[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200914.165835.2089542967228126257.davem@davemloft.net>
Date: Mon, 14 Sep 2020 16:58:35 -0700 (PDT)
From: David Miller <davem@...emloft.net>
To: soheil.kdev@...il.com
Cc: netdev@...r.kernel.org, edumazet@...gle.com, soheil@...gle.com
Subject: Re: [PATCH net-next 1/2] tcp: return EPOLLOUT from tcp_poll only
when notsent_bytes is half the limit
From: Soheil Hassas Yeganeh <soheil.kdev@...il.com>
Date: Mon, 14 Sep 2020 17:52:09 -0400
> From: Soheil Hassas Yeganeh <soheil@...gle.com>
>
> 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@...gle.com>
> Signed-off-by: Eric Dumazet <edumazet@...gle.com>
Applied.
Powered by blists - more mailing lists