Message-Id: <1182431826.5614.38.camel@moonstone.uk.level5networks.com>
Date:	Thu, 21 Jun 2007 14:17:06 +0100
From:	Kieran Mansley <kmansley@...arflare.com>
To:	xen-devel@...ts.xensource.com
Cc:	netdev@...r.kernel.org
Subject: [PATCH 0/4] [Net] Support accelerated network plugin modules

This is a another iteration of some earlier patches sent to the xen-
devel mailing list, with a number of changes thanks to some useful
suggestions from others.

I've also CC'd netdev@...r.kernel.org at Herbert Xu's request as some of
the files being patched may be merged into upstream linux soon, and so
folks there may have opinions too.

Major changes from last time:
 - Modify protection in frontend to use an atomic ref count to reduce
the number of spinlocks that are required, as suggested by Keir Fraser
and Zhu Han.  This change required an improvement to the protection of
the hooks when they are being installed for a second (or subsequent
time) to prevent the new copy being inserted before the old ones have
been completely finished with.

 - Move the majority of the acceleration code out of existing
netfront/netback source files and into separate accel.c source file in
each of those directories, as requested by Keir.  Unfortunately separate
header files don't make a lot of sense due to mutual dependencies.

 - A number of coding style changes, again requested by Keir.  Apologies
for not getting this right first time.

What follows is the full description from the earlier posting, included
here for ease of access should anyone need them:

This set of patches provides the hooks and support necessary for
accelerated network plugin modules to attach to Xen's netback and
netfront.  These modules provide a fast path for network traffic where
there is hardware support available for the netfront driver to send and
receive packets directly to a NIC (such as those available from
Solarflare).

As there are currently no available plugins, I've attached a couple of
dummy ones to illustrate how the hooks could be used.  These are
incomplete (and clearly wouldn't even compile) in that they only include
code to show the interface between the accelerated module and
netfront/netback.  A lot of the comments hint at what code should go
where.  They don't show any interface between the accelerated frontend
and accelerated backend, or hardware access, for example, as those would
both be specific to the implementation.  I hope they help illustrate
this, but if you have any questions I'm happy to provide more
information.

A brief overview of the operation of the plugins:  When the accelerated
modules are loaded, a VI is created by the accelerated backend to allow
the accelerated frontend to safely access portions of the NIC.  For RX,
when packets are received by the accelerated backend, it will examine
them and if appropriate insert filters into the NIC to deliver future
packets on that address directly to the accelerated frontend's VI.  For
TX, netfront gives each accelerated frontend the option of sending each
packet, which it can accept (if it wants to send it directly to the
hardware) or decline (if it thinks this is more appropriate to send via
the normal network path).

We have found that using this approach to accelerating network traffic,
domU to domU connections (across the network) can achieve close to the
performance of dom0 to dom0 connections on a 10Gbps ethernet.  This is
roughly double the bandwidth seen with unmodified Xen.

View attachment "dummy_accel_backend.c" of type "text/x-csrc" (3325 bytes)

View attachment "dummy_accel_frontend.c" of type "text/x-csrc" (9658 bytes)

Powered by blists - more mailing lists