Restrict L0->L0 compaction according to max_compaction_bytes option (#5329)

Summary:
Modified FindIntraL0Compaction to stop picking more files if total
amount of compensated bytes would be larger than max_compaction_bytes
option.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5329

Differential Revision: D15435728

Pulled By: ThomasFersch

fbshipit-source-id: d118a6da88d5df8ee20944422ade37cf6b15d60c

db/compaction_picker.cc

@@ -42,19 +42,23 @@ uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
 bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
                            size_t min_files_to_compact,
                            uint64_t max_compact_bytes_per_del_file,
+                           uint64_t max_compaction_bytes,
                            CompactionInputFiles* comp_inputs) {
   size_t compact_bytes = static_cast<size_t>(level_files[0]->fd.file_size);
+  uint64_t compensated_compact_bytes = level_files[0]->compensated_file_size;
   size_t compact_bytes_per_del_file = port::kMaxSizet;
-  // compaction range will be [0, span_len).
+  // Compaction range will be [0, span_len).
   size_t span_len;
-  // pull in files until the amount of compaction work per deleted file begins
+  // Pull in files until the amount of compaction work per deleted file begins
-  // increasing.
+  // increasing or maximum total compaction size is reached.
   size_t new_compact_bytes_per_del_file = 0;
   for (span_len = 1; span_len < level_files.size(); ++span_len) {
     compact_bytes += static_cast<size_t>(level_files[span_len]->fd.file_size);
+    compensated_compact_bytes += level_files[span_len]->compensated_file_size;
     new_compact_bytes_per_del_file = compact_bytes / span_len;
     if (level_files[span_len]->being_compacted ||
-        new_compact_bytes_per_del_file > compact_bytes_per_del_file) {
+        new_compact_bytes_per_del_file > compact_bytes_per_del_file ||
+        compensated_compact_bytes > max_compaction_bytes) {
       break;
     }
     compact_bytes_per_del_file = new_compact_bytes_per_del_file;
@@ -1627,7 +1631,9 @@ bool LevelCompactionBuilder::PickIntraL0Compaction() {
     return false;
   }
   return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
-                               port::kMaxUint64, &start_level_inputs_);
+                               port::kMaxUint64,
+                               mutable_cf_options_.max_compaction_bytes,
+                               &start_level_inputs_);
 }
 }  // namespace
 

db/compaction_picker.h

@@ -273,9 +273,26 @@ class NullCompactionPicker : public CompactionPicker {
 };
 #endif  // !ROCKSDB_LITE
 
+// Attempts to find an intra L0 compaction conforming to the given parameters.
+//
+// @param level_files                     Metadata for L0 files.
+// @param min_files_to_compact            Minimum number of files required to
+//                                        do the compaction.
+// @param max_compact_bytes_per_del_file  Maximum average size in bytes per
+//                                        file that is going to get deleted by
+//                                        the compaction.
+// @param max_compaction_bytes            Maximum total size in bytes (in terms
+//                                        of compensated file size) for files
+//                                        to be compacted.
+// @param [out] comp_inputs               If a compaction was found, will be
+//                                        initialized with corresponding input
+//                                        files. Cannot be nullptr.
+//
+// @return                                true iff compaction was found.
 bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
                            size_t min_files_to_compact,
                            uint64_t max_compact_bytes_per_del_file,
+                           uint64_t max_compaction_bytes,
                            CompactionInputFiles* comp_inputs);
 
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,

db/compaction_picker_fifo.cc

@@ -134,7 +134,8 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
               mutable_cf_options
                   .level0_file_num_compaction_trigger /* min_files_to_compact */
               ,
-              max_compact_bytes_per_del_file, &comp_inputs)) {
+              max_compact_bytes_per_del_file,
+              mutable_cf_options.max_compaction_bytes, &comp_inputs)) {
         Compaction* c = new Compaction(
             vstorage, ioptions_, mutable_cf_options, {comp_inputs}, 0,
             16 * 1024 * 1024 /* output file size limit */,

db/compaction_picker_test.cc

@@ -1478,6 +1478,65 @@ TEST_F(CompactionPickerTest, CacheNextCompactionIndex) {
   ASSERT_EQ(4, vstorage_->NextCompactionIndex(1 /* level */));
 }
 
+TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesNotHit) {
+  // Intra L0 compaction triggers only if there are at least
+  // level0_file_num_compaction_trigger + 2 L0 files.
+  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
+  mutable_cf_options_.max_compaction_bytes = 1000000u;
+  NewVersionStorage(6, kCompactionStyleLevel);
+
+  // All 5 L0 files will be picked for intra L0 compaction. The one L1 file
+  // spans entire L0 key range and is marked as being compacted to avoid
+  // L0->L1 compaction.
+  Add(0, 1U, "100", "150", 200000U);
+  Add(0, 2U, "151", "200", 200000U);
+  Add(0, 3U, "201", "250", 200000U);
+  Add(0, 4U, "251", "300", 200000U);
+  Add(0, 5U, "301", "350", 200000U);
+  Add(1, 6U, "100", "350", 200000U);
+  vstorage_->LevelFiles(1)[0]->being_compacted = true;
+  UpdateVersionStorageInfo();
+
+  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1U, compaction->num_input_levels());
+  ASSERT_EQ(5U, compaction->num_input_files(0));
+  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
+            compaction->compaction_reason());
+  ASSERT_EQ(0U, compaction->output_level());
+}
+
+TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesHit) {
+  // Intra L0 compaction triggers only if there are at least
+  // level0_file_num_compaction_trigger + 2 L0 files.
+  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
+  mutable_cf_options_.max_compaction_bytes = 999999u;
+  NewVersionStorage(6, kCompactionStyleLevel);
+
+  // 4 out of 5 L0 files will be picked for intra L0 compaction due to
+  // max_compaction_bytes limit (the minimum number of files for triggering
+  // intra L0 compaction is 4). The one L1 file spans entire L0 key range and
+  // is marked as being compacted to avoid L0->L1 compaction.
+  Add(0, 1U, "100", "150", 200000U);
+  Add(0, 2U, "151", "200", 200000U);
+  Add(0, 3U, "201", "250", 200000U);
+  Add(0, 4U, "251", "300", 200000U);
+  Add(0, 5U, "301", "350", 200000U);
+  Add(1, 6U, "100", "350", 200000U);
+  vstorage_->LevelFiles(1)[0]->being_compacted = true;
+  UpdateVersionStorageInfo();
+
+  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1U, compaction->num_input_levels());
+  ASSERT_EQ(4U, compaction->num_input_files(0));
+  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
+            compaction->compaction_reason());
+  ASSERT_EQ(0U, compaction->output_level());
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {