On Thu, 20 Jul 2000, Linus Torvalds wrote:
> Considering that the inode is probably 200+ bytes, the million inodes case
> is fairly scary. And the 4 bytes won't be that noticeable..
oh hey, we've got an estimated 1.7 billion inodes in production right now.
of course, they're not *all* active, nor are they all on the same
server... :)
it is scary though. filesystems and tools don't really scale well to this
size at the moment. you certainly don't want to do more than several
million inodes on one fs -- otherwise you start running into insane backup
difficulties plus unacceptably long fsck times. (of course we use a
logging fs -- but at scale, you produce filesystem corruption on a regular
basis regardless what the filesystem/os/hardware is, and fsck time
determines downtime some users might experience.)
mmm. scaling. it's such a wonderful problem space.
-dean
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun Jul 23 2000 - 21:00:14 EST