@nxtedition/rocksdb 5.2.21 → 5.2.26

package/deps/rocksdb/rocksdb/db/compaction/compaction_iterator.h

@@ -23,6 +23,53 @@
 namespace ROCKSDB_NAMESPACE {
 
 class BlobFileBuilder;
+class BlobFetcher;
+class PrefetchBufferCollection;
+
+// A wrapper of internal iterator whose purpose is to count how
+// many entries there are in the iterator.
+class SequenceIterWrapper : public InternalIterator {
+ public:
+  SequenceIterWrapper(InternalIterator* iter, const Comparator* cmp,
+                      bool need_count_entries)
+      : icmp_(cmp, /*named=*/false),
+        inner_iter_(iter),
+        need_count_entries_(need_count_entries) {}
+  bool Valid() const override { return inner_iter_->Valid(); }
+  Status status() const override { return inner_iter_->status(); }
+  void Next() override {
+    num_itered_++;
+    inner_iter_->Next();
+  }
+  void Seek(const Slice& target) override {
+    if (!need_count_entries_) {
+      inner_iter_->Seek(target);
+    } else {
+      // For flush cases, we need to count total number of entries, so we
+      // do Next() rather than Seek().
+      while (inner_iter_->Valid() &&
+             icmp_.Compare(inner_iter_->key(), target) < 0) {
+        Next();
+      }
+    }
+  }
+  Slice key() const override { return inner_iter_->key(); }
+  Slice value() const override { return inner_iter_->value(); }
+
+  // Unused InternalIterator methods
+  void SeekToFirst() override { assert(false); }
+  void Prev() override { assert(false); }
+  void SeekForPrev(const Slice& /* target */) override { assert(false); }
+  void SeekToLast() override { assert(false); }
+
+  uint64_t num_itered() const { return num_itered_; }
+
+ private:
+  InternalKeyComparator icmp_;
+  InternalIterator* inner_iter_;  // not owned
+  uint64_t num_itered_ = 0;
+  bool need_count_entries_;
+};
 
 class CompactionIterator {
  public:
@@ -45,13 +92,19 @@ class CompactionIterator {
 
     virtual bool allow_ingest_behind() const = 0;
 
-    virtual bool preserve_deletes() const = 0;
+    virtual bool allow_mmap_reads() const = 0;
 
     virtual bool enable_blob_garbage_collection() const = 0;
 
     virtual double blob_garbage_collection_age_cutoff() const = 0;
 
-    virtual Version* input_version() const = 0;
+    virtual uint64_t blob_compaction_readahead_size() const = 0;
+
+    virtual const Version* input_version() const = 0;
+
+    virtual bool DoesInputReferenceBlobFiles() const = 0;
+
+    virtual const Compaction* real_compaction() const = 0;
   };
 
   class RealCompaction : public CompactionProxy {
@@ -59,7 +112,7 @@ class CompactionIterator {
     explicit RealCompaction(const Compaction* compaction)
         : compaction_(compaction) {
       assert(compaction_);
-      assert(compaction_->immutable_cf_options());
+      assert(compaction_->immutable_options());
       assert(compaction_->mutable_cf_options());
     }
 
@@ -81,11 +134,11 @@ class CompactionIterator {
     }
 
     bool allow_ingest_behind() const override {
-      return compaction_->immutable_cf_options()->allow_ingest_behind;
+      return compaction_->immutable_options()->allow_ingest_behind;
     }
 
-    bool preserve_deletes() const override {
-      return compaction_->immutable_cf_options()->preserve_deletes;
+    bool allow_mmap_reads() const override {
+      return compaction_->immutable_options()->allow_mmap_reads;
     }
 
     bool enable_blob_garbage_collection() const override {
@@ -97,48 +150,56 @@ class CompactionIterator {
           ->blob_garbage_collection_age_cutoff;
     }
 
-    Version* input_version() const override {
+    uint64_t blob_compaction_readahead_size() const override {
+      return compaction_->mutable_cf_options()->blob_compaction_readahead_size;
+    }
+
+    const Version* input_version() const override {
       return compaction_->input_version();
     }
 
+    bool DoesInputReferenceBlobFiles() const override {
+      return compaction_->DoesInputReferenceBlobFiles();
+    }
+
+    const Compaction* real_compaction() const override { return compaction_; }
+
    private:
     const Compaction* compaction_;
   };
 
-  CompactionIterator(InternalIterator* input, const Comparator* cmp,
-                     MergeHelper* merge_helper, SequenceNumber last_sequence,
-                     std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot,
-                     const SnapshotChecker* snapshot_checker, Env* env,
-                     bool report_detailed_time, bool expect_valid_internal_key,
-                     CompactionRangeDelAggregator* range_del_agg,
-                     BlobFileBuilder* blob_file_builder,
-                     bool allow_data_in_errors,
-                     const Compaction* compaction = nullptr,
-                     const CompactionFilter* compaction_filter = nullptr,
-                     const std::atomic<bool>* shutting_down = nullptr,
-                     const SequenceNumber preserve_deletes_seqnum = 0,
-                     const std::atomic<int>* manual_compaction_paused = nullptr,
-                     const std::shared_ptr<Logger> info_log = nullptr,
-                     const std::string* full_history_ts_low = nullptr);
+  CompactionIterator(
+      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
+      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
+      SequenceNumber earliest_write_conflict_snapshot,
+      SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
+      Env* env, bool report_detailed_time, bool expect_valid_internal_key,
+      CompactionRangeDelAggregator* range_del_agg,
+      BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
+      const Compaction* compaction = nullptr,
+      const CompactionFilter* compaction_filter = nullptr,
+      const std::atomic<bool>* shutting_down = nullptr,
+      const std::atomic<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
+      const std::shared_ptr<Logger> info_log = nullptr,
+      const std::string* full_history_ts_low = nullptr);
 
   // Constructor with custom CompactionProxy, used for tests.
-  CompactionIterator(InternalIterator* input, const Comparator* cmp,
-                     MergeHelper* merge_helper, SequenceNumber last_sequence,
-                     std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot,
-                     const SnapshotChecker* snapshot_checker, Env* env,
-                     bool report_detailed_time, bool expect_valid_internal_key,
-                     CompactionRangeDelAggregator* range_del_agg,
-                     BlobFileBuilder* blob_file_builder,
-                     bool allow_data_in_errors,
-                     std::unique_ptr<CompactionProxy> compaction,
-                     const CompactionFilter* compaction_filter = nullptr,
-                     const std::atomic<bool>* shutting_down = nullptr,
-                     const SequenceNumber preserve_deletes_seqnum = 0,
-                     const std::atomic<int>* manual_compaction_paused = nullptr,
-                     const std::shared_ptr<Logger> info_log = nullptr,
-                     const std::string* full_history_ts_low = nullptr);
+  CompactionIterator(
+      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
+      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
+      SequenceNumber earliest_write_conflict_snapshot,
+      SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
+      Env* env, bool report_detailed_time, bool expect_valid_internal_key,
+      CompactionRangeDelAggregator* range_del_agg,
+      BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
+      std::unique_ptr<CompactionProxy> compaction,
+      const CompactionFilter* compaction_filter = nullptr,
+      const std::atomic<bool>* shutting_down = nullptr,
+      const std::atomic<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
+      const std::shared_ptr<Logger> info_log = nullptr,
+      const std::string* full_history_ts_low = nullptr);
 
   ~CompactionIterator();
 
@@ -162,6 +223,7 @@ class CompactionIterator {
   bool Valid() const { return valid_; }
   const Slice& user_key() const { return current_user_key_; }
   const CompactionIterationStats& iter_stats() const { return iter_stats_; }
+  uint64_t num_input_entry_scanned() const { return input_.num_itered(); }
 
  private:
   // Processes the input stream to find the next output
@@ -204,18 +266,15 @@ class CompactionIterator {
   inline SequenceNumber findEarliestVisibleSnapshot(
       SequenceNumber in, SequenceNumber* prev_snapshot);
 
-  // Checks whether the currently seen ikey_ is needed for
-  // incremental (differential) snapshot and hence can't be dropped
-  // or seqnum be zero-ed out even if all other conditions for it are met.
-  inline bool ikeyNotNeededForIncrementalSnapshot();
-
   inline bool KeyCommitted(SequenceNumber sequence) {
     return snapshot_checker_ == nullptr ||
-           snapshot_checker_->CheckInSnapshot(sequence, kMaxSequenceNumber) ==
+           snapshot_checker_->CheckInSnapshot(sequence, job_snapshot_) ==
                SnapshotCheckerResult::kInSnapshot;
   }
 
-  bool IsInEarliestSnapshot(SequenceNumber sequence);
+  bool DefinitelyInSnapshot(SequenceNumber seq, SequenceNumber snapshot);
+
+  bool DefinitelyNotInSnapshot(SequenceNumber seq, SequenceNumber snapshot);
 
   // Extract user-defined timestamp from user key if possible and compare it
   // with *full_history_ts_low_ if applicable.
@@ -233,8 +292,12 @@ class CompactionIterator {
 
   static uint64_t ComputeBlobGarbageCollectionCutoffFileNumber(
       const CompactionProxy* compaction);
+  static std::unique_ptr<BlobFetcher> CreateBlobFetcherIfNeeded(
+      const CompactionProxy* compaction);
+  static std::unique_ptr<PrefetchBufferCollection>
+  CreatePrefetchBufferCollectionIfNeeded(const CompactionProxy* compaction);
 
-  InternalIterator* input_;
+  SequenceIterWrapper input_;
   const Comparator* cmp_;
   MergeHelper* merge_helper_;
   const std::vector<SequenceNumber>* snapshots_;
@@ -246,8 +309,10 @@ class CompactionIterator {
   std::unordered_set<SequenceNumber> released_snapshots_;
   std::vector<SequenceNumber>::const_iterator earliest_snapshot_iter_;
   const SequenceNumber earliest_write_conflict_snapshot_;
+  const SequenceNumber job_snapshot_;
   const SnapshotChecker* const snapshot_checker_;
   Env* env_;
+  SystemClock* clock_;
   bool report_detailed_time_;
   bool expect_valid_internal_key_;
   CompactionRangeDelAggregator* range_del_agg_;
@@ -256,7 +321,7 @@ class CompactionIterator {
   const CompactionFilter* compaction_filter_;
   const std::atomic<bool>* shutting_down_;
   const std::atomic<int>* manual_compaction_paused_;
-  const SequenceNumber preserve_deletes_seqnum_;
+  const std::atomic<bool>* manual_compaction_canceled_;
   bool bottommost_level_;
   bool valid_ = false;
   bool visible_at_tip_;
@@ -319,6 +384,9 @@ class CompactionIterator {
 
   uint64_t blob_garbage_collection_cutoff_file_number_;
 
+  std::unique_ptr<BlobFetcher> blob_fetcher_;
+  std::unique_ptr<PrefetchBufferCollection> prefetch_buffers_;
+
   std::string blob_index_;
   PinnableSlice blob_value_;
   std::string compaction_filter_value_;
@@ -339,6 +407,16 @@ class CompactionIterator {
   // Saved result of ucmp->CompareTimestamp(current_ts_, *full_history_ts_low_)
   int cmp_with_history_ts_low_;
 
+  const int level_;
+
+  // True if the previous internal key (same user key)'s sequence number has
+  // just been zeroed out during bottommost compaction.
+  bool last_key_seq_zeroed_{false};
+
+  void AdvanceInputIter() { input_.Next(); }
+
+  void SkipUntil(const Slice& skip_until) { input_.Seek(skip_until); }
+
   bool IsShuttingDown() {
     // This is a best-effort facility, so memory_order_relaxed is sufficient.
     return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);
@@ -346,8 +424,27 @@ class CompactionIterator {
 
   bool IsPausingManualCompaction() {
     // This is a best-effort facility, so memory_order_relaxed is sufficient.
-    return manual_compaction_paused_ &&
-           manual_compaction_paused_->load(std::memory_order_relaxed) > 0;
+    return (manual_compaction_paused_ &&
+            manual_compaction_paused_->load(std::memory_order_relaxed) > 0) ||
+           (manual_compaction_canceled_ &&
+            manual_compaction_canceled_->load(std::memory_order_relaxed));
   }
 };
+
+inline bool CompactionIterator::DefinitelyInSnapshot(SequenceNumber seq,
+                                                     SequenceNumber snapshot) {
+  return ((seq) <= (snapshot) &&
+          (snapshot_checker_ == nullptr ||
+           LIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                  SnapshotCheckerResult::kInSnapshot)));
+}
+
+inline bool CompactionIterator::DefinitelyNotInSnapshot(
+    SequenceNumber seq, SequenceNumber snapshot) {
+  return ((seq) > (snapshot) ||
+          (snapshot_checker_ != nullptr &&
+           UNLIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                    SnapshotCheckerResult::kNotInSnapshot)));
+}
+
 }  // namespace ROCKSDB_NAMESPACE