Instead of going through 'hal' then 'scheduler', use directly the AP_HAL
functions. Besides removing indirection that is not necessary for such
functions, this patch ends up reducing the code size in the call sites.
For example, building ArduCopter for PX4 with this change (compared to
before introduction of the functions) yields almost 3k bytes of code
size.
# ArduCopter build before the functions (1b29a1af46)
text data bss dec hex filename
895264 2812 62732 960808 ea928 /.../px4fmu-v2_APM.build/firmware.elf
# ArduCopter build after this patch
text data bss dec hex filename
892264 2812 62732 957808 e9d70 /.../px4fmu-v2_APM.build/firmware.elf
A later patch will remove the unused functions in the Schedulers.
Implement the new AP_HAL functions and use them in the Scheduler when
possible.
Because the functions are in a namespace, there's no need to do the
define/undef trick and avoid the globals millis() and micros() provided
by libmaple.
Implement the new AP_HAL functions and use them in the Scheduler when
possible.
The '_sketch_start_time' was renamed and moved as a detail of
implementation of the functions code. It allows the code to return time
starting from zero.
The 'stopped_clock_usec' was renamed to follow convention in the file
and add a getter so that AP_HAL functions can reach it. It's not a
problem this getter is public because in practice, regular code
shouldn't even access the Linux::Scheduler directly -- only code that
should is from Linux implementation.
Implement the new AP_HAL functions and use them in the Scheduler when
possible.
The '_sketch_start_time' was renamed and moved as a detail of
implementation of the functions code. It allows the code to return time
starting from zero.
The 'stopped_clock_usec' was renamed to follow convention in the file
and add a getter so that AP_HAL functions can reach it. It's not a
problem this getter is public because in practice, regular code
shouldn't even access the SITLScheduler directly -- only code that
should is from SITL itself.
For certain basic functionality, there aren't much benefit to be able to
vary the implementation easily at runtime. So instead of using virtual
functions, use regular functions that are "resolved" at link time. The
implementation of such functions is provided per board/platform.
Examples of functions that fit this include: getting the current
time (since boot), panic'ing, getting system information, rebooting.
These functions are less likely to benefit from the indirection provided
by virtual interfaces. For more complex hardware access APIs the
indirection makes more sense and ease the testing (when we have it!).
The idea is that instead of calling
hal.scheduler->panic("on the streets of london");
now use
AP_HAL::panic("on the streets of london");
A less important side-effect is that call-site code gets
smaller. Currently the compiler needs to get the hal, get the scheduler
pointer, get the right function pointer in the vtable for that
scheduler. And the call must include an extra parameter ("this"). Now it
will be just a function call, with the address resolved at link time.
This patch introduces the first functions that will be in the namespace,
further patches will implementations for each board and then switch the
call-sites. The extra init() function allow any initial setup needed for
the functions to work.
This revised threshold value is still double the maximum that has been observed in flight logs so far with healthy sensors
The previous value was too slow to switch for sudden IMU gyro faults
We can afford an ocasional false trigger becasue the front end will only select another instance if it is healthy and has lower errors
The ad-hoc scaling of error growth has been replaced with a consistent method that uses the main nav filters published vertical velocity uncertainty and the terrain gradient assumption.
Caio Marcelo de Oliveira Filho
Randy Mackay
bugobliterator
Jonathan Challinger
Paul Riseborough
Andrew Tridgell