Commit 6393d6a102 (cpufreq: ondemand: Eliminate the deadband effect) introduced a performance regression for systems using pcc-cpufreq and ondemand governor. This is measurable with different workloads. E.g. wall-clock time for kernel compilation significantly increased.
The elimination of the deadband effect significantly increased the number of frequency changes with pcc-cpufreq. Instead of reverting commit 6393d6a102 I suggest to add a workaround in pcc-cpufreq to re-introduce the deadband effect for this driver only - to restore the old performance behaviour with pcc-cpufreq with ondemand governor. Following some performance numbers for similar kernel compilations to illustrate the effect of commit 6393d6a102 and the proposed fix. Following typical numbers of kernel compilation tests with varying number of compile jobs: v4.8.0-rc2 4.8.0-rc2-pcc-cpufreq-deadband # of jobst user sys elapsed CPU user sys elapsed CPU 2 440.39 116.49 4:33.35 203% 404.85 109.10 4:10.35 205% 4 436.87 133.39 2:22.88 399% 381.83 128.00 2:06.84 401% 8 475.49 157.68 1:22.24 769% 344.36 149.08 1:04.29 767% 16 620.69 188.33 0:54.74 1477% 374.60 157.40 0:36.76 1447% 32 815.79 209.58 0:37.22 2754% 490.46 160.22 0:24.87 2616% 64 394.13 60.55 0:13.54 3355% 386.54 60.33 0:12.79 3493% 120 398.24 61.55 0:14.60 3148% 390.44 61.19 0:13.07 3453% (HP ProLiant DL580 Gen8 system, 60 CPUs @ 2.80GHz) Link: http://marc.info/?l=linux-pm&m=147160912625600 Signed-off-by: Andreas Herrmann <aherrm...@suse.com> --- drivers/cpufreq/pcc-cpufreq.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) If this change is accepted maybe it's a good idea to tag it also for stable kernels, e.g. starting with v4.4. Thanks, Andreas diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 3f0ce2a..d2e2963 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -200,10 +200,26 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy, { struct pcc_cpu *pcc_cpu_data; struct cpufreq_freqs freqs; + static u32 limit = 0; + u16 status; u32 input_buffer; int cpu; + if (!limit) { + u32 f_min = policy->cpuinfo.min_freq / 1000; + u32 f_max = policy->cpuinfo.max_freq / 1000; + limit = (f_max - f_min) * f_min; + limit /= f_max; + limit *= 1000; + limit += f_min * 1000; + pr_debug("pcc-cpufreq: setting deadband limit to %u kHz\n", + limit); + } + + if (target_freq < limit) + target_freq = policy->min; + cpu = policy->cpu; pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu); @@ -214,6 +230,10 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy, freqs.old = policy->cur; freqs.new = target_freq; + + if (freqs.new == freqs.old) + return 0; + cpufreq_freq_transition_begin(policy, &freqs); spin_lock(&pcc_lock); -- 2.1.4