From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Hutchings Subject: Re: bugs/regressions: report in LKML or in bugzilla? Date: Tue, 07 Dec 2010 21:02:56 +0000 Message-ID: <1291755776.21627.13.camel@bwh-desktop> References: <201012071639.58884.Martin@lichtvoll.de> <1291738321.2695.338.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Martin Steigerwald , linux-kernel@vger.kernel.org, netdev To: Eric Dumazet Return-path: In-Reply-To: <1291738321.2695.338.camel@edumazet-laptop> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Tue, 2010-12-07 at 17:12 +0100, Eric Dumazet wrote: > Le mardi 07 d=C3=A9cembre 2010 =C3=A0 16:39 +0100, Martin Steigerwald= a =C3=A9crit : >=20 > > A participant of a linux performance training I hold found a bug wi= th=20 > > window scaling which did not receive any reply as well: > >=20 > > Bug 20312 - System freeze with multiples of 32 in=20 > > /proc/sys/net/ipv4/tcp_adv_win_scale > > https://bugzilla.kernel.org/show_bug.cgi?id=3D20312 > >=20 >=20 > User bug ? >=20 > Documentation/networking/ip-sysctl.txt >=20 > tcp_adv_win_scale - INTEGER > Count buffering overhead as bytes/2^tcp_adv_win_scale=20 > (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale), > if it is <=3D 0. > Default: 2 >=20 > Given we use 32bit numbers, using values outside of [-31 ... 31] make= s litle sense. >=20 > We could add sysctl range limit, but user should not mess with=20 > /proc/sys/net/ipv4/parameters unless he knows what he is doing ? [...] =46or mere humans, the range is not quite os obvious. Which is why thi= s has been fixed in net-2.6 (as noted on that bug report now). Ben. --=20 Ben Hutchings, Senior Software Engineer, Solarflare Communications Not speaking for my employer; that's the marketing department's job. They asked us to note that Solarflare product names are trademarked.