Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 5 Mar 2013 14:11:24 -0500
From:      John Baldwin <jhb@freebsd.org>
To:        freebsd-hackers@freebsd.org
Cc:        gary mazzaferro <garym@oedata.com>
Subject:   Re: Need advice on sys5 shm and zero copy sockets
Message-ID:  <201303051411.24608.jhb@freebsd.org>
In-Reply-To: <CAGwOJnzr%2BJ5XCFP8dRynpzMxHrvWMFyS_iecTRhewNYptM3xMQ@mail.gmail.com>
References:  <CAGwOJnybaQ7%2BAgnoiFZEBruvFyZOKjW3S8tAYzkTx7pX9K%2B_Vw@mail.gmail.com> <CAGwOJnzr%2BJ5XCFP8dRynpzMxHrvWMFyS_iecTRhewNYptM3xMQ@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Monday, March 04, 2013 1:24:08 pm gary mazzaferro wrote:
> Hi,
> 
> Thanks for all the help..  Looks like I'll move forward with
> recommending linux as a base for our new cloud execution containers.
> 
> Personally, I thought freebsd would be a technically superior and
> longer term solution for scientific grid and cloud, but if I can't get
> support on best architectural practices. I'll need to move to
> something I that will be supported during eval, design and prototyping
> processes.

There is not anything in stock FreeBSD that currently does zero-copy sockets
for TCP.  You could add such a thing, but you would have to implement your
own. :(  Some of the building blocks are in place.  For example, you can
create POSIX shared memory objects via shm_open() (and FreeBSD has an extension
where a path of SHM_ANON creates anonymous, unnamed objects) and pass that fd
into the kernel where an ioctl handler can map it into KVA using shm_map()
and shm_unmap().  You'd have to change TCP to do something useful with this
buffer however.

-- 
John Baldwin



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201303051411.24608.jhb>