@nxtedition/rocksdb 9.0.0 → 9.0.1

package/deps/rocksdb/rocksdb/db/db_impl/db_impl_compaction_flush.cc

@@ -23,6 +23,7 @@
 #include "util/cast_util.h"
 #include "util/coding.h"
 #include "util/concurrent_task_limiter_impl.h"
+#include "util/udt_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -112,7 +113,8 @@ bool DBImpl::ShouldRescheduleFlushRequestToRetainUDT(
 }
 
 IOStatus DBImpl::SyncClosedLogs(JobContext* job_context,
-                                VersionEdit* synced_wals) {
+                                VersionEdit* synced_wals,
+                                bool error_recovery_in_prog) {
   TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Start");
   InstrumentedMutexLock l(&log_write_mutex_);
   autovector<log::Writer*, 1> logs_to_sync;
@@ -138,7 +140,7 @@ IOStatus DBImpl::SyncClosedLogs(JobContext* job_context,
       ROCKS_LOG_INFO(immutable_db_options_.info_log,
                      "[JOB %d] Syncing log #%" PRIu64, job_context->job_id,
                      log->get_log_number());
-      if (error_handler_.IsRecoveryInProgress()) {
+      if (error_recovery_in_prog) {
         log->file()->reset_seen_error();
       }
       io_s = log->file()->Sync(immutable_db_options_.use_fsync);
@@ -147,7 +149,7 @@ IOStatus DBImpl::SyncClosedLogs(JobContext* job_context,
       }
 
       if (immutable_db_options_.recycle_log_file_num > 0) {
-        if (error_handler_.IsRecoveryInProgress()) {
+        if (error_recovery_in_prog) {
           log->file()->reset_seen_error();
         }
         io_s = log->Close();
@@ -221,9 +223,10 @@ Status DBImpl::FlushMemTableToOutputFile(
   // `snapshot_seqs` has already been computed before this function starts.
   // Recording the max memtable ID ensures that the flush job does not flush
   // a memtable without knowing such snapshot(s).
-  uint64_t max_memtable_id = needs_to_sync_closed_wals
-                                 ? cfd->imm()->GetLatestMemTableID()
-                                 : std::numeric_limits<uint64_t>::max();
+  uint64_t max_memtable_id =
+      needs_to_sync_closed_wals
+          ? cfd->imm()->GetLatestMemTableID(false /* for_atomic_flush */)
+          : std::numeric_limits<uint64_t>::max();
 
   // If needs_to_sync_closed_wals is false, then the flush job will pick ALL
   // existing memtables of the column family when PickMemTable() is called
@@ -232,7 +235,7 @@ Status DBImpl::FlushMemTableToOutputFile(
   // releases and re-acquires the db mutex. In the meantime, the application
   // can still insert into the memtables and increase the db's sequence number.
   // The application can take a snapshot, hoping that the latest visible state
-  // to this snapshto is preserved. This is hard to guarantee since db mutex
+  // to this snapshot is preserved. This is hard to guarantee since db mutex
   // not held. This newly-created snapshot is not included in `snapshot_seqs`
   // and the flush job is unaware of its presence. Consequently, the flush job
   // may drop certain keys when generating the L0, causing incorrect data to be
@@ -249,7 +252,7 @@ Status DBImpl::FlushMemTableToOutputFile(
       GetCompressionFlush(*cfd->ioptions(), mutable_cf_options), stats_,
       &event_logger_, mutable_cf_options.report_bg_io_stats,
       true /* sync_output_directory */, true /* write_manifest */, thread_pri,
-      io_tracer_, seqno_time_mapping_, db_id_, db_session_id_,
+      io_tracer_, seqno_to_time_mapping_, db_id_, db_session_id_,
       cfd->GetFullHistoryTsLow(), &blob_callback_);
   FileMetaData file_meta;
 
@@ -260,8 +263,10 @@ Status DBImpl::FlushMemTableToOutputFile(
     // SyncClosedLogs() may unlock and re-lock the log_write_mutex multiple
     // times.
     VersionEdit synced_wals;
+    bool error_recovery_in_prog = error_handler_.IsRecoveryInProgress();
     mutex_.Unlock();
-    log_io_s = SyncClosedLogs(job_context, &synced_wals);
+    log_io_s =
+        SyncClosedLogs(job_context, &synced_wals, error_recovery_in_prog);
     mutex_.Lock();
     if (log_io_s.ok() && synced_wals.IsWalAddition()) {
       const ReadOptions read_options(Env::IOActivity::kFlush);
@@ -521,7 +526,7 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
         GetCompressionFlush(*cfd->ioptions(), mutable_cf_options), stats_,
         &event_logger_, mutable_cf_options.report_bg_io_stats,
         false /* sync_output_directory */, false /* write_manifest */,
-        thread_pri, io_tracer_, seqno_time_mapping_, db_id_, db_session_id_,
+        thread_pri, io_tracer_, seqno_to_time_mapping_, db_id_, db_session_id_,
         cfd->GetFullHistoryTsLow(), &blob_callback_));
   }
 
@@ -545,8 +550,10 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     // TODO (yanqin) investigate whether we should sync the closed logs for
     // single column family case.
     VersionEdit synced_wals;
+    bool error_recovery_in_prog = error_handler_.IsRecoveryInProgress();
     mutex_.Unlock();
-    log_io_s = SyncClosedLogs(job_context, &synced_wals);
+    log_io_s =
+        SyncClosedLogs(job_context, &synced_wals, error_recovery_in_prog);
     mutex_.Lock();
     if (log_io_s.ok() && synced_wals.IsWalAddition()) {
       const ReadOptions read_options(Env::IOActivity::kFlush);
@@ -1005,26 +1012,14 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
                                 end_without_ts, "" /*trim_ts*/);
   }
 
-  std::string begin_str;
-  std::string end_str;
-
-  // CompactRange compact all keys: [begin, end] inclusively. Add maximum
-  // timestamp to include all `begin` keys, and add minimal timestamp to include
-  // all `end` keys.
-  if (begin_without_ts != nullptr) {
-    AppendKeyWithMaxTimestamp(&begin_str, *begin_without_ts, ts_sz);
-  }
-  if (end_without_ts != nullptr) {
-    AppendKeyWithMinTimestamp(&end_str, *end_without_ts, ts_sz);
-  }
-  Slice begin(begin_str);
-  Slice end(end_str);
+  std::string begin_str, end_str;
+  auto [begin, end] =
+      MaybeAddTimestampsToRange(begin_without_ts, end_without_ts, ts_sz,
+                                &begin_str, &end_str, false /*exclusive_end*/);
 
-  Slice* begin_with_ts = begin_without_ts ? &begin : nullptr;
-  Slice* end_with_ts = end_without_ts ? &end : nullptr;
-
-  return CompactRangeInternal(options, column_family, begin_with_ts,
-                              end_with_ts, "" /*trim_ts*/);
+  return CompactRangeInternal(
+      options, column_family, begin.has_value() ? &begin.value() : nullptr,
+      end.has_value() ? &end.value() : nullptr, "" /*trim_ts*/);
 }
 
 Status DBImpl::IncreaseFullHistoryTsLow(ColumnFamilyHandle* column_family,
@@ -1531,7 +1526,8 @@ Status DBImpl::CompactFilesImpl(
   // without releasing the lock, so we're guaranteed a compaction can be formed.
   assert(c != nullptr);
 
-  c->SetInputVersion(version);
+  c->FinalizeInputInfo(version);
+
   // deletion compaction currently not allowed in CompactFiles.
   assert(!c->deletion_compaction());
 
@@ -1581,7 +1577,12 @@ Status DBImpl::CompactFilesImpl(
   TEST_SYNC_POINT("CompactFilesImpl:3");
   mutex_.Lock();
 
-  Status status = compaction_job.Install(*c->mutable_cf_options());
+  bool compaction_released = false;
+  Status status =
+      compaction_job.Install(*c->mutable_cf_options(), &compaction_released);
+  if (!compaction_released) {
+    c->ReleaseCompactionFiles(s);
+  }
   if (status.ok()) {
     assert(compaction_job.io_status().ok());
     InstallSuperVersionAndScheduleWork(c->column_family_data(),
@@ -1592,7 +1593,6 @@ Status DBImpl::CompactFilesImpl(
   // not check compaction_job.io_status() explicitly if we're not calling
   // SetBGError
   compaction_job.io_status().PermitUncheckedError();
-  c->ReleaseCompactionFiles(s);
   // Need to make sure SstFileManager does its bookkeeping
   auto sfm = static_cast<SstFileManagerImpl*>(
       immutable_db_options_.sst_file_manager.get());
@@ -2236,7 +2236,8 @@ void DBImpl::GenerateFlushRequest(const autovector<ColumnFamilyData*>& cfds,
       // cfd may be null, see DBImpl::ScheduleFlushes
       continue;
     }
-    uint64_t max_memtable_id = cfd->imm()->GetLatestMemTableID();
+    uint64_t max_memtable_id = cfd->imm()->GetLatestMemTableID(
+        immutable_db_options_.atomic_flush /* for_atomic_flush */);
     req->cfd_to_max_mem_id_to_persist.emplace(cfd, max_memtable_id);
   }
 }
@@ -2280,19 +2281,7 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
     }
     WaitForPendingWrites();
 
-    if (flush_reason != FlushReason::kErrorRecoveryRetryFlush &&
-        flush_reason != FlushReason::kCatchUpAfterErrorRecovery &&
-        (!cfd->mem()->IsEmpty() || !cached_recoverable_state_empty_.load())) {
-      // Note that, when flush reason is kErrorRecoveryRetryFlush, during the
-      // auto retry resume, we want to avoid creating new small memtables.
-      // If flush reason is kCatchUpAfterErrorRecovery, we try to flush any new
-      // memtable that filled up during recovery, and we also want to avoid
-      // switching memtable to create small memtables.
-      // Therefore, SwitchMemtable will not be called. Also, since ResumeImpl
-      // will iterate through all the CFs and call FlushMemtable during auto
-      // retry resume, it is possible that in some CFs,
-      // cfd->imm()->NumNotFlushed() = 0. In this case, so no flush request will
-      // be created and scheduled, status::OK() will be returned.
+    if (!cfd->mem()->IsEmpty() || !cached_recoverable_state_empty_.load()) {
       s = SwitchMemtable(cfd, &context);
     }
     const uint64_t flush_memtable_id = std::numeric_limits<uint64_t>::max();
@@ -2301,10 +2290,10 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
           !cached_recoverable_state_empty_.load()) {
         FlushRequest req{flush_reason, {{cfd, flush_memtable_id}}};
         flush_reqs.emplace_back(std::move(req));
-        memtable_ids_to_wait.emplace_back(cfd->imm()->GetLatestMemTableID());
+        memtable_ids_to_wait.emplace_back(
+            cfd->imm()->GetLatestMemTableID(false /* for_atomic_flush */));
       }
-      if (immutable_db_options_.persist_stats_to_disk &&
-          flush_reason != FlushReason::kErrorRecoveryRetryFlush) {
+      if (immutable_db_options_.persist_stats_to_disk) {
         ColumnFamilyData* cfd_stats =
             versions_->GetColumnFamilySet()->GetColumnFamily(
                 kPersistentStatsColumnFamilyName);
@@ -2330,7 +2319,8 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
             FlushRequest req{flush_reason, {{cfd_stats, flush_memtable_id}}};
             flush_reqs.emplace_back(std::move(req));
             memtable_ids_to_wait.emplace_back(
-                cfd_stats->imm()->GetLatestMemTableID());
+                cfd_stats->imm()->GetLatestMemTableID(
+                    false /* for_atomic_flush */));
           }
         }
       }
@@ -2381,8 +2371,7 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
     }
     s = WaitForFlushMemTables(
         cfds, flush_memtable_ids,
-        (flush_reason == FlushReason::kErrorRecovery ||
-         flush_reason == FlushReason::kErrorRecoveryRetryFlush));
+        flush_reason == FlushReason::kErrorRecovery /* resuming_from_bg_err */);
     InstrumentedMutexLock lock_guard(&mutex_);
     for (auto* tmp_cfd : cfds) {
       tmp_cfd->UnrefAndTryDelete();
@@ -2477,9 +2466,7 @@ Status DBImpl::AtomicFlushMemTables(
     }
 
     for (auto cfd : cfds) {
-      if ((cfd->mem()->IsEmpty() && cached_recoverable_state_empty_.load()) ||
-          flush_reason == FlushReason::kErrorRecoveryRetryFlush ||
-          flush_reason == FlushReason::kCatchUpAfterErrorRecovery) {
+      if (cfd->mem()->IsEmpty() && cached_recoverable_state_empty_.load()) {
         continue;
       }
       cfd->Ref();
@@ -2524,8 +2511,7 @@ Status DBImpl::AtomicFlushMemTables(
     }
     s = WaitForFlushMemTables(
         cfds, flush_memtable_ids,
-        (flush_reason == FlushReason::kErrorRecovery ||
-         flush_reason == FlushReason::kErrorRecoveryRetryFlush));
+        flush_reason == FlushReason::kErrorRecovery /* resuming_from_bg_err */);
     InstrumentedMutexLock lock_guard(&mutex_);
     for (auto* cfd : cfds) {
       cfd->UnrefAndTryDelete();
@@ -2534,6 +2520,68 @@ Status DBImpl::AtomicFlushMemTables(
   return s;
 }
 
+Status DBImpl::RetryFlushesForErrorRecovery(FlushReason flush_reason,
+                                            bool wait) {
+  mutex_.AssertHeld();
+  assert(flush_reason == FlushReason::kErrorRecoveryRetryFlush ||
+         flush_reason == FlushReason::kCatchUpAfterErrorRecovery);
+
+  // Collect referenced CFDs.
+  autovector<ColumnFamilyData*> cfds;
+  for (ColumnFamilyData* cfd : *versions_->GetColumnFamilySet()) {
+    if (!cfd->IsDropped() && cfd->initialized() &&
+        cfd->imm()->NumNotFlushed() != 0) {
+      cfd->Ref();
+      cfd->imm()->FlushRequested();
+      cfds.push_back(cfd);
+    }
+  }
+
+  // Submit flush requests for all immutable memtables needing flush.
+  // `flush_memtable_ids` will be populated such that all immutable
+  // memtables eligible for flush are waited on before this function
+  // returns.
+  autovector<uint64_t> flush_memtable_ids;
+  if (immutable_db_options_.atomic_flush) {
+    FlushRequest flush_req;
+    GenerateFlushRequest(cfds, flush_reason, &flush_req);
+    SchedulePendingFlush(flush_req);
+    for (auto& iter : flush_req.cfd_to_max_mem_id_to_persist) {
+      flush_memtable_ids.push_back(iter.second);
+    }
+  } else {
+    for (auto cfd : cfds) {
+      flush_memtable_ids.push_back(
+          cfd->imm()->GetLatestMemTableID(false /* for_atomic_flush */));
+      // Impose no bound on the highest memtable ID flushed. There is no
+      // reason to do so outside of atomic flush.
+      FlushRequest flush_req{
+          flush_reason,
+          {{cfd,
+            std::numeric_limits<uint64_t>::max() /* max_mem_id_to_persist */}}};
+      SchedulePendingFlush(flush_req);
+    }
+  }
+  MaybeScheduleFlushOrCompaction();
+
+  Status s;
+  if (wait) {
+    mutex_.Unlock();
+    autovector<const uint64_t*> flush_memtable_id_ptrs;
+    for (auto& flush_memtable_id : flush_memtable_ids) {
+      flush_memtable_id_ptrs.push_back(&flush_memtable_id);
+    }
+    s = WaitForFlushMemTables(cfds, flush_memtable_id_ptrs,
+                              true /* resuming_from_bg_err */);
+    mutex_.Lock();
+  }
+
+  for (auto* cfd : cfds) {
+    cfd->UnrefAndTryDelete();
+  }
+  return s;
+}
+
 // Calling FlushMemTable(), whether from DB::Flush() or from Backup Engine, can
 // cause write stall, for example if one memtable is being flushed already.
 // This method tries to avoid write stall (similar to CompactRange() behavior)
@@ -3485,8 +3533,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
 
   std::unique_ptr<TaskLimiterToken> task_token;
 
-  // InternalKey manual_end_storage;
-  // InternalKey* manual_end = &manual_end_storage;
   bool sfm_reserved_compact_space = false;
   if (is_manual) {
     ManualCompactionState* m = manual_compaction;
@@ -3622,6 +3668,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
   }
 
   IOStatus io_s;
+  bool compaction_released = false;
   if (!c) {
     // Nothing to do
     ROCKS_LOG_BUFFER(log_buffer, "Compaction nothing to do");
@@ -3644,7 +3691,12 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     }
     status = versions_->LogAndApply(
         c->column_family_data(), *c->mutable_cf_options(), read_options,
-        c->edit(), &mutex_, directories_.GetDbDir());
+        c->edit(), &mutex_, directories_.GetDbDir(),
+        /*new_descriptor_log=*/false, /*column_family_options=*/nullptr,
+        [&c, &compaction_released](const Status& s) {
+          c->ReleaseCompactionFiles(s);
+          compaction_released = true;
+        });
     io_s = versions_->io_status();
     InstallSuperVersionAndScheduleWork(c->column_family_data(),
                                        &job_context->superversion_contexts[0],
@@ -3652,6 +3704,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     ROCKS_LOG_BUFFER(log_buffer, "[%s] Deleted %d files\n",
                      c->column_family_data()->GetName().c_str(),
                      c->num_input_files(0));
+    if (status.ok() && io_s.ok()) {
+      UpdateDeletionCompactionStats(c);
+    }
     *made_progress = true;
     TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:AfterCompaction",
                              c->column_family_data());
@@ -3710,7 +3765,12 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     }
     status = versions_->LogAndApply(
         c->column_family_data(), *c->mutable_cf_options(), read_options,
-        c->edit(), &mutex_, directories_.GetDbDir());
+        c->edit(), &mutex_, directories_.GetDbDir(),
+        /*new_descriptor_log=*/false, /*column_family_options=*/nullptr,
+        [&c, &compaction_released](const Status& s) {
+          c->ReleaseCompactionFiles(s);
+          compaction_released = true;
+        });
     io_s = versions_->io_status();
     // Use latest MutableCFOptions
     InstallSuperVersionAndScheduleWork(c->column_family_data(),
@@ -3760,6 +3820,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     // Transfer requested token, so it doesn't need to do it again.
     ca->prepicked_compaction->task_token = std::move(task_token);
     ++bg_bottom_compaction_scheduled_;
+    assert(c == nullptr);
     env_->Schedule(&DBImpl::BGWorkBottomCompaction, ca, Env::Priority::BOTTOM,
                    this, &DBImpl::UnscheduleCompactionCallback);
   } else {
@@ -3803,8 +3864,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     compaction_job.Run().PermitUncheckedError();
     TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
     mutex_.Lock();
-
-    status = compaction_job.Install(*c->mutable_cf_options());
+    status =
+        compaction_job.Install(*c->mutable_cf_options(), &compaction_released);
     io_s = compaction_job.io_status();
     if (status.ok()) {
       InstallSuperVersionAndScheduleWork(c->column_family_data(),
@@ -3823,7 +3884,23 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
   }
 
   if (c != nullptr) {
-    c->ReleaseCompactionFiles(status);
+    if (!compaction_released) {
+      c->ReleaseCompactionFiles(status);
+    } else {
+#ifndef NDEBUG
+      // Sanity checking that compaction files are freed.
+      for (size_t i = 0; i < c->num_input_levels(); i++) {
+        for (size_t j = 0; j < c->inputs(i)->size(); j++) {
+          assert(!c->input(i, j)->being_compacted);
+        }
+      }
+      std::unordered_set<Compaction*>* cip = c->column_family_data()
+                                                 ->compaction_picker()
+                                                 ->compactions_in_progress();
+      assert(cip->find(c.get()) == cip->end());
+#endif
+    }
+
     *made_progress = true;
 
     // Need to make sure SstFileManager does its bookkeeping
@@ -4008,6 +4085,27 @@ bool DBImpl::MCOverlap(ManualCompactionState* m, ManualCompactionState* m1) {
   return false;
 }
 
+void DBImpl::UpdateDeletionCompactionStats(
+    const std::unique_ptr<Compaction>& c) {
+  if (c == nullptr) {
+    return;
+  }
+
+  CompactionReason reason = c->compaction_reason();
+
+  switch (reason) {
+    case CompactionReason::kFIFOMaxSize:
+      RecordTick(stats_, FIFO_MAX_SIZE_COMPACTIONS);
+      break;
+    case CompactionReason::kFIFOTtl:
+      RecordTick(stats_, FIFO_TTL_COMPACTIONS);
+      break;
+    default:
+      assert(false);
+      break;
+  }
+}
+
 void DBImpl::BuildCompactionJobInfo(
     const ColumnFamilyData* cfd, Compaction* c, const Status& st,
     const CompactionJobStats& compaction_job_stats, const int job_id,
@@ -4021,7 +4119,12 @@ void DBImpl::BuildCompactionJobInfo(
   compaction_job_info->base_input_level = c->start_level();
   compaction_job_info->output_level = c->output_level();
   compaction_job_info->stats = compaction_job_stats;
-  compaction_job_info->table_properties = c->GetTableProperties();
+  const auto& input_table_properties = c->GetInputTableProperties();
+  const auto& output_table_properties = c->GetOutputTableProperties();
+  compaction_job_info->table_properties.insert(input_table_properties.begin(),
+                                               input_table_properties.end());
+  compaction_job_info->table_properties.insert(output_table_properties.begin(),
+                                               output_table_properties.end());
   compaction_job_info->compaction_reason = c->compaction_reason();
   compaction_job_info->compression = c->output_compression();
 

package/deps/rocksdb/rocksdb/db/db_impl/db_impl_debug.cc

@@ -306,11 +306,12 @@ const PeriodicTaskScheduler& DBImpl::TEST_GetPeriodicTaskScheduler() const {
 
 SeqnoToTimeMapping DBImpl::TEST_GetSeqnoToTimeMapping() const {
   InstrumentedMutexLock l(&mutex_);
-  return seqno_time_mapping_;
+  return seqno_to_time_mapping_;
 }
 
 
 size_t DBImpl::TEST_EstimateInMemoryStatsHistorySize() const {
+  InstrumentedMutexLock l(&const_cast<DBImpl*>(this)->stats_history_mutex_);
   return EstimateInMemoryStatsHistorySize();
 }
 }  // namespace ROCKSDB_NAMESPACE

package/deps/rocksdb/rocksdb/db/db_impl/db_impl_files.cc

@@ -100,6 +100,14 @@ Status DBImpl::EnableFileDeletions(bool force) {
   return Status::OK();
 }
 
+int DBImpl::EnableFileDeletionsWithLock() {
+  mutex_.AssertHeld();
+  // In case others have called EnableFileDeletions(true /* force */) in between
+  disable_delete_obsolete_files_ =
+      std::max(0, disable_delete_obsolete_files_ - 1);
+  return disable_delete_obsolete_files_;
+}
+
 bool DBImpl::IsFileDeletionsEnabled() const {
   return 0 == disable_delete_obsolete_files_;
 }
@@ -457,12 +465,12 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
   std::sort(candidate_files.begin(), candidate_files.end(),
             [](const JobContext::CandidateFileInfo& lhs,
                const JobContext::CandidateFileInfo& rhs) {
-              if (lhs.file_name > rhs.file_name) {
+              if (lhs.file_name < rhs.file_name) {
                 return true;
-              } else if (lhs.file_name < rhs.file_name) {
+              } else if (lhs.file_name > rhs.file_name) {
                 return false;
               } else {
-                return (lhs.file_path > rhs.file_path);
+                return (lhs.file_path < rhs.file_path);
               }
             });
   candidate_files.erase(
@@ -995,7 +1003,7 @@ Status DBImpl::DeleteUnreferencedSstFiles(RecoveryContext* recovery_ctx) {
       if (type == kTableFile && number >= next_file_number &&
           recovery_ctx->files_to_delete_.find(normalized_fpath) ==
               recovery_ctx->files_to_delete_.end()) {
-        recovery_ctx->files_to_delete_.emplace(normalized_fpath);
+        recovery_ctx->files_to_delete_.emplace(normalized_fpath, path);
       }
     }
   }

package/deps/rocksdb/rocksdb/db/db_impl/db_impl_open.cc

@@ -25,6 +25,7 @@
 #include "rocksdb/wal_filter.h"
 #include "test_util/sync_point.h"
 #include "util/rate_limiter_impl.h"
+#include "util/string_util.h"
 #include "util/udt_util.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -291,6 +292,18 @@ Status DBImpl::ValidateOptions(const DBOptions& db_options) {
         "writes in direct IO require writable_file_max_buffer_size > 0");
   }
 
+  if (db_options.daily_offpeak_time_utc != "") {
+    int start_time, end_time;
+    if (!TryParseTimeRangeString(db_options.daily_offpeak_time_utc, start_time,
+                                 end_time)) {
+      return Status::InvalidArgument(
+          "daily_offpeak_time_utc should be set in the format HH:mm-HH:mm "
+          "(e.g. 04:30-07:30)");
+    } else if (start_time == end_time) {
+      return Status::InvalidArgument(
+          "start_time and end_time cannot be the same");
+    }
+  }
   return Status::OK();
 }
 
@@ -405,7 +418,8 @@ Status DBImpl::Recover(
     uint64_t* recovered_seq, RecoveryContext* recovery_ctx) {
   mutex_.AssertHeld();
 
-  bool is_new_db = false;
+  bool tmp_is_new_db = false;
+  bool& is_new_db = recovery_ctx ? recovery_ctx->is_new_db_ : tmp_is_new_db;
   assert(db_lock_ == nullptr);
   std::vector<std::string> files_in_dbname;
   if (!read_only) {
@@ -858,7 +872,8 @@ Status DBImpl::PersistentStatsProcessFormatVersion() {
       if (s.ok()) {
         ColumnFamilyOptions cfo;
         OptimizeForPersistentStats(&cfo);
-        s = CreateColumnFamily(cfo, kPersistentStatsColumnFamilyName, &handle);
+        s = CreateColumnFamilyImpl(cfo, kPersistentStatsColumnFamilyName,
+                                   &handle);
       }
       if (s.ok()) {
         persist_stats_cf_handle_ = static_cast<ColumnFamilyHandleImpl*>(handle);
@@ -911,7 +926,7 @@ Status DBImpl::InitPersistStatsColumnFamily() {
     ColumnFamilyHandle* handle = nullptr;
     ColumnFamilyOptions cfo;
     OptimizeForPersistentStats(&cfo);
-    s = CreateColumnFamily(cfo, kPersistentStatsColumnFamilyName, &handle);
+    s = CreateColumnFamilyImpl(cfo, kPersistentStatsColumnFamilyName, &handle);
     persist_stats_cf_handle_ = static_cast<ColumnFamilyHandleImpl*>(handle);
     mutex_.Lock();
   }
@@ -927,8 +942,11 @@ Status DBImpl::LogAndApplyForRecovery(const RecoveryContext& recovery_ctx) {
       recovery_ctx.edit_lists_, &mutex_, directories_.GetDbDir());
   if (s.ok() && !(recovery_ctx.files_to_delete_.empty())) {
     mutex_.Unlock();
-    for (const auto& fname : recovery_ctx.files_to_delete_) {
-      s = env_->DeleteFile(fname);
+    for (const auto& stale_sst_file : recovery_ctx.files_to_delete_) {
+      s = DeleteDBFile(&immutable_db_options_, stale_sst_file.first,
+                       stale_sst_file.second,
+                       /*force_bg=*/false,
+                       /*force_fg=*/false);
       if (!s.ok()) {
         break;
       }
@@ -1298,7 +1316,7 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
           flushed = true;
 
           cfd->CreateNewMemtable(*cfd->GetLatestMutableCFOptions(),
-                                 *next_sequence);
+                                 *next_sequence - 1);
         }
       }
     }
@@ -1649,7 +1667,7 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
           TableFileCreationReason::kRecovery, 0 /* oldest_key_time */,
           0 /* file_creation_time */, db_id_, db_session_id_,
           0 /* target_file_size */, meta.fd.GetNumber());
-      SeqnoToTimeMapping empty_seqno_time_mapping;
+      SeqnoToTimeMapping empty_seqno_to_time_mapping;
       Version* version = cfd->current();
       version->Ref();
       const ReadOptions read_option(Env::IOActivity::kDBOpen);
@@ -1661,7 +1679,7 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
           snapshot_seqs, earliest_write_conflict_snapshot, kMaxSequenceNumber,
           snapshot_checker, paranoid_file_checks, cfd->internal_stats(), &io_s,
           io_tracer_, BlobFileCreationReason::kRecovery,
-          empty_seqno_time_mapping, &event_logger_, job_id, Env::IO_HIGH,
+          empty_seqno_to_time_mapping, &event_logger_, job_id, Env::IO_HIGH,
           nullptr /* table_properties */, write_hint,
           nullptr /*full_history_ts_low*/, &blob_callback_, version,
           &num_input_entries);
@@ -1715,6 +1733,22 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
     for (const auto& blob : blob_file_additions) {
       edit->AddBlobFile(blob);
     }
+
+    // For UDT in memtable only feature, move up the cutoff timestamp whenever
+    // a flush happens.
+    const Comparator* ucmp = cfd->user_comparator();
+    size_t ts_sz = ucmp->timestamp_size();
+    if (ts_sz > 0 && !cfd->ioptions()->persist_user_defined_timestamps) {
+      Slice mem_newest_udt = mem->GetNewestUDT();
+      std::string full_history_ts_low = cfd->GetFullHistoryTsLow();
+      if (full_history_ts_low.empty() ||
+          ucmp->CompareTimestamp(mem_newest_udt, full_history_ts_low) >= 0) {
+        std::string new_full_history_ts_low;
+        GetFullHistoryTsLowFromU64CutoffTs(&mem_newest_udt,
+                                           &new_full_history_ts_low);
+        edit->SetFullHistoryTsLow(new_full_history_ts_low);
+      }
+    }
   }
 
   InternalStats::CompactionStats stats(CompactionReason::kFlush, 1);
@@ -1959,6 +1993,7 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
 
   impl->wal_in_db_path_ = impl->immutable_db_options_.IsWalDirSameAsDBPath();
   RecoveryContext recovery_ctx;
+  impl->options_mutex_.Lock();
   impl->mutex_.Lock();
 
   // Handles create_if_missing, error_if_exists
@@ -2040,7 +2075,9 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
           // missing column family, create it
           ColumnFamilyHandle* handle = nullptr;
           impl->mutex_.Unlock();
-          s = impl->CreateColumnFamily(cf.options, cf.name, &handle);
+          // NOTE: the work normally done in WrapUpCreateColumnFamilies will
+          // be done separately below.
+          s = impl->CreateColumnFamilyImpl(cf.options, cf.name, &handle);
           impl->mutex_.Lock();
           if (s.ok()) {
             handles->push_back(handle);
@@ -2091,9 +2128,8 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
   if (s.ok()) {
     // Persist RocksDB Options before scheduling the compaction.
     // The WriteOptionsFile() will release and lock the mutex internally.
-    persist_options_status = impl->WriteOptionsFile(
-        false /*need_mutex_lock*/, false /*need_enter_write_thread*/);
-
+    persist_options_status =
+        impl->WriteOptionsFile(true /*db_mutex_already_held*/);
     *dbptr = impl;
     impl->opened_successfully_ = true;
     impl->DeleteObsoleteFiles();
@@ -2214,10 +2250,10 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
   if (s.ok()) {
     s = impl->StartPeriodicTaskScheduler();
   }
-
   if (s.ok()) {
-    s = impl->RegisterRecordSeqnoTimeWorker();
+    s = impl->RegisterRecordSeqnoTimeWorker(recovery_ctx.is_new_db_);
   }
+  impl->options_mutex_.Unlock();
   if (!s.ok()) {
     for (auto* h : *handles) {
       delete h;