Various people have been fixing the NFS client a lot. Notably Trond's
work makes it go a lot faster and Linus has been doing some fixes to
certain caching cases.
The "server not responding" normally comes from true server congestion,
the "can't get a request slot" is the client then backing up requests and
is fine.
The big problem one is with the VM - its quite possible to get a heavily
loaded 2.2.x box to the point where it has no 8K blocks and thus cannot
complete an NFS transaction. The existing VM layer fails to get out of this
problem (block size aggregation isnt yet in it - though there are some
patches for this too).
Alan
-
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/