I've been doing more testing, and have a couple of observations. I'm
attaching a minimal form of my changes as a patch for the latest
2.6.pre36 git version of the driver. However, it is difficult for me to
test under anything other than 2.6.32 (RHEL 6 beta 2), and there are
some minor differences, though I don't believe they are relevant to my
results.
It looks like "io_is_busy" set to 1 is quite beneficial for quickly
reacting the onset of load.
I do see a lot of downshifting from the top speed when a core is at
"100%" CPU, presumably this means little stalls and lulls, so I expect
"sampling_down_factor" values greater than 1 continue to be useful and
the sampling_down_factor continues to be desirable.
I've testing on a dual Xeon X5680 system (other times I've been testing
on 2-year-old dual Opterons).
I observe about a 10W power consumption reduction at idle between the
"performance" governor and the "ondemand" governor. I've seen even
bigger differences under load, as much as 40 watts, though that could be
associated with some performance differences. I haven't tried to
quantify the effect of the sampling_down_factor tunable on power
consumption under load, presumably it increases it, but its usage is
voluntary and that is to be expected.
I have been unable to find a value of up_threshold that does not switch
frequency on at least one core pretty frequently (ranging a couple of
times a minute to several times a second). However, with fairly fast
sampling intervals (10000 to 50000) I see pretty quick reaction to load
even with UP_THRESHOLD set high (e.g. 50 or even 95). So it is likely
my previous efforts to extend the possible values of UP_THRESHOLD from
11 to 5 are no longer necessary, and are not included in the attached
patch. There are other things I would like to consider doing, however,
that I'll bring up afterwards, but not in this minimal patch.
David C Niemi
--- cpufreq_ondemand.c-git 2010-09-08 16:02:01.000000000 -0400
+++ cpufreq_ondemand.c-git-dcn 2010-09-16 16:31:27.000000000 -0400
@@ -30,10 +30,12 @@
#define DEF_FREQUENCY_DOWN_DIFFERENTIAL (10)
#define DEF_FREQUENCY_UP_THRESHOLD (80)
+#define DEF_SAMPLING_DOWN_FACTOR (1)
+#define MAX_SAMPLING_DOWN_FACTOR (100000)
#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL (3)
#define MICRO_FREQUENCY_UP_THRESHOLD (95)
#define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000)
-#define MIN_FREQUENCY_UP_THRESHOLD (11)
+#define MIN_FREQUENCY_UP_THRESHOLD (5)
#define MAX_FREQUENCY_UP_THRESHOLD (100)
/*
@@ -82,6 +84,7 @@
unsigned int freq_lo;
unsigned int freq_lo_jiffies;
unsigned int freq_hi_jiffies;
+ unsigned int rate_mult;
int cpu;
unsigned int sample_type:1;
/*
@@ -108,10 +111,12 @@
unsigned int up_threshold;
unsigned int down_differential;
unsigned int ignore_nice;
+ unsigned int sampling_down_factor;
unsigned int powersave_bias;
unsigned int io_is_busy;
} dbs_tuners_ins = {
.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
+ .sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
.down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
.ignore_nice = 0,
.powersave_bias = 0,
@@ -259,6 +264,7 @@
show_one(sampling_rate, sampling_rate);
show_one(io_is_busy, io_is_busy);
show_one(up_threshold, up_threshold);
+show_one(sampling_down_factor, sampling_down_factor);
show_one(ignore_nice_load, ignore_nice);
show_one(powersave_bias, powersave_bias);
@@ -340,6 +346,32 @@
return count;
}
+static ssize_t store_sampling_down_factor(struct kobject *a,
+ struct attribute *b, const char *buf, size_t count)
+{
+ unsigned int input, j;
+ int ret;
+ ret = sscanf(buf, "%u", &input);
+
+ mutex_lock(&dbs_mutex);
+ if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1) {
+ mutex_unlock(&dbs_mutex);
+ return -EINVAL;
+ }
+
+ dbs_tuners_ins.sampling_down_factor = input;
+
+ /* Reset down sampling multiplier in case it was active */
+ for_each_online_cpu(j) {
+ struct cpu_dbs_info_s *dbs_info;
+ dbs_info = &per_cpu(od_cpu_dbs_info, j);
+ dbs_info->rate_mult = 1;
+ }
+ mutex_unlock(&dbs_mutex);
+
+ return count;
+}
+
static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
const char *buf, size_t count)
{
@@ -409,6 +441,7 @@
&sampling_rate_min.attr,
&sampling_rate.attr,
&up_threshold.attr,
+ &sampling_down_factor.attr,
&ignore_nice_load.attr,
&powersave_bias.attr,
&io_is_busy.attr,
@@ -562,6 +595,10 @@
/* Check for frequency increase */
if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) {
+ /* If switching to max speed, apply sampling_down_factor */
+ if (policy->cur < policy->max)
+ this_dbs_info->rate_mult =
+ dbs_tuners_ins.sampling_down_factor;
dbs_freq_increase(policy, policy->max);
return;
}
@@ -584,6 +621,9 @@
(dbs_tuners_ins.up_threshold -
dbs_tuners_ins.down_differential);
+ /* No longer fully busy, reset rate_mult */
+ this_dbs_info->rate_mult = 1;
+
if (freq_next < policy->min)
freq_next = policy->min;
@@ -607,7 +647,8 @@
int sample_type = dbs_info->sample_type;
/* We want all CPUs to do sampling nearly on same jiffy */
- int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+ int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate
+ * dbs_info->rate_mult);
if (num_online_cpus() > 1)
delay -= jiffies % delay;
@@ -711,6 +752,7 @@
}
}
this_dbs_info->cpu = cpu;
+ this_dbs_info->rate_mult = 1;
ondemand_powersave_bias_init_cpu(cpu);
/*
* Start the timerschedule work, when this governor
