From 2e8cc98ab2c106836d972ae843b85bdd01f79bea Mon Sep 17 00:00:00 2001
From: Changyu Bi <changyubi@meta.com>
Date: Tue, 6 Jun 2023 13:36:02 -0700
Subject: [PATCH] Fix subcompaction bug to allow running two subcompactions
 (#11501)

Summary:
as reported in https://github.com/facebook/rocksdb/issues/11476, RocksDB currently does not execute compactions in two subcompactions even when they qualify. This PR fixes this issue.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11501

Test Plan:
* Add a new unit test.
* Run crash test with max_subcompactions=2: `python3 tools/db_crashtest.py blackbox --simple  --subcompactions=2 --target_file_size_base=1048576 --compaction_style=0`
  * saw logs showing compactions being executed as 2 subcompactions
```
2023/06/01-17:28:44.028470 3147486 (Original Log Time 2023/06/01-17:28:44.025972) EVENT_LOG_v1 {"time_micros": 1685665724025939, "job": 6, "event": "compaction_finished", "compaction_time_micros": 34539, "compaction_time_cpu_micros": 26404, "output_level": 6, "num_output_files": 2, "total_output_size": 1109796, "num_input_records": 13188, "num_output_records": 13021, "num_subcompactions": 2, "output_compression": "NoCompression", "num_single_delete_mismatches": 0, "num_single_delete_fallthrough": 0, "lsm_state": [0, 0, 0, 0, 0, 0, 13]}
```

Reviewed By: ajkr

Differential Revision: D46411497

Pulled By: cbi42

fbshipit-source-id: 3ebfc02e19f78f782e114a9546dc3d481d496258
---
 db/compaction/compaction_job.cc               |  2 +-
 db/db_compaction_test.cc                      | 53 +++++++++++++++++++
 .../bug_fixes/subcompaction_2.md              |  1 +
 3 files changed, 55 insertions(+), 1 deletion(-)
 create mode 100644 unreleased_history/bug_fixes/subcompaction_2.md

diff --git a/db/compaction/compaction_job.cc b/db/compaction/compaction_job.cc
index b16ca2ca6..f8fb5a910 100644
--- a/db/compaction/compaction_job.cc
+++ b/db/compaction/compaction_job.cc
@@ -260,7 +260,7 @@ void CompactionJob::Prepare() {
     StopWatch sw(db_options_.clock, stats_, SUBCOMPACTION_SETUP_TIME);
     GenSubcompactionBoundaries();
   }
-  if (boundaries_.size() > 1) {
+  if (boundaries_.size() >= 1) {
     for (size_t i = 0; i <= boundaries_.size(); i++) {
       compact_->sub_compact_states.emplace_back(
           c, (i != 0) ? std::optional<Slice>(boundaries_[i - 1]) : std::nullopt,
diff --git a/db/db_compaction_test.cc b/db/db_compaction_test.cc
index 1e9721949..46ea1fcae 100644
--- a/db/db_compaction_test.cc
+++ b/db/db_compaction_test.cc
@@ -9753,6 +9753,59 @@ TEST_F(DBCompactionTest,
   ASSERT_EQ(0, NumTableFilesAtLevel(5));
 }
 
+TEST_F(DBCompactionTest, NumberOfSubcompactions) {
+  // Tests that expected number of subcompactions are created.
+  class SubCompactionEventListener : public EventListener {
+   public:
+    void OnSubcompactionCompleted(const SubcompactionJobInfo&) override {
+      sub_compaction_finished_++;
+    }
+    void OnCompactionCompleted(DB*, const CompactionJobInfo&) override {
+      compaction_finished_++;
+    }
+    std::atomic<int> sub_compaction_finished_{0};
+    std::atomic<int> compaction_finished_{0};
+  };
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleLevel;
+  options.compression = kNoCompression;
+  const int kFileSize = 100 << 10;  // 100KB
+  options.target_file_size_base = kFileSize;
+  const int kLevel0CompactTrigger = 2;
+  options.level0_file_num_compaction_trigger = kLevel0CompactTrigger;
+  Destroy(options);
+  Random rnd(301);
+
+  // Exposing internal implementation detail here where the
+  // number of subcompactions depends on the size of data
+  // being compacted. In particular, to enable x subcompactions,
+  // we need to compact at least x * target file size amount
+  // of data.
+  //
+  // Will write two files below to avoid trivial move.
+  // Size written in total: 500 * 1000 * 2 ~ 10MB ~ 100 * target file size.
+  const int kValueSize = 500;
+  const int kNumKeyPerFile = 1000;
+  for (int i = 1; i <= 8; ++i) {
+    options.max_subcompactions = i;
+    SubCompactionEventListener* listener = new SubCompactionEventListener();
+    options.listeners.clear();
+    options.listeners.emplace_back(listener);
+    TryReopen(options);
+
+    for (int file = 0; file < kLevel0CompactTrigger; ++file) {
+      for (int key = file; key < 2 * kNumKeyPerFile; key += 2) {
+        ASSERT_OK(Put(Key(key), rnd.RandomString(kValueSize)));
+      }
+      ASSERT_OK(Flush());
+    }
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    ASSERT_EQ(listener->compaction_finished_, 1);
+    EXPECT_EQ(listener->sub_compaction_finished_, i);
+    Destroy(options);
+  }
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {
diff --git a/unreleased_history/bug_fixes/subcompaction_2.md b/unreleased_history/bug_fixes/subcompaction_2.md
new file mode 100644
index 000000000..b56fc5dea
--- /dev/null
+++ b/unreleased_history/bug_fixes/subcompaction_2.md
@@ -0,0 +1 @@
+Fix a bug where compactions that are qualified to be run as 2 subcompactions were only run as one subcompaction. 
\ No newline at end of file