I'm seeing ADSM restores of large filesystems (750,000 files) get CPU bound
on the client side (DU 4.0D client, ADSM v3.1.06).  I think it's the same
problem that's been talked about several times before - once about 100,000
files arrive back on the client, things slow *way* down, though the server
is not busy.  Throughput goes from 400Kb/s at the beginning to a paltry
50-70 Kb/s as more files are restored, and the CPU is running 70% busy
(doing nothing else).   This test setup has *only* data (and only one copy,
at that) from this client on it, so it's nothing to do with anything 
server-side,
as far as we can tell.

Is there any hope that it'll be fixed, or is it fundemental to the way ADSM
is designed?  What (if anything) can I tune?  I've already got all the
directories in their own DIRMc, and they stay in their own disk
storagepool...  Trying to restore the filesystem as smaller subdirectories
would be messy at best.

Thanks.

Pat Wilson
paw AT dartmouth DOT edu