[Gnu-arch-users] stat performance on AFS [was Re: [PATCH] arch speedups on big trees]

[Charles Duffy]

On Wed, 2004-01-07 at 00:09, Miles Bader wrote:
> Charles Duffy <address@hidden> writes:
> > Depends on where you are. On AFS, for instance, stat() calls aren't
> > cached on the client, so they're potentially much slower (!) than
> > read()s; for that reason, checking the inode signatures is exceedingly
> > slow there, and so this optimization will be a very substantial gain.
> 
> Does AFS not special-case stats of files that are in the cache?!?

Put it this way: Doing an inode-signature-based operation twice in a row
on our home network (in many respects a scaled-down model of the network
at work) results in quite a bit of a clatter from the AFS server both
times, whereas in the case of a read()-based operation done twice, the
second run has no server involvement at all.

"Files that are in the cache" is something of a misnomer -- the cache
contains chunks rather than complete files; hence, one can't simply stat
the cache's copy of the file and expect it to represent the correct
values.