Re: [prepatch] address_space-based writeback

[Andrew Morton <akpm@zip.com.au>]

An update to these patches is at

	http://www.zip.com.au/~akpm/linux/patches/2.5/2.5.8/

All work at this time is on

dallocbase-10-page_alloc_fail.patch
dallocbase-35-pageprivate_fixes.patch
dallocbase-55-ext2_dir.patch
dallocbase-60-page_accounting.patch
ratcache-pf_memalloc.patch
mempool-node.patch
dallocbase-70-writeback.patch
ttd		(my current 2.5 things-to-do-list, just for fun)

none of the patches beyond these have even been tested in a week..

The new buffer<->page relationship rules seem to be working
out OK.  In a six-hour stress test on a quad Xeon with
1k blocksize ext3 in ordered-data mode there was one failure:
a block in a file which came up with wrong data.  There appears
to be a race in ext3 or the patch or 2.5 or something somewhere.
Still hunting this one.

It is all relatively stable now.  ramdisk, loop, reiserfs, ext2,
ext3-ordered, ext3-journalled, JFS and vfat have been tested.

minixfs and sysvfs are broken with these patches.  They rely
on preservation of directory data outside i_size.   Will fix.

-