[dm-devel] Re: [mauelshagen at sistina.com: sparse target]
Heinz J . Mauelshagen
Heinz.Mauelshagen at t-online.de
Wed Dec 18 07:29:02 UTC 2002
On Mon, Dec 16, 2002 at 04:29:13PM -0600, Steve Pratt wrote:
>
> Heinz Mauelshagen wrote:
>
> >EVMS team (Steve or Corry are the ones to ask i guess),
>
> >Joe mentioned that you are implementing a sparse and a bbr target
> >for device-mapper.
>
> Yes, we are.
:)
How long do you estimate till first public code will be available ?
>
> >I've got a couple of questions for you.
>
> >1. Is it read-only or read-write sparse?
>
> Read/Write
Ok.
>
> >1b. If it's read-write sparse it must allocate storage dynamically on
> >writes kicking of a user space allocator waiting for those writes
> >on a table event queue, right?
>
> No, it use the same basic COW logic as snapshotting, only there is no read.
> Basically a device is allocated as a sparse target with a chunk size.
> Space is reserved for a table of allocations, and as writes to
> previously unused virtual chunks occur the next avaible real chunk is
> allocated. This is all done in kernel space like in snapshots.
Ah, that was the other way i had in the back of my head...
Do you stack on another target (i.e linear) to store the written chunks to ?
>
>
> >2. I assume that the bbr target uses preallocated and inaccessable table
> space
> >(inaccessable in terms of regular io queued to the bbr target) to be
> >allocated on the fly on io error?
>
> Correct.
>
> >2a. If that allocation happens, do you send an event to update metadata in
> user
> >space in order to reflect the relocation?
>
> No, again we use in kernel (DM) metadata writes to record the allocation.
Alright.
>
> >2b. How do you guarantee that that update is atomic?
>
> Locking in the kernel.
If you don't rely on any user space interaction that's pretty obvious ;)
>
> >2b. Preallocation is fine to gain performance. Additionally you guys must
> be
> >planning to stack bbr onto sparse (presuming read-write sparse),
> right?
>
> Ow, that hurts my head. Preallocation solves the problem of where do you
> put it. We could stack bbr and sparse, but I don't see why.
Because you implement the mechanism for pre-allocation just once that way ?
>
>
> Steve
>
Regards,
Heinz -- The LVM Guy --
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Heinz Mauelshagen Sistina Software Inc.
Senior Consultant/Developer Am Sonnenhang 11
56242 Marienrachdorf
Germany
Mauelshagen at Sistina.com +49 2626 141200
FAX 924446
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
More information about the dm-devel
mailing list