From owner-freebsd-net@FreeBSD.ORG  Fri Mar 11 14:31:18 2005
Return-Path: <owner-freebsd-net@FreeBSD.ORG>
Delivered-To: freebsd-net@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP
	id 7B4F116A4DF; Fri, 11 Mar 2005 14:31:18 +0000 (GMT)
Received: from f7.mail.ru (f7.mail.ru [194.67.57.37])
	by mx1.FreeBSD.org (Postfix) with ESMTP
	id C2F1C43D58; Fri, 11 Mar 2005 14:31:17 +0000 (GMT)
	(envelope-from _pppp@mail.ru)
Received: from mail by f7.mail.ru with local 
	id 1D9lAa-000FJD-00; Fri, 11 Mar 2005 17:31:16 +0300
Received: from [81.200.13.122] by win.mail.ru with HTTP;
	Fri, 11 Mar 2005 17:31:16 +0300
From: dima <_pppp@mail.ru>
To: Pawel Jakub Dawidek <pjd@FreeBSD.org>
Mime-Version: 1.0
X-Mailer: mPOP Web-Mail 2.19
X-Originating-IP: [81.200.13.122]
Date: Fri, 11 Mar 2005 17:31:16 +0300
In-Reply-To: <20050311141450.GF9291@darkness.comp.waw.pl>
Content-Type: text/plain; charset=koi8-r
Content-Transfer-Encoding: 8bit
Message-Id: <E1D9lAa-000FJD-00._pppp-mail-ru@f7.mail.ru>
cc: John Baldwin <jhb@FreeBSD.org>
cc: Luigi Rizzo <rizzo@icir.org>
cc: Gleb Smirnoff <glebius@FreeBSD.org>
cc: ru@FreeBSD.org
cc: net@FreeBSD.org
cc: rwatson@FreeBSD.org
Subject: Re[2]: Giant-free polling [PATCH]
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
Reply-To: dima <_pppp@mail.ru>
List-Id: Networking and TCP/IP with FreeBSD <freebsd-net.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-net>,
	<mailto:freebsd-net-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-net>
List-Post: <mailto:freebsd-net@freebsd.org>
List-Help: <mailto:freebsd-net-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-net>,
	<mailto:freebsd-net-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Fri, 11 Mar 2005 14:31:18 -0000

> On Fri, Mar 11, 2005 at 04:55:25PM +0300, dima wrote:
> +> I thought about using list also, but considered it to bring
> +> too much overhead to the code. The original idea of handling arrays
> +> seems to be very elegant.
> 
> Overhead? Did you run any benchmarks to prove it?
> I find list-version much more elegant that using an array.

It was an assumption in fact.
So, I didn't try to implement a list-based version.
We should merge our efforts anyway and both versions
should naturally be tested and benchmarked.

> 
> I also don't like the idea of calling handler method with two locks
> held (one sx and one mutex)...

This gives the highest possible granularity though...

> 
> There is still an unresolved problem (in your and our patch as well) of
> using ifnet structure fields without synchronization, as we don't have
> access tointerface's internal mutex, which protects those fields.

I guess iface_locks[] should be removed then. We actually can get
the interface's internal mutex as ifp->ifq_mtx; I will think about
that on weekend.

> 
> -- 
> Pawel Jakub Dawidek                       http://www.wheel.pl
> pjd@FreeBSD.org                           http://www.FreeBSD.org
> FreeBSD committer                         Am I Evil? Yes, I Am!
> 
> ATTACHMENT: application/pgp-signature
>