aboutsummaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
authorLen Brown <len.brown@intel.com>2016-02-27 03:11:29 -0500
committerLen Brown <len.brown@intel.com>2016-03-13 03:55:41 -0400
commit0102b06747c7d24e334d2b27c4b43eed693676f1 (patch)
tree6da6cef237200c4bc3743676dfb0d8371b98ee82 /tools
parenttools/power turbostat: show GFX%rc6 (diff)
downloadlinux-dev-0102b06747c7d24e334d2b27c4b43eed693676f1.tar.xz
linux-dev-0102b06747c7d24e334d2b27c4b43eed693676f1.zip
tools/power turbostat: detect and work around syscall jitter
The accuracy of Bzy_Mhz and Busy% depend on reading the TSC, APERF, and MPERF close together in time. When there is a very short measurement interval, or a large system is profoundly idle, the changes in APERF and MPERF may be very small. They can be small enough that an expensive interrupt between reading APERF and MPERF can cause the APERF/MPERF ratio to become inaccurate, resulting in invalid calculation and display of Bzy_MHz. A dummy APERF read of APERF makes this problem much more rare. Apparently this 1st systemn call after exiting a long stretch of idle is when we typically see expensive timer interrupts that cause large jitter. For the cases that dummy APERF read fails to prevent, we compare the latency of the APERF and MPERF reads. If they differ by more than 2x, we re-issue them. Signed-off-by: Len Brown <len.brown@intel.com>
Diffstat (limited to 'tools')
-rw-r--r--tools/power/x86/turbostat/turbostat.c51
1 files changed, 50 insertions, 1 deletions
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9896619e4382..43a6dda434ef 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1059,19 +1059,68 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int cpu = t->cpu_id;
unsigned long long msr;
+ int aperf_mperf_retry_count = 0;
if (cpu_migrate(cpu)) {
fprintf(outf, "Could not migrate to CPU %d\n", cpu);
return -1;
}
+retry:
t->tsc = rdtsc(); /* we are running on local CPU of interest */
if (has_aperf) {
+ unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
+
+ /*
+ * The TSC, APERF and MPERF must be read together for
+ * APERF/MPERF and MPERF/TSC to give accurate results.
+ *
+ * Unfortunately, APERF and MPERF are read by
+ * individual system call, so delays may occur
+ * between them. If the time to read them
+ * varies by a large amount, we re-read them.
+ */
+
+ /*
+ * This initial dummy APERF read has been seen to
+ * reduce jitter in the subsequent reads.
+ */
+
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+ return -3;
+
+ t->tsc = rdtsc(); /* re-read close to APERF */
+
+ tsc_before = t->tsc;
+
if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
return -3;
+
+ tsc_between = rdtsc();
+
if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
return -4;
+
+ tsc_after = rdtsc();
+
+ aperf_time = tsc_between - tsc_before;
+ mperf_time = tsc_after - tsc_between;
+
+ /*
+ * If the system call latency to read APERF and MPERF
+ * differ by more than 2x, then try again.
+ */
+ if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
+ aperf_mperf_retry_count++;
+ if (aperf_mperf_retry_count < 5)
+ goto retry;
+ else
+ warnx("cpu%d jitter %lld %lld",
+ cpu, aperf_time, mperf_time);
+ }
+ aperf_mperf_retry_count = 0;
+
t->aperf = t->aperf * aperf_mperf_multiplier;
t->mperf = t->mperf * aperf_mperf_multiplier;
}
@@ -3554,7 +3603,7 @@ int get_and_dump_counters(void)
}
void print_version() {
- fprintf(outf, "turbostat version 4.10 10 Dec, 2015"
+ fprintf(outf, "turbostat version 4.11 27 Feb 2016"
" - Len Brown <lenb@kernel.org>\n");
}