[Stuff Deleted]
> 1) inode thrashing, you need to be extremely careful here, because
> you must age your LRU based upon two things, dnlc hits and inode
> hits (via iget()'s) I have no idea if a sensible aging scheme can
> be made to work with this
[Stuff Deleted]
> It certainly needs more thought, I am probably going to setup some
> statistic/profiling mechanism into the dcache and inode manager to see
> what I can learn about all this.
Maybe what is needed is a "cost of refresh" field. This could then
be used along with the LRU, and "modified" to select which buffers
will be flushed.
Different devices would be assigned different "costs". For example
a block from a floppy is much more expensive to load than one from
a fast hard disk. An NFS block would be somewhere in between. The
fastest would be romfs.
.....................................................................
: Peter "Eyes" Eiserloh eiserloh@llab.chinalake.navy.mil
: None of the opinions expressed here are in any way related those
: of my employer.
: Keywords: Linux, Modula-2, Compilers, Esperanto, Physics, Babylon-5
.....................................................................