summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorNick Piggin <npiggin@suse.de>2008-12-01 09:33:43 +0100
committerAl Viro <viro@zeniv.linux.org.uk>2008-12-31 18:07:38 -0500
commitc2452f32786159ed85f0e4b21fec09258f822fc8 (patch)
tree50d93df47f4547a5699c87a608e85596e4c6165f /include
parente2b689d82c0394e5239a3557a217f19e2f47f1be (diff)
downloadop-kernel-dev-c2452f32786159ed85f0e4b21fec09258f822fc8.zip
op-kernel-dev-c2452f32786159ed85f0e4b21fec09258f822fc8.tar.gz
shrink struct dentry
struct dentry is one of the most critical structures in the kernel. So it's sad to see it going neglected. With CONFIG_PROFILING turned on (which is probably the common case at least for distros and kernel developers), sizeof(struct dcache) == 208 here (64-bit). This gives 19 objects per slab. I packed d_mounted into a hole, and took another 4 bytes off the inline name length to take the padding out from the end of the structure. This shinks it to 200 bytes. I could have gone the other way and increased the length to 40, but I'm aiming for a magic number, read on... I then got rid of the d_cookie pointer. This shrinks it to 192 bytes. Rant: why was this ever a good idea? The cookie system should increase its hash size or use a tree or something if lookups are a problem. Also the "fast dcookie lookups" in oprofile should be moved into the dcookie code -- how can oprofile possibly care about the dcookie_mutex? It gets dropped after get_dcookie() returns so it can't be providing any sort of protection. At 192 bytes, 21 objects fit into a 4K page, saving about 3MB on my system with ~140 000 entries allocated. 192 is also a multiple of 64, so we get nice cacheline alignment on 64 and 32 byte line systems -- any given dentry will now require 3 cachelines to touch all fields wheras previously it would require 4. I know the inline name size was chosen quite carefully, however with the reduction in cacheline footprint, it should actually be just about as fast to do a name lookup for a 36 character name as it was before the patch (and faster for other sizes). The memory footprint savings for names which are <= 32 or > 36 bytes long should more than make up for the memory cost for 33-36 byte names. Performance is a feature... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Diffstat (limited to 'include')
-rw-r--r--include/linux/dcache.h21
1 files changed, 14 insertions, 7 deletions
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index a37359d..c66d224 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -75,14 +75,22 @@ full_name_hash(const unsigned char *name, unsigned int len)
return end_name_hash(hash);
}
-struct dcookie_struct;
-
-#define DNAME_INLINE_LEN_MIN 36
+/*
+ * Try to keep struct dentry aligned on 64 byte cachelines (this will
+ * give reasonable cacheline footprint with larger lines without the
+ * large memory footprint increase).
+ */
+#ifdef CONFIG_64BIT
+#define DNAME_INLINE_LEN_MIN 32 /* 192 bytes */
+#else
+#define DNAME_INLINE_LEN_MIN 40 /* 128 bytes */
+#endif
struct dentry {
atomic_t d_count;
unsigned int d_flags; /* protected by d_lock */
spinlock_t d_lock; /* per dentry lock */
+ int d_mounted;
struct inode *d_inode; /* Where the name belongs to - NULL is
* negative */
/*
@@ -107,10 +115,7 @@ struct dentry {
struct dentry_operations *d_op;
struct super_block *d_sb; /* The root of the dentry tree */
void *d_fsdata; /* fs-specific data */
-#ifdef CONFIG_PROFILING
- struct dcookie_struct *d_cookie; /* cookie, if any */
-#endif
- int d_mounted;
+
unsigned char d_iname[DNAME_INLINE_LEN_MIN]; /* small names */
};
@@ -177,6 +182,8 @@ d_iput: no no no yes
#define DCACHE_INOTIFY_PARENT_WATCHED 0x0020 /* Parent inode is watched */
+#define DCACHE_COOKIE 0x0040 /* For use by dcookie subsystem */
+
extern spinlock_t dcache_lock;
extern seqlock_t rename_lock;
OpenPOWER on IntegriCloud