Soheil Hassas Yeganeh 41ca938616 tcp: return EPOLLOUT from tcp_poll only when notsent_bytes is half the limit
[ Upstream commit 8ba3c9d1c6d75d1e6af2087278b30e17f68e1fff ]

If there was any event available on the TCP socket, tcp_poll()
will be called to retrieve all the events.  In tcp_poll(), we call
sk_stream_is_writeable() which returns true as long as we are at least
one byte below notsent_lowat.  This will result in quite a few
spurious EPLLOUT and frequent tiny sendmsg() calls as a result.

Similar to sk_stream_write_space(), use __sk_stream_is_writeable
with a wake value of 1, so that we set EPOLLOUT only if half the
space is available for write.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-01 13:13:34 +01:00
..
2022-04-20 09:19:40 +02:00
2023-10-25 11:53:19 +02:00
2023-06-21 15:44:10 +02:00
2023-01-18 11:41:09 +01:00
2023-09-23 10:59:43 +02:00
2024-03-01 13:13:32 +01:00
2023-07-27 08:37:23 +02:00
2023-10-25 11:53:21 +02:00
2021-06-18 09:59:00 +02:00
2023-06-21 15:44:10 +02:00
2023-06-21 15:44:10 +02:00