Date: Thu, 21 Sep 2006 12:30:30 +0200 From: Claudio Jeker <cjeker@diehard.n-r-g.com> To: freebsd-net@freebsd.org Subject: Re: Much improved sendfile(2) kernel implementation Message-ID: <20060921103030.GA30890@diehard.n-r-g.com> In-Reply-To: <20060921075903.GD960@turion.vk2pj.dyndns.org> References: <4511B9B1.2000903@freebsd.org> <20060921075903.GD960@turion.vk2pj.dyndns.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Sep 21, 2006 at 05:59:03PM +1000, Peter Jeremy wrote: > On Wed, 2006-Sep-20 23:59:13 +0200, Andre Oppermann wrote: > >I have rewritten kern_sendfile() to work in two loops, the inner which turns > >as many pages into mbufs as it can up to the free send socket buffer space. > > The 64K blocks sounds good but how does this interact with TCP slow > start? Is there the possibility that a couple (for some reasonably > large value of 'couple') of TCP connections slowly accepting a file > could eat all the mbuf space? > You always have this issue no matter if you use sendfile or not. This is why the socket buffers are limited and why sometimes having large sendbuffers is bad -- especially on busy servers. -- :wq Claudio
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060921103030.GA30890>