Date: Thu, 21 Sep 2006 17:59:03 +1000 From: Peter Jeremy <peterjeremy@optushome.com.au> To: Andre Oppermann <andre@freebsd.org> Cc: freebsd-net@freebsd.org, freebsd-current@freebsd.org Subject: Re: Much improved sendfile(2) kernel implementation Message-ID: <20060921075903.GD960@turion.vk2pj.dyndns.org> In-Reply-To: <4511B9B1.2000903@freebsd.org> References: <4511B9B1.2000903@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--Pk6IbRAofICFmK5e Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable 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 tur= ns >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? --=20 Peter Jeremy --Pk6IbRAofICFmK5e Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (FreeBSD) iD8DBQFFEkZH/opHv/APuIcRAhDiAJ9him08wniFTAjcmVqdhFvVpAN5GgCfYtE5 +6i5j8cghQVlzSOqu+LjT0I= =TCn6 -----END PGP SIGNATURE----- --Pk6IbRAofICFmK5e--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060921075903.GD960>