From e8d40c31b3cca0c3e1ae9abe9b9003b1288026a9 Mon Sep 17 00:00:00 2001
From: Igor Canadi <icanadi@fb.com>
Date: Wed, 11 Dec 2013 08:33:29 -0800
Subject: [PATCH] [RocksDB perf] Cache speedup

Summary:
I have ran a get benchmark where all the data is in the cache and observed that most of the time is spent on waiting for lock in LRUCache.

This is an effort to optimize LRUCache.

Test Plan:
The data was loaded with fillseq. Then, I ran a benchmark:

    /db_bench --db=/tmp/rocksdb_stat_bench --num=1000000 --benchmarks=readrandom --statistics=1 --use_existing_db=1 --threads=16 --disable_seek_compaction=1 --cache_size=20000000000 --cache_numshardbits=8 --table_cache_numshardbits=8

I ran the benchmark three times. Here are the results:
AFTER THE PATCH: 798072, 803998, 811807
BEFORE THE PATCH: 782008, 815593, 763017

Reviewers: dhruba, haobo, kailiu

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D14571
---
 util/cache.cc | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/util/cache.cc b/util/cache.cc
index deec52864..8fa03626b 100644
--- a/util/cache.cc
+++ b/util/cache.cc
@@ -10,7 +10,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <list>
+#include <vector>
 
 #include "rocksdb/cache.h"
 #include "port/port.h"
@@ -111,8 +111,8 @@ class HandleTable {
   }
 
   void Resize() {
-    uint32_t new_length = 4;
-    while (new_length < elems_) {
+    uint32_t new_length = 16;
+    while (new_length < elems_ * 1.5) {
       new_length *= 2;
     }
     LRUHandle** new_list = new LRUHandle*[new_length];
@@ -255,18 +255,20 @@ Cache::Handle* LRUCache::Insert(
 
   LRUHandle* e = reinterpret_cast<LRUHandle*>(
       malloc(sizeof(LRUHandle)-1 + key.size()));
-  std::list<LRUHandle*> last_reference_list;
+  std::vector<LRUHandle*> last_reference_list;
+  last_reference_list.reserve(1);
+
+  e->value = value;
+  e->deleter = deleter;
+  e->charge = charge;
+  e->key_length = key.size();
+  e->hash = hash;
+  e->refs = 2;  // One from LRUCache, one for the returned handle
+  memcpy(e->key_data, key.data(), key.size());
 
   {
     MutexLock l(&mutex_);
 
-    e->value = value;
-    e->deleter = deleter;
-    e->charge = charge;
-    e->key_length = key.size();
-    e->hash = hash;
-    e->refs = 2;  // One from LRUCache, one for the returned handle
-    memcpy(e->key_data, key.data(), key.size());
     LRU_Append(e);
 
     LRUHandle* old = table_.Insert(e);