From owner-freebsd-hackers Fri Dec 28 8:55:53 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from anansi.vpha.health.ufl.edu (anansi.vpha.health.ufl.edu [159.178.78.153]) by hub.freebsd.org (Postfix) with ESMTP id 5217C37B427 for ; Fri, 28 Dec 2001 08:55:37 -0800 (PST) Received: (from dymphna@localhost) by anansi.vpha.health.ufl.edu (8.9.3/8.9.3) id LAA19207; Fri, 28 Dec 2001 11:55:36 -0500 Date: Fri, 28 Dec 2001 11:55:36 -0500 From: sridharv@ufl.edu Message-Id: <200112281655.LAA19207@anansi.vpha.health.ufl.edu> X-Authentication-Warning: anansi.vpha.health.ufl.edu: dymphna set sender to sridharv@ufl.edu using -f To: hackers@FreeBSD.ORG Reply-To: sridharv@ufl.edu References: <200112280640.BAA01182@anansi.vpha.health.ufl.edu> <20011227224726.A3662@iguana.icir.org> In-Reply-To: <20011227224726.A3662@iguana.icir.org> MIME-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 8bit User-Agent: IMP/PHP3 Imap webMail Program 2.0.10 X-Originating-IP: 216.78.162.73 Subject: Re: IP queue question Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG is there any specific advantage in using device_polling method? does is give sth other than fairness? or is the multiple queue a 100% a;ternative? can u tell me a bit more about inline processing? or pointers to text would also do cheers s Quoting Luigi Rizzo : > Hi, > FreeBSD uses a single queue, but as long as you make sure that you > do not fill the queue with packets coming from a single interface, > you can still give some fairness to the system. Recent "DEVICE_POLLING" > code in -current (hopefully going into -stable at some point) does > exactly this -- an alternative way, which is not terribly hard to > implement, could be to put packets from each interface into a > separate queue as Comer suggests, and then going round-robin on > these queues upon the software interrupt. > > As for the soft interrupt going away soon, this won't happen, there > are pros and cons for using delayed processing so the goal is to > augment the mechanism with inline processing, not replace it. > > cheers > luigi > > On Fri, Dec 28, 2001 at 01:40:00AM -0500, sridharv@ufl.edu wrote: > > I was reading TCP/IP Vol 2 by douglas comer. In that > > he has one queue for each interface from which the IP > > layer processes the incoming datagrams. He has used > > round-robin for fairness. I checked up the BSD code > > and it seems to use only one queue 'ipintrq'. The > > ethernet driver places the mbuf in this queue for an > > IP payload. Comer has also asked a review question > > pertaining to the disadvantage of having a single > > queue ( which i presume inhibits fair scheduling and > > stuff) > > Have I interpreted the code correctly? Y is this so in > > BSD? > > Also when I took a look at FreeBSD ipinput code the > > ipintr function which handles the software interrupt > > had a comment which said " to go away sometime soon" . > > Why and what is the alternative? > > > > The fastest way to change is to laugh at your own > > folly - Who moved my cheese > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > > with "unsubscribe freebsd-hackers" in the body of the message > The fastest way to change is to laugh at your own folly - Who moved my cheese To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message