Do LRU-bumps while already holding item lock

item_get() would hash, item_lock, fetch item.
consumers which can bump the LRU would then call item_update(),
which would hash, item_lock, then update the item.

Good performance bump by inlining the LRU bump when it's necessary.

1 files changed, 1 insertions, 1 deletions

diff --git a/items.h b/items.h
index cc89a61..8f0f78a 100644
--- a/items.h
+++ b/items.h
@@ -42,7 +42,7 @@ void item_stats_sizes_add(item *it);
 void item_stats_sizes_remove(item *it);
 bool item_stats_sizes_status(void);
 
-item *do_item_get(const char *key, const size_t nkey, const uint32_t hv, conn *c);
+item *do_item_get(const char *key, const size_t nkey, const uint32_t hv, conn *c, const bool do_update);
 item *do_item_touch(const char *key, const size_t nkey, uint32_t exptime, const uint32_t hv, conn *c);
 void item_stats_reset(void);
 extern pthread_mutex_t lru_locks[POWER_LARGEST];