Date: Thu, 29 Jan 1998 10:33:58 -0700 From: "Justin T. Gibbs" <gibbs@plutotech.com> To: Bruce Evans <bde@zeta.org.au> Cc: toor@dyson.iquest.net, cvs-all@FreeBSD.ORG, cvs-committers@FreeBSD.ORG, cvs-sys@FreeBSD.ORG, mike@smith.net.au Subject: Re: cvs commit: src/sys/i386/isa wfd.c Message-ID: <199801291736.KAA09603@pluto.plutotech.com> In-Reply-To: Your message of "Fri, 30 Jan 1998 04:00:36 %2B1100." <199801291700.EAA04615@godzilla.zeta.org.au>
next in thread | previous in thread | raw e-mail | index | archive | help
>I didn't see the discussion. Yeah. It was private. >I think a function call bdevswp->d_maxio() would be efficient enough. >You copy the value the vnode on open and always access it from there. >At least if the vnode remains bloated with v_maxio. > >There should also be a cdevsw function to give the "best" i/o size. Exactly. This was mostly what John and I talked about. I think a single function call that returns the "maximum efficient" i/o size and the "maximum possible" I/O size along with some information to indicate any alignment constraints on those values is better than adding more functions for each piece of information. Right now the "best" and the "max" are the same, but if I can ever get back to adding code to consolidate large transfers in the bus dma code, we should be able to handle things like large tape blocks even on controllers that support relatively few SG elements. >Bruce -- Justin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199801291736.KAA09603>