@nxtedition/rocksdb 8.2.8 → 9.0.1

package/deps/rocksdb/rocksdb/db/db_iter.cc

@@ -18,6 +18,7 @@
 #include "db/merge_helper.h"
 #include "db/pinned_iterators_manager.h"
 #include "db/wide/wide_column_serialization.h"
+#include "db/wide/wide_columns_helper.h"
 #include "file/filename.h"
 #include "logging/logging.h"
 #include "memory/arena.h"
@@ -77,11 +78,13 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
       expose_blob_index_(expose_blob_index),
       is_blob_(false),
       arena_mode_(arena_mode),
+      io_activity_(read_options.io_activity),
       db_impl_(db_impl),
       cfd_(cfd),
       timestamp_ub_(read_options.timestamp),
       timestamp_lb_(read_options.iter_start_ts),
-      timestamp_size_(timestamp_ub_ ? timestamp_ub_->size() : 0) {
+      timestamp_size_(timestamp_ub_ ? timestamp_ub_->size() : 0),
+      auto_readahead_size_(read_options.auto_readahead_size) {
   RecordTick(statistics_, NO_ITERATOR_CREATED);
   if (pin_thru_lifetime_) {
     pinned_iters_mgr_.StartPinning();
@@ -196,12 +199,11 @@ bool DBIter::SetBlobValueIfNeeded(const Slice& user_key,
 
   // TODO: consider moving ReadOptions from ArenaWrappedDBIter to DBIter to
   // avoid having to copy options back and forth.
-  // TODO: plumb Env::IOActivity
   ReadOptions read_options;
   read_options.read_tier = read_tier_;
   read_options.fill_cache = fill_cache_;
   read_options.verify_checksums = verify_checksums_;
-
+  read_options.io_activity = io_activity_;
   constexpr FilePrefetchBuffer* prefetch_buffer = nullptr;
   constexpr uint64_t* bytes_read = nullptr;
 
@@ -230,11 +232,35 @@ bool DBIter::SetValueAndColumnsFromEntity(Slice slice) {
     return false;
   }
 
-  if (!wide_columns_.empty() &&
-      wide_columns_[0].name() == kDefaultWideColumnName) {
-    value_ = wide_columns_[0].value();
+  if (WideColumnsHelper::HasDefaultColumn(wide_columns_)) {
+    value_ = WideColumnsHelper::GetDefaultColumn(wide_columns_);
+  }
+
+  return true;
+}
+
+bool DBIter::SetValueAndColumnsFromMergeResult(const Status& merge_status,
+                                               ValueType result_type) {
+  if (!merge_status.ok()) {
+    valid_ = false;
+    status_ = merge_status;
+    return false;
+  }
+
+  if (result_type == kTypeWideColumnEntity) {
+    if (!SetValueAndColumnsFromEntity(saved_value_)) {
+      assert(!valid_);
+      return false;
+    }
+
+    valid_ = true;
+    return true;
   }
 
+  assert(result_type == kTypeValue);
+  SetValueAndColumnsFromPlain(pinned_value_.data() ? pinned_value_
+                                                   : saved_value_);
+  valid_ = true;
   return true;
 }
 
@@ -554,8 +580,7 @@ bool DBIter::MergeValuesNewToOld() {
     if (kTypeValue == ikey.type) {
       // hit a put, merge the put value with operands and store the
       // final result in saved_value_. We are done!
-      const Slice val = iter_.value();
-      if (!Merge(&val, ikey.user_key)) {
+      if (!MergeWithPlainBaseValue(iter_.value(), ikey.user_key)) {
         return false;
       }
       // iter_ is positioned after put
@@ -584,7 +609,7 @@ bool DBIter::MergeValuesNewToOld() {
         return false;
       }
       valid_ = true;
-      if (!Merge(&blob_value_, ikey.user_key)) {
+      if (!MergeWithPlainBaseValue(blob_value_, ikey.user_key)) {
         return false;
       }
 
@@ -598,7 +623,7 @@ bool DBIter::MergeValuesNewToOld() {
       }
       return true;
     } else if (kTypeWideColumnEntity == ikey.type) {
-      if (!MergeEntity(iter_.value(), ikey.user_key)) {
+      if (!MergeWithWideColumnBaseValue(iter_.value(), ikey.user_key)) {
         return false;
       }
 
@@ -628,7 +653,7 @@ bool DBIter::MergeValuesNewToOld() {
   // a deletion marker.
   // feed null as the existing value to the merge operator, such that
   // client can differentiate this scenario and do things accordingly.
-  if (!Merge(nullptr, saved_key_.GetUserKey())) {
+  if (!MergeWithNoBaseValue(saved_key_.GetUserKey())) {
     return false;
   }
   assert(status_.ok());
@@ -719,15 +744,22 @@ bool DBIter::ReverseToBackward() {
   // When current_entry_is_merged_ is true, iter_ may be positioned on the next
   // key, which may not exist or may have prefix different from current.
   // If that's the case, seek to saved_key_.
-  if (current_entry_is_merged_ &&
-      (!expect_total_order_inner_iter() || !iter_.Valid())) {
+  //
+  // In case of auto_readahead_size enabled, index_iter moves forward during
+  // forward scan for block cache lookup and points to different block. If Prev
+  // op is called, it needs to call SeekForPrev to point to right index_iter_ in
+  // BlockBasedTableIterator. This only happens when direction is changed from
+  // forward to backward.
+  if ((current_entry_is_merged_ &&
+       (!expect_total_order_inner_iter() || !iter_.Valid())) ||
+      auto_readahead_size_) {
     IterKey last_key;
     // Using kMaxSequenceNumber and kValueTypeForSeek
     // (not kValueTypeForSeekForPrev) to seek to a key strictly smaller
     // than saved_key_.
     last_key.SetInternalKey(ParsedInternalKey(
         saved_key_.GetUserKey(), kMaxSequenceNumber, kValueTypeForSeek));
-    if (!expect_total_order_inner_iter()) {
+    if (!expect_total_order_inner_iter() || auto_readahead_size_) {
       iter_.SeekForPrev(last_key.GetInternalKey());
     } else {
       // Some iterators may not support SeekForPrev(), so we avoid using it
@@ -979,7 +1011,7 @@ bool DBIter::FindValueForCurrentKey() {
       if (last_not_merge_type == kTypeDeletion ||
           last_not_merge_type == kTypeSingleDeletion ||
           last_not_merge_type == kTypeDeletionWithTimestamp) {
-        if (!Merge(nullptr, saved_key_.GetUserKey())) {
+        if (!MergeWithNoBaseValue(saved_key_.GetUserKey())) {
           return false;
         }
         return true;
@@ -994,7 +1026,7 @@ bool DBIter::FindValueForCurrentKey() {
           return false;
         }
         valid_ = true;
-        if (!Merge(&blob_value_, saved_key_.GetUserKey())) {
+        if (!MergeWithPlainBaseValue(blob_value_, saved_key_.GetUserKey())) {
           return false;
         }
 
@@ -1002,14 +1034,15 @@ bool DBIter::FindValueForCurrentKey() {
 
         return true;
       } else if (last_not_merge_type == kTypeWideColumnEntity) {
-        if (!MergeEntity(pinned_value_, saved_key_.GetUserKey())) {
+        if (!MergeWithWideColumnBaseValue(pinned_value_,
+                                          saved_key_.GetUserKey())) {
           return false;
         }
 
         return true;
       } else {
         assert(last_not_merge_type == kTypeValue);
-        if (!Merge(&pinned_value_, saved_key_.GetUserKey())) {
+        if (!MergeWithPlainBaseValue(pinned_value_, saved_key_.GetUserKey())) {
           return false;
         }
         return true;
@@ -1185,8 +1218,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
     }
 
     if (ikey.type == kTypeValue) {
-      const Slice val = iter_.value();
-      if (!Merge(&val, saved_key_.GetUserKey())) {
+      if (!MergeWithPlainBaseValue(iter_.value(), saved_key_.GetUserKey())) {
         return false;
       }
       return true;
@@ -1205,7 +1237,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
         return false;
       }
       valid_ = true;
-      if (!Merge(&blob_value_, saved_key_.GetUserKey())) {
+      if (!MergeWithPlainBaseValue(blob_value_, saved_key_.GetUserKey())) {
         return false;
       }
 
@@ -1213,7 +1245,8 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
 
       return true;
     } else if (ikey.type == kTypeWideColumnEntity) {
-      if (!MergeEntity(iter_.value(), saved_key_.GetUserKey())) {
+      if (!MergeWithWideColumnBaseValue(iter_.value(),
+                                        saved_key_.GetUserKey())) {
         return false;
       }
 
@@ -1227,7 +1260,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
     }
   }
 
-  if (!Merge(nullptr, saved_key_.GetUserKey())) {
+  if (!MergeWithNoBaseValue(saved_key_.GetUserKey())) {
     return false;
   }
 
@@ -1250,47 +1283,42 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
   return true;
 }
 
-bool DBIter::Merge(const Slice* val, const Slice& user_key) {
+bool DBIter::MergeWithNoBaseValue(const Slice& user_key) {
   // `op_failure_scope` (an output parameter) is not provided (set to nullptr)
   // since a failure must be propagated regardless of its value.
-  Status s = MergeHelper::TimedFullMerge(
-      merge_operator_, user_key, val, merge_context_.GetOperands(),
-      &saved_value_, logger_, statistics_, clock_, &pinned_value_,
-      /* update_num_ops_stats */ true,
-      /* op_failure_scope */ nullptr);
-  if (!s.ok()) {
-    valid_ = false;
-    status_ = s;
-    return false;
-  }
-
-  SetValueAndColumnsFromPlain(pinned_value_.data() ? pinned_value_
-                                                   : saved_value_);
-
-  valid_ = true;
-  return true;
+  ValueType result_type;
+  const Status s = MergeHelper::TimedFullMerge(
+      merge_operator_, user_key, MergeHelper::kNoBaseValue,
+      merge_context_.GetOperands(), logger_, statistics_, clock_,
+      /* update_num_ops_stats */ true, &saved_value_, &pinned_value_,
+      &result_type, /* op_failure_scope */ nullptr);
+  return SetValueAndColumnsFromMergeResult(s, result_type);
 }
 
-bool DBIter::MergeEntity(const Slice& entity, const Slice& user_key) {
+bool DBIter::MergeWithPlainBaseValue(const Slice& value,
+                                     const Slice& user_key) {
   // `op_failure_scope` (an output parameter) is not provided (set to nullptr)
   // since a failure must be propagated regardless of its value.
-  Status s = MergeHelper::TimedFullMergeWithEntity(
-      merge_operator_, user_key, entity, merge_context_.GetOperands(),
-      &saved_value_, logger_, statistics_, clock_,
-      /* update_num_ops_stats */ true,
-      /* op_failure_scope */ nullptr);
-  if (!s.ok()) {
-    valid_ = false;
-    status_ = s;
-    return false;
-  }
-
-  if (!SetValueAndColumnsFromEntity(saved_value_)) {
-    return false;
-  }
+  ValueType result_type;
+  const Status s = MergeHelper::TimedFullMerge(
+      merge_operator_, user_key, MergeHelper::kPlainBaseValue, value,
+      merge_context_.GetOperands(), logger_, statistics_, clock_,
+      /* update_num_ops_stats */ true, &saved_value_, &pinned_value_,
+      &result_type, /* op_failure_scope */ nullptr);
+  return SetValueAndColumnsFromMergeResult(s, result_type);
+}
 
-  valid_ = true;
-  return true;
+bool DBIter::MergeWithWideColumnBaseValue(const Slice& entity,
+                                          const Slice& user_key) {
+  // `op_failure_scope` (an output parameter) is not provided (set to nullptr)
+  // since a failure must be propagated regardless of its value.
+  ValueType result_type;
+  const Status s = MergeHelper::TimedFullMerge(
+      merge_operator_, user_key, MergeHelper::kWideBaseValue, entity,
+      merge_context_.GetOperands(), logger_, statistics_, clock_,
+      /* update_num_ops_stats */ true, &saved_value_, &pinned_value_,
+      &result_type, /* op_failure_scope */ nullptr);
+  return SetValueAndColumnsFromMergeResult(s, result_type);
 }
 
 // Move backwards until the key smaller than saved_key_.

package/deps/rocksdb/rocksdb/db/db_iter.h

@@ -209,6 +209,7 @@ class DBIter final : public Iterator {
     if (read_callback_) {
       read_callback_->Refresh(s);
     }
+    iter_.SetRangeDelReadSeqno(s);
   }
   void set_valid(bool v) { valid_ = v; }
 
@@ -312,14 +313,20 @@ class DBIter final : public Iterator {
 
   bool SetValueAndColumnsFromEntity(Slice slice);
 
+  bool SetValueAndColumnsFromMergeResult(const Status& merge_status,
+                                         ValueType result_type);
+
   void ResetValueAndColumns() {
     value_.clear();
     wide_columns_.clear();
   }
 
+  // The following methods perform the actual merge operation for the
+  // no base value/plain base value/wide-column base value cases.
   // If user-defined timestamp is enabled, `user_key` includes timestamp.
-  bool Merge(const Slice* val, const Slice& user_key);
-  bool MergeEntity(const Slice& entity, const Slice& user_key);
+  bool MergeWithNoBaseValue(const Slice& user_key);
+  bool MergeWithPlainBaseValue(const Slice& value, const Slice& user_key);
+  bool MergeWithWideColumnBaseValue(const Slice& entity, const Slice& user_key);
 
   const SliceTransform* prefix_extractor_;
   Env* const env_;
@@ -384,6 +391,7 @@ class DBIter final : public Iterator {
   bool expose_blob_index_;
   bool is_blob_;
   bool arena_mode_;
+  const Env::IOActivity io_activity_;
   // List of operands for merge operator.
   MergeContext merge_context_;
   LocalStatistics local_stats_;
@@ -394,6 +402,7 @@ class DBIter final : public Iterator {
   const Slice* const timestamp_lb_;
   const size_t timestamp_size_;
   std::string saved_timestamp_;
+  bool auto_readahead_size_;
 };
 
 // Return a new iterator that converts internal keys (yielded by

package/deps/rocksdb/rocksdb/db/db_iter_test.cc

@@ -275,6 +275,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     db_iter->Next();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
   // Test to check the SeekToLast() with iterate_upper_bound not set
   {
@@ -1415,6 +1416,7 @@ TEST_F(DBIteratorTest, DBIterator1) {
   ASSERT_EQ(db_iter->key().ToString(), "b");
   db_iter->Next();
   ASSERT_FALSE(db_iter->Valid());
+  ASSERT_OK(db_iter->status());
 }
 
 TEST_F(DBIteratorTest, DBIterator2) {
@@ -1528,6 +1530,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1552,6 +1555,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1,merge_2");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1576,6 +1580,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1,merge_2,merge_3");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1600,6 +1605,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     ASSERT_EQ(db_iter->value().ToString(), "put_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1624,6 +1630,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     ASSERT_EQ(db_iter->value().ToString(), "put_1,merge_4");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1648,6 +1655,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     ASSERT_EQ(db_iter->value().ToString(), "put_1,merge_4,merge_5");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1672,6 +1680,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
     ASSERT_EQ(db_iter->value().ToString(), "put_1,merge_4,merge_5,merge_6");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1726,6 +1735,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1750,6 +1760,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1,merge_2");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1774,6 +1785,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1,merge_2,merge_3");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1794,6 +1806,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
         nullptr /* read_callback */));
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1818,6 +1831,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_4");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1842,6 +1856,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_4,merge_5");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1866,6 +1881,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_4,merge_5,merge_6");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 }
 
@@ -1910,6 +1926,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1952,6 +1969,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -1994,6 +2012,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -2041,6 +2060,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -2089,6 +2109,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -2131,6 +2152,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -2179,6 +2201,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -2228,6 +2251,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 
   {
@@ -2271,6 +2295,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
     ASSERT_EQ(db_iter->value().ToString(), "merge_1");
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
+    ASSERT_OK(db_iter->status());
   }
 }
 
@@ -2440,6 +2465,7 @@ TEST_F(DBIteratorTest, SeekToLastOccurrenceSeq0) {
   ASSERT_EQ(db_iter->value().ToString(), "2");
   db_iter->Next();
   ASSERT_FALSE(db_iter->Valid());
+  ASSERT_OK(db_iter->status());
 }
 
 TEST_F(DBIteratorTest, DBIterator11) {
@@ -2469,6 +2495,7 @@ TEST_F(DBIteratorTest, DBIterator11) {
   ASSERT_EQ(db_iter->key().ToString(), "b");
   db_iter->Next();
   ASSERT_FALSE(db_iter->Valid());
+  ASSERT_OK(db_iter->status());
 }
 
 TEST_F(DBIteratorTest, DBIterator12) {
@@ -2497,6 +2524,7 @@ TEST_F(DBIteratorTest, DBIterator12) {
   ASSERT_EQ(db_iter->value().ToString(), "1");
   db_iter->Prev();
   ASSERT_FALSE(db_iter->Valid());
+  ASSERT_OK(db_iter->status());
 }
 
 TEST_F(DBIteratorTest, DBIterator13) {
@@ -2635,6 +2663,7 @@ TEST_F(DBIterWithMergeIterTest, InnerMergeIterator1) {
   ASSERT_EQ(db_iter_->value().ToString(), "3");
   db_iter_->Next();
   ASSERT_FALSE(db_iter_->Valid());
+  ASSERT_OK(db_iter_->status());
 }
 
 TEST_F(DBIterWithMergeIterTest, InnerMergeIterator2) {