Re: [ossig] Two obscure questions: directory access times and atomicrename()

[tai <tai@xxxxxxxxxxxxxxxx>]

On Wed, 8 Sep 2004, Christopher DeMarco wrote:

> Yup.  But  that's a useless fix  by itself, as  without a check on the
> number of inodes allowed to exist in a given sub-directory you'll just
> wind up with a BUNCH  of really obscenely  stuffed-full queuedirs.  So
> my  question was whether there's   a "magic  number" of inodes  beyond
> which directory   access  slows  worse-than-linearly,  or an  abstract
> method  for determining that  number   (aside, of course, from  simply
> waiting until you hear/smell your disks thrashing).

	I think something in the 5k range or more.  I've actually read
about this, so the information is out there.  You just have to learn to
tickle the google monster better.  Try the various unix faqs, like the ones
from comp.os.unix.* Also remember, it's fs dependent, so you might want to
tell us what fs you're thinking about using.  reiser4 claims that opening
one file out of 10 files, or 1 million files will not make any difference,
so if you like bleeding edge stuff, that might be fun as well :)  Else, you
might just want to use reiser's technique.

-Tai
-- 
http://www.vcnet.com/bms/features/serendipities.html
http://www2.hunter.com/~skh/humor/admin-horror.html
http://www.despair.com/demotivators/cluelessness.html
"What we have done with PCs so far is not natural" - Craig Mundie, CTO Microsoft


---------------------------------------------------------
To unsubscribe: send mail to ossig-request@mncc.com.my
with "unsubscribe ossig" in the body of the message