Pixhawk performance monitoring

Hello,

I've just got my first pixhawk after building a few UAVs with apm 2.x boards.

when using the apm i used to download the dataflash logs (the on-board logs) and analyze them, specifically the cpu performance monitoring values (to check and compare modified firmwares).

i usually looked on these parameters:

(for copters)
NLon: number of long running main loops (i.e. loops that take more than 5% longer than the 10ms they should).
NLoop: the total number of loops since the last PM message was displayed. Normally 1000 and allows you to calculate the percentage of slow running loops which should never be higher than 15%.

MaxT: the maximum time that any loop took since the last PM message. This should be close to 10,000 but will be up to 6,000,000 during the interval where the motors are armed.

(for planes)
Ltime
GDT-Maximum time to execute fast loop for.

1) when using apm project firmwares (which can be configured and calibrated by mission planner but not by qgroundcontrol) with the pixhawk board i receive logs in the same format and with the same parameters, but I would like to know what are the ranges that these parameters (above) should be in, while using a pixhawk? are they different from the normal values for the apm boards (because of the hardware difference)?

2) i would like to use the pixhawk firmwares (which can be configured and calibrated by qgroundcontrol but not by mission planner) with qgroundcontrol, but for the pixhawk logs (.px4log which i change to .bin and parse with sdlog2_dump.py, or view with FlightPlot) i can't find any documentation that explains what is the meaning of the parameters in the logs. as i said i'm specifically interested in the parameters that are related to cpu performance monitoring.

what are the parameters that are related to performance monitoring, what is their meaning and what are normal values for them? 

Thanks in advance, Jack.

You need to be a member of diydrones to add comments!

Join diydrones

Email me when people reply –

Replies

This reply was deleted.