In message <20050223173951.GA10427@panix.com>, Thor Lancelot Simon writes:

[...]

>The most damning criticism, to me, though, is that the seek load
>can generally be entirely eliminated simply by incoring all the
>metadata while the filesystem runs.  As I understand it, that is
>precisely what the current HFS+ implementation does.

Hmmm. but that won't't scale so well for those multi-terabyte
filesystems we were hypothesizing, will it?


That aside: I opined this would make a good Ph.D Quals question.  I'm
not familiar with your en-passant references (got citaitons for the
critiques by Osterhout? I'd look for more in a written answer), but
for what it's worth, your response would get a high grade from me.