On-going multiple blocksizes work.
Date: Sat Apr 27 01:30:41 PDT 2002
Workarea: snort.melbourne.sgi.com:/home/nathans/pagebuf
The following file(s) were checked into:
bonnie.engr.sgi.com:/isms/slinx/2.4.x-xfs
Modid: 2.4.x-xfs:slinx:117626a
linux/fs/xfs/linux/xfs_lrw.c - 1.133
- pass the correct offset into bmap, ie. the one used in the original
xfs_bmapi call. seems to be benign though...
Date: Sat Apr 27 01:38:25 PDT 2002
Workarea: snort.melbourne.sgi.com:/home/nathans/pagebuf
The following file(s) were checked into:
bonnie.engr.sgi.com:/isms/slinx/2.4.x-xfs
Modid: 2.4.x-xfs:slinx:117627a
linux/fs/xfs/pagebuf/page_buf_io.c - 1.29
- add a check to map match routine to ensure we don't attempt to match
a buffer before the map starts; deadlock fixup for multiple blocksize
only; ensure map_page can propogate bmap errors back out; refined the
submit_page_io test to only skip non-dirty uptodate pages to get some
write performance back at Steve's suggestion.
linux/fs/xfs/pagebuf/page_buf.c - 1.17
- initial attempt at supporting multiple block sizes on the metadata
path. lots of new code which is only executed for non-pagesized
filesystems, so should be no change for pagesize case. had to move
a few chunks of code around to allow some bit sharing, but shouldn't
be any ill side-effects.
linux/fs/xfs/pagebuf/page_buf_internal.h - 1.3
- move page_buffers macros in here for sharing, recant on need for
offset match/map routines on metadata path.
|