Date: Thu, 26 Jul 2001 08:37:40 +0100 (BST) From: =?iso-8859-1?q?vishwanath=20pargaonkar?= <vishubp@yahoo.com> To: Julian Elischer <julian@elischer.org>, Zhihui Zhang <zzhang@cs.binghamton.edu> Cc: Bosko Milekic <bmilekic@technokratis.com>, Terry Lambert <tlambert2@mindspring.com>, vishwanath pargaonkar <vishubp@yahoo.com>, freebsd-hackers@FreeBSD.ORG Subject: Re: cluster size Message-ID: <20010726073740.5662.qmail@web5301.mail.yahoo.com> In-Reply-To: <Pine.BSF.4.21.0107251404390.4973-100000@InterJet.elischer.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi, lets come to my question please. tell me can i change mbuf cluster size from 2048 to 4096?? how shd i do it if i can do it? --- Julian Elischer <julian@elischer.org> wrote: > no.. it has to do with the fact that it would be > unwise > to make a cluster > 1 page size since we have no > guarantee that > all drivers could handle breaking up a DMA if a > cluster spanned 2 > physical address ranges. (they can handle a chain of > discontinuous > mbufs but may assume that a single mbuf will have > physically > contiguous data. Now since we cannot span a page > boundary, > we should fit in exacly to get as much room as > possible > and since (pagesize/3) is too small, the next > possibility is (pagesize/2). > > If pagesize/3 was big enough, we might have used > that.. > > > On Wed, 25 Jul 2001, Zhihui Zhang wrote: > > > > > I see. It has something to do with the > power-of-two allocator we are > > using inside the kernel. > > > > -Zhihui > > > > On Wed, 25 Jul 2001, Bosko Milekic wrote: > > > > > > > > On Wed, Jul 25, 2001 at 01:51:51PM -0400, Zhihui > Zhang wrote: > > > > > > > > > > > > On Tue, 24 Jul 2001, Terry Lambert wrote: > > > > > > > > > Zhihui Zhang wrote: > > > > > > > Hi, > > > > > > > in freebsd can we change the cluster > size from 2048 > > > > > > > bytes.If yes how can we do that? > > > > > > > do we have to configure in some file? > > > > > > > > > > > > You must be asking why the mbuf cluster > size is chosen as 2048, right? It > > > > > > is probably a tradeoff between memory > efficient and speed. > > > > > > > > > > Ask yourselves: > > > > > > > > > > "What is the minimum cluster size I would > have to have > > > > > to be able to contain the maximum MTU > worth of data, > > > > > yet remain an even multiple of > sizeof(mbuf) -- 256 > > > > > bytes?" > > > > > > > > A dumb question: why even not odd multiple? > > > > > > > > -Zhihui > > > > > > It actually has to do with the fact that 2K is > the only size equal to > > > or greater than the maximum MTU worth of data > that can be multiplied to a page > > > size without any leftover (in other words, page > size modulo 2K is zero). > > > > > > -- > > > Bosko Milekic > > > bmilekic@technokratis.com > > > > > > > > > To Unsubscribe: send mail to > majordomo@FreeBSD.org > > > with "unsubscribe freebsd-hackers" in the body > of the message > > > > > > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > > with "unsubscribe freebsd-hackers" in the body of > the message > > > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010726073740.5662.qmail>