rocksdb-native 2.2.0 → 2.3.0

package/vendor/librocksdb/vendor/rocksdb/db/error_handler.cc

@@ -250,8 +250,6 @@ void ErrorHandler::CancelErrorRecovery() {
   EndAutoRecovery();
 }
 
-STATIC_AVOID_DESTRUCTION(const Status, kOkStatus){Status::OK()};
-
 // This is the main function for looking at an error during a background
 // operation and deciding the severity, and error recovery strategy. The high
 // level algorithm is as follows -
@@ -270,11 +268,11 @@ STATIC_AVOID_DESTRUCTION(const Status, kOkStatus){Status::OK()};
 // This can also get called as part of a recovery operation. In that case, we
 // also track the error separately in recovery_error_ so we can tell in the
 // end whether recovery succeeded or not
-const Status& ErrorHandler::HandleKnownErrors(const Status& bg_err,
-                                              BackgroundErrorReason reason) {
+void ErrorHandler::HandleKnownErrors(const Status& bg_err,
+                                     BackgroundErrorReason reason) {
   db_mutex_->AssertHeld();
   if (bg_err.ok()) {
-    return kOkStatus;
+    return;
   }
 
   ROCKS_LOG_INFO(db_options_.info_log,
@@ -339,7 +337,7 @@ const Status& ErrorHandler::HandleKnownErrors(const Status& bg_err,
     } else {
       // This error is less severe than previously encountered error. Don't
       // take any further action
-      return bg_error_;
+      return;
     }
   }
 
@@ -356,7 +354,6 @@ const Status& ErrorHandler::HandleKnownErrors(const Status& bg_err,
   if (bg_error_.severity() >= Status::Severity::kHardError) {
     is_db_stopped_.store(true, std::memory_order_release);
   }
-  return bg_error_;
 }
 
 // This is the main function for looking at IO related error during the
@@ -383,14 +380,14 @@ const Status& ErrorHandler::HandleKnownErrors(const Status& bg_err,
 // 3) for other cases, HandleKnownErrors(const Status& bg_err,
 //    BackgroundErrorReason reason) will be called to handle other error cases
 //    such as delegating to SstFileManager to handle no space error.
-const Status& ErrorHandler::SetBGError(const Status& bg_status,
-                                       BackgroundErrorReason reason) {
+void ErrorHandler::SetBGError(const Status& bg_status,
+                              BackgroundErrorReason reason) {
   db_mutex_->AssertHeld();
   Status tmp_status = bg_status;
   IOStatus bg_io_err = status_to_io_status(std::move(tmp_status));
 
   if (bg_io_err.ok()) {
-    return kOkStatus;
+    return;
   }
   ROCKS_LOG_WARN(db_options_.info_log, "Background IO error %s",
                  bg_io_err.ToString().c_str());
@@ -413,11 +410,11 @@ const Status& ErrorHandler::SetBGError(const Status& bg_status,
     EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason,
                                           &bg_err, db_mutex_, &auto_recovery);
     recover_context_ = context;
-    return bg_error_;
-  } else if (bg_io_err.subcode() != IOStatus::SubCode::kNoSpace &&
-             (bg_io_err.GetScope() ==
-                  IOStatus::IOErrorScope::kIOErrorScopeFile ||
-              bg_io_err.GetRetryable())) {
+    return;
+  }
+  if (bg_io_err.subcode() != IOStatus::SubCode::kNoSpace &&
+      (bg_io_err.GetScope() == IOStatus::IOErrorScope::kIOErrorScopeFile ||
+       bg_io_err.GetRetryable())) {
     // Second, check if the error is a retryable IO error (file scope IO error
     // is also treated as retryable IO error in RocksDB write path). if it is
     // retryable error and its severity is higher than bg_error_, overwrite the
@@ -426,10 +423,6 @@ const Status& ErrorHandler::SetBGError(const Status& bg_status,
     // IO error as hard error. Note that, all the NoSpace error should be
     // handled by the SstFileManager::StartErrorRecovery(). Therefore, no matter
     // it is retryable or file scope, this logic will be bypassed.
-    bool auto_recovery = false;
-    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason,
-                                          &new_bg_io_err, db_mutex_,
-                                          &auto_recovery);
 
     RecordStats({ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT},
                 {} /* int_histograms */);
@@ -445,9 +438,13 @@ const Status& ErrorHandler::SetBGError(const Status& bg_status,
       ROCKS_LOG_INFO(
           db_options_.info_log,
           "ErrorHandler: Compaction will schedule by itself to resume\n");
+      bool auto_recovery = false;
+      EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason,
+                                            &new_bg_io_err, db_mutex_,
+                                            &auto_recovery);
       // Not used in this code path.
       new_bg_io_err.PermitUncheckedError();
-      return bg_error_;
+      return;
     }
 
     Status::Severity severity;
@@ -469,10 +466,14 @@ const Status& ErrorHandler::SetBGError(const Status& bg_status,
     Status bg_err(new_bg_io_err, severity);
     CheckAndSetRecoveryAndBGError(bg_err);
     recover_context_ = context;
-    return StartRecoverFromRetryableBGIOError(bg_io_err);
-  } else {
-    return HandleKnownErrors(new_bg_io_err, reason);
+    bool auto_recovery = db_options_.max_bgerror_resume_count > 0;
+    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason,
+                                          &new_bg_io_err, db_mutex_,
+                                          &auto_recovery);
+    StartRecoverFromRetryableBGIOError(bg_io_err);
+    return;
   }
+  HandleKnownErrors(new_bg_io_err, reason);
 }
 
 void ErrorHandler::AddFilesToQuarantine(
@@ -620,23 +621,23 @@ Status ErrorHandler::RecoverFromBGError(bool is_manual) {
   return s;
 }
 
-const Status& ErrorHandler::StartRecoverFromRetryableBGIOError(
+void ErrorHandler::StartRecoverFromRetryableBGIOError(
     const IOStatus& io_error) {
   db_mutex_->AssertHeld();
-  if (bg_error_.ok()) {
-    return bg_error_;
-  } else if (io_error.ok()) {
-    return kOkStatus;
-  } else if (db_options_.max_bgerror_resume_count <= 0 || recovery_in_prog_) {
-    // Auto resume BG error is not enabled, directly return bg_error_.
-    return bg_error_;
-  } else if (end_recovery_) {
+  if (bg_error_.ok() || io_error.ok()) {
+    return;
+  }
+  if (db_options_.max_bgerror_resume_count <= 0 || recovery_in_prog_) {
+    // Auto resume BG error is not enabled
+    return;
+  }
+  if (end_recovery_) {
     // Can temporarily release db mutex
     EventHelpers::NotifyOnErrorRecoveryEnd(db_options_.listeners, bg_error_,
                                            Status::ShutdownInProgress(),
                                            db_mutex_);
     db_mutex_->AssertHeld();
-    return bg_error_;
+    return;
   }
   RecordStats({ERROR_HANDLER_AUTORESUME_COUNT}, {} /* int_histograms */);
   ROCKS_LOG_INFO(
@@ -664,12 +665,6 @@ const Status& ErrorHandler::StartRecoverFromRetryableBGIOError(
 
   recovery_thread_.reset(
       new port::Thread(&ErrorHandler::RecoverFromRetryableBGIOError, this));
-
-  if (recovery_error_.ok()) {
-    return recovery_error_;
-  } else {
-    return bg_error_;
-  }
 }
 
 // Automatic recover from Retryable BG IO error. Must be called after db

package/vendor/librocksdb/vendor/rocksdb/db/error_handler.h

@@ -56,7 +56,7 @@ class ErrorHandler {
   Status::Severity GetErrorSeverity(BackgroundErrorReason reason,
                                     Status::Code code, Status::SubCode subcode);
 
-  const Status& SetBGError(const Status& bg_err, BackgroundErrorReason reason);
+  void SetBGError(const Status& bg_err, BackgroundErrorReason reason);
 
   Status GetBGError() const { return bg_error_; }
 
@@ -135,11 +135,10 @@ class ErrorHandler {
   // unsorted.
   autovector<uint64_t> files_to_quarantine_;
 
-  const Status& HandleKnownErrors(const Status& bg_err,
-                                  BackgroundErrorReason reason);
+  void HandleKnownErrors(const Status& bg_err, BackgroundErrorReason reason);
   Status OverrideNoSpaceError(const Status& bg_error, bool* auto_recovery);
   void RecoverFromNoSpace();
-  const Status& StartRecoverFromRetryableBGIOError(const IOStatus& io_error);
+  void StartRecoverFromRetryableBGIOError(const IOStatus& io_error);
   void RecoverFromRetryableBGIOError();
   // First, if it is in recovery and the recovery_error is ok. Set the
   // recovery_error_ to bg_err. Second, if the severity is higher than the

package/vendor/librocksdb/vendor/rocksdb/db/event_helpers.cc

@@ -228,15 +228,18 @@ void EventHelpers::NotifyOnErrorRecoveryEnd(
     InstrumentedMutex* db_mutex) {
   if (!listeners.empty()) {
     db_mutex->AssertHeld();
+    // Make copies before releasing mutex to avoid race.
+    Status old_bg_error_cp = old_bg_error;
+    Status new_bg_error_cp = new_bg_error;
     // release lock while notifying events
     db_mutex->Unlock();
     TEST_SYNC_POINT("NotifyOnErrorRecoveryEnd:MutexUnlocked:1");
     TEST_SYNC_POINT("NotifyOnErrorRecoveryEnd:MutexUnlocked:2");
     for (auto& listener : listeners) {
       BackgroundErrorRecoveryInfo info;
-      info.old_bg_error = old_bg_error;
-      info.new_bg_error = new_bg_error;
-      listener->OnErrorRecoveryCompleted(old_bg_error);
+      info.old_bg_error = old_bg_error_cp;
+      info.new_bg_error = new_bg_error_cp;
+      listener->OnErrorRecoveryCompleted(old_bg_error_cp);
       listener->OnErrorRecoveryEnd(info);
       info.old_bg_error.PermitUncheckedError();
       info.new_bg_error.PermitUncheckedError();

package/vendor/librocksdb/vendor/rocksdb/db/experimental.cc

@@ -711,7 +711,7 @@ class SstQueryFilterConfigsManagerImpl : public SstQueryFilterConfigsManager {
                       uint64_t /*file_size*/) override {
       // FIXME later: `key` might contain user timestamp. That should be
       // exposed properly in a future update to TablePropertiesCollector
-      KeySegmentsExtractor::Result extracted;
+      extracted.Reset();
       if (extractor) {
         extractor->Extract(key, KeySegmentsExtractor::kFullUserKey, &extracted);
         if (UNLIKELY(extracted.category >=
@@ -750,7 +750,7 @@ class SstQueryFilterConfigsManagerImpl : public SstQueryFilterConfigsManager {
         }
       }
       prev_key.assign(key.data(), key.size());
-      prev_extracted = std::move(extracted);
+      std::swap(prev_extracted, extracted);
       first_key = false;
       return Status::OK();
     }
@@ -859,6 +859,7 @@ class SstQueryFilterConfigsManagerImpl : public SstQueryFilterConfigsManager {
     std::vector<std::shared_ptr<SstQueryFilterBuilder>> builders;
     bool first_key = true;
     std::string prev_key;
+    KeySegmentsExtractor::Result extracted;
     KeySegmentsExtractor::Result prev_extracted;
     KeySegmentsExtractor::KeyCategorySet categories_seen;
   };

package/vendor/librocksdb/vendor/rocksdb/db/external_sst_file_ingestion_job.cc

@@ -44,9 +44,12 @@ Status ExternalSstFileIngestionJob::Prepare(
       return status;
     }
 
+    // Files generated in another DB or CF may have a different column family
+    // ID, so we let it pass here.
     if (file_to_ingest.cf_id !=
             TablePropertiesCollectorFactory::Context::kUnknownColumnFamily &&
-        file_to_ingest.cf_id != cfd_->GetID()) {
+        file_to_ingest.cf_id != cfd_->GetID() &&
+        !ingestion_options_.allow_db_generated_files) {
       return Status::InvalidArgument(
           "External file column family id don't match");
     }
@@ -111,6 +114,7 @@ Status ExternalSstFileIngestionJob::Prepare(
     const std::string path_inside_db = TableFileName(
         cfd_->ioptions()->cf_paths, f.fd.GetNumber(), f.fd.GetPathId());
     if (ingestion_options_.move_files) {
+      assert(!ingestion_options_.allow_db_generated_files);
       status =
           fs_->LinkFile(path_outside_db, path_inside_db, IOOptions(), nullptr);
       if (status.ok()) {
@@ -342,8 +346,7 @@ Status ExternalSstFileIngestionJob::NeedsFlush(bool* flush_needed,
   autovector<UserKeyRange> ranges;
   ranges.reserve(n);
   for (const IngestedFileInfo& file_to_ingest : files_to_ingest_) {
-    ranges.emplace_back(file_to_ingest.smallest_internal_key.user_key(),
-                        file_to_ingest.largest_internal_key.user_key());
+    ranges.emplace_back(file_to_ingest.start_ukey, file_to_ingest.limit_ukey);
   }
   Status status = cfd_->RangesOverlapWithMemtables(
       ranges, super_version, db_options_.allow_data_in_errors, flush_needed);
@@ -705,9 +708,16 @@ Status ExternalSstFileIngestionJob::SanityCheckTableProperties(
   // Get table version
   auto version_iter = uprops.find(ExternalSstFilePropertyNames::kVersion);
   if (version_iter == uprops.end()) {
-    return Status::Corruption("External file version not found");
+    if (!ingestion_options_.allow_db_generated_files) {
+      return Status::Corruption("External file version not found");
+    } else {
+      // 0 is special version for when a file from live DB does not have the
+      // version table property
+      file_to_ingest->version = 0;
+    }
+  } else {
+    file_to_ingest->version = DecodeFixed32(version_iter->second.c_str());
   }
-  file_to_ingest->version = DecodeFixed32(version_iter->second.c_str());
 
   auto seqno_iter = uprops.find(ExternalSstFilePropertyNames::kGlobalSeqno);
   if (file_to_ingest->version == 2) {
@@ -734,8 +744,15 @@ Status ExternalSstFileIngestionJob::SanityCheckTableProperties(
       return Status::InvalidArgument(
           "External SST file V1 does not support global seqno");
     }
+  } else if (file_to_ingest->version == 0) {
+    // allow_db_generated_files is true
+    assert(seqno_iter == uprops.end());
+    file_to_ingest->original_seqno = 0;
+    file_to_ingest->global_seqno_offset = 0;
   } else {
-    return Status::InvalidArgument("External file version is not supported");
+    return Status::InvalidArgument("External file version " +
+                                   std::to_string(file_to_ingest->version) +
+                                   " is not supported");
   }
 
   file_to_ingest->cf_id = static_cast<uint32_t>(props->column_family_id);
@@ -897,6 +914,25 @@ Status ExternalSstFileIngestionJob::GetIngestedFileInfo(
   } else if (!iter->status().ok()) {
     return iter->status();
   }
+  if (ingestion_options_.allow_db_generated_files) {
+    // Verify that all keys have seqno zero.
+    // TODO: store largest seqno in table property and validate it instead.
+    for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+      Status pik_status =
+          ParseInternalKey(iter->key(), &key, allow_data_in_errors);
+      if (!pik_status.ok()) {
+        return Status::Corruption("Corrupted key in external file. ",
+                                  pik_status.getState());
+      }
+      if (key.sequence != 0) {
+        return Status::NotSupported(
+            "External file has a key with non zero sequence number.");
+      }
+    }
+    if (!iter->status().ok()) {
+      return iter->status();
+    }
+  }
 
   std::unique_ptr<InternalIterator> range_del_iter(
       table_reader->NewRangeTombstoneIterator(ro));
@@ -912,6 +948,11 @@ Status ExternalSstFileIngestionJob::GetIngestedFileInfo(
         return Status::Corruption("Corrupted key in external file. ",
                                   pik_status.getState());
       }
+      if (key.sequence != 0) {
+        return Status::Corruption(
+            "External file has a range deletion with non zero sequence "
+            "number.");
+      }
       RangeTombstone tombstone(key, range_del_iter->value());
 
       InternalKey start_key = tombstone.SerializeKey();
@@ -930,6 +971,17 @@ Status ExternalSstFileIngestionJob::GetIngestedFileInfo(
     }
   }
 
+  const size_t ts_sz = ucmp->timestamp_size();
+  Slice smallest = file_to_ingest->smallest_internal_key.user_key();
+  Slice largest = file_to_ingest->largest_internal_key.user_key();
+  if (ts_sz > 0) {
+    AppendUserKeyWithMaxTimestamp(&file_to_ingest->start_ukey, smallest, ts_sz);
+    AppendUserKeyWithMinTimestamp(&file_to_ingest->limit_ukey, largest, ts_sz);
+  } else {
+    file_to_ingest->start_ukey.assign(smallest.data(), smallest.size());
+    file_to_ingest->limit_ukey.assign(largest.data(), largest.size());
+  }
+
   auto s =
       GetSstInternalUniqueId(file_to_ingest->table_properties.db_id,
                              file_to_ingest->table_properties.db_session_id,
@@ -953,13 +1005,15 @@ Status ExternalSstFileIngestionJob::AssignLevelAndSeqnoForIngestedFile(
   *assigned_seqno = 0;
   auto ucmp = cfd_->user_comparator();
   const size_t ts_sz = ucmp->timestamp_size();
-  if (force_global_seqno || files_overlap_) {
+  if (force_global_seqno || files_overlap_ ||
+      compaction_style == kCompactionStyleFIFO) {
     *assigned_seqno = last_seqno + 1;
     // If files overlap, we have to ingest them at level 0.
-    if (files_overlap_) {
+    if (files_overlap_ || compaction_style == kCompactionStyleFIFO) {
       assert(ts_sz == 0);
       file_to_ingest->picked_level = 0;
-      if (ingestion_options_.fail_if_not_bottommost_level) {
+      if (ingestion_options_.fail_if_not_bottommost_level &&
+          cfd_->NumberLevels() > 1) {
         status = Status::TryAgain(
             "Files cannot be ingested to Lmax. Please make sure key range of "
             "Lmax does not overlap with files to ingest.");
@@ -980,9 +1034,8 @@ Status ExternalSstFileIngestionJob::AssignLevelAndSeqnoForIngestedFile(
     if (lvl > 0 && lvl < vstorage->base_level()) {
       continue;
     }
-    if (cfd_->RangeOverlapWithCompaction(
-            file_to_ingest->smallest_internal_key.user_key(),
-            file_to_ingest->largest_internal_key.user_key(), lvl)) {
+    if (cfd_->RangeOverlapWithCompaction(file_to_ingest->start_ukey,
+                                         file_to_ingest->limit_ukey, lvl)) {
       // We must use L0 or any level higher than `lvl` to be able to overwrite
       // the compaction output keys that we overlap with in this level, We also
       // need to assign this file a seqno to overwrite the compaction output
@@ -992,9 +1045,8 @@ Status ExternalSstFileIngestionJob::AssignLevelAndSeqnoForIngestedFile(
     } else if (vstorage->NumLevelFiles(lvl) > 0) {
       bool overlap_with_level = false;
       status = sv->current->OverlapWithLevelIterator(
-          ro, env_options_, file_to_ingest->smallest_internal_key.user_key(),
-          file_to_ingest->largest_internal_key.user_key(), lvl,
-          &overlap_with_level);
+          ro, env_options_, file_to_ingest->start_ukey,
+          file_to_ingest->limit_ukey, lvl, &overlap_with_level);
       if (!status.ok()) {
         return status;
       }
@@ -1035,11 +1087,18 @@ Status ExternalSstFileIngestionJob::AssignLevelAndSeqnoForIngestedFile(
           "Column family enables user-defined timestamps, please make sure the "
           "key range (without timestamp) of external file does not overlap "
           "with key range (without timestamp) in the db");
+      return status;
     }
     if (*assigned_seqno == 0) {
       *assigned_seqno = last_seqno + 1;
     }
   }
+
+  if (ingestion_options_.allow_db_generated_files && *assigned_seqno != 0) {
+    return Status::InvalidArgument(
+        "An ingested file is assigned to a non-zero sequence number, which is "
+        "incompatible with ingestion option allow_db_generated_files.");
+  }
   return status;
 }
 
@@ -1163,9 +1222,8 @@ bool ExternalSstFileIngestionJob::IngestedFileFitInLevel(
   }
 
   auto* vstorage = cfd_->current()->storage_info();
-  Slice file_smallest_user_key(
-      file_to_ingest->smallest_internal_key.user_key());
-  Slice file_largest_user_key(file_to_ingest->largest_internal_key.user_key());
+  Slice file_smallest_user_key(file_to_ingest->start_ukey);
+  Slice file_largest_user_key(file_to_ingest->limit_ukey);
 
   if (vstorage->OverlapInLevel(level, &file_smallest_user_key,
                                &file_largest_user_key)) {

package/vendor/librocksdb/vendor/rocksdb/db/external_sst_file_ingestion_job.h

@@ -32,6 +32,17 @@ struct IngestedFileInfo {
   InternalKey smallest_internal_key;
   // Largest internal key in external file
   InternalKey largest_internal_key;
+  // NOTE: use below two fields for all `*Overlap*` types of checks instead of
+  // smallest_internal_key.user_key() and largest_internal_key.user_key().
+  // The smallest / largest user key contained in the file for key range checks.
+  // These could be different from smallest_internal_key.user_key(), and
+  // largest_internal_key.user_key() when user-defined timestamps are enabled,
+  // because the check is about making sure the user key without timestamps part
+  // does not overlap. To achieve that, the smallest user key will be updated
+  // with the maximum timestamp while the largest user key will be updated with
+  // the min timestamp. It's otherwise the same.
+  std::string start_ukey;
+  std::string limit_ukey;
   // Sequence number for keys in external file
   SequenceNumber original_seqno;
   // Offset of the global sequence number field in the file, will

package/vendor/librocksdb/vendor/rocksdb/db/flush_job.cc

@@ -115,6 +115,9 @@ FlushJob::FlushJob(
       db_mutex_(db_mutex),
       shutting_down_(shutting_down),
       existing_snapshots_(std::move(existing_snapshots)),
+      earliest_snapshot_(existing_snapshots_.empty()
+                             ? kMaxSequenceNumber
+                             : existing_snapshots_.at(0)),
       earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
       snapshot_checker_(snapshot_checker),
       job_context_(job_context),
@@ -194,6 +197,7 @@ void FlushJob::PickMemTable() {
   // Track effective cutoff user-defined timestamp during flush if
   // user-defined timestamps can be stripped.
   GetEffectiveCutoffUDTForPickedMemTables();
+  GetPrecludeLastLevelMinSeqno();
 
   ReportFlushInputSize(mems_);
 
@@ -231,7 +235,7 @@ Status FlushJob::Run(LogsWithPrepTracker* prep_tracker, FileMetaData* file_meta,
 
   AutoThreadOperationStageUpdater stage_run(ThreadStatus::STAGE_FLUSH_RUN);
   if (mems_.empty()) {
-    ROCKS_LOG_BUFFER(log_buffer_, "[%s] Nothing in memtable to flush",
+    ROCKS_LOG_BUFFER(log_buffer_, "[%s] No memtable to flush",
                      cfd_->GetName().c_str());
     return Status::OK();
   }
@@ -502,7 +506,7 @@ Status FlushJob::MemPurge() {
     const std::atomic<bool> kManualCompactionCanceledFalse{false};
     CompactionIterator c_iter(
         iter.get(), (cfd_->internal_comparator()).user_comparator(), &merge,
-        kMaxSequenceNumber, &existing_snapshots_,
+        kMaxSequenceNumber, &existing_snapshots_, earliest_snapshot_,
         earliest_write_conflict_snapshot_, job_snapshot_seq, snapshot_checker_,
         env, ShouldReportDetailedTime(env, ioptions->stats),
         true /* internal key corruption is not ok */, range_del_agg.get(),
@@ -968,14 +972,17 @@ Status FlushJob::WriteLevel0Table() {
           cfd_->GetID(), cfd_->GetName(), 0 /* level */,
           false /* is_bottommost */, TableFileCreationReason::kFlush,
           oldest_key_time, current_time, db_id_, db_session_id_,
-          0 /* target_file_size */, meta_.fd.GetNumber());
+          0 /* target_file_size */, meta_.fd.GetNumber(),
+          preclude_last_level_min_seqno_ == kMaxSequenceNumber
+              ? preclude_last_level_min_seqno_
+              : std::min(earliest_snapshot_, preclude_last_level_min_seqno_));
       const SequenceNumber job_snapshot_seq =
           job_context_->GetJobSnapshotSequence();
 
       s = BuildTable(
           dbname_, versions_, db_options_, tboptions, file_options_,
           cfd_->table_cache(), iter.get(), std::move(range_del_iters), &meta_,
-          &blob_file_additions, existing_snapshots_,
+          &blob_file_additions, existing_snapshots_, earliest_snapshot_,
           earliest_write_conflict_snapshot_, job_snapshot_seq,
           snapshot_checker_, mutable_cf_options_.paranoid_file_checks,
           cfd_->internal_stats(), &io_s, io_tracer_,
@@ -1010,10 +1017,15 @@ Status FlushJob::WriteLevel0Table() {
     ROCKS_LOG_BUFFER(log_buffer_,
                      "[%s] [JOB %d] Level-0 flush table #%" PRIu64 ": %" PRIu64
                      " bytes %s"
-                     "%s",
+                     " %s"
+                     " %s",
                      cfd_->GetName().c_str(), job_context_->job_id,
                      meta_.fd.GetNumber(), meta_.fd.GetFileSize(),
                      s.ToString().c_str(),
+                     s.ok() && meta_.fd.GetFileSize() == 0
+                         ? "It's an empty SST file from a successful flush so "
+                           "won't be kept in the DB"
+                         : "",
                      meta_.marked_for_compaction ? " (needs compaction)" : "");
 
     if (s.ok() && output_file_directory_ != nullptr && sync_output_directory_) {
@@ -1154,6 +1166,26 @@ void FlushJob::GetEffectiveCutoffUDTForPickedMemTables() {
   }
 }
 
+void FlushJob::GetPrecludeLastLevelMinSeqno() {
+  if (cfd_->ioptions()->preclude_last_level_data_seconds == 0) {
+    return;
+  }
+  int64_t current_time = 0;
+  Status s = db_options_.clock->GetCurrentTime(&current_time);
+  if (!s.ok()) {
+    ROCKS_LOG_WARN(db_options_.info_log,
+                   "Failed to get current time in Flush: Status: %s",
+                   s.ToString().c_str());
+  } else {
+    SequenceNumber preserve_time_min_seqno;
+    seqno_to_time_mapping_->GetCurrentTieringCutoffSeqnos(
+        static_cast<uint64_t>(current_time),
+        cfd_->ioptions()->preserve_internal_time_seconds,
+        cfd_->ioptions()->preclude_last_level_data_seconds,
+        &preserve_time_min_seqno, &preclude_last_level_min_seqno_);
+  }
+}
+
 Status FlushJob::MaybeIncreaseFullHistoryTsLowToAboveCutoffUDT() {
   db_mutex_->AssertHeld();
   const auto* ucmp = cfd_->user_comparator();

package/vendor/librocksdb/vendor/rocksdb/db/flush_job.h

@@ -143,6 +143,13 @@ class FlushJob {
   // `MaybeIncreaseFullHistoryTsLowToAboveCutoffUDT` for details.
   void GetEffectiveCutoffUDTForPickedMemTables();
 
+  // If this column family enables tiering feature, it will find the current
+  // `preclude_last_level_min_seqno_`, and the smaller one between this and
+  // the `earliset_snapshot_` will later be announced to user property
+  // collectors. It indicates to tiering use cases which data are old enough to
+  // be placed on the last level.
+  void GetPrecludeLastLevelMinSeqno();
+
   Status MaybeIncreaseFullHistoryTsLowToAboveCutoffUDT();
 
   const std::string& dbname_;
@@ -161,6 +168,7 @@ class FlushJob {
   InstrumentedMutex* db_mutex_;
   std::atomic<bool>* shutting_down_;
   std::vector<SequenceNumber> existing_snapshots_;
+  SequenceNumber earliest_snapshot_;
   SequenceNumber earliest_write_conflict_snapshot_;
   SnapshotChecker* snapshot_checker_;
   JobContext* job_context_;
@@ -221,6 +229,12 @@ class FlushJob {
   // Keeps track of the newest user-defined timestamp for this flush job if
   // `persist_user_defined_timestamps` flag is false.
   std::string cutoff_udt_;
+
+  // The current minimum seqno that compaction jobs will preclude the data from
+  // the last level. Data with seqnos larger than this or larger than
+  // `earliest_snapshot_` will be output to the penultimate level had it gone
+  // through a compaction to the last level.
+  SequenceNumber preclude_last_level_min_seqno_ = kMaxSequenceNumber;
 };
 
 }  // namespace ROCKSDB_NAMESPACE