Messages in this thread | | | Subject | Re: [PATCH V2 0/7] Cleancache (was Transcendent Memory): overview | From | Andreas Dilger <> | Date | Wed, 2 Jun 2010 22:53:44 -0600 |
| |
On 2010-06-02, at 20:46, Nitin Gupta wrote: > On 06/03/2010 04:32 AM, Dan Magenheimer wrote: >>> From: Minchan Kim [mailto:minchan.kim@gmail.com] >> >>>> I am also eagerly awaiting Nitin Gupta's cleancache backend >>>> and implementation to do in-kernel page cache compression. >>> >>> Do Nitin say he will make backend of cleancache for >>> page cache compression? >>> >>> It would be good feature. >>> I have a interest, too. :) >> >> That was Nitin's plan for his GSOC project when we last discussed >> this. Nitin is on the cc list and can comment if this has >> changed. > > Yes, I have just started work on in-kernel page cache compression > backend for cleancache :)
Is there a design doc for this implementation? I was thinking it would be quite clever to do compression in, say, 64kB or 128kB chunks in a mapping (to get decent compression) and then write these compressed chunks directly from the page cache to disk in btrfs and/or a revived compressed ext4.
That would mean that the on-disk compression algorithm needs to match the in-memory algorithm, which implies that the in-memory compression algorithm should be selectable on a per-mapping basis.
Cheers, Andreas -- Andreas Dilger Lustre Technical Lead Oracle Corporation Canada Inc.
| |