Re: Linux & NFS caching: reducing TCO

Charles K Hardin (chardin+@andrew.cmu.edu)
Thu, 13 May 1999 14:52:11 -0400 (EDT)


I do believe you are trying to rationalize between NFS ver 2 and ver 3,
Linux right now does NFS v2 semantics - which according to the RFC does
not allow caching. I believe I have seen snipets of code for NFSv3 circling
around the kernel lately, so you should look into assisting the development
of these efforts to address your client side caching concerns.

Charles

>
> Colin Hirsch <hirsch@informatik.rwth-aachen.de> writes:
>
>
> > Is there any way to let the clients use a "proper" caching (even if just
> > for ro mounted /usr or so)? This could just make all the difference...
> >
> > In such a case it might be necessary to let the server be able to
send a kin
> d
> > of invalidate message to the clients if something changes (I thought
of keep
> ing
> > data in cache for tens of minutes). This whole setup obviously
relies on onl
> y
> > few changes and only makes sense for e.g. /usr but _not_ /home.
>
> That would not be NFS. NFS is stateless: the server neither knows nor
> cares what the clients are caching.
>
> Feel free to invent your own protocol, but beware that the sort of
> thing you're proposing will most likely place a very heavy burden on
> both the server and your network.
>
> Cheers,
> Trond
>

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/