@nxtedition/rocksdb 8.0.0 → 8.0.2

package/deps/rocksdb/rocksdb/db/version_set.cc

@@ -39,6 +39,8 @@
 #include "db/table_cache.h"
 #include "db/version_builder.h"
 #include "db/version_edit_handler.h"
+#include "table/compaction_merging_iterator.h"
+
 #if USE_COROUTINES
 #include "folly/experimental/coro/BlockingWait.h"
 #include "folly/experimental/coro/Collect.h"
@@ -1771,8 +1773,8 @@ void Version::GetColumnFamilyMetaData(ColumnFamilyMetaData* cf_meta) {
           file->stats.num_reads_sampled.load(std::memory_order_relaxed),
           file->being_compacted, file->temperature,
           file->oldest_blob_file_number, file->TryGetOldestAncesterTime(),
-          file->TryGetFileCreationTime(), file->file_checksum,
-          file->file_checksum_func_name);
+          file->TryGetFileCreationTime(), file->epoch_number,
+          file->file_checksum, file->file_checksum_func_name);
       files.back().num_entries = file->num_entries;
       files.back().num_deletions = file->num_deletions;
       level_size += file->fd.GetFileSize();
@@ -2036,7 +2038,8 @@ VersionStorageInfo::VersionStorageInfo(
     const InternalKeyComparator* internal_comparator,
     const Comparator* user_comparator, int levels,
     CompactionStyle compaction_style, VersionStorageInfo* ref_vstorage,
-    bool _force_consistency_checks)
+    bool _force_consistency_checks,
+    EpochNumberRequirement epoch_number_requirement)
     : internal_comparator_(internal_comparator),
       user_comparator_(user_comparator),
       // cfd is nullptr if Version is dummy
@@ -2064,7 +2067,8 @@ VersionStorageInfo::VersionStorageInfo(
       current_num_samples_(0),
       estimated_compaction_needed_bytes_(0),
       finalized_(false),
-      force_consistency_checks_(_force_consistency_checks) {
+      force_consistency_checks_(_force_consistency_checks),
+      epoch_number_requirement_(epoch_number_requirement) {
   if (ref_vstorage != nullptr) {
     accumulated_file_size_ = ref_vstorage->accumulated_file_size_;
     accumulated_raw_key_size_ = ref_vstorage->accumulated_raw_key_size_;
@@ -2085,7 +2089,8 @@ Version::Version(ColumnFamilyData* column_family_data, VersionSet* vset,
                  const FileOptions& file_opt,
                  const MutableCFOptions mutable_cf_options,
                  const std::shared_ptr<IOTracer>& io_tracer,
-                 uint64_t version_number)
+                 uint64_t version_number,
+                 EpochNumberRequirement epoch_number_requirement)
     : env_(vset->env_),
       clock_(vset->clock_),
       cfd_(column_family_data),
@@ -2104,7 +2109,8 @@ Version::Version(ColumnFamilyData* column_family_data, VersionSet* vset,
           (cfd_ == nullptr || cfd_->current() == nullptr)
               ? nullptr
               : cfd_->current()->storage_info(),
-          cfd_ == nullptr ? false : cfd_->ioptions()->force_consistency_checks),
+          cfd_ == nullptr ? false : cfd_->ioptions()->force_consistency_checks,
+          epoch_number_requirement),
       vset_(vset),
       next_(this),
       prev_(this),
@@ -2384,15 +2390,19 @@ void Version::Get(const ReadOptions& read_options, const LookupKey& k,
     }
     // merge_operands are in saver and we hit the beginning of the key history
     // do a final merge of nullptr and operands;
-    std::string* str_value = value != nullptr ? value->GetSelf() : nullptr;
-    if (str_value || columns) {
+    if (value || columns) {
+      std::string result;
       *status = MergeHelper::TimedFullMerge(
           merge_operator_, user_key, nullptr, merge_context->GetOperands(),
-          str_value, columns, info_log_, db_statistics_, clock_,
+          &result, info_log_, db_statistics_, clock_,
           /* result_operand */ nullptr, /* update_num_ops_stats */ true);
       if (status->ok()) {
         if (LIKELY(value != nullptr)) {
+          *(value->GetSelf()) = std::move(result);
           value->PinSelf();
+        } else {
+          assert(columns != nullptr);
+          columns->SetPlainValue(result);
         }
       }
     }
@@ -2535,16 +2545,19 @@ void Version::MultiGet(const ReadOptions& read_options, MultiGetRange* range,
           }
           f = fp.GetNextFileInLevel();
         }
-        if (s.ok() && mget_tasks.size() > 0) {
+        if (mget_tasks.size() > 0) {
           RecordTick(db_statistics_, MULTIGET_COROUTINE_COUNT,
                      mget_tasks.size());
           // Collect all results so far
           std::vector<Status> statuses = folly::coro::blockingWait(
               folly::coro::collectAllRange(std::move(mget_tasks))
                   .scheduleOn(&range->context()->executor()));
-          for (Status stat : statuses) {
-            if (!stat.ok()) {
-              s = stat;
+          if (s.ok()) {
+            for (Status stat : statuses) {
+              if (!stat.ok()) {
+                s = std::move(stat);
+                break;
+              }
             }
           }
 
@@ -2790,6 +2803,9 @@ Status Version::MultiGetAsync(
     unsigned int num_tasks_queued = 0;
     to_process.pop_front();
     if (batch->IsSearchEnded() || batch->GetRange().empty()) {
+      // If to_process is empty, i.e no more batches to look at, then we need
+      // schedule the enqueued coroutines and wait for them. Otherwise, we
+      // skip this batch and move to the next one in to_process.
       if (!to_process.empty()) {
         continue;
       }
@@ -2798,9 +2814,6 @@ Status Version::MultiGetAsync(
       // to_process
       s = ProcessBatch(options, batch, mget_tasks, blob_ctxs, batches, waiting,
                        to_process, num_tasks_queued, mget_stats);
-      if (!s.ok()) {
-        break;
-      }
       // If ProcessBatch didn't enqueue any coroutine tasks, it means all
       // keys were filtered out. So put the batch back in to_process to
       // lookup in the next level
@@ -2811,8 +2824,10 @@ Status Version::MultiGetAsync(
         waiting.emplace_back(idx);
       }
     }
-    if (to_process.empty()) {
-      if (s.ok() && mget_tasks.size() > 0) {
+    // If ProcessBatch() returned an error, then schedule the enqueued
+    // coroutines and wait for them, then abort the MultiGet.
+    if (to_process.empty() || !s.ok()) {
+      if (mget_tasks.size() > 0) {
         assert(waiting.size());
         RecordTick(db_statistics_, MULTIGET_COROUTINE_COUNT, mget_tasks.size());
         // Collect all results so far
@@ -2820,10 +2835,12 @@ Status Version::MultiGetAsync(
             folly::coro::collectAllRange(std::move(mget_tasks))
                 .scheduleOn(&range->context()->executor()));
         mget_tasks.clear();
-        for (Status stat : statuses) {
-          if (!stat.ok()) {
-            s = stat;
-            break;
+        if (s.ok()) {
+          for (Status stat : statuses) {
+            if (!stat.ok()) {
+              s = std::move(stat);
+              break;
+            }
           }
         }
 
@@ -2846,6 +2863,9 @@ Status Version::MultiGetAsync(
         assert(!s.ok() || waiting.size() == 0);
       }
     }
+    if (!s.ok()) {
+      break;
+    }
   }
 
   uint64_t num_levels = 0;
@@ -4266,6 +4286,74 @@ const char* VersionStorageInfo::LevelFileSummary(FileSummaryStorage* scratch,
   return scratch->buffer;
 }
 
+bool VersionStorageInfo::HasMissingEpochNumber() const {
+  for (int level = 0; level < num_levels_; ++level) {
+    for (const FileMetaData* f : files_[level]) {
+      if (f->epoch_number == kUnknownEpochNumber) {
+        return true;
+      }
+    }
+  }
+  return false;
+}
+
+uint64_t VersionStorageInfo::GetMaxEpochNumberOfFiles() const {
+  uint64_t max_epoch_number = kUnknownEpochNumber;
+  for (int level = 0; level < num_levels_; ++level) {
+    for (const FileMetaData* f : files_[level]) {
+      max_epoch_number = std::max(max_epoch_number, f->epoch_number);
+    }
+  }
+  return max_epoch_number;
+}
+
+void VersionStorageInfo::RecoverEpochNumbers(ColumnFamilyData* cfd) {
+  cfd->ResetNextEpochNumber();
+
+  bool reserve_epoch_num_for_file_ingested_behind =
+      cfd->ioptions()->allow_ingest_behind;
+  if (reserve_epoch_num_for_file_ingested_behind) {
+    uint64_t reserved_epoch_number = cfd->NewEpochNumber();
+    assert(reserved_epoch_number == kReservedEpochNumberForFileIngestedBehind);
+    ROCKS_LOG_INFO(cfd->ioptions()->info_log.get(),
+                   "[%s]CF has reserved epoch number %" PRIu64
+                   " for files ingested "
+                   "behind since `Options::allow_ingest_behind` is true",
+                   cfd->GetName().c_str(), reserved_epoch_number);
+  }
+
+  if (HasMissingEpochNumber()) {
+    assert(epoch_number_requirement_ == EpochNumberRequirement::kMightMissing);
+    assert(num_levels_ >= 1);
+
+    for (int level = num_levels_ - 1; level >= 1; --level) {
+      auto& files_at_level = files_[level];
+      if (files_at_level.empty()) {
+        continue;
+      }
+      uint64_t next_epoch_number = cfd->NewEpochNumber();
+      for (FileMetaData* f : files_at_level) {
+        f->epoch_number = next_epoch_number;
+      }
+    }
+
+    for (auto file_meta_iter = files_[0].rbegin();
+         file_meta_iter != files_[0].rend(); file_meta_iter++) {
+      FileMetaData* f = *file_meta_iter;
+      f->epoch_number = cfd->NewEpochNumber();
+    }
+
+    ROCKS_LOG_WARN(cfd->ioptions()->info_log.get(),
+                   "[%s]CF's epoch numbers are inferred based on seqno",
+                   cfd->GetName().c_str());
+    epoch_number_requirement_ = EpochNumberRequirement::kMustPresent;
+  } else {
+    assert(epoch_number_requirement_ == EpochNumberRequirement::kMustPresent);
+    cfd->SetNextEpochNumber(
+        std::max(GetMaxEpochNumberOfFiles() + 1, cfd->GetNextEpochNumber()));
+  }
+}
+
 uint64_t VersionStorageInfo::MaxNextLevelOverlappingBytes() {
   uint64_t result = 0;
   std::vector<FileMetaData*> overlaps;
@@ -4963,10 +5051,15 @@ Status VersionSet::ProcessManifestWrites(
   if (!descriptor_log_ ||
       manifest_file_size_ > db_options_->max_manifest_file_size) {
     TEST_SYNC_POINT("VersionSet::ProcessManifestWrites:BeforeNewManifest");
+    TEST_SYNC_POINT_CALLBACK(
+        "VersionSet::ProcessManifestWrites:BeforeNewManifest", nullptr);
     new_descriptor_log = true;
   } else {
     pending_manifest_file_number_ = manifest_file_number_;
   }
+  TEST_SYNC_POINT_CALLBACK(
+      "VersionSet::ProcessManifestWrites:PostDecidingCreateNewManifestOrNot",
+      &new_descriptor_log);
 
   // Local cached copy of state variable(s). WriteCurrentStateToManifest()
   // reads its content after releasing db mutex to avoid race with
@@ -5095,6 +5188,7 @@ Status VersionSet::ProcessManifestWrites(
           break;
         }
       }
+
       if (s.ok()) {
         io_s = SyncManifest(db_options_, descriptor_log_->file());
         manifest_io_status = io_s;
@@ -5502,7 +5596,8 @@ Status VersionSet::GetCurrentManifestPath(const std::string& dbname,
 Status VersionSet::Recover(
     const std::vector<ColumnFamilyDescriptor>& column_families, bool read_only,
     std::string* db_id, bool no_error_if_files_missing) {
-  // Read "CURRENT" file, which contains a pointer to the current manifest file
+  // Read "CURRENT" file, which contains a pointer to the current manifest
+  // file
   std::string manifest_path;
   Status s = GetCurrentManifestPath(dbname_, fs_.get(), &manifest_path,
                                     &manifest_file_number_);
@@ -5536,7 +5631,8 @@ Status VersionSet::Recover(
                        true /* checksum */, 0 /* log_number */);
     VersionEditHandler handler(
         read_only, column_families, const_cast<VersionSet*>(this),
-        /*track_missing_files=*/false, no_error_if_files_missing, io_tracer_);
+        /*track_missing_files=*/false, no_error_if_files_missing, io_tracer_,
+        EpochNumberRequirement::kMightMissing);
     handler.Iterate(reader, &log_read_status);
     s = handler.status();
     if (s.ok()) {
@@ -5545,6 +5641,9 @@ Status VersionSet::Recover(
       assert(current_manifest_file_size != 0);
       handler.GetDbId(db_id);
     }
+    if (s.ok()) {
+      RecoverEpochNumbers();
+    }
   }
 
   if (s.ok()) {
@@ -5704,7 +5803,8 @@ Status VersionSet::TryRecoverFromOneManifest(
   log::Reader reader(nullptr, std::move(manifest_file_reader), &reporter,
                      /*checksum=*/true, /*log_num=*/0);
   VersionEditHandlerPointInTime handler_pit(
-      read_only, column_families, const_cast<VersionSet*>(this), io_tracer_);
+      read_only, column_families, const_cast<VersionSet*>(this), io_tracer_,
+      EpochNumberRequirement::kMightMissing);
 
   handler_pit.Iterate(reader, &s);
 
@@ -5713,7 +5813,21 @@ Status VersionSet::TryRecoverFromOneManifest(
   assert(nullptr != has_missing_table_file);
   *has_missing_table_file = handler_pit.HasMissingFiles();
 
-  return handler_pit.status();
+  s = handler_pit.status();
+  if (s.ok()) {
+    RecoverEpochNumbers();
+  }
+  return s;
+}
+
+void VersionSet::RecoverEpochNumbers() {
+  for (auto cfd : *column_family_set_) {
+    if (cfd->IsDropped()) {
+      continue;
+    }
+    assert(cfd->initialized());
+    cfd->RecoverEpochNumbers();
+  }
 }
 
 Status VersionSet::ListColumnFamilies(std::vector<std::string>* column_families,
@@ -6033,6 +6147,22 @@ Status VersionSet::WriteCurrentStateToManifest(
     }
   }
 
+  // New manifest should rollover the WAL deletion record from previous
+  // manifest. Otherwise, when an addition record of a deleted WAL gets added to
+  // this new manifest later (which can happens in e.g, SyncWAL()), this new
+  // manifest creates an illusion that such WAL hasn't been deleted.
+  VersionEdit wal_deletions;
+  wal_deletions.DeleteWalsBefore(min_log_number_to_keep());
+  std::string wal_deletions_record;
+  if (!wal_deletions.EncodeTo(&wal_deletions_record)) {
+    return Status::Corruption("Unable to Encode VersionEdit: " +
+                              wal_deletions.DebugString(true));
+  }
+  io_s = log->AddRecord(wal_deletions_record);
+  if (!io_s.ok()) {
+    return io_s;
+  }
+
   for (auto cfd : *column_family_set_) {
     assert(cfd);
 
@@ -6084,7 +6214,7 @@ Status VersionSet::WriteCurrentStateToManifest(
                        f->fd.smallest_seqno, f->fd.largest_seqno,
                        f->marked_for_compaction, f->temperature,
                        f->oldest_blob_file_number, f->oldest_ancester_time,
-                       f->file_creation_time, f->file_checksum,
+                       f->file_creation_time, f->epoch_number, f->file_checksum,
                        f->file_checksum_func_name, f->unique_id);
         }
       }
@@ -6456,6 +6586,14 @@ InternalIterator* VersionSet::MakeInputIterator(
                                               c->num_input_levels() - 1
                                         : c->num_input_levels());
   InternalIterator** list = new InternalIterator*[space];
+  // First item in the pair is a pointer to range tombstones.
+  // Second item is a pointer to a member of a LevelIterator,
+  // that will be initialized to where CompactionMergingIterator stores
+  // pointer to its range tombstones. This is used by LevelIterator
+  // to update pointer to range tombstones as it traverse different SST files.
+  std::vector<
+      std::pair<TruncatedRangeDelIterator*, TruncatedRangeDelIterator***>>
+      range_tombstones;
   size_t num = 0;
   for (size_t which = 0; which < c->num_input_levels(); which++) {
     if (c->input_levels(which)->num_files != 0) {
@@ -6476,7 +6614,7 @@ InternalIterator* VersionSet::MakeInputIterator(
                   end.value(), fmd.smallest.user_key()) < 0) {
             continue;
           }
-
+          TruncatedRangeDelIterator* range_tombstone_iter = nullptr;
           list[num++] = cfd->table_cache()->NewIterator(
               read_options, file_options_compactions,
               cfd->internal_comparator(), fmd, range_del_agg,
@@ -6489,10 +6627,13 @@ InternalIterator* VersionSet::MakeInputIterator(
               MaxFileSizeForL0MetaPin(*c->mutable_cf_options()),
               /*smallest_compaction_key=*/nullptr,
               /*largest_compaction_key=*/nullptr,
-              /*allow_unprepared_value=*/false);
+              /*allow_unprepared_value=*/false,
+              /*range_del_iter=*/&range_tombstone_iter);
+          range_tombstones.emplace_back(range_tombstone_iter, nullptr);
         }
       } else {
         // Create concatenating iterator for the files from this level
+        TruncatedRangeDelIterator*** tombstone_iter_ptr = nullptr;
         list[num++] = new LevelIterator(
             cfd->table_cache(), read_options, file_options_compactions,
             cfd->internal_comparator(), c->input_levels(which),
@@ -6501,14 +6642,15 @@ InternalIterator* VersionSet::MakeInputIterator(
             /*no per level latency histogram=*/nullptr,
             TableReaderCaller::kCompaction, /*skip_filters=*/false,
             /*level=*/static_cast<int>(c->level(which)), range_del_agg,
-            c->boundaries(which));
+            c->boundaries(which), false, &tombstone_iter_ptr);
+        range_tombstones.emplace_back(nullptr, tombstone_iter_ptr);
       }
     }
   }
   assert(num <= space);
-  InternalIterator* result =
-      NewMergingIterator(&c->column_family_data()->internal_comparator(), list,
-                         static_cast<int>(num));
+  InternalIterator* result = NewCompactionMergingIterator(
+      &c->column_family_data()->internal_comparator(), list,
+      static_cast<int>(num), range_tombstones);
   delete[] list;
   return result;
 }
@@ -6575,6 +6717,7 @@ void VersionSet::GetLiveFilesMetaData(std::vector<LiveFileMetaData>* metadata) {
         filemetadata.temperature = file->temperature;
         filemetadata.oldest_ancester_time = file->TryGetOldestAncesterTime();
         filemetadata.file_creation_time = file->TryGetFileCreationTime();
+        filemetadata.epoch_number = file->epoch_number;
         metadata->push_back(filemetadata);
       }
     }
@@ -6700,8 +6843,9 @@ uint64_t VersionSet::GetTotalBlobFileSize(Version* dummy_versions) {
   return all_versions_blob_file_size;
 }
 
-Status VersionSet::VerifyFileMetadata(const std::string& fpath,
-                                      const FileMetaData& meta) const {
+Status VersionSet::VerifyFileMetadata(ColumnFamilyData* cfd,
+                                      const std::string& fpath, int level,
+                                      const FileMetaData& meta) {
   uint64_t fsize = 0;
   Status status = fs_->GetFileSize(fpath, IOOptions(), &fsize, nullptr);
   if (status.ok()) {
@@ -6709,6 +6853,38 @@ Status VersionSet::VerifyFileMetadata(const std::string& fpath,
       status = Status::Corruption("File size mismatch: " + fpath);
     }
   }
+  if (status.ok() && db_options_->verify_sst_unique_id_in_manifest) {
+    assert(cfd);
+    TableCache* table_cache = cfd->table_cache();
+    assert(table_cache);
+
+    const MutableCFOptions* const cf_opts = cfd->GetLatestMutableCFOptions();
+    assert(cf_opts);
+    std::shared_ptr<const SliceTransform> pe = cf_opts->prefix_extractor;
+    size_t max_sz_for_l0_meta_pin = MaxFileSizeForL0MetaPin(*cf_opts);
+
+    const FileOptions& file_opts = file_options();
+
+    Version* version = cfd->current();
+    assert(version);
+    VersionStorageInfo& storage_info = version->storage_info_;
+    const InternalKeyComparator* icmp = storage_info.InternalComparator();
+    assert(icmp);
+
+    InternalStats* internal_stats = cfd->internal_stats();
+
+    FileMetaData meta_copy = meta;
+    status = table_cache->FindTable(
+        ReadOptions(), file_opts, *icmp, meta_copy,
+        &(meta_copy.table_reader_handle), pe,
+        /*no_io=*/false, /*record_read_stats=*/true,
+        internal_stats->GetFileReadHist(level), false, level,
+        /*prefetch_index_and_filter_in_cache*/ false, max_sz_for_l0_meta_pin,
+        meta_copy.temperature);
+    if (meta_copy.table_reader_handle) {
+      table_cache->ReleaseHandle(meta_copy.table_reader_handle);
+    }
+  }
   return status;
 }
 
@@ -6744,12 +6920,17 @@ Status ReactiveVersionSet::Recover(
   log::Reader* reader = manifest_reader->get();
   assert(reader);
 
-  manifest_tailer_.reset(new ManifestTailer(
-      column_families, const_cast<ReactiveVersionSet*>(this), io_tracer_));
+  manifest_tailer_.reset(
+      new ManifestTailer(column_families, const_cast<ReactiveVersionSet*>(this),
+                         io_tracer_, EpochNumberRequirement::kMightMissing));
 
   manifest_tailer_->Iterate(*reader, manifest_reader_status->get());
 
-  return manifest_tailer_->status();
+  s = manifest_tailer_->status();
+  if (s.ok()) {
+    RecoverEpochNumbers();
+  }
+  return s;
 }
 
 Status ReactiveVersionSet::ReadAndApply(

package/deps/rocksdb/rocksdb/db/version_set.h

@@ -116,6 +116,10 @@ extern bool SomeFileOverlapsRange(const InternalKeyComparator& icmp,
 extern void DoGenerateLevelFilesBrief(LevelFilesBrief* file_level,
                                       const std::vector<FileMetaData*>& files,
                                       Arena* arena);
+enum EpochNumberRequirement {
+  kMightMissing,
+  kMustPresent,
+};
 
 // Information of the storage associated with each Version, including number of
 // levels of LSM tree, files information at each level, files marked for
@@ -126,7 +130,9 @@ class VersionStorageInfo {
                      const Comparator* user_comparator, int num_levels,
                      CompactionStyle compaction_style,
                      VersionStorageInfo* src_vstorage,
-                     bool _force_consistency_checks);
+                     bool _force_consistency_checks,
+                     EpochNumberRequirement epoch_number_requirement =
+                         EpochNumberRequirement::kMustPresent);
   // No copying allowed
   VersionStorageInfo(const VersionStorageInfo&) = delete;
   void operator=(const VersionStorageInfo&) = delete;
@@ -319,6 +325,17 @@ class VersionStorageInfo {
     return files_[level];
   }
 
+  bool HasMissingEpochNumber() const;
+  uint64_t GetMaxEpochNumberOfFiles() const;
+  EpochNumberRequirement GetEpochNumberRequirement() const {
+    return epoch_number_requirement_;
+  }
+  void SetEpochNumberRequirement(
+      EpochNumberRequirement epoch_number_requirement) {
+    epoch_number_requirement_ = epoch_number_requirement;
+  }
+  void RecoverEpochNumbers(ColumnFamilyData* cfd);
+
   class FileLocation {
    public:
     FileLocation() = default;
@@ -440,6 +457,11 @@ class VersionStorageInfo {
     return files_marked_for_compaction_;
   }
 
+  void TEST_AddFileMarkedForCompaction(int level, FileMetaData* f) {
+    f->marked_for_compaction = true;
+    files_marked_for_compaction_.emplace_back(level, f);
+  }
+
   // REQUIRES: ComputeCompactionScore has been called
   // REQUIRES: DB mutex held during access
   const autovector<std::pair<int, FileMetaData*>>& ExpiredTtlFiles() const {
@@ -723,6 +745,8 @@ class VersionStorageInfo {
   // is compiled in release mode
   bool force_consistency_checks_;
 
+  EpochNumberRequirement epoch_number_requirement_;
+
   friend class Version;
   friend class VersionSet;
 };
@@ -1047,7 +1071,9 @@ class Version {
   Version(ColumnFamilyData* cfd, VersionSet* vset, const FileOptions& file_opt,
           MutableCFOptions mutable_cf_options,
           const std::shared_ptr<IOTracer>& io_tracer,
-          uint64_t version_number = 0);
+          uint64_t version_number = 0,
+          EpochNumberRequirement epoch_number_requirement =
+              EpochNumberRequirement::kMustPresent);
 
   ~Version();
 
@@ -1188,6 +1214,10 @@ class VersionSet {
       const std::vector<ColumnFamilyDescriptor>& column_families,
       bool read_only, std::string* db_id, bool* has_missing_table_file);
 
+  // Recover the next epoch number of each CFs and epoch number
+  // of their files (if missing)
+  void RecoverEpochNumbers();
+
   // Reads a manifest file and returns a list of column families in
   // column_families.
   static Status ListColumnFamilies(std::vector<std::string>* column_families,
@@ -1501,8 +1531,8 @@ class VersionSet {
   ColumnFamilyData* CreateColumnFamily(const ColumnFamilyOptions& cf_options,
                                        const VersionEdit* edit);
 
-  Status VerifyFileMetadata(const std::string& fpath,
-                            const FileMetaData& meta) const;
+  Status VerifyFileMetadata(ColumnFamilyData* cfd, const std::string& fpath,
+                            int level, const FileMetaData& meta);
 
   // Protected by DB mutex.
   WalSet wals_;