Re: HAMMER update 06-Feb-2008

[Ivan Voras <ivoras@xxxxxxxxxxx>]

Matthew Dillon wrote:

>     * Get rid of the A-list's (the recursive bitmap radix tree allocation
>       model).  Poof, gone.  All of them, gone.  Have no random block
>       allocation model at all.
>
>     * Get rid of the per-cluster B-Tree's.  Instead have just one global
>       B-Tree for the entire filesystem, able to access any record anywhere
>       in the filesystem (currently a per-cluster B-Tree can only access
>       information within that cluster).
>
>     * Implement the filesystem as one big huge circular FIFO, pretty much
>       laid down linearly on disk, with a B-Tree to locate and access data.

How will this affect parallel IO (reads, but especially writes)? Would 
having such a global structure serialize it? (I'm assuming, possibly 
wrongly, that having trees per-cluster allowed you to lock individual 
clusters).

Attachment: signature.asc
Description: OpenPGP digital signature