mbcache: add reusable flag to cache entries
To reduce amount of damage caused by single bad block, we limit number
of inodes sharing an xattr block to 1024. Thus there can be more xattr
blocks with the same contents when there are lots of files with the same
extended attributes. These xattr blocks naturally result in hash
collisions and can form long hash chains and we unnecessarily check each
such block only to find out we cannot use it because it is already
shared by too many inodes.
Add a reusable flag to cache entries which is cleared when a cache entry
has reached its maximum refcount. Cache entries which are not marked
reusable are skipped by mb_cache_entry_find_{first,next}. This
significantly speeds up mbcache when there are many same xattr blocks.
For example for xattr-bench with 5 values and each process handling
20000 files, the run for 64 processes is 25x faster with this patch.
Even for 8 processes the speedup is almost 3x. We have also verified
that for situations where there is only one xattr block of each kind,
the patch doesn't have a measurable cost.
[JK: Remove handling of setting the same value since it is not needed
anymore, check for races in e_reusable setting, improve changelog,
add measurements]
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 903be15..eccda3a 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -63,13 +63,14 @@
* @mask - gfp mask with which the entry should be allocated
* @key - key of the entry
* @block - block that contains data
+ * @reusable - is the block reusable by other inodes?
*
* Creates entry in @cache with key @key and records that data is stored in
* block @block. The function returns -EBUSY if entry with the same key
* and for the same block already exists in cache. Otherwise 0 is returned.
*/
int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
- sector_t block)
+ sector_t block, bool reusable)
{
struct mb_cache_entry *entry, *dup;
struct hlist_bl_node *dup_node;
@@ -91,6 +92,7 @@
atomic_set(&entry->e_refcnt, 1);
entry->e_key = key;
entry->e_block = block;
+ entry->e_reusable = reusable;
head = mb_cache_entry_head(cache, key);
hlist_bl_lock(head);
hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
@@ -137,7 +139,7 @@
while (node) {
entry = hlist_bl_entry(node, struct mb_cache_entry,
e_hash_list);
- if (entry->e_key == key) {
+ if (entry->e_key == key && entry->e_reusable) {
atomic_inc(&entry->e_refcnt);
goto out;
}
@@ -184,10 +186,38 @@
}
EXPORT_SYMBOL(mb_cache_entry_find_next);
+/*
+ * mb_cache_entry_get - get a cache entry by block number (and key)
+ * @cache - cache we work with
+ * @key - key of block number @block
+ * @block - block number
+ */
+struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
+ sector_t block)
+{
+ struct hlist_bl_node *node;
+ struct hlist_bl_head *head;
+ struct mb_cache_entry *entry;
+
+ head = mb_cache_entry_head(cache, key);
+ hlist_bl_lock(head);
+ hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+ if (entry->e_key == key && entry->e_block == block) {
+ atomic_inc(&entry->e_refcnt);
+ goto out;
+ }
+ }
+ entry = NULL;
+out:
+ hlist_bl_unlock(head);
+ return entry;
+}
+EXPORT_SYMBOL(mb_cache_entry_get);
+
/* mb_cache_entry_delete_block - remove information about block from cache
* @cache - cache we work with
- * @key - key of the entry to remove
- * @block - block containing data for @key
+ * @key - key of block @block
+ * @block - block number
*
* Remove entry from cache @cache with key @key with data stored in @block.
*/