[OpenAFS] About AFS performance over WAN
Thu, 04 Dec 2008 05:56:36 -0500
-----BEGIN PGP SIGNED MESSAGE-----
I'm personally interested in SCTP, but having followed the tsvwg and
other development channels for more than a year, I'm not convinced that
SCTP is going to provide an immediate term viable bulk transport, though
it may turn out to be a brilliant choice in the medium-longer term,
especially if you like FreeBSD.
Some of the issues include not just platform coverage, but also
interoperability, checksum offload (or proposal by some folks to remove
the crc32c checksum requirement) [though that is CPU-specific, cf SSE
4.2 on Intel], and performance properties of (the Linux) SCTP driver, or
so it appears to me.
Derrick Brashear wrote:
> On Wed, Dec 3, 2008 at 11:10 PM, Dale Ghent <email@example.com> wrote:
>> On Dec 1, 2008, at 4:24 AM, Rainer Toebbicke wrote:
>>> With unlimited development resources AFS would deserve a better suited
>>> protocol than TCP, in practice with a little more realism my gut feeling is
>>> that at least some more brain should be devoted to improving plain RX rather
>>> than betting on another horse. I occasionally tried over the past years,
>>> with some improvements that Hartmut tested as well, but my brain being what
>>> it is and the matter relatively complicated results remain modest.
>> Given this, what are your thoughts on STCP and whether it would be useful in
>> this arena?
> SCTP. At this point it may have critical mass of platforms we support
> and thus be a viable option. That I know of the Windows options for it
> are slim. There is a MacOS version from KAME, but I don't know the
> licensing details. Since it doesn't ship with the OS (and in any case
> where it doesn't) that's a practical consideration.
> OpenAFS-info mailing list
The Linux Box
206 South Fifth Ave. Suite 150
Ann Arbor, MI 48104
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.7 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
-----END PGP SIGNATURE-----