From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ingo Molnar Subject: Re: 50 Watt idle power regression bisected to Linux-3.10 Date: Tue, 10 Dec 2013 16:06:56 +0100 Message-ID: <20131210150656.GB873@gmail.com> References: <1386478624.4748.19.camel@marge.simpson.net> <1386559014.4875.16.camel@marge.simpson.net> <1386652637.5374.72.camel@marge.simpson.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org To: Thomas Gleixner Cc: Mike Galbraith , Len Brown , Peter Zijlstra , Linux PM list , "linux-kernel@vger.kernel.org" , Jeremy Eder , x86@kernel.org List-Id: linux-pm@vger.kernel.org * Thomas Gleixner wrote: > On Tue, 10 Dec 2013, Mike Galbraith wrote: > > vogelweide:~/:[130]# turbostat -P -i 60 > > pk cor CPU %c0 GHz TSC SMI %c1 %c3 %c6 CTMP %pc3 %pc6 > > 0.02 2.12 2.26 0 43.40 56.57 0.00 53 33.81 0.00 > > 0 0 0 0.23 2.10 2.26 5 65.47 34.30 0.00 52 10.69 0.00 > > ... > > > That, vs solid >99% pc3 for old 3.0 enterprise kernel. What happened, > > dunno, kernel called itself master. Whatever, I don't like test bogons, > > and this is one, so I thought I should let you know. DL980 refuses to > > come close to the previous result. > > Hmm, that's very similar to the issue Len is seing on his quad > socket WM. > > But I can't see it on my dual socket SNB, neither does PeterZ on his > dual socket WM machine. Heisenbugs .... > > Can you offline all cpus except core 0, enable all trace events (nop > tracer), run "sleep 100" and stop and grab the trace? Please make > sure that your tracebuffer is big enough to cover the full thing. I guess because we are facing a Heisenbug it might be prudent to check that the bug is still present with all those cpus offlined and with tracing enabled :-/ Thanks, Ingo