diff options
author | Nick Piggin <npiggin@kernel.dk> | 2011-01-07 01:49:49 -0500 |
---|---|---|
committer | Nick Piggin <npiggin@kernel.dk> | 2011-01-07 01:50:26 -0500 |
commit | fa0d7e3de6d6fc5004ad9dea0dd6b286af8f03e9 (patch) | |
tree | 203e0f73883e4c26b5597e36042386a1237dab35 /fs/freevxfs/vxfs_inode.c | |
parent | 77812a1ef139d84270d27faacc0630c887411013 (diff) |
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>
Diffstat (limited to 'fs/freevxfs/vxfs_inode.c')
-rw-r--r-- | fs/freevxfs/vxfs_inode.c | 9 |
1 files changed, 8 insertions, 1 deletions
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 8c04eac5079d..2ba6719ac612 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c | |||
@@ -337,6 +337,13 @@ vxfs_iget(struct super_block *sbp, ino_t ino) | |||
337 | return ip; | 337 | return ip; |
338 | } | 338 | } |
339 | 339 | ||
340 | static void vxfs_i_callback(struct rcu_head *head) | ||
341 | { | ||
342 | struct inode *inode = container_of(head, struct inode, i_rcu); | ||
343 | INIT_LIST_HEAD(&inode->i_dentry); | ||
344 | kmem_cache_free(vxfs_inode_cachep, inode->i_private); | ||
345 | } | ||
346 | |||
340 | /** | 347 | /** |
341 | * vxfs_evict_inode - remove inode from main memory | 348 | * vxfs_evict_inode - remove inode from main memory |
342 | * @ip: inode to discard. | 349 | * @ip: inode to discard. |
@@ -350,5 +357,5 @@ vxfs_evict_inode(struct inode *ip) | |||
350 | { | 357 | { |
351 | truncate_inode_pages(&ip->i_data, 0); | 358 | truncate_inode_pages(&ip->i_data, 0); |
352 | end_writeback(ip); | 359 | end_writeback(ip); |
353 | kmem_cache_free(vxfs_inode_cachep, ip->i_private); | 360 | call_rcu(&ip->i_rcu, vxfs_i_callback); |
354 | } | 361 | } |