Messages in this thread | | | Date | Wed, 13 Oct 1999 19:46:16 +0100 | From | Steve Dodd <> | Subject | Re: [patch] [possible race in ext2] Re: how to write get_block? |
| |
[I hope you lot still want to be on the Cc: for this <g>]
On Tue, Oct 12, 1999 at 12:52:11PM +0100, Stephen C. Tweedie wrote: > On 11 Oct 1999 17:58:54 -0500, ebiederm+eric@ccr.net (Eric W. Biederman) > said:
> > Ultimately we really want to have indirect blocks, and > > the directory in the page cache as it should result in > > more uniform code, and faster partial truncates (as well as faster > > syncs). > > There is one major potential future problem with moving this to the page > cache. At some point I want to be able to extend the large (64G) memory > support on Intel to include the page cache in high memory. The buffer > cache would still live in low memory. [..]
So I guess we need to look at why people want to stuff metadata in the page cache. For me, I have a problem in NTFS that all metadata is stored in files, and comes in chunks that can be multiples of the block size of the device/fs. The current tiny prototype I have (started during the summer and then forgotten about) was stuffing these in the page cache, on the grounds that in practice metadata blocks never exceeded the page size, though I don't believe this is set in stone.
-- "Pascal is Pascal is Pascal is dog meat." -- M. Devine and P. Larson, Computer Science 340
- 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/
| |