Date: Mon, 24 May 1999 12:18:29 +0300 (EEST) From: Narvi <narvi@haldjas.folklore.ee> To: Alfred Perlstein <bright@rush.net> Cc: fs@FreeBSD.ORG Subject: Re: reference for filesystem with btree layout? Message-ID: <Pine.BSF.3.96.990524120157.3570B-100000@haldjas.folklore.ee> In-Reply-To: <Pine.BSF.3.96.990524041815.9491Q-100000@cygnus.rush.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 24 May 1999, Alfred Perlstein wrote: > On Mon, 24 May 1999, Narvi wrote: > > > > > Presently ffs uses ufs code for directory related operations. It should be > > possible (and not too hard at my reading of it back when I had a similar > > idea) to replace them. > > It would change the on disk structure otherwise there would be a lot > of extra IO involved no? > The way I thought of it, it would have been a btree inside an "ordinary" directory file. The on disk directory structure would have two additional fields, right & left which point to the offsets of respective lower brances in the tree. The tree is kept Balanced. But I guess that is just one way. There will be slightly more I/O. > > > also, specifically in FreeBSD, I don't see a reason why a filesystem can't > > > take ownership of multiple block devices, is there a reason? > > > > > > > What's the need? You can stripe the block devices with ccd (or concat > > with vinum) and get the same result. > > the point would be to at runtime add more backing block devices > to expand or migrate the filesystem. > That would require more extensive re-engineering of the FS. > -Alfred > Sander There is no love, no good, no happiness and no future - all these are just illusions. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.3.96.990524120157.3570B-100000>