From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH] tcp: Expose the initial RTO via a new sysctl. Date: Tue, 17 May 2011 14:20:23 +0200 Message-ID: <1305634823.2850.90.camel@edumazet-laptop> References: <1305618020-72535-1-git-send-email-tsunanet@gmail.com> <1305618020-72535-2-git-send-email-tsunanet@gmail.com> <1305619677.2850.11.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Benoit Sigoure , davem@davemloft.net, kuznet@ms2.inr.ac.ru, pekkas@netcore.fi, jmorris@namei.org, yoshfuji@linux-ipv6.org, kaber@trash.net, netdev@vger.kernel.org, linux-kernel@vger.kernel.org To: Hagen Paul Pfeifer Return-path: In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Le mardi 17 mai 2011 =C3=A0 13:02 +0200, Hagen Paul Pfeifer a =C3=A9cri= t : > On Tue, 17 May 2011 10:07:57 +0200, Eric Dumazet wrote: >=20 > > I wont discuss if introducing a new sysctl is welcomed, only on pat= ch > > issues. I believe some work in IETF is done to reduce the 3sec valu= e to > > 1sec anyway. >=20 > Why not?=20 Just because I let this point to David and others. I personally dont care that much. > I though all new knobs in this area should be done on a per route > metric so it can be controlled on a per path basis. RTO should be > adjustable on a per path basis, because it depends on the path. >=20 Adding many knobs to each clone had a huge cost on previous kernels. (Think some machines have millions entries in IP route cache), this use= d quite a lot of memory. With latest David work, we'll consume less ram, because we can now shar= e settings, instead of copying them on each dst entry. > Some months back [1] I posted a patch to enable/disable TCP quick ack > mode, which has nothing to do with network paths, just with a local s= erver > policy. But David rejected the patch with the argument that I should = use a > per path knob (this is a little bit inapprehensible for me, but David= has > the last word). Well, if nobody speaks after David, he has the last word indeed. BTW, I remember Stephen actually asked the per route thing, not David. http://kerneltrap.org/mailarchive/linux-netdev/2010/8/23/6283641 Then David also stated it : http://kerneltrap.org/mailarchive/linux-netdev/2010/8/23/6283678 If you really want tcp_quickack thing you really should do it as requested by both Stephen & David ;) Unfortunately, I dont know if its really needed or worthwhile.