Date: Tue, 9 Jul 2002 09:51:32 -1000 From: Clifton Royston <cliftonr@lava.net> To: Andy Sporner <sporner@nentec.de> Cc: Derek Barrett <derekbarrett@graffiti.net>, freebsd-cluster@FreeBSD.ORG Subject: Re: SPREAD clusters Message-ID: <20020709095132.D12519@lava.net> In-Reply-To: <3D2ABBF4.5010807@nentec.de>; from sporner@nentec.de on Tue, Jul 09, 2002 at 12:33:24PM %2B0200 References: <20020709083759.11726.qmail@graffiti.net> <3D2ABBF4.5010807@nentec.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Jul 09, 2002 at 12:33:24PM +0200, Andy Sporner wrote:
> Derek Barrett wrote:
>
> >Hi everybody,
> >
> >I picked this up from another mailing list.
> >
> >There is a toolkit over at Johns Hopkins University called
> >SPREAD, which has been implemented to clustered applications such as
> >Apache-SSL and Postgres-R.
> >
> >"Spread is designed to encapsulate the challenging aspects of asynchronous networks and enable the construction of scalable distributed applications, allowing application builders to focus on the differentiating components of their application. "
> >
> >Maybe this code would work in conjunction with Andy's code, as
> >part of the "Phase 2" project.
> >
> >Derek
> >
>
> Hi,
>
> Nice idea, but the idea I had was more lower level. In that it was a
> modification on the VM system. The basic premise is that a process
> does not need to be "cluster-aware" to operate. But this is not to
> discourage their usage--it's just not in focus for Phase-2.
Is there a document explaining the scope of the project, what kinds
of problems it's intended to address, and the overall outline or
roadmap? I'm having a hard time getting that from the URL you posted.
(I'm also new to this list, obviously.)
Is the current project aimed at application failover and load-balancing
for specific applications, i.e. providing the software equivalent of a
"layer 4" or load balancing Ethernet switch?
Or does it generically instantiate all network applications into the
same failover and load-balancing environment?
Or is it more like Mosix, in which servers join a kind of "hive mind"
where any processor can vfork() a process onto a different server with
more RAM/CPU available, but processes have to remain on the original
machine to do device I/O?
Or is it like Digital (R.I.P.s) Vax VMS or "TrueUNIX" clustering,
where for most purposes the clustered servers behaved like a single
machine, with shared storage, unified access to file systems and
devices, etc.?
My main practical interest is in the nitty-gritty of building
practical highly reliable and highly scalable mail server clusters,
both for mail delivery (SMTP,LMTP) and mail retrieval (POP, IMAP.) The
main challenge in doing this right now is dealing with the need for all
servers to have a coherent common view of the file systems where mail
is stored. This means the cluster solution needs to include shared
storage, either via NFS or via some better mechanism which provides
reliable sharing of file systems between multiple servers and allows
for server failure without interruption of data access.
Is this kind of question outside the scope of the current project?
-- Clifton
--
Clifton Royston -- LavaNet Systems Architect -- cliftonr@lava.net
"What do we need to make our world come alive?
What does it take to make us sing?
While we're waiting for the next one to arrive..." - Sisters of Mercy
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-cluster" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020709095132.D12519>