Something I have gotten in a habit of recently, is running lots of rm jobs
in parallel because it seems to keep the kernel busy while the disk is
seeking. I have a cheap script method that tries to remove stuff in roughly
'find' order so it's not totally random across the disk and it does seem
to speed things up on most of my machines.

However, on the diskless machines, it's a lose, and when I forget, it
causes real trouble because it appears to wedge NFS hard.

Specifically, a 333mhz iMac mounting root/swap from a 125mhz HPUX 10.20
box which holds up quite well under load.

When I start running, say, -j16 rm's, very shortly the iMac complains
that the server is not responding, exactly once. I believe NFS is hung
from that point on, because further attempts to use the iMac result in
more and more processes getting blocked on something over NFS, until
the whole iMac is effectively wedged.

nfsiod is at the default of 4, but I don't understand why overloading them
would have such a nasty effect.

Known issue? PR time? What say thee?

Todd Whitesel
toddpw @ best.com