From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Gleixner Subject: Re: yield() in i2c non-happy paths hits BUG under -rt patch Date: Thu, 19 Nov 2009 14:22:59 +0100 (CET) Message-ID: References: <20091107210147.3e754278@hyperion.delvare> <4AF7148C.9090706@thebigcorporation.com> <20091112211255.09cd884a@hyperion.delvare> <20091116155606.GC29479@sirena.org.uk> <20091118010520.4cd397d4@lxorguk.ukuu.org.uk> <20091118175202.490989d8@hyperion.delvare> <20091119130526.23a69b85@hyperion.delvare> <1258636872.4372.354.camel@twins> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Return-path: In-Reply-To: <1258636872.4372.354.camel@twins> Sender: linux-rt-users-owner@vger.kernel.org To: Peter Zijlstra Cc: Jean Delvare , Leon Woestenberg , Alan Cox , Mark Brown , Sven-Thorsten Dietrich , linux-i2c@vger.kernel.org, rt-users , "Ben Dooks (embedded platforms)" , LKML List-Id: linux-i2c@vger.kernel.org On Thu, 19 Nov 2009, Peter Zijlstra wrote: > On Thu, 2009-11-19 at 14:11 +0100, Thomas Gleixner wrote: > > > You say "NOOP by default", does this imply there is a way to change > > > this? > > > > There is a sysctl: sysctl_sched_compat_yield > > This makes yield() place current behind all other tasks, and sucks too > for some workloads. yield() sucks anyway, so it depends which flavour of suckage you prefer. tglx