Hi @Rafael and @Shuah,
Gentle ping.
Is there any feedback on this patch-set?
Quick summary and history:
1. The patchset introduces a kernel module and a bash selftest driver to
estimate wakeup latency caused by entering idle states
2. The patchset has seemed to provide useful feedback on latency of idle
states
on the IBM POWER architecture
3. It also seems to also be providing desirable results on Intel
machines with
the IPI mechanism (Timer tests are optional here due to some Intel
processors having a pre-wakeup feature and may not tend to actual idle
latency) as reviewed by Doug Smythies.
Intel numbers for reference: https://lkml.org/lkml/2021/4/13/785
--
Thanks
Pratik
On 30/04/21 1:58 pm, Pratik R. Sampat wrote:
Changelog RFC v4 --> PATCH v5:
1. Added a CPU online check prior to parsing the CPU topology to avoid
parsing topologies for CPUs unavailable for the latency test
2. Added comment describing the selftest in cpuidle.sh
As I have made changes to cpuidle.sh's working, hence dropping
"Reviewed-by" from Doug Smythies for the second patch, while retaining
it for the first patch.
RFC v4: https://lkml.org/lkml/2021/4/12/99
---
A kernel module + userspace driver to estimate the wakeup latency
caused by going into stop states. The motivation behind this program is
to find significant deviations behind advertised latency and residency
values.
The patchset measures latencies for two kinds of events. IPIs and Timers
As this is a software-only mechanism, there will additional latencies of
the kernel-firmware-hardware interactions. To account for that, the
program also measures a baseline latency on a 100 percent loaded CPU
and the latencies achieved must be in view relative to that.
To achieve this, we introduce a kernel module and expose its control
knobs through the debugfs interface that the selftests can engage with.
The kernel module provides the following interfaces within
/sys/kernel/debug/latency_test/ for,
IPI test:
ipi_cpu_dest = Destination CPU for the IPI
ipi_cpu_src = Origin of the IPI
ipi_latency_ns = Measured latency time in ns
Timeout test:
timeout_cpu_src = CPU on which the timer to be queued
timeout_expected_ns = Timer duration
timeout_diff_ns = Difference of actual duration vs expected timer
Sample output on a POWER9 system is as follows:
# --IPI Latency Test---
# Baseline Average IPI latency(ns): 3114
# Observed Average IPI latency(ns) - State0: 3265
# Observed Average IPI latency(ns) - State1: 3507
# Observed Average IPI latency(ns) - State2: 3739
# Observed Average IPI latency(ns) - State3: 3807
# Observed Average IPI latency(ns) - State4: 17070
# Observed Average IPI latency(ns) - State5: 1038174
# Observed Average IPI latency(ns) - State6: 1068784
#
# --Timeout Latency Test--
# Baseline Average timeout diff(ns): 1420
# Observed Average timeout diff(ns) - State0: 1640
# Observed Average timeout diff(ns) - State1: 1764
# Observed Average timeout diff(ns) - State2: 1715
# Observed Average timeout diff(ns) - State3: 1845
# Observed Average timeout diff(ns) - State4: 16581
# Observed Average timeout diff(ns) - State5: 939977
# Observed Average timeout diff(ns) - State6: 1073024
Things to keep in mind:
1. This kernel module + bash driver does not guarantee idleness on a
core when the IPI and the Timer is armed. It only invokes sleep and
hopes that the core is idle once the IPI/Timer is invoked onto it.
Hence this program must be run on a completely idle system for best
results
2. Even on a completely idle system, there maybe book-keeping tasks or
jitter tasks that can run on the core we want idle. This can create
outliers in the latency measurement. Thankfully, these outliers
should be large enough to easily weed them out.
3. A userspace only selftest variant was also sent out as RFC based on
suggestions over the previous patchset to simply the kernel
complexeity. However, a userspace only approach had more noise in
the latency measurement due to userspace-kernel interactions
which led to run to run variance and a lesser accurate test.
Another downside of the nature of a userspace program is that it
takes orders of magnitude longer to complete a full system test
compared to the kernel framework.
RFC patch: https://lkml.org/lkml/2020/9/2/356
4. For Intel Systems, the Timer based latencies don't exactly give out
the measure of idle latencies. This is because of a hardware
optimization mechanism that pre-arms a CPU when a timer is set to
wakeup. That doesn't make this metric useless for Intel systems,
it just means that is measuring IPI/Timer responding latency rather
than idle wakeup latencies.
(Source: https://lkml.org/lkml/2020/9/2/610)
For solution to this problem, a hardware based latency analyzer is
devised by Artem Bityutskiy from Intel.
https://youtu.be/Opk92aQyvt0?t=8266
https://intel.github.io/wult/
Pratik R. Sampat (2):
cpuidle: Extract IPI based and timer based wakeup latency from idle
states
selftest/cpuidle: Add support for cpuidle latency measurement
drivers/cpuidle/Makefile | 1 +
drivers/cpuidle/test-cpuidle_latency.c | 157 ++++++++
lib/Kconfig.debug | 10 +
tools/testing/selftests/Makefile | 1 +
tools/testing/selftests/cpuidle/Makefile | 6 +
tools/testing/selftests/cpuidle/cpuidle.sh | 414 +++++++++++++++++++++
tools/testing/selftests/cpuidle/settings | 2 +
7 files changed, 591 insertions(+)
create mode 100644 drivers/cpuidle/test-cpuidle_latency.c
create mode 100644 tools/testing/selftests/cpuidle/Makefile
create mode 100755 tools/testing/selftests/cpuidle/cpuidle.sh
create mode 100644 tools/testing/selftests/cpuidle/settings
