> it also doesn't matter if the backing FS can't keep up with the server. > the failure mode can be graceful, so that as the backing FS becomes > loaded, it passes more requests back to the server and caches less data > and fewer requests. this is how it works when there is more data to > cache than there is space to cache it; it should work the same way if > the I/O rate is higher than the backing FS can handle. Wow. There is nice mode I did not consider before: With good network, server used by just one client and some good luck we can see twofold speedup on the principle of disk mirror. So even with GigE, FSCache can make a lot of sense. (However I am much more interested in one server very overloaded by 10 clients. I expect marvelous speedup in this case and I am going to test this soon unless somebody tells me that things are still too broken for this to work.) Many many thanks for this work. Vaclav Hanzl
