VersionBuilder to optimize for applying a later edit deleting files added by previous edits

Summary: During recovery, VersionBuilder::Apply() was called multiple times. If the DB is open for long enough, most of files added earlier will be deleted by later deletes. In current solution, sorting added file happens first and then deletes are applied. In this patch, deletes are applied when possible inside Apply(), which can significantly reduce the sorting time in some cases.

Test Plan:
Add unit tests in version_builder
valgrind_check
Open a manifest of 50MB, with 9K live files. The manifest read time reduced from 1.6 seconds to 0.7 seconds.

Reviewers: rven, yhchiang, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D30765

db/version_builder.cc

@@ -101,22 +101,25 @@ class VersionBuilder::Rep {
     for (int level = 0; level < base_vstorage_->num_levels(); level++) {
       const auto& added = levels_[level].added_files;
       for (auto& pair : added) {
-        FileMetaData* f = pair.second;
-        f->refs--;
-        if (f->refs <= 0) {
-          if (f->table_reader_handle) {
-            assert(table_cache_ != nullptr);
-            table_cache_->ReleaseHandle(f->table_reader_handle);
-            f->table_reader_handle = nullptr;
-          }
-          delete f;
-        }
+        UnrefFile(pair.second);
       }
     }
 
     delete[] levels_;
   }
 
+  void UnrefFile(FileMetaData* f) {
+    f->refs--;
+    if (f->refs <= 0) {
+      if (f->table_reader_handle) {
+        assert(table_cache_ != nullptr);
+        table_cache_->ReleaseHandle(f->table_reader_handle);
+        f->table_reader_handle = nullptr;
+      }
+      delete f;
+    }
+  }
+
   void CheckConsistency(VersionStorageInfo* vstorage) {
 #ifndef NDEBUG
     // make sure the files are sorted correctly
@@ -199,6 +202,12 @@ class VersionBuilder::Rep {
       const auto number = del_file.second;
       levels_[level].deleted_files.insert(number);
       CheckConsistencyForDeletes(edit, number, level);
+
+      auto exising = levels_[level].added_files.find(number);
+      if (exising != levels_[level].added_files.end()) {
+        UnrefFile(exising->second);
+        levels_[level].added_files.erase(number);
+      }
     }
 
     // Add new files

db/version_builder_test.cc

@@ -126,6 +126,84 @@ TEST(VersionBuilderTest, ApplyAndSaveTo) {
   }
 }
 
+TEST(VersionBuilderTest, ApplyMultipleAndSaveTo) {
+  UpdateVersionStorageInfo();
+
+  VersionEdit version_edit;
+  version_edit.AddFile(2, 666, 0, 100U, GetInternalKey("301"),
+                       GetInternalKey("350"), 200, 200);
+  version_edit.AddFile(2, 676, 0, 100U, GetInternalKey("401"),
+                       GetInternalKey("450"), 200, 200);
+  version_edit.AddFile(2, 636, 0, 100U, GetInternalKey("601"),
+                       GetInternalKey("650"), 200, 200);
+  version_edit.AddFile(2, 616, 0, 100U, GetInternalKey("501"),
+                       GetInternalKey("550"), 200, 200);
+  version_edit.AddFile(2, 606, 0, 100U, GetInternalKey("701"),
+                       GetInternalKey("750"), 200, 200);
+
+  EnvOptions env_options;
+
+  VersionBuilder version_builder(env_options, nullptr, &vstorage_);
+
+  VersionStorageInfo new_vstorage(&icmp_, ucmp_, options_.num_levels,
+                                  kCompactionStyleLevel, nullptr);
+  version_builder.Apply(&version_edit);
+  version_builder.SaveTo(&new_vstorage);
+
+  ASSERT_EQ(500U, new_vstorage.NumLevelBytes(2));
+
+  for (int i = 0; i < new_vstorage.num_levels(); i++) {
+    for (auto* f : new_vstorage.LevelFiles(i)) {
+      if (--f->refs == 0) {
+        delete f;
+      }
+    }
+  }
+}
+
+TEST(VersionBuilderTest, ApplyDeleteAndSaveTo) {
+  UpdateVersionStorageInfo();
+
+  EnvOptions env_options;
+  VersionBuilder version_builder(env_options, nullptr, &vstorage_);
+  VersionStorageInfo new_vstorage(&icmp_, ucmp_, options_.num_levels,
+                                  kCompactionStyleLevel, nullptr);
+
+  VersionEdit version_edit;
+  version_edit.AddFile(2, 666, 0, 100U, GetInternalKey("301"),
+                       GetInternalKey("350"), 200, 200);
+  version_edit.AddFile(2, 676, 0, 100U, GetInternalKey("401"),
+                       GetInternalKey("450"), 200, 200);
+  version_edit.AddFile(2, 636, 0, 100U, GetInternalKey("601"),
+                       GetInternalKey("650"), 200, 200);
+  version_edit.AddFile(2, 616, 0, 100U, GetInternalKey("501"),
+                       GetInternalKey("550"), 200, 200);
+  version_edit.AddFile(2, 606, 0, 100U, GetInternalKey("701"),
+                       GetInternalKey("750"), 200, 200);
+  version_builder.Apply(&version_edit);
+
+  VersionEdit version_edit2;
+  version_edit.AddFile(2, 808, 0, 100U, GetInternalKey("901"),
+                       GetInternalKey("950"), 200, 200);
+  version_edit2.DeleteFile(2, 616);
+  version_edit2.DeleteFile(2, 636);
+  version_edit.AddFile(2, 806, 0, 100U, GetInternalKey("801"),
+                       GetInternalKey("850"), 200, 200);
+  version_builder.Apply(&version_edit2);
+
+  version_builder.SaveTo(&new_vstorage);
+
+  ASSERT_EQ(300U, new_vstorage.NumLevelBytes(2));
+
+  for (int i = 0; i < new_vstorage.num_levels(); i++) {
+    for (auto* f : new_vstorage.LevelFiles(i)) {
+      if (--f->refs == 0) {
+        delete f;
+      }
+    }
+  }
+}
+
 TEST(VersionBuilderTest, EstimatedActiveKeys) {
   const uint32_t kTotalSamples = 20;
   const uint32_t kNumLevels = 5;