From mboxrd@z Thu Jan 1 00:00:00 1970 From: Phil Dibowitz Subject: Re: reminder, 2.6.18 window... Date: Wed, 24 May 2006 12:14:42 -0700 Message-ID: <20060524191442.GG22881@ipom.com> References: <20060523.182217.59656237.davem@davemloft.net> <447412CA.50303@ipom.com> <4474A489.4080308@garzik.org> <20060524185644.GF22881@ipom.com> <4474AE92.3030501@garzik.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="PW0Eas8rCkcu1VkF" Cc: David Miller , netdev@vger.kernel.org Return-path: Received: from cpe-24-24-245-191.socal.res.rr.com ([24.24.245.191]:29750 "EHLO alt") by vger.kernel.org with ESMTP id S1751263AbWEXTOq (ORCPT ); Wed, 24 May 2006 15:14:46 -0400 To: Jeff Garzik Content-Disposition: inline In-Reply-To: <4474AE92.3030501@garzik.org> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org --PW0Eas8rCkcu1VkF Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, May 24, 2006 at 03:05:54PM -0400, Jeff Garzik wrote: > Phil Dibowitz wrote: > >On Wed, May 24, 2006 at 02:23:05PM -0400, Jeff Garzik wrote: > >>I disagree that we should bother about clearing statistics. It always= =20 > >>adds more complication than necessary. Few (if any) other statistics i= n=20 > >>Linux permit easy clearing, often because adding operations other than= =20 > >>'increment' or 'read' requires adding expensive spinlocks or atomic=20 > >>operations. > > > >Every networking device in the world supports clearing interface=20 > >statistics. > >Why should linux not be able to do the most basic operation on any > >cisco/juniper/enterasys/whatever managed switch or router? > > > >It's a common operation on a network interface, I don't see why this is a > >concern. > > > >When I'm debugging a networking issue On a cluster of hundreds and hundr= eds > >of machines at work, I want to be able to reset them all quickly, and ge= t a > >rough idea of if they're all climbing, if they're all climbing at the sa= me > >rate, etc. And being able to do "for i in `cat hostlist`; do ssh $i=20 > >ethtool -z > >eth0; done" is really, really, REALLY, useful. >=20 > Obtaining the difference between two numbers is not that difficult. >=20 > Given any method of clearing statistics across your cluster, I'm certain= =20 > you can come up with a similar method of obtaining the current statistic= =20 > (the baseline). Right, I'm aware there are other ways of doing this - I've written scripts = to record a hundreds of numbers, and then subtract them from each other. But those scripts are work arounds for a feature _lacking_ in the kernel. A feature that, as I've mentioned, is supported on any piece of networking ge= ar (and of course, lets not forget there's a specific option in the kernel con= fig *just* for "behave like a router"). If my patch was invasive and broke things, I would understand the hesitatio= n, but this is a feature that allows people to *choose* to do this if they need to and the code is pretty self-contained. --=20 Phil Dibowitz phil@ipom.com Freeware and Technical Pages Insanity Palace of Metallica http://www.phildev.net/ http://www.ipom.com/ "They that can give up essential liberty to obtain a little temporary safety deserve neither liberty nor safety." - Benjamin Franklin, 1759 --PW0Eas8rCkcu1VkF Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.3 (GNU/Linux) iD8DBQFEdLCiN5XoxaHnMrsRAumnAJ9zfoGnfP6yIFju+FQkKodcTi/ycACfdky5 ysDgNbQ8j2Ehh5RFlozlLeM= =bUm4 -----END PGP SIGNATURE----- --PW0Eas8rCkcu1VkF--