Date: Thu, 8 Jun 2017 20:46:19 +0200 From: peter.blok@bsd4all.org To: =?utf-8?Q?Edward_Tomasz_Napiera=C5=82a?= <trasz@FreeBSD.org> Cc: Hans Petter Selasky <hps@selasky.org>, Tomoaki AOKI <junchoon@dec.sakura.ne.jp>, freebsd-current@freebsd.org Subject: Re: Time to increase MAXPHYS? Message-ID: <D75904BC-BA95-495B-8AC5-29AE7F9B99D1@bsd4all.org> In-Reply-To: <20170605174930.GA6259@brick> 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> <CANCZdfrkc1ERKnJr4JzHpePmU%2BrN5JOgAVePCShPHLDCAE19=w@mail.gmail.com> <CANCZdfpD3G8gR=C2_AekM6VeJ6dzKOnP820OOoF1M_eS0MfJ3g@mail.gmail.com> <20170604163948.eb5f74ce2a233b8f204ba671@dec.sakura.ne.jp> <15e42fd1-055d-28f6-5e24-1448e16954a9@selasky.org> <20170605174930.GA6259@brick>
next in thread | previous in thread | raw e-mail | index | archive | help
One area that breaks after changing MAXPHYS from 128K to 1MB is the = iscsi target. I don=E2=80=99t have details, because that server is = semi-production and I reverted it back ASAP > On 5 Jun 2017, at 19:49, Edward Tomasz Napiera=C5=82a = <trasz@FreeBSD.org> wrote: >=20 > On 0604T0952, Hans Petter Selasky wrote: >> On 06/04/17 09:39, Tomoaki AOKI wrote: >>> Hi >>>=20 >>> One possibility would be to make it MD build-time OTIONS, >>> defaulting 1M on regular systems and 128k on smaller systems. >>>=20 >>> Of course I guess making it a tunable (or sysctl) would be best, >>> though. >>>=20 >>=20 >> Hi, >>=20 >> A tunable sysctl would be fine, but beware that commonly used = firmware=20 >> out there produced in the millions might hang in a non-recoverable = way=20 >> if you exceed their "internal limits". Conditionally lowering this=20 >> definition is fine, but increasing it needs to be carefully verified. >>=20 >> For example many USB devices are only tested with OS'es like Windows = and=20 >> MacOS and if these have any kind of limitation on the SCSI transfer=20= >> sizes, it is very likely many devices out there do not support any=20 >> larger transfer sizes either. >=20 > FWIW, when testing cfiscsi(4) with Windows and OSX I've noticed > that both issue 1MB requests. I wouldn't be surprised if they avoided > doing that for older devices, depending on eg the SCSI version = reported > by device. >=20 > _______________________________________________ > freebsd-current@freebsd.org <mailto:freebsd-current@freebsd.org> = mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-current = <https://lists.freebsd.org/mailman/listinfo/freebsd-current>; > To unsubscribe, send any mail to = "freebsd-current-unsubscribe@freebsd.org = <mailto:freebsd-current-unsubscribe@freebsd.org>"
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?D75904BC-BA95-495B-8AC5-29AE7F9B99D1>