Re: [RFC PATCH 0/5] Btrfs: Add hot data tracking functionality

[Mingming Cao <cmm@us.ibm.com>]

On Thu, 2010-07-29 at 22:17 +1000, Dave Chinner wrote:
> On Wed, Jul 28, 2010 at 03:00:48PM -0700, Mingming Cao wrote:
> > On Wed, 2010-07-28 at 01:38 +0200, Christian Stroetmann wrote:
> > > At the 28.07.2010 00:00, Ben Chociej wrote:
> > > Wouldn't this feature be useful for other file systems as well, so that 
> > > a more general and not an only Btrfs related solution is preferable?
> > > 
> > 
> > Would certainly nice to add this feature to all filesystem, but right
> > now btrfs is the only fs which have multiple device support in itself.
> 
> Why does it even need multiple devices in the filesystem? All the
> filesystem needs to know is the relative speed of regions of it's
> block address space and to be provided allocation hints. everything
> else is just movement of data. You could keep the speed information
> in the device mapper table and add an interface for filesystems to
> query it, and then you've got infrastructure  that all filesystems
> could hook into.
> 
> The tracking features dont' appear to have anything btrfs specific
> in them, so t iseems wrong to implement it there just because you're
> only looking at btrfs' method of tracking multiple block devices
> and moving blocks....
> 


I agree hot data tracking could be done at vfs layer. The current hot
data temperature calculation and indexing code is very self-contained,
and could be reuse to other fs or move up to vfs. We could define a
common interface to export to hot data tempreture out. The relocation
eventually has to be filesystem specific. btrfs does cow and knows where
is the data on/off SSD directly makes the relocation to and from very
straightforward.

Mingming