Re: [RFC] TileFS - a proposal for scalable integrity checking

[Matt Mackall <mpm@selenic.com>]

On Mon, Apr 30, 2007 at 01:26:24PM -0400, Theodore Tso wrote:
> On Sun, Apr 29, 2007 at 08:40:42PM -0500, Matt Mackall wrote:
> > chunkfs. The other is reverse maps (aka back pointers) for blocks ->
> > inodes and inodes -> directories that obviate the need to have large
> > amounts of memory to check for collisions.
> 
> Yes, I missed the fact that you had back pointers for blocks as well
> as inodes.  So the block table in the tile header gets used for
> determing if a block is free, much like is done with FAT, right?  

We could eliminate the block bitmap, but I don't think there's much
reason to. It improves allocator performance with negligible footprint
and improves redundancy.
 
> That's a clever system; I like it.  It does mean that there is a lot
> more metadata updates, but since you're not journaling, that should
> counter that effect to some extent.

I had actually envisioned this as working with or without a journal.
I suspect there are ways to keep the performance downside here low.

> IMHO, it's definitely worth a try to see how well it works!

I'm not much of an FS hacker and I've got a lot of other projects in
the air, but I may give it a shot. Any help on this front would be
appreciated.

-- 
Mathematics is the supreme nostalgia of our time.