From owner-freebsd-current@freebsd.org Fri Sep 15 15:18:50 2017 Return-Path: Delivered-To: freebsd-current@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id BB98EE1C95C for ; Fri, 15 Sep 2017 15:18:50 +0000 (UTC) (envelope-from lifanov@FreeBSD.org) Received: from mail.lifanov.com (mail.lifanov.com [206.125.175.12]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 9BC3D6B800; Fri, 15 Sep 2017 15:18:50 +0000 (UTC) (envelope-from lifanov@FreeBSD.org) Received: from lm0.local (108-91-140-246.lightspeed.rlghnc.sbcglobal.net [108.91.140.246]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.lifanov.com (Postfix) with ESMTPSA id 74F0B239A28; Fri, 15 Sep 2017 11:18:49 -0400 (EDT) Subject: Re: Time to increase MAXPHYS? References: <0100015c6fc1167c-6e139920-60d9-4ce3-9f59-15520276aebb-000000@email.amazonses.com> <972dbd34-b5b3-c363-721e-c6e48806e2cd@elischer.org> <3719c729-9434-3121-cf52-393a4453d0b2@freebsd.org> To: allanjude@FreeBSD.org Cc: freebsd-current@freebsd.org From: Nikolai Lifanov Message-ID: Date: Fri, 15 Sep 2017 11:18:40 -0400 User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:52.0) Gecko/20100101 Thunderbird/52.3.0 MIME-Version: 1.0 In-Reply-To: <3719c729-9434-3121-cf52-393a4453d0b2@freebsd.org> Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="ECLU8prB6Un7pB8OLocBThOpcIkjEPxKT" X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.23 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: Fri, 15 Sep 2017 15:18:50 -0000 This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --ECLU8prB6Un7pB8OLocBThOpcIkjEPxKT Content-Type: multipart/mixed; boundary="rHFlLT9CQi9OogUgGUTqXnVXHBeiMWdkE"; protected-headers="v1" From: Nikolai Lifanov To: allanjude@FreeBSD.org Cc: freebsd-current@freebsd.org Message-ID: Subject: Re: Time to increase MAXPHYS? References: <0100015c6fc1167c-6e139920-60d9-4ce3-9f59-15520276aebb-000000@email.amazonses.com> <972dbd34-b5b3-c363-721e-c6e48806e2cd@elischer.org> <3719c729-9434-3121-cf52-393a4453d0b2@freebsd.org> In-Reply-To: <3719c729-9434-3121-cf52-393a4453d0b2@freebsd.org> --rHFlLT9CQi9OogUgGUTqXnVXHBeiMWdkE Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: quoted-printable On 6/3/17 11:55 PM, Allan Jude wrote: > On 2017-06-03 22:35, Julian Elischer wrote: >> On 4/6/17 4:59 am, Colin Percival wrote: >>> On January 24, 1998, in what was later renumbered to SVN r32724, dyso= n@ >>> wrote: >>>> Add better support for larger I/O clusters, including larger physica= l >>>> I/O. The support is not mature yet, and some of the underlying >>>> implementation >>>> needs help. However, support does exist for IDE devices now. >>> and increased MAXPHYS from 64 kB to 128 kB. Is it time to increase i= t >>> again, >>> or do we need to wait at least two decades between changes? >>> >>> This is hurting performance on some systems; in particular, EC2 "io1"= >>> disks >>> are optimized for 256 kB I/Os, EC2 "st1" (throughput optimized >>> spinning rust) >>> disks are optimized for 1 MB I/Os, and Amazon's NFS service (EFS) >>> recommends >>> using a maximum I/O size of 1 MB (and despite NFS not being *physical= * >>> I/O it >>> seems to still be limited by MAXPHYS). >>> >> We increase it in freebsd 8 and 10.3 on our systems, Only good result= s. >> >> sys/sys/param.h:#define MAXPHYS (1024 * 1024) /* max raw I/O= >> transfer size */ >> >> _______________________________________________ >> freebsd-current@freebsd.org mailing list >> https://lists.freebsd.org/mailman/listinfo/freebsd-current >> To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.= org" >=20 > At some point Warner and I discussed how hard it might be to make this = a > boot time tunable, so that big amd64 machines can have a larger value > without causing problems for smaller machines. >=20 > ZFS supports a block size of 1mb, and doing I/Os in 128kb negates some > of the benefit. >=20 > I am preparing some benchmarks and other data along with a patch to > increase the maximum size of pipe I/O's as well, because using 1MB > offers a relatively large performance gain there as well. >=20 Hi! I also migrated to 1mb recordsize. What's the status of your patches and/or making MAXPHYS a boot-time tunable? I can help test these. - Nikolai --rHFlLT9CQi9OogUgGUTqXnVXHBeiMWdkE-- --ECLU8prB6Un7pB8OLocBThOpcIkjEPxKT Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- iQJIBAEBCAAyFiEE5oT6TcuaWvG5gtjzZ6sv56ecR0UFAlm771AUHGxpZmFub3ZA ZnJlZWJzZC5vcmcACgkQZ6sv56ecR0WTZhAAt8y0JeghS7+EAmBDIJ/AojjaMr1X rXUvFR+Sc59m3LCQxrXf7gjaB0VG7K+2m39/ky5dI524gnvw0QtWw5Ge2GkyqIEM NMEUouV6n4sYrttC5VAcb0IB9gfV6D0NaUZqFILZrEUBw6prxjU9xx2k8yt/meVJ WbdG/Ci6R3t9TiHY/k5QlPqLwYmQ5cg1mtPw1tawhZxCMd/z8izqZsi6MAKY3tTi XLULXnD0xjbL6SUnxzy26DHeSHeqdAViAThgqj7KbrOUavCtwIJvuR7fRl6vO4Us BHWHsbq9SDk1Ol9QyFyaQ2cpz6I0cwkE/hqBtGn96tZgIVWH5vI29GgreHdNfNYo nFWxGdjvwfqVaLsHySZfIV/C2cCFjC9HxyatgmGk3idwApepbD72Ezn7YUda7PdJ r82Qf/nmTU+R1cTmqfQcTdVJduLpVol9wyiSpkkX2QVSiwrMVHCwDGohnI20vrhj SBMLLVPyu8VWbs96s3AufP5GMmOCfowK8tKNCVYYu1Lbqu7lUIj834Hu2EhMN+uK xVuhu+XgmrdDG6Zqh8lZ3OI92smRdvrdmESp11N4LJIzaU56wXUdVwR3wyGfV/Yo H6DZYYti9Y/FNJkVA/LbXz0vno62rw+1F4x6QhYoOPdRMf5/vxZxi7vv41AhFJdQ MHo/d5ebTEUFWYg= =mSaT -----END PGP SIGNATURE----- --ECLU8prB6Un7pB8OLocBThOpcIkjEPxKT--