| commit | 05ffbccfb2eaec7ad8a1b6f4c1b8ef2706854089 | [log] [tgz] |
|---|---|---|
| author | Javi Merino <javi.merino@arm.com> | Fri Feb 26 11:37:42 2016 +0000 |
| committer | Javi Merino <javi.merino@arm.com> | Fri Feb 26 14:11:01 2016 +0000 |
| tree | 9c72ed84fb163841468c5acc4a39a46dab3bc6a4 | |
| parent | f703d77cfc6f8f36051d6e5944370974326afddf [diff] |
Trigger: narrow the data_frame with the pivot before applying the filter
Some complex filters require you to look at previous values of the
data. For example, we may want to know when a frequency is no longer
used for a given cpu.
Trigger(trace, trace.cpu_frequency, pivot="cpu",
filters={"frequency": freq_no_longer(max_freq)}, value=-1)
freq_no_longer(max_freq) returns True if the previous frequency of this
cpu was max_freq and the current is not. The tricky bit is "of this
cpu". With the current implementation, all freq_no_longer() sees is the
previous value, but it doesn't know to which cpu it corresponds.
Filter the data_frame with the pivot (as we are going to end up doing
regardless) before applying the filter to avoid exposing the filter to
values that are useless to it.
trappy is a visualization tool to help analyze data generated on a device. It depends on ipython notebook and pandas. First install these dependencies if you don't have them already:
$ apt-get install ipython-notebook python-pandas
Now launch the ipython notebook server:
$ ipython notebook
This should pop up a browser. If it doesn't, open a web browser and go to http://localhost:8888/tree/
In the doc/ folder there's a 00 - Quick start which describes how to run trappy. Other notebooks in that directory describe other functions of trappy.