Date: Mon, 21 Apr 2014 17:27:03 -0600 From: Chris Torek <torek@torek.net> To: John-Mark Gurney <jmg@funkthat.com> Cc: freebsd-hackers@freebsd.org Subject: Re: MAXPHYS in md(4) Message-ID: <201404212327.s3LNR3LS046107@elf.torek.net> In-Reply-To: Your message of "Mon, 21 Apr 2014 16:15:34 -0700." <20140421231534.GY43976@funkthat.com>
next in thread | previous in thread | raw e-mail | index | archive | help
>Why? GEOM modules are written on the assumption that no IO larger >than MAXPHYS will ever be seen... They allocate arrays of structures >or other items based upon MAXPHYS, and will smash the stack/crash//do >bad things if it receives an IO larger than MAXPHYS... > >The change would not break anything that isn't already broken (or >working by luck)... > >Now if you're talking about wanting to increase MAXPHYS, there are many >threads talking about what needs to be done about it, but that is >completely different than this issue... Yes, I was thinking of the latter. It's not *completely* different as it would be nice to let devices crank down the I/O size if they have various address and/or byte-count limits. (Not that I know of any *modern* devices with such limits. I see this is mentioned in old freebsd-arch discussions...) Chris
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201404212327.s3LNR3LS046107>