Estimate pending compaction bytes more accurately

Summary: Currently we estimate bytes needed for compaction by assuming fanout value to be level multiplier. It overestimates when size of a level exceeds the target by large. We estimate by the ratio of actual sizes in levels instead.

Test Plan: Fix existing test cases and add a new one.

Reviewers: IslamAbdelRahman, igor, yhchiang

Reviewed By: yhchiang

Subscribers: MarkCallaghan, leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D57789

db/compaction_picker_test.cc

@@ -776,19 +776,22 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded1) {
   Add(1, 4U, "400", "500", 600);
   Add(1, 5U, "600", "700", 600);
   // Level 2 is less than target 10000 even added size of level 1
+  // Size ratio of L2/L1 is 9600 / 1200 = 8
   Add(2, 6U, "150", "200", 2500);
   Add(2, 7U, "201", "210", 2000);
-  Add(2, 8U, "300", "310", 2500);
+  Add(2, 8U, "300", "310", 2600);
   Add(2, 9U, "400", "500", 2500);
   // Level 3 exceeds target 100,000 of 1000
   Add(3, 10U, "400", "500", 101000);
-  // Level 4 exceeds target 1,000,000 of 500 after adding size from level 3
+  // Level 4 exceeds target 1,000,000 by 900 after adding size from level 3
-  Add(4, 11U, "400", "500", 999500);
+  // Size ratio L4/L3 is 9.9
-  Add(5, 11U, "400", "500", 8000000);
+  // After merge from L3, L4 size is 1000900
+  Add(4, 11U, "400", "500", 999900);
+  Add(5, 11U, "400", "500", 8007200);
 
   UpdateVersionStorageInfo();
 
-  ASSERT_EQ(2200u + 11000u + 5500u,
+  ASSERT_EQ(200u * 9u + 10900u + 900u * 9,
             vstorage_->estimated_compaction_needed_bytes());
 }
 
@@ -804,17 +807,42 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded2) {
   Add(0, 4U, "150", "200", 200);
   Add(0, 5U, "150", "200", 200);
   Add(0, 6U, "150", "200", 200);
-  // Level 1 is over target by
+  // Level 1 size will be 1400 after merging with L0
   Add(1, 7U, "400", "500", 200);
   Add(1, 8U, "600", "700", 200);
   // Level 2 is less than target 10000 even added size of level 1
-  Add(2, 9U, "150", "200", 9500);
+  Add(2, 9U, "150", "200", 9100);
+  // Level 3 over the target, but since level 4 is empty, we assume it will be
+  // a trivial move.
   Add(3, 10U, "400", "500", 101000);
 
   UpdateVersionStorageInfo();
 
-  ASSERT_EQ(1400u + 4400u + 11000u,
+  // estimated L1->L2 merge: 400 * (9100.0 / 1400.0 + 1.0)
-            vstorage_->estimated_compaction_needed_bytes());
+  ASSERT_EQ(1400u + 3000u, vstorage_->estimated_compaction_needed_bytes());
+}
+
+TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded3) {
+  int num_levels = ioptions_.num_levels;
+  ioptions_.level_compaction_dynamic_level_bytes = false;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
+  mutable_cf_options_.max_bytes_for_level_base = 1000;
+  mutable_cf_options_.max_bytes_for_level_multiplier = 10;
+  NewVersionStorage(num_levels, kCompactionStyleLevel);
+  Add(0, 1U, "150", "200", 2000);
+  Add(0, 2U, "150", "200", 2000);
+  Add(0, 4U, "150", "200", 2000);
+  Add(0, 5U, "150", "200", 2000);
+  Add(0, 6U, "150", "200", 1000);
+  // Level 1 size will be 10000 after merging with L0
+  Add(1, 7U, "400", "500", 500);
+  Add(1, 8U, "600", "700", 500);
+
+  Add(2, 9U, "150", "200", 10000);
+
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(10000u + 18000u, vstorage_->estimated_compaction_needed_bytes());
 }
 
 TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
@@ -838,12 +866,14 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
   // num_levels - 3 is over target by 100 + 1000
   Add(num_levels - 3, 7U, "400", "500", 300);
   Add(num_levels - 3, 8U, "600", "700", 300);
-  // Level 2 is over target by 1100 + 100
+  // num_levels - 2 is over target by 1100 + 200
-  Add(num_levels - 2, 9U, "150", "200", 5100);
+  Add(num_levels - 2, 9U, "150", "200", 5200);
 
   UpdateVersionStorageInfo();
 
-  ASSERT_EQ(1600u + 12100u + 13200u,
+  // Merging to the second last level: (5200 / 1600 + 1) * 1100
+  // Merging to the last level: (50000 / 6300 + 1) * 1300
+  ASSERT_EQ(1600u + 4675u + 11617u,
             vstorage_->estimated_compaction_needed_bytes());
 }
 

db/db_test.cc

@@ -5675,7 +5675,7 @@ TEST_F(DBTest, SoftLimit) {
   options.level0_slowdown_writes_trigger = 3;
   options.level0_stop_writes_trigger = 999999;
   options.delayed_write_rate = 20000;  // About 200KB/s limited rate
-  options.soft_pending_compaction_bytes_limit = 200000;
+  options.soft_pending_compaction_bytes_limit = 160000;
   options.target_file_size_base = 99999999;  // All into one file
   options.max_bytes_for_level_base = 50000;
   options.max_bytes_for_level_multiplier = 10;
@@ -5683,6 +5683,27 @@ TEST_F(DBTest, SoftLimit) {
   options.compression = kNoCompression;
 
   Reopen(options);
+
+  // Generating 360KB in Level 3
+  for (int i = 0; i < 72; i++) {
+    Put(Key(i), std::string(5000, 'x'));
+    if (i % 10 == 0) {
+      Flush();
+    }
+  }
+  dbfull()->TEST_WaitForCompact();
+  MoveFilesToLevel(3);
+
+  // Generating 360KB in Level 2
+  for (int i = 0; i < 72; i++) {
+    Put(Key(i), std::string(5000, 'x'));
+    if (i % 10 == 0) {
+      Flush();
+    }
+  }
+  dbfull()->TEST_WaitForCompact();
+  MoveFilesToLevel(2);
+
   Put(Key(0), "");
 
   test::SleepingBackgroundTask sleeping_task_low;
@@ -5758,7 +5779,8 @@ TEST_F(DBTest, SoftLimit) {
   sleeping_task_low.WaitUntilSleeping();
 
   // Now there is one L1 file (around 90KB) which exceeds 50KB base by 40KB
-  // Given level multiplier 10, estimated pending compaction is around 400KB
+  // L2 size is 360KB, so the estimated level fanout 4, estimated pending
+  // compaction is around 200KB
   // triggerring soft_pending_compaction_bytes_limit
   ASSERT_EQ(NumTableFilesAtLevel(1), 1);
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());

db/version_set.cc

@@ -1195,10 +1195,23 @@ void VersionStorageInfo::EstimateCompactionBytesNeeded(
   }
 
   // Level 1 and up.
+  uint64_t bytes_next_level = 0;
   for (int level = base_level(); level <= MaxInputLevel(); level++) {
     uint64_t level_size = 0;
-    for (auto* f : files_[level]) {
+    if (bytes_next_level > 0) {
-      level_size += f->fd.GetFileSize();
+#ifndef NDEBUG
+      uint64_t level_size2 = 0;
+      for (auto* f : files_[level]) {
+        level_size2 += f->fd.GetFileSize();
+      }
+      assert(level_size2 == bytes_next_level);
+#endif
+      level_size = bytes_next_level;
+      bytes_next_level = 0;
+    } else {
+      for (auto* f : files_[level]) {
+        level_size += f->fd.GetFileSize();
+      }
     }
     if (level == base_level() && level0_compact_triggered) {
       // Add base level size to compaction if level0 compaction triggered.
@@ -1210,11 +1223,23 @@ void VersionStorageInfo::EstimateCompactionBytesNeeded(
     uint64_t level_target = MaxBytesForLevel(level);
     if (level_size > level_target) {
       bytes_compact_to_next_level = level_size - level_target;
-      // Simplify to assume the actual compaction fan-out ratio is always
+      // Estimate the actual compaction fan-out ratio as size ratio between
-      // mutable_cf_options.max_bytes_for_level_multiplier.
+      // the two levels.
-      estimated_compaction_needed_bytes_ +=
+
-          bytes_compact_to_next_level *
+      assert(bytes_next_level == 0);
-          (1 + mutable_cf_options.max_bytes_for_level_multiplier);
+      if (level + 1 < num_levels_) {
+        for (auto* f : files_[level + 1]) {
+          bytes_next_level += f->fd.GetFileSize();
+        }
+      }
+      if (bytes_next_level > 0) {
+        assert(level_size > 0);
+        estimated_compaction_needed_bytes_ += static_cast<uint64_t>(
+            static_cast<double>(bytes_compact_to_next_level) *
+            (static_cast<double>(bytes_next_level) /
+                 static_cast<double>(level_size) +
+             1));
+      }
     }
   }
 }