Re: [jetty-dev] NIO inefficiency?

[Simone Bordet <sbordet@xxxxxxxxxxx>]

Hi,

On Fri, Aug 9, 2013 at 2:53 PM, Viktor Szathmary <phraktle@xxxxxxxxx> wrote:
> I believe the scenario here is that the gzip filter does a flush at the end,
> leading to a NIO write.

Correct.

> Then the close at the end of the request forces
> another NIO write (w/ empty buffer, but the overhead is there).

No.
I just checked 9.1, and we don't call
java.nio.channels.SocketChannel.write() if the buffer is empty.

-- 
Simone Bordet
----
http://cometd.org
http://webtide.com
http://intalio.com
Developer advice, training, services and support
from the Jetty & CometD experts.
Intalio, the modern way to build business applications.