tmp_suning_uos_patched/fs/logfs
Nick Piggin fa0d7e3de6 fs: icache RCU free inodes
RCU free the struct inode. This will allow:

- Subsequent store-free path walking patch. The inode must be consulted for
  permissions when walking, so an RCU inode reference is a must.
- sb_inode_list_lock to be moved inside i_lock because sb list walkers who want
  to take i_lock no longer need to take sb_inode_list_lock to walk the list in
  the first place. This will simplify and optimize locking.
- Could remove some nested trylock loops in dcache code
- Could potentially simplify things a bit in VM land. Do not need to take the
  page lock to follow page->mapping.

The downsides of this is the performance cost of using RCU. In a simple
creat/unlink microbenchmark, performance drops by about 10% due to inability to
reuse cache-hot slab objects. As iterations increase and RCU freeing starts
kicking over, this increases to about 20%.

In cases where inode lifetimes are longer (ie. many inodes may be allocated
during the average life span of a single inode), a lot of this cache reuse is
not applicable, so the regression caused by this patch is smaller.

The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU,
however this adds some complexity to list walking and store-free path walking,
so I prefer to implement this at a later date, if it is shown to be a win in
real situations. I haven't found a regression in any non-micro benchmark so I
doubt it will be a problem.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:26 +11:00
..
compr.c [LogFS] add new flash file system 2009-11-20 20:13:39 +01:00
dev_bdev.c logfs: fix a leak in get_sb 2010-10-29 04:16:48 -04:00
dev_mtd.c logfs: fix a leak in get_sb 2010-10-29 04:16:48 -04:00
dir.c new helper: ihold() 2010-10-25 21:26:11 -04:00
file.c logfs: kill BKL 2010-08-14 00:24:24 +02:00
gc.c logfs: handle powerfail on NAND flash 2010-05-07 19:38:40 +02:00
inode.c fs: icache RCU free inodes 2011-01-07 17:50:26 +11:00
journal.c logfs: fix deadlock in logfs_get_wblocks, hold and wait on super->s_write_mutex 2010-12-22 19:43:33 -08:00
Kconfig [LogFS] add new flash file system 2009-11-20 20:13:39 +01:00
logfs_abi.h fix "seperate" typos in comments 2010-05-10 11:56:30 +02:00
logfs.h fs: logfs: Fix up MTD=y build. 2010-11-01 16:34:56 -04:00
Makefile [LogFS] add new flash file system 2009-11-20 20:13:39 +01:00
readwrite.c logfs: fix "Kernel BUG at readwrite.c:1193" 2010-12-22 19:43:33 -08:00
segment.c logfs: get rid of magical inodes 2010-08-09 16:48:26 -04:00
super.c switch logfs to ->mount() 2010-10-29 04:16:51 -04:00