MicroPython code may rely on the return value of sys.stdout.buffer.write()
to reflect the number of bytes actually written. While in most scenarios a
write() operation is successful, there are cases where it fails, leading to
data loss. This problem arises because, currently, write() merely returns
the number of bytes it was supposed to write, without indication of
failure.
One scenario where write() might fail, is where USB is used and the
receiving end doesn't read quickly enough to empty the receive buffer. In
that case, write() on the MicroPython side can timeout, resulting in the
loss of data without any indication, a behavior observed notably in
communication between a Pi Pico as a client and a Linux host using the ACM
driver.
A complex issue arises with mp_hal_stdout_tx_strn() when it involves
multiple outputs, such as USB, dupterm and hardware UART. The challenge is
in handling cases where writing to one output is successful, but another
fails, either fully or partially. This patch implements the following
solution:
mp_hal_stdout_tx_strn() attempts to write len bytes to all of the possible
destinations for that data, and returns the minimum successful write
length.
The implementation of this is complicated by several factors:
- multiple outputs may be enabled or disabled at compiled time
- multiple outputs may be enabled or disabled at runtime
- mp_os_dupterm_tx_strn() is one such output, optionally containing
multiple additional outputs
- each of these outputs may or may not be able to report success
- each of these outputs may or may not be able to report partial writes
As a result, there's no single strategy that fits all ports, necessitating
unique logic for each instance of mp_hal_stdout_tx_strn().
Note that addressing sys.stdout.write() is more complex due to its data
modification process ("cooked" output), and it remains unchanged in this
patch. Developers who are concerned about accurate return values from
write operations should use sys.stdout.buffer.write().
This patch might disrupt some existing code, but it's also expected to
resolve issues, considering that the peculiar return value behavior of
sys.stdout.buffer.write() is not well-documented and likely not widely
known. Therefore, it's improbable that much existing code relies on the
previous behavior.
Signed-off-by: Maarten van der Schrieck <maarten@thingsconnected.nl>
This is a best-effort implementation of write polling. It's difficult to
do correctly because if there are multiple output streams (eg UART and USB
CDC) then some may not be writeable while others are. A full solution
should also have a return value from mp_hal_stdout_tx_strn(), returning the
number of bytes written to the stream(s). That's also hard to define.
The renesas-ra and stm32 ports already implement a similar best-effort
mechanism for write polling.
Fixes issue #11026.
Signed-off-by: Damien George <damien@micropython.org>
This uses MP_REGISTER_ROOT_POINTER() to register keyboard_interrupt_obj
and removes the same from mpconfigport.h.
Signed-off-by: David Lechner <david@pybricks.com>
This is to keep the top-level directory clean, to make it clear what is
core and what is a port, and to allow the repository to grow with new ports
in a sustainable way.
Maarten van der Schrieck