Regression: ftdi_sio is slow (since Wed Oct 10 15:05:06 2012)

[Stas Sergeev]

Hi.

We have a regression because of this patch:
http://lkml.indiana.edu/hypermail/linux/kernel/1210.1/01456.html
While it is arguably reasonable to have this for tcdrain or close,
it also slows down poll/select a lot because n_tty_poll() does this:

tty_chars_in_buffer(tty) < WAKEUP_CHARS

And it also slows down TIOCOUTQ ioctl I think (not measured).
The slowdown of select() is big, the customer reports the inability
to work that way.

Is this patch really needed? I mean, if the time to check TEMT is
longer than to xmit that char, then what's the use?
Or, if it is really a big deal, I guess it would be necessary to add
a separate, .chars_in_buffer_fast method.

Thoughts?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/