From fb84c49a36bd89346cac4bf833b130c5a8db5621 Mon Sep 17 00:00:00 2001
From: Lei Jin <lei@fb.com>
Date: Wed, 29 Jan 2014 15:08:41 -0800
Subject: [PATCH] convert Tickers back to array with padding and alignment

Summary:
Pad each Ticker structure to be 64 bytes and make them align on 64 bytes
boundary to avoid cache line false sharing issue.
Please refer to task 3615553 for more details

Test Plan:
db_bench

LevelDB:    version 2.0s
Date:       Wed Jan 29 12:23:17 2014
CPU:        32 * Intel(R) Xeon(R) CPU E5-2660 0 @ 2.20GHz
CPUCache:   20480 KB
rocksdb.build.overwrite.qps 49638
rocksdb.build.overwrite.p50_micros 58.73
rocksdb.build.overwrite.p75_micros 210.56
rocksdb.build.overwrite.p99_micros 733.28
rocksdb.build.fillseq.qps 366729
rocksdb.build.fillseq.p50_micros 1.00
rocksdb.build.fillseq.p75_micros 1.00
rocksdb.build.fillseq.p99_micros 2.65
rocksdb.build.readrandom.qps 1152995
rocksdb.build.readrandom.p50_micros 11.27
rocksdb.build.readrandom.p75_micros 15.69
rocksdb.build.readrandom.p99_micros 33.59
rocksdb.build.readrandom_smallblockcache.qps 956047
rocksdb.build.readrandom_smallblockcache.p50_micros 15.23
rocksdb.build.readrandom_smallblockcache.p75_micros 17.31
rocksdb.build.readrandom_smallblockcache.p99_micros 31.49
rocksdb.build.readrandom_memtable_sst.qps 1105183
rocksdb.build.readrandom_memtable_sst.p50_micros 12.04
rocksdb.build.readrandom_memtable_sst.p75_micros 15.78
rocksdb.build.readrandom_memtable_sst.p99_micros 32.49
rocksdb.build.readrandom_fillunique_random.qps 487856
rocksdb.build.readrandom_fillunique_random.p50_micros 29.65
rocksdb.build.readrandom_fillunique_random.p75_micros 40.93
rocksdb.build.readrandom_fillunique_random.p99_micros 78.68
rocksdb.build.memtablefillrandom.qps 91304
rocksdb.build.memtablefillrandom.p50_micros 171.05
rocksdb.build.memtablefillrandom.p75_micros 196.12
rocksdb.build.memtablefillrandom.p99_micros 291.73
rocksdb.build.memtablereadrandom.qps 1340411
rocksdb.build.memtablereadrandom.p50_micros 9.48
rocksdb.build.memtablereadrandom.p75_micros 13.95
rocksdb.build.memtablereadrandom.p99_micros 30.36
rocksdb.build.readwhilewriting.qps 491004
rocksdb.build.readwhilewriting.p50_micros 29.58
rocksdb.build.readwhilewriting.p75_micros 40.34
rocksdb.build.readwhilewriting.p99_micros 76.78

Reviewers: igor, haobo

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15573
---
 util/statistics.cc | 10 ++++------
 util/statistics.h  | 14 ++++++++++++--
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/util/statistics.cc b/util/statistics.cc
index f86eb2c54..4fc240018 100644
--- a/util/statistics.cc
+++ b/util/statistics.cc
@@ -14,25 +14,23 @@ std::shared_ptr<Statistics> CreateDBStatistics() {
   return std::make_shared<StatisticsImpl>();
 }
 
-StatisticsImpl::StatisticsImpl()
-    : tickers_(TICKER_ENUM_MAX),
-      histograms_(HISTOGRAM_ENUM_MAX) {}
+StatisticsImpl::StatisticsImpl() {}
 
 StatisticsImpl::~StatisticsImpl() {}
 
 long StatisticsImpl::getTickerCount(Tickers tickerType) {
   assert(tickerType < TICKER_ENUM_MAX);
-  return tickers_[tickerType];
+  return tickers_[tickerType].value;
 }
 
 void StatisticsImpl::setTickerCount(Tickers tickerType, uint64_t count) {
   assert(tickerType < TICKER_ENUM_MAX);
-  tickers_[tickerType] = count;
+  tickers_[tickerType].value = count;
 }
 
 void StatisticsImpl::recordTick(Tickers tickerType, uint64_t count) {
   assert(tickerType < TICKER_ENUM_MAX);
-  tickers_[tickerType] += count;
+  tickers_[tickerType].value += count;
 }
 
 void StatisticsImpl::measureTime(Histograms histogramType, uint64_t value) {
diff --git a/util/statistics.h b/util/statistics.h
index f598bdbf9..d8cb36e0a 100644
--- a/util/statistics.h
+++ b/util/statistics.h
@@ -28,8 +28,18 @@ class StatisticsImpl : public Statistics {
                              HistogramData* const data);
 
  private:
-  std::vector<std::atomic_uint_fast64_t> tickers_;
-  std::vector<HistogramImpl> histograms_;
+  struct Ticker {
+    Ticker() : value(uint_fast64_t()) {}
+
+    std::atomic_uint_fast64_t value;
+    // Pad the structure to make it size of 64 bytes. A plain array of
+    // std::atomic_uint_fast64_t results in huge performance degradataion
+    // due to false sharing.
+    char padding[64 - sizeof(std::atomic_uint_fast64_t)];
+  };
+
+  Ticker tickers_[TICKER_ENUM_MAX] __attribute__((aligned(64)));
+  HistogramImpl histograms_[HISTOGRAM_ENUM_MAX] __attribute__((aligned(64)));
 };
 
 // Utility functions