README.rst
1Wait Queue Measurements
2#######################
3
4A Zehpyr application developer may choose between two different wait queue
5implementations: dumb and scalable. These two queue implementations perform
6differently under different loads. This benchmark can be used to showcase how
7the performance of these two implementations vary under varying conditions.
8
9These conditions include:
10
11* Time to add threads of increasing priority to a wait queue
12* Time to add threads of decreasing priority to a wait queue
13* Time to remove highest priority thread from a wait queue
14* Time to remove lowest priority thread from a wait queue
15
16By default, these tests show the minimum, maximum, and averages of the measured
17times. However, if the verbose option is enabled then the raw timings will also
18be displayed. The following will build this project with verbose support:
19
20.. code-block:: shell
21
22 EXTRA_CONF_FILE="prj.verbose.conf" west build -p -b <board> <path to project>
23
24Alternative output with ``CONFIG_BENCHMARK_RECORDING=y`` is to show the measured
25summary statistics as records to allow Twister parse the log and save that data
26into ``recording.csv`` files and ``twister.json`` report.
27This output mode can be used together with the verbose output, however only
28the summary statistics will be parsed as data records.
29
