail.ne1.yahoo.com [98.138.91.175]) by mx1.freebsd.org (Postfix) with ESMTP id BD7856EC for ; Sun, 20 Jan 2013 00:11:03 +0000 (UTC) Received: from [98.138.90.48] by nm15.bullet.mail.ne1.yahoo.com with NNFMP; 20 Jan 2013 00:10:57 -0000 Received: from [98.138.84.45] by tm1.bullet.mail.ne1.yahoo.com with NNFMP; 20 Jan 2013 00:10:57 -0000 Received: from [127.0.0.1] by smtp113.mail.ne1.yahoo.com with NNFMP; 20 Jan 2013 00:10:57 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1358640657; bh=5wZ1oqPghfnXLKaF++uLOenHoGZSRLmZWjPlIXY+/YI=; h=X-Yahoo-Newman-Id:X-Yahoo-Newman-Property:X-YMail-OSG:X-Yahoo-SMTP:Received:Content-Type:Mime-Version:Subject:From:In-Reply-To:Date:Cc:Content-Transfer-Encoding:Message-Id:References:To:X-Mailer; b=Dwv6ky5Hsq/5wb1zuvlPzt2/DaXS4RS9z9TdTXWUuXVFuBi+TCoQ6qKNm2/HYKcjVlWM4xwFGLqpJ+jKFu712yZ/sYqc/8bQs1NBAoZ//TfZ1dbMAEJ5/m9Z36v33Zz6ewXjAC2Z0kgwzH7MzfpYNVK5vTA2KtAUcD09Uox0AAU= X-Yahoo-Newman-Id: 565520.14309.bm@smtp113.mail.ne1.yahoo.com X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: mvZTaN0VM1kI6fZMmHgSMCKft_bu7TKse8ELx.f1YdFriRR d_plXLAdEqch9aQmIdvGprV_3GVJ1nkAOff.3H2l6vvccHyx7DDmszMclGpo GkCzSf93O8LXcTcfUBMKI._GcsrJufBwyoNWJqMT9c2ZYLRzUT8SoorfoGTX T81TLWMLlKqSau9lD6.Xm1s6b6.IUH_TSaLZTNZMN8RGjGHxMEbrdejrFlF_ UoLlgk5F3wLiwy7P5Vkr6GV2N9Edn1Z8VIW7yLHbvab.vnWpQeYlSF8SsuGP mwzBjXlTHoJTADpsAS1fncMdbRpjN59b80NPTI_10BPyPxqqAdCSDyS1618o F1Ket1HQjhD02ziTujNvh.KgsNepZ127dkSDmmH.KYKpGBZxjtqkqv08rwkc zvlil8VDvDiDb8Qo0.5T6OLwbELhh1vDwfitkK7a7NanAkj80NUoy2Rr3Q5A L8G13y.6.qEq5 X-Yahoo-SMTP: clhABp.swBB7fs.LwIJpv3jkWgo2NU8- Received: from [192.168.1.108] (scott4long@216.237.246.3 with plain) by smtp113.mail.ne1.yahoo.com with SMTP; 19 Jan 2013 16:10:57 -0800 PST Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 6.2 \(1499\)) Subject: Re: IBM blade server abysmal disk write performances From: Scott Long In-Reply-To: Date: Sat, 19 Jan 2013 17:10:57 -0700 Content-Transfer-Encoding: quoted-printable Message-Id: References: <6C0B86E6-195C-4D35-AE40-3D2F9F6D28FB@yahoo.com> <1358544287.32417.251.camel@revolution.hippie.lan> <50F9CFEB.5060302@feral.com> <50F9DB9A.9050303@gmail.com> <50FABB71.6050406@freebsd.org> To: Wojciech Puchar X-Mailer: Apple Mail (2.1499) X-Mailman-Approved-At: Sun, 20 Jan 2013 00:36:31 +0000 Cc: Karim Fodil-Lemelin , "freebsd-hackers@freebsd.org Hackers" , "gibbs@FreeBSD.org Gibbs" , "mjacob@FreeBSD.org Jacob" X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 20 Jan 2013 00:11:04 -0000 On Jan 19, 2013, at 4:33 PM, Wojciech Puchar = wrote: >> to be enabled to get any speed-up from tagged commands. This was no >> risk with SCSI drives, since the cache did not make the drives lye >=20 > i see no correlation between interface type and possibility of lying = about command completion. >=20 Any interface that enables write cache will lie about write completions. = This is true for SAS, SATA, SCSI, and PATA (and probably FC and iSCSI). = That's the whole point of the write cache =3D-) Where things got interesting was in the days of SCSI vs PATA. There was no tagged queuing for PATA, except for a hack that allowed CDROMs to disconnect from the shared bus. So you only got 1 command at a time, = and you payed a serialized latency penalty. The only way to get reasonable write performance on PATA was to enable the write cache. Meanwhile, SCSI had TCQ and could amortize the latency penalty to the point where performance with TCQ and no WC was almost as good at with WC. This made SCSI the clear choice for performance + data safety. With SATA vs SAS, the gap is much narrower. The TCQ command set (still used by SAS) is still better than the NCQ command set, but the differences are minor enough that it doesn't matter for most = applications. Scott