store file_indexer info in sequential memory

Summary:
  use arena to allocate space for next_level_index_ and level_rb_
  Thus increasing data locality and make Version::Get faster.

Benchmark detail
Base version: commit d2a727c182

command used:
./db_bench --db=/mnt/db/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --block_size=4096 --cache_size=17179869184 --cache_numshardbits=6 --compression_type=none --compression_ratio=1 --min_level_to_compress=-1 --disable_seek_compaction=1 --hard_rate_limit=2 --write_buffer_size=134217728 --max_write_buffer_number=2 --level0_file_num_compaction_trigger=8 --target_file_size_base=2097152 --max_bytes_for_level_base=1073741824 --disable_wal=0 --sync=0 --disable_data_sync=1 --verify_checksum=1 --delete_obsolete_files_period_micros=314572800 --max_grandparent_overlap_factor=10 --max_background_compactions=4 --max_background_flushes=0 --level0_slowdown_writes_trigger=16 --level0_stop_writes_trigger=24 --statistics=0 --stats_per_interval=0 --stats_interval=1048576 --histogram=0 --use_plain_table=1 --open_files=-1 --mmap_read=1 --mmap_write=0 --memtablerep=prefix_hash --bloom_bits=10 --bloom_locality=1 --perf_level=0 --benchmarks=fillseq, readrandom,readrandom,readrandom --use_existing_db=0 --num=52428800 --threads=1

Result:
cpu running percentage:
Version::Get, improved from 7.98% to 7.42%
FileIndexer::GetNextLevelIndex, improved from 1.18% to 0.68%.

Test Plan:
  make all check

Reviewers: ljin, haobo, yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba, igor

Differential Revision: https://reviews.facebook.net/D19845

db/file_indexer.cc

@@ -14,21 +14,18 @@
 
 namespace rocksdb {
 
-FileIndexer::FileIndexer(const uint32_t num_levels,
-                         const Comparator* ucmp)
-  : num_levels_(num_levels),
+FileIndexer::FileIndexer(const Comparator* ucmp)
+  : num_levels_(0),
     ucmp_(ucmp),
-    next_level_index_(num_levels),
-    level_rb_(num_levels, -1) {
+    level_rb_(nullptr) {
 }
 
-
 uint32_t FileIndexer::NumLevelIndex() {
   return next_level_index_.size();
 }
 
 uint32_t FileIndexer::LevelIndexSize(uint32_t level) {
-  return next_level_index_[level].size();
+  return next_level_index_[level].num_index;
 }
 
 void FileIndexer::GetNextLevelIndex(
@@ -46,11 +43,12 @@ void FileIndexer::GetNextLevelIndex(
   assert(level < num_levels_ - 1);
   assert(static_cast<int32_t>(file_index) <= level_rb_[level]);
 
-  const auto& index = next_level_index_[level][file_index];
+  const IndexUnit* index_units = next_level_index_[level].index_units;
+  const auto& index = index_units[file_index];
 
   if (cmp_smallest < 0) {
     *left_bound = (level > 0 && file_index > 0) ?
-      next_level_index_[level][file_index - 1].largest_lb : 0;
+      index_units[file_index - 1].largest_lb : 0;
     *right_bound = index.smallest_rb;
   } else if (cmp_smallest == 0) {
     *left_bound = index.smallest_lb;
@@ -73,16 +71,26 @@ void FileIndexer::GetNextLevelIndex(
   assert(*right_bound <= level_rb_[level + 1]);
 }
 
-void FileIndexer::ClearIndex() {
-  for (uint32_t level = 1; level < num_levels_; ++level) {
-    next_level_index_[level].clear();
-  }
-}
-
-void FileIndexer::UpdateIndex(std::vector<FileMetaData*>* const files) {
+void FileIndexer::UpdateIndex(Arena* arena,
+                              const uint32_t num_levels,
+                              std::vector<FileMetaData*>* const files) {
   if (files == nullptr) {
     return;
   }
+  if (num_levels == 0) {        // uint_32 0-1 would cause bad behavior
+    num_levels_ = num_levels;
+    return;
+  }
+  assert(level_rb_ == nullptr);      // level_rb_ should be init here
+
+  num_levels_ = num_levels;
+  next_level_index_.resize(num_levels);
+
+  char* mem = arena->AllocateAligned(num_levels_ * sizeof(int32_t));
+  level_rb_ = new (mem)int32_t[num_levels_];
+  for (size_t i = 0; i < num_levels_; i++) {
+    level_rb_[i] = -1;
+  }
 
   // L1 - Ln-1
   for (uint32_t level = 1; level < num_levels_ - 1; ++level) {
@@ -93,31 +101,33 @@ void FileIndexer::UpdateIndex(std::vector<FileMetaData*>* const files) {
     if (upper_size == 0) {
       continue;
     }
-    auto& index = next_level_index_[level];
-    index.resize(upper_size);
+    IndexLevel& index_level = next_level_index_[level];
+    index_level.num_index = upper_size;
+    char* mem = arena->AllocateAligned(upper_size * sizeof(IndexUnit));
+    index_level.index_units = new (mem)IndexUnit[upper_size];
 
-    CalculateLB(upper_files, lower_files, &index,
+    CalculateLB(upper_files, lower_files, &index_level,
         [this](const FileMetaData* a, const FileMetaData* b) -> int {
           return ucmp_->Compare(a->smallest.user_key(), b->largest.user_key());
         },
         [](IndexUnit* index, int32_t f_idx) {
           index->smallest_lb = f_idx;
         });
-    CalculateLB(upper_files, lower_files, &index,
+    CalculateLB(upper_files, lower_files, &index_level,
         [this](const FileMetaData* a, const FileMetaData* b) -> int {
           return ucmp_->Compare(a->largest.user_key(), b->largest.user_key());
         },
         [](IndexUnit* index, int32_t f_idx) {
           index->largest_lb = f_idx;
         });
-    CalculateRB(upper_files, lower_files, &index,
+    CalculateRB(upper_files, lower_files, &index_level,
         [this](const FileMetaData* a, const FileMetaData* b) -> int {
           return ucmp_->Compare(a->smallest.user_key(), b->smallest.user_key());
         },
         [](IndexUnit* index, int32_t f_idx) {
           index->smallest_rb = f_idx;
         });
-    CalculateRB(upper_files, lower_files, &index,
+    CalculateRB(upper_files, lower_files, &index_level,
         [this](const FileMetaData* a, const FileMetaData* b) -> int {
           return ucmp_->Compare(a->largest.user_key(), b->smallest.user_key());
         },
@@ -125,23 +135,26 @@ void FileIndexer::UpdateIndex(std::vector<FileMetaData*>* const files) {
           index->largest_rb = f_idx;
         });
   }
+
   level_rb_[num_levels_ - 1] = files[num_levels_ - 1].size() - 1;
 }
 
 void FileIndexer::CalculateLB(const std::vector<FileMetaData*>& upper_files,
     const std::vector<FileMetaData*>& lower_files,
-    std::vector<IndexUnit>* index,
+    IndexLevel *index_level,
     std::function<int(const FileMetaData*, const FileMetaData*)> cmp_op,
     std::function<void(IndexUnit*, int32_t)> set_index) {
   const int32_t upper_size = upper_files.size();
   const int32_t lower_size = lower_files.size();
   int32_t upper_idx = 0;
   int32_t lower_idx = 0;
+
+  IndexUnit* index = index_level->index_units;
   while (upper_idx < upper_size && lower_idx < lower_size) {
     int cmp = cmp_op(upper_files[upper_idx], lower_files[lower_idx]);
 
     if (cmp == 0) {
-      set_index(&(*index)[upper_idx], lower_idx);
+      set_index(&index[upper_idx], lower_idx);
       ++upper_idx;
       ++lower_idx;
     } else if (cmp > 0) {
@@ -151,7 +164,7 @@ void FileIndexer::CalculateLB(const std::vector<FileMetaData*>& upper_files,
     } else {
       // Lower level's file becomes larger, update the index, and
       // move to the next upper file
-      set_index(&(*index)[upper_idx], lower_idx);
+      set_index(&index[upper_idx], lower_idx);
       ++upper_idx;
     }
   }
@@ -159,25 +172,27 @@ void FileIndexer::CalculateLB(const std::vector<FileMetaData*>& upper_files,
   while (upper_idx < upper_size) {
     // Lower files are exhausted, that means the remaining upper files are
     // greater than any lower files. Set the index to be the lower level size.
-    set_index(&(*index)[upper_idx], lower_size);
+    set_index(&index[upper_idx], lower_size);
     ++upper_idx;
   }
 }
 
 void FileIndexer::CalculateRB(const std::vector<FileMetaData*>& upper_files,
     const std::vector<FileMetaData*>& lower_files,
-    std::vector<IndexUnit>* index,
+    IndexLevel *index_level,
     std::function<int(const FileMetaData*, const FileMetaData*)> cmp_op,
     std::function<void(IndexUnit*, int32_t)> set_index) {
   const int32_t upper_size = upper_files.size();
   const int32_t lower_size = lower_files.size();
   int32_t upper_idx = upper_size - 1;
   int32_t lower_idx = lower_size - 1;
+
+  IndexUnit* index = index_level->index_units;
   while (upper_idx >= 0 && lower_idx >= 0) {
     int cmp = cmp_op(upper_files[upper_idx], lower_files[lower_idx]);
 
     if (cmp == 0) {
-      set_index(&(*index)[upper_idx], lower_idx);
+      set_index(&index[upper_idx], lower_idx);
       --upper_idx;
       --lower_idx;
     } else if (cmp < 0) {
@@ -187,14 +202,14 @@ void FileIndexer::CalculateRB(const std::vector<FileMetaData*>& upper_files,
     } else {
       // Lower level's file becomes smaller, update the index, and move to
       // the next the upper file
-      set_index(&(*index)[upper_idx], lower_idx);
+      set_index(&index[upper_idx], lower_idx);
       --upper_idx;
     }
   }
   while (upper_idx >= 0) {
     // Lower files are exhausted, that means the remaining upper files are
     // smaller than any lower files. Set it to -1.
-    set_index(&(*index)[upper_idx], -1);
+    set_index(&index[upper_idx], -1);
     --upper_idx;
   }
 }

db/file_indexer.h

@@ -12,11 +12,15 @@
 #include <functional>
 #include <limits>
 #include <vector>
+#include "util/arena.h"
+#include "util/autovector.h"
 
 namespace rocksdb {
 
 class Comparator;
 struct FileMetaData;
+struct FdWithKeyRange;
+struct FileLevel;
 
 // The file tree structure in Version is prebuilt and the range of each file
 // is known. On Version::Get(), it uses binary search to find a potential file
@@ -36,7 +40,7 @@ struct FileMetaData;
 // naive approach.
 class FileIndexer {
  public:
-  FileIndexer(const uint32_t num_levels, const Comparator* ucmp);
+  explicit FileIndexer(const Comparator* ucmp);
 
   uint32_t NumLevelIndex();
 
@@ -50,16 +54,16 @@ class FileIndexer {
     const uint32_t level, const uint32_t file_index, const int cmp_smallest,
     const int cmp_largest, int32_t* left_bound, int32_t* right_bound);
 
-  void ClearIndex();
-
-  void UpdateIndex(std::vector<FileMetaData*>* const files);
+  void UpdateIndex(Arena* arena,
+                   const uint32_t num_levels,
+                   std::vector<FileMetaData*>* const files);
 
   enum {
     kLevelMaxIndex = std::numeric_limits<int32_t>::max()
   };
 
  private:
-  const uint32_t num_levels_;
+  uint32_t num_levels_;
   const Comparator* ucmp_;
 
   struct IndexUnit {
@@ -110,20 +114,28 @@ class FileIndexer {
     int32_t largest_rb;
   };
 
+  // Data structure to store IndexUnits in a whole level
+  struct IndexLevel {
+    size_t num_index;
+    IndexUnit* index_units;
+
+    IndexLevel(): num_index(0), index_units(nullptr) {}
+  };
+
   void CalculateLB(const std::vector<FileMetaData*>& upper_files,
     const std::vector<FileMetaData*>& lower_files,
-    std::vector<IndexUnit>* index,
+    IndexLevel* index_level,
     std::function<int(const FileMetaData*, const FileMetaData*)> cmp_op,
     std::function<void(IndexUnit*, int32_t)> set_index);
 
   void CalculateRB(const std::vector<FileMetaData*>& upper_files,
     const std::vector<FileMetaData*>& lower_files,
-    std::vector<IndexUnit>* index,
+    IndexLevel* index_level,
     std::function<int(const FileMetaData*, const FileMetaData*)> cmp_op,
     std::function<void(IndexUnit*, int32_t)> set_index);
 
-  std::vector<std::vector<IndexUnit>> next_level_index_;
-  std::vector<int32_t> level_rb_;
+  autovector<IndexLevel> next_level_index_;
+  int32_t* level_rb_;
 };
 
 }  // namespace rocksdb

db/file_indexer_test.cc

@@ -35,16 +35,15 @@ class IntComparator : public Comparator {
   void FindShortSuccessor(std::string* key) const {}
 };
 
-
 struct FileIndexerTest {
  public:
   FileIndexerTest() :
-    kNumLevels(4), indexer(kNumLevels, &ucmp),
+    kNumLevels(4),
     files(new std::vector<FileMetaData*>[kNumLevels]) {
   }
 
   ~FileIndexerTest() {
-    Reset();
+    ClearFiles();
     delete[] files;
   }
 
@@ -59,14 +58,13 @@ struct FileIndexerTest {
     return InternalKey(Slice(reinterpret_cast<char*>(&v), 8), 0, kTypeValue);
   }
 
-  void Reset() {
+  void ClearFiles() {
     for (uint32_t i = 0; i < kNumLevels; ++i) {
       for (auto* f : files[i]) {
         delete f;
       }
       files[i].clear();
     }
-    indexer.ClearIndex();
   }
 
   void GetNextLevelIndex(const uint32_t level, const uint32_t file_index,
@@ -74,23 +72,32 @@ struct FileIndexerTest {
       int32_t* right_index) {
     *left_index = 100;
     *right_index = 100;
-    indexer.GetNextLevelIndex(level, file_index, cmp_smallest, cmp_largest,
+    indexer->GetNextLevelIndex(level, file_index, cmp_smallest, cmp_largest,
         left_index, right_index);
   }
 
+  int32_t left = 100;
+  int32_t right = 100;
   const uint32_t kNumLevels;
   IntComparator ucmp;
-  FileIndexer indexer;
+  FileIndexer* indexer;
 
   std::vector<FileMetaData*>* files;
 };
 
-TEST(FileIndexerTest, next_level_hint) {
-  for (uint32_t i = 0; i < kNumLevels; ++i) {
-    ASSERT_EQ(0U, indexer.LevelIndexSize(i));
-  }
+// Case 0: Empty
+TEST(FileIndexerTest, Empty) {
+  Arena arena;
+  indexer = new FileIndexer(&ucmp);
+  indexer->UpdateIndex(&arena, 0, files);
+  delete indexer;
+}
 
-  // Case 1: no overlap, files are on the left of next level files
+// Case 1: no overlap, files are on the left of next level files
+TEST(FileIndexerTest, no_overlap_left) {
+  Arena arena;
+  uint32_t kNumLevels = 4;
+  indexer = new FileIndexer(&ucmp);
   // level 1
   AddFile(1, 100, 200);
   AddFile(1, 300, 400);
@@ -103,9 +110,7 @@ TEST(FileIndexerTest, next_level_hint) {
   AddFile(3, 2500, 2600);
   AddFile(3, 2601, 2699);
   AddFile(3, 2700, 2800);
-  indexer.UpdateIndex(files);
-  int32_t left = 100;
-  int32_t right = 100;
+  indexer->UpdateIndex(&arena, kNumLevels, files);
   for (uint32_t level = 1; level < 3; ++level) {
     for (uint32_t f = 0; f < 3; ++f) {
       GetNextLevelIndex(level, f, -1, -1, &left, &right);
@@ -125,12 +130,15 @@ TEST(FileIndexerTest, next_level_hint) {
       ASSERT_EQ(2, right);
     }
   }
+  delete indexer;
+  ClearFiles();
+}
 
-  // Case 2: no overlap, files are on the right of next level files
-  Reset();
-  for (uint32_t i = 1; i < kNumLevels; ++i) {
-    ASSERT_EQ(0U, indexer.LevelIndexSize(i));
-  }
+// Case 2: no overlap, files are on the right of next level files
+TEST(FileIndexerTest, no_overlap_right) {
+  Arena arena;
+  uint32_t kNumLevels = 4;
+  indexer = new FileIndexer(&ucmp);
   // level 1
   AddFile(1, 2100, 2200);
   AddFile(1, 2300, 2400);
@@ -143,7 +151,7 @@ TEST(FileIndexerTest, next_level_hint) {
   AddFile(3, 500, 600);
   AddFile(3, 501, 699);
   AddFile(3, 700, 800);
-  indexer.UpdateIndex(files);
+  indexer->UpdateIndex(&arena, kNumLevels, files);
   for (uint32_t level = 1; level < 3; ++level) {
     for (uint32_t f = 0; f < 3; ++f) {
       GetNextLevelIndex(level, f, -1, -1, &left, &right);
@@ -166,11 +174,16 @@ TEST(FileIndexerTest, next_level_hint) {
       ASSERT_EQ(2, right);
     }
   }
+  delete indexer;
+}
 
-  // Case 3: empty L2
-  Reset();
+// Case 3: empty L2
+TEST(FileIndexerTest, empty_L2) {
+  Arena arena;
+  uint32_t kNumLevels = 4;
+  indexer = new FileIndexer(&ucmp);
   for (uint32_t i = 1; i < kNumLevels; ++i) {
-    ASSERT_EQ(0U, indexer.LevelIndexSize(i));
+    ASSERT_EQ(0U, indexer->LevelIndexSize(i));
   }
   // level 1
   AddFile(1, 2100, 2200);
@@ -180,7 +193,7 @@ TEST(FileIndexerTest, next_level_hint) {
   AddFile(3, 500, 600);
   AddFile(3, 501, 699);
   AddFile(3, 700, 800);
-  indexer.UpdateIndex(files);
+  indexer->UpdateIndex(&arena, kNumLevels, files);
   for (uint32_t f = 0; f < 3; ++f) {
     GetNextLevelIndex(1, f, -1, -1, &left, &right);
     ASSERT_EQ(0, left);
@@ -201,13 +214,14 @@ TEST(FileIndexerTest, next_level_hint) {
     ASSERT_EQ(0, left);
     ASSERT_EQ(-1, right);
   }
+  delete indexer;
+  ClearFiles();
+}
 
-
-  // Case 4: mixed
-  Reset();
-  for (uint32_t i = 1; i < kNumLevels; ++i) {
-    ASSERT_EQ(0U, indexer.LevelIndexSize(i));
-  }
+// Case 4: mixed
+TEST(FileIndexerTest, mixed) {
+  Arena arena;
+  indexer = new FileIndexer(&ucmp);
   // level 1
   AddFile(1, 100, 200);
   AddFile(1, 250, 400);
@@ -222,7 +236,7 @@ TEST(FileIndexerTest, next_level_hint) {
   AddFile(3, 0, 50);
   AddFile(3, 100, 200);
   AddFile(3, 201, 250);
-  indexer.UpdateIndex(files);
+  indexer->UpdateIndex(&arena, kNumLevels, files);
   // level 1, 0
   GetNextLevelIndex(1, 0, -1, -1, &left, &right);
   ASSERT_EQ(0, left);
@@ -321,6 +335,8 @@ TEST(FileIndexerTest, next_level_hint) {
     ASSERT_EQ(3, left);
     ASSERT_EQ(2, right);
   }
+  delete indexer;
+  ClearFiles();
 }
 
 }  // namespace rocksdb

db/version_set.cc

@@ -546,6 +546,8 @@ Version::Version(ColumnFamilyData* cfd, VersionSet* vset,
       // cfd is nullptr if Version is dummy
       num_levels_(cfd == nullptr ? 0 : cfd->NumberLevels()),
       num_non_empty_levels_(num_levels_),
+      file_indexer_(cfd == nullptr ?  nullptr
+          : cfd->internal_comparator().user_comparator()),
       vset_(vset),
       next_(this),
       prev_(this),
@@ -556,8 +558,6 @@ Version::Version(ColumnFamilyData* cfd, VersionSet* vset,
       compaction_score_(num_levels_),
       compaction_level_(num_levels_),
       version_number_(version_number),
-      file_indexer_(num_levels_, cfd == nullptr ?  nullptr
-          : cfd->internal_comparator().user_comparator()),
       total_file_size_(0),
       total_raw_key_size_(0),
       total_raw_value_size_(0),
@@ -782,6 +782,7 @@ void Version::PrepareApply(std::vector<uint64_t>& size_being_compacted) {
   ComputeCompactionScore(size_being_compacted);
   UpdateFilesBySize();
   UpdateNumNonEmptyLevels();
+  file_indexer_.UpdateIndex(&arena_, num_non_empty_levels_, files_);
   GenerateFileLevels();
 }
 
@@ -1599,8 +1600,6 @@ class VersionSet::Builder {
     }
 
     CheckConsistency(v);
-
-    v->file_indexer_.UpdateIndex(v->files_);
   }
 
   void LoadTableHandlers() {

db/version_set.h

@@ -283,6 +283,7 @@ class Version {
   int num_levels_;              // Number of levels
   int num_non_empty_levels_;    // Number of levels. Any level larger than it
                                 // is guaranteed to be empty.
+  FileIndexer file_indexer_;
   VersionSet* vset_;            // VersionSet to which this Version belongs
   Arena arena_;                 // Used to allocate space for file_levels_
   Version* next_;               // Next version in linked list
@@ -325,7 +326,6 @@ class Version {
   uint64_t version_number_;
 
   Version(ColumnFamilyData* cfd, VersionSet* vset, uint64_t version_number = 0);
-  FileIndexer file_indexer_;
 
   // total file size
   uint64_t total_file_size_;