Messages in this thread | | | From | (Stuart Lynne) | Subject | Re: [OFFTOPIC] Re: disk head scheduling | Date | 23 Mar 1999 05:44:38 GMT |
| |
In article <14070.58301.339007.437665@dukat.scot.redhat.com>, Stephen C. Tweedie <sct@redhat.com> wrote: >Hi, > >On Sun, 21 Mar 1999 11:49:31 -0800, jg@pa.dec.com (Jim Gettys) said: > >indexed by block numbers). If the filesystem can also deallocate such >space, then we have an abstraction behind which filesystem shrinking
As a side-effect this would help make devices built on FLASH memory a little easier to deal with. FLASH has the interesting principle of being able to be written from 1 to 0 at any time, But writing a 0 to a 1 requires erasing a (relatively) large block. The end result is that rewriting a single block can involve copying about 100k of data from one area to another.
If the filesystem can tell the device layer that a block is no longer being used then the device layer can stop moving it around when erasing. This not only speeds that operation but opens up more empty space to copy new data to. [The device layer doesn't erase to rewrite blocks, it marks it as unused and writes it to somewhere that is currently not being used. It only erases when it runs out of empty blocks and needs to recover some.]
-- Stuart Lynne <sl@fireplug.net> 604-461-7532 <http://edge.fireplug.net> PGP Fingerprint: 28 E2 A0 15 99 62 9A 00 88 EC A3 EE 2D 1C 15 68
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |