Content-Type: multipart/mixed; boundary="===============2864864613545993138==" MIME-Version: 1.0 From: Dietmar Eggemann To: lkp@lists.01.org Subject: Re: [sched] WARNING: CPU: 0 PID: 0 at arch/x86/kernel/cpu/common.c:1439 warn_pre_alternatives() Date: Fri, 19 Dec 2014 15:51:22 +0100 Message-ID: <54943B6A.9050309@arm.com> In-Reply-To: <20141210232645.GD24163@wfg-t540p.sh.intel.com> List-Id: --===============2864864613545993138== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Hi Fengguang, On 11/12/14 00:26, Fengguang Wu wrote: > Hi Dietmar, > > FYI, here is another bisect result. thanks for testing this on another arch then ARM! The problem is that the weak arch_scale_cpu_capacity calls = default_scale_cpu_capacity on a system which doesn't overwrite it and = the default one accesses the sched_domain which is not allocated that = early when called by scheduler_tick. I only tested it on an ARM system which in this tree which overwrites = arch_scale_cpu_capacity and does not access sched_domain. Have to look into it and will test the default case from now on too. -- Dietmar > > https://git.linaro.org/people/mturquette/linux.git eas-next > commit 1fadb581b0be9420b143e43ff2f4a07ea7e45f6c > Author: Dietmar Eggemann > AuthorDate: Tue Dec 2 14:06:24 2014 +0000 > Commit: Michael Turquette > CommitDate: Tue Dec 9 20:33:17 2014 -0800 > > sched: Make usage and load tracking cpu scale-invariant > > Besides the existing frequency scale-invariance correction factor, a= pply > cpu scale-invariance correction factor to usage and load tracking. > > Cpu scale-invariance takes cpu performance deviations due to > micro-architectural differences (i.e. instructions per seconds) betw= een > cpus in HMP systems (e.g. big.LITTLE) and differences in the frequen= cy > value of the highest OPP between cpus in SMP systems into considerat= ion. > > Each segment of the sched_avg::{running_avg_sum, runnable_avg_sum} > geometric series is now scaled by the cpu performance factor too so = the > sched_avg::{utilization_avg_contrib, load_avg_contrib} of each entit= y will > be invariant from the particular cpu of the HMP/SMP system it is gat= hered > on. As a result, cfs_rq::runnable_load_avg which is the sum of > sched_avg::load_avg_contrib, becomes cpu scale-invariant too. > > So the {usage, load} level that is returned by {get_cpu_usage, > weighted_cpuload} stays relative to the max cpu performance of the s= ystem. > > Cc: Ingo Molnar > Cc: Peter Zijlstra > Signed-off-by: Dietmar Eggemann > [...] --===============2864864613545993138==--