This shows you the differences between two versions of the page.
Both sides previous revision Previous revision | |||
realtime:documentation:howto:debugging:smi-latency:cyclictest-tracing [2018/08/22 10:39] ebugden [Tracing] Remove duplicated content and point to more general cyclictest tracing page |
realtime:documentation:howto:debugging:smi-latency:cyclictest-tracing [2018/08/23 15:24] (current) ebugden [Tracing] Add warning about cyclictest smi count |
||
---|---|---|---|
Line 18: | Line 18: | ||
The steps for obtaining a relevant trace using Cyclictest are explained in detail [[realtime:documentation:howto:tools:cyclictest:tracing|here]]. Since the desired tracer (function tracer) has already been selected, the section on the linked page about selecting instrumentation can be skipped. | The steps for obtaining a relevant trace using Cyclictest are explained in detail [[realtime:documentation:howto:tools:cyclictest:tracing|here]]. Since the desired tracer (function tracer) has already been selected, the section on the linked page about selecting instrumentation can be skipped. | ||
+ | |||
+ | <WRAP center round info 60%> | ||
+ | When using the breaktrace option along with the [[realtime:documentation:howto:tools:cyclictest:options:smi-count|SMI count]] option, the SMI count shown in the Cyclictest output may not increment even if the tracing was stopped after a latency caused by an SMI. This is probably because Cyclictest is stopped before the visual output of the SMI count is updated. | ||
+ | </WRAP> | ||
+ | |||
+ | To make sure that the tracing stopped at the correct time, look at the break value specified below the Cyclictest output after the test stops. This value should correspond to the expected SMI related latency value even if the SMI count on the Cyclictest output is not updated. The latency should also have occurred in the same conditions as the expected SMI latency. | ||
+ | |||
===== Analysis ===== | ===== Analysis ===== | ||