Hi,
On Thu, Nov 02, 2000 at 09:03:22AM -0800, Peter J. Braam wrote:
>
> BTW, I nearly fell off my chair when I saw that you, one of the true Unix
> monuments on this list, showed mild signs of approval of propagation on
> close, instead of write!
It's not _that_ shocking: NFS already behaves pretty much this way,
after all!
Full cluster-wide byte-level cache coherency is a great goal, but
there are a lot of situations where you really don't care enough about
it to justify the overhead.
Cheers,
Stephen
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to [EMAIL PROTECTED]