Make IncreaseFullHistoryTsLow to a public API (#9221)

Summary:
As (https://github.com/facebook/rocksdb/issues/9210) discussed, the **full_history_ts_low** is a member of CompactRangeOptions currently, which means a CF's fullHistoryTsLow is advanced only when users submit a CompactRange request.
However, users may want to advance the fllHistoryTsLow without an immediate compact.
This merge make IncreaseFullHistoryTsLow to a public API so users can advance each CF's fullHistoryTsLow seperately.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/9221

Reviewed By: akankshamahajan15

Differential Revision: D33201106

Pulled By: riversand963

fbshipit-source-id: 9cb1d013ba93260f72e16353e693ffee167b47ee

HISTORY.md

@@ -17,6 +17,8 @@
 ### Public API change
 * Extend WriteBatch::AssignTimestamp and AssignTimestamps API so that both functions can accept an optional `checker` argument that performs additional checking on timestamp sizes.
 * Introduce a new EventListener callback that will be called upon the end of automatic error recovery.
+* Add IncreaseFullHistoryTsLow API so users can advance each column family's full_history_ts_low seperately.
+* Add GetFullHistoryTsLow API so users can query current full_history_low value of specified column family.
 
 ### Performance Improvements
 * Replaced map property `TableProperties::properties_offsets`  with uint64_t property `external_sst_file_global_seqno_offset` to save table properties's memory.

db/db_impl/db_impl.cc

@@ -1496,6 +1496,30 @@ bool DBImpl::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum) {
   }
 }
 
+Status DBImpl::GetFullHistoryTsLow(ColumnFamilyHandle* column_family,
+                                   std::string* ts_low) {
+  if (ts_low == nullptr) {
+    return Status::InvalidArgument("ts_low is nullptr");
+  }
+  ColumnFamilyData* cfd = nullptr;
+  if (column_family == nullptr) {
+    cfd = default_cf_handle_->cfd();
+  } else {
+    auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
+    assert(cfh != nullptr);
+    cfd = cfh->cfd();
+  }
+  assert(cfd != nullptr && cfd->user_comparator() != nullptr);
+  if (cfd->user_comparator()->timestamp_size() == 0) {
+    return Status::InvalidArgument(
+        "Timestamp is not enabled in this column family");
+  }
+  InstrumentedMutexLock l(&mutex_);
+  *ts_low = cfd->GetFullHistoryTsLow();
+  assert(cfd->user_comparator()->timestamp_size() == ts_low->size());
+  return Status::OK();
+}
+
 InternalIterator* DBImpl::NewInternalIterator(const ReadOptions& read_options,
                                               Arena* arena,
                                               RangeDelAggregator* range_del_agg,

db/db_impl/db_impl.h

@@ -355,6 +355,16 @@ class DBImpl : public DB {
 
   virtual bool SetPreserveDeletesSequenceNumber(SequenceNumber seqnum) override;
 
+  // IncreaseFullHistoryTsLow(ColumnFamilyHandle*, std::string) will acquire
+  // and release db_mutex
+  Status IncreaseFullHistoryTsLow(ColumnFamilyHandle* column_family,
+                                  std::string ts_low) override;
+
+  // GetFullHistoryTsLow(ColumnFamilyHandle*, std::string*) will acquire and
+  // release db_mutex
+  Status GetFullHistoryTsLow(ColumnFamilyHandle* column_family,
+                             std::string* ts_low) override;
+
   virtual Status GetDbIdentity(std::string& identity) const override;
 
   virtual Status GetDbIdentityFromIdentityFile(std::string* identity) const;
@@ -1987,7 +1997,8 @@ class DBImpl : public DB {
 
   Status DisableFileDeletionsWithLock();
 
-  Status IncreaseFullHistoryTsLow(ColumnFamilyData* cfd, std::string ts_low);
+  Status IncreaseFullHistoryTsLowImpl(ColumnFamilyData* cfd,
+                                      std::string ts_low);
 
   // Lock over the persistent DB state.  Non-nullptr iff successfully acquired.
   FileLock* db_lock_;

db/db_impl/db_impl_compaction_flush.cc

@@ -917,8 +917,29 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
                               end_with_ts);
 }
 
-Status DBImpl::IncreaseFullHistoryTsLow(ColumnFamilyData* cfd,
+Status DBImpl::IncreaseFullHistoryTsLow(ColumnFamilyHandle* column_family,
                                         std::string ts_low) {
+  ColumnFamilyData* cfd = nullptr;
+  if (column_family == nullptr) {
+    cfd = default_cf_handle_->cfd();
+  } else {
+    auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
+    assert(cfh != nullptr);
+    cfd = cfh->cfd();
+  }
+  assert(cfd != nullptr && cfd->user_comparator() != nullptr);
+  if (cfd->user_comparator()->timestamp_size() == 0) {
+    return Status::InvalidArgument(
+        "Timestamp is not enabled in this column family");
+  }
+  if (cfd->user_comparator()->timestamp_size() != ts_low.size()) {
+    return Status::InvalidArgument("ts_low size mismatch");
+  }
+  return IncreaseFullHistoryTsLowImpl(cfd, ts_low);
+}
+
+Status DBImpl::IncreaseFullHistoryTsLowImpl(ColumnFamilyData* cfd,
+                                            std::string ts_low) {
   VersionEdit edit;
   edit.SetColumnFamily(cfd->GetID());
   edit.SetFullHistoryTsLow(ts_low);
@@ -926,6 +947,7 @@ Status DBImpl::IncreaseFullHistoryTsLow(ColumnFamilyData* cfd,
   InstrumentedMutexLock l(&mutex_);
   std::string current_ts_low = cfd->GetFullHistoryTsLow();
   const Comparator* ucmp = cfd->user_comparator();
+  assert(ucmp->timestamp_size() == ts_low.size() && !ts_low.empty());
   if (!current_ts_low.empty() &&
       ucmp->CompareTimestamp(ts_low, current_ts_low) < 0) {
     return Status::InvalidArgument(
@@ -956,7 +978,7 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
       return Status::InvalidArgument(
           "Cannot specify compaction range with full_history_ts_low");
     }
-    Status s = IncreaseFullHistoryTsLow(cfd, ts_low);
+    Status s = IncreaseFullHistoryTsLowImpl(cfd, ts_low);
     if (!s.ok()) {
       LogFlush(immutable_db_options_.info_log);
       return s;

db/db_test.cc

@@ -3214,6 +3214,16 @@ class ModelDB : public DB {
     return true;
   }
 
+  Status IncreaseFullHistoryTsLow(ColumnFamilyHandle* /*cf*/,
+                                  std::string /*ts_low*/) override {
+    return Status::OK();
+  }
+
+  Status GetFullHistoryTsLow(ColumnFamilyHandle* /*cf*/,
+                             std::string* /*ts_low*/) override {
+    return Status::OK();
+  }
+
   ColumnFamilyHandle* DefaultColumnFamily() const override { return nullptr; }
 
  private:

db/db_with_timestamp_basic_test.cc

@@ -435,6 +435,51 @@ TEST_F(DBBasicTestWithTimestamp, UpdateFullHistoryTsLow) {
   Close();
 }
 
+TEST_F(DBBasicTestWithTimestamp, UpdateFullHistoryTsLowWithPublicAPI) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.create_if_missing = true;
+  const size_t kTimestampSize = Timestamp(0, 0).size();
+  TestComparator test_cmp(kTimestampSize);
+  options.comparator = &test_cmp;
+  DestroyAndReopen(options);
+  std::string ts_low_str = Timestamp(9, 0);
+  ASSERT_OK(
+      db_->IncreaseFullHistoryTsLow(db_->DefaultColumnFamily(), ts_low_str));
+  std::string result_ts_low;
+  ASSERT_OK(db_->GetFullHistoryTsLow(nullptr, &result_ts_low));
+  ASSERT_TRUE(test_cmp.CompareTimestamp(ts_low_str, result_ts_low) == 0);
+  // test increase full_history_low backward
+  std::string ts_low_str_back = Timestamp(8, 0);
+  auto s = db_->IncreaseFullHistoryTsLow(db_->DefaultColumnFamily(),
+                                         ts_low_str_back);
+  ASSERT_EQ(s, Status::InvalidArgument());
+  // test IncreaseFullHistoryTsLow with a timestamp whose length is longger
+  // than the cf's timestamp size
+  std::string ts_low_str_long(Timestamp(0, 0).size() + 1, 'a');
+  s = db_->IncreaseFullHistoryTsLow(db_->DefaultColumnFamily(),
+                                    ts_low_str_long);
+  ASSERT_EQ(s, Status::InvalidArgument());
+  // test IncreaseFullHistoryTsLow with a timestamp which is null
+  std::string ts_low_str_null = "";
+  s = db_->IncreaseFullHistoryTsLow(db_->DefaultColumnFamily(),
+                                    ts_low_str_null);
+  ASSERT_EQ(s, Status::InvalidArgument());
+  // test IncreaseFullHistoryTsLow for a column family that does not enable
+  // timestamp
+  options.comparator = BytewiseComparator();
+  DestroyAndReopen(options);
+  ts_low_str = Timestamp(10, 0);
+  s = db_->IncreaseFullHistoryTsLow(db_->DefaultColumnFamily(), ts_low_str);
+  ASSERT_EQ(s, Status::InvalidArgument());
+  // test GetFullHistoryTsLow for a column family that does not enable
+  // timestamp
+  std::string current_ts_low;
+  s = db_->GetFullHistoryTsLow(db_->DefaultColumnFamily(), &current_ts_low);
+  ASSERT_EQ(s, Status::InvalidArgument());
+  Close();
+}
+
 TEST_F(DBBasicTestWithTimestamp, GetApproximateSizes) {
   Options options = CurrentOptions();
   options.write_buffer_size = 100000000;  // Large write buffer

include/rocksdb/db.h

@@ -1356,6 +1356,15 @@ class DB {
   // times have the same effect as calling it once.
   virtual Status DisableFileDeletions() = 0;
 
+  // Increase the full_history_ts of column family. The new ts_low value should
+  // be newer than current full_history_ts value.
+  virtual Status IncreaseFullHistoryTsLow(ColumnFamilyHandle* column_family,
+                                          std::string ts_low) = 0;
+
+  // Get current full_history_ts value.
+  virtual Status GetFullHistoryTsLow(ColumnFamilyHandle* column_family,
+                                     std::string* ts_low) = 0;
+
   // Allow compactions to delete obsolete files.
   // If force == true, the call to EnableFileDeletions() will guarantee that
   // file deletions are enabled after the call, even if DisableFileDeletions()

include/rocksdb/utilities/stackable_db.h

@@ -419,6 +419,16 @@ class StackableDB : public DB {
     return db_->SetPreserveDeletesSequenceNumber(seqnum);
   }
 
+  Status IncreaseFullHistoryTsLow(ColumnFamilyHandle* column_family,
+                                  std::string ts_low) override {
+    return db_->IncreaseFullHistoryTsLow(column_family, ts_low);
+  }
+
+  Status GetFullHistoryTsLow(ColumnFamilyHandle* column_family,
+                             std::string* ts_low) override {
+    return db_->GetFullHistoryTsLow(column_family, ts_low);
+  }
+
   virtual Status GetSortedWalFiles(VectorLogPtr& files) override {
     return db_->GetSortedWalFiles(files);
   }