Re: [Qemu-devel] unix sockets for qemu

[Paolo Bonzini]

Il 26/02/2013 17:51, Daniel P. Berrange ha scritto:
> On Tue, Feb 26, 2013 at 05:31:04PM +0100, Stefan Hajnoczi wrote:
>> On Mon, Feb 25, 2013 at 07:02:30PM -0600, address@hidden wrote:
>>> The associated file contains a README that will guide you through the
>>> experiment that shows the difference between unix socket carried pings:
>>> 0.7ms and inet carried pings: 40ms!!!
>>
>> There is no fundamental reason for inet sockets to have a 40 millisecond
>> round-trip time on localhost.  I remember from years ago that Solaris
>> "fuses" localhost inet sockets and bypasses TCP for them.
>>
>> Adding a call to socket_set_nodelay() net/socket.c might help.
> 
> Yes, I'm pretty sure it will be the nagle algorithm that is causing this
> delay. Localhost IP sockets can round-trip ICMP packets in <0.1 ms
> 
> If we don't want to disable nagle by default here, we could at least
> make it a configurable option for people.

The guest will do Nagle's algorithm on its own, there's no reason to
keep it on the host.

Paolo