Bump version to 5.14.2 and update HISTORY

Summary:
Now by default, with NewSstFileManager, checkpoints may be corrupted. Disable this feature to avoid this issue.
Closes https://github.com/facebook/rocksdb/pull/4092

Differential Revision: D8729856

Pulled By: siying

fbshipit-source-id: 914c321d6eaf52d8c5981171322d85dd29088307

CMakeLists.txt

@@ -657,8 +657,6 @@ set(SOURCES
         utilities/transactions/transaction_util.cc
         utilities/transactions/write_prepared_txn.cc
         utilities/transactions/write_prepared_txn_db.cc
-        utilities/transactions/write_unprepared_txn.cc
-        utilities/transactions/write_unprepared_txn_db.cc
         utilities/ttl/db_ttl_impl.cc
         utilities/write_batch_with_index/write_batch_with_index.cc
         utilities/write_batch_with_index/write_batch_with_index_internal.cc

HISTORY.md

@@ -1,14 +1,13 @@
 # Rocksdb Change Log
-## Unreleased
-### Public API Change
-* For users of `Statistics` objects created via `CreateDBStatistics()`, the format of the string returned by its `ToString()` method has changed.
-* With LRUCache, when high_pri_pool_ratio > 0, midpoint insertion strategy will be enabled to put low-pri items to the tail of low-pri list (the midpoint) when they first inserted into the cache. This is to make cache entries never get hit age out faster, improving cache efficiency when large background scan presents.
-
-### New Features
-* Changes the format of index blocks by storing the key in their raw form rather than converting them to InternalKey. This saves 8 bytes per index key. The feature is backward compatbile but not forward compatible. It is disabled by default unless format_version 3 or above is used.
-
+## 5.14.2 (7/3/2018)
 ### Bug Fixes
-* fix deadlock with enable_pipelined_write=true and max_successive_merges > 0
+* Change default value of `bytes_max_delete_chunk` to 0 in NewSstFileManager() as it doesn't work well with checkpoints.
+* Set DEBUG_LEVEL=0 for RocksJava Mac Release build.
+
+## 5.14.1 (6/20/2018)
+### Bug Fixes
+* Fix block-based table reader pinning blocks throughout its lifetime, causing memory usage increase.
+* Fix bug with prefix search in partition filters where a shared prefix would be ignored from the later partitions. The bug could report an eixstent key as missing. The bug could be triggered if prefix_extractor is set and partition filters is enabled.
 
 ## 5.14.0 (5/16/2018)
 ### Public API Change
@@ -20,7 +19,6 @@
 * Now, `DBOptions::use_direct_io_for_flush_and_compaction` only applies to background writes, and `DBOptions::use_direct_reads` applies to both user reads and background reads. This conforms with Linux's `open(2)` manpage, which advises against simultaneously reading a file in buffered and direct modes, due to possibly undefined behavior and degraded performance.
 * Iterator::Valid() always returns false if !status().ok(). So, now when doing a Seek() followed by some Next()s, there's no need to check status() after every operation.
 * Iterator::Seek()/SeekForPrev()/SeekToFirst()/SeekToLast() always resets status().
-* Introduced `CompressionOptions::kDefaultCompressionLevel`, which is a generic way to tell RocksDB to use the compression library's default level. It is now the default value for `CompressionOptions::level`. Previously the level defaulted to -1, which gave poor compression ratios in ZSTD.
 
 ### New Features
 * Introduce TTL for level compaction so that all files older than ttl go through the compaction process to get rid of old data.
@@ -29,7 +27,6 @@
 * Add `Env::LowerThreadPoolCPUPriority(Priority)` method, which lowers the CPU priority of background (esp. compaction) threads to minimize interference with foreground tasks.
 * Fsync parent directory after deleting a file in delete scheduler.
 * In level-based compaction, if bottom-pri thread pool was setup via `Env::SetBackgroundThreads()`, compactions to the bottom level will be delegated to that thread pool.
-* `prefix_extractor` has been moved from ImmutableCFOptions to MutableCFOptions, meaning it can be dynamically changed without a DB restart.
 
 ### Bug Fixes
 * Fsync after writing global seq number to the ingestion file in ExternalSstFileIngestionJob.
@@ -37,7 +34,7 @@
 * Fix `BackupableDBOptions::max_valid_backups_to_open` to not delete backup files when refcount cannot be accurately determined.
 * Fix memory leak when pin_l0_filter_and_index_blocks_in_cache is used with partitioned filters
 * Disable rollback of merge operands in WritePrepared transactions to work around an issue in MyRocks. It can be enabled back by setting TransactionDBOptions::rollback_merge_operands to true.
-* Fix wrong results by ReverseBytewiseComparator::FindShortSuccessor()
+* Fix bug with prefix search in partition filters where a shared prefix would be ignored from the later partitions. The bug could report an eixstent key as missing. The bug could be triggered if prefix_extractor is set and partition filters is enabled.
 
 ### Java API Changes
 * Add `BlockBasedTableConfig.setBlockCache` to allow sharing a block cache across DB instances.

Makefile

@@ -85,6 +85,10 @@ ifeq ($(MAKECMDGOALS),rocksdbjavastaticrelease)
 	DEBUG_LEVEL=0
 endif
 
+ifeq ($(MAKECMDGOALS),rocksdbjavastaticreleasedocker)
+        DEBUG_LEVEL=0
+endif
+
 ifeq ($(MAKECMDGOALS),rocksdbjavastaticpublish)
 	DEBUG_LEVEL=0
 endif

TARGETS

@@ -28,7 +28,7 @@ rocksdb_compiler_flags = [
     # Added missing flags from output of build_detect_platform
     "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
     "-DROCKSDB_BACKTRACE",
-    "-Wshorten-64-to-32",
+    "-Wnarrowing",
 ]
 
 rocksdb_external_deps = [
@@ -280,8 +280,6 @@ cpp_library(
         "utilities/transactions/transaction_util.cc",
         "utilities/transactions/write_prepared_txn.cc",
         "utilities/transactions/write_prepared_txn_db.cc",
-        "utilities/transactions/write_unprepared_txn.cc",
-        "utilities/transactions/write_unprepared_txn_db.cc",
         "utilities/ttl/db_ttl_impl.cc",
         "utilities/write_batch_with_index/write_batch_with_index.cc",
         "utilities/write_batch_with_index/write_batch_with_index_internal.cc",
@@ -558,13 +556,13 @@ ROCKS_TESTS = [
         "serial",
     ],
     [
-        "db_iter_test",
-        "db/db_iter_test.cc",
+        "db_iter_stress_test",
+        "db/db_iter_stress_test.cc",
         "serial",
     ],
     [
-        "db_iter_stress_test",
-        "db/db_iter_stress_test.cc",
+        "db_iter_test",
+        "db/db_iter_test.cc",
         "serial",
     ],
     [

buckifier/targets_cfg.py

@@ -32,7 +32,7 @@ rocksdb_compiler_flags = [
     # Added missing flags from output of build_detect_platform
     "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
     "-DROCKSDB_BACKTRACE",
-    "-Wshorten-64-to-32",
+    "-Wnarrowing",
 ]
 
 rocksdb_external_deps = [

cache/lru_cache.cc

@@ -99,20 +99,14 @@ void LRUHandleTable::Resize() {
   length_ = new_length;
 }
 
-LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                             double high_pri_pool_ratio)
-    : capacity_(0),
-      high_pri_pool_usage_(0),
-      strict_capacity_limit_(strict_capacity_limit),
-      high_pri_pool_ratio_(high_pri_pool_ratio),
-      high_pri_pool_capacity_(0),
-      usage_(0),
+LRUCacheShard::LRUCacheShard()
+    : capacity_(0), high_pri_pool_usage_(0), strict_capacity_limit_(false),
+      high_pri_pool_ratio_(0), high_pri_pool_capacity_(0), usage_(0),
       lru_usage_(0) {
   // Make empty circular linked list
   lru_.next = &lru_;
   lru_.prev = &lru_;
   lru_low_pri_ = &lru_;
-  SetCapacity(capacity);
 }
 
 LRUCacheShard::~LRUCacheShard() {}
@@ -199,7 +193,7 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
 void LRUCacheShard::LRU_Insert(LRUHandle* e) {
   assert(e->next == nullptr);
   assert(e->prev == nullptr);
-  if (high_pri_pool_ratio_ > 0 && (e->IsHighPri() || e->HasHit())) {
+  if (high_pri_pool_ratio_ > 0 && e->IsHighPri()) {
     // Inset "e" to head of LRU list.
     e->next = &lru_;
     e->prev = lru_.prev;
@@ -246,6 +240,22 @@ void LRUCacheShard::EvictFromLRU(size_t charge,
   }
 }
 
+void* LRUCacheShard::operator new(size_t size) {
+  return port::cacheline_aligned_alloc(size);
+}
+
+void* LRUCacheShard::operator new[](size_t size) {
+  return port::cacheline_aligned_alloc(size);
+}
+
+void LRUCacheShard::operator delete(void *memblock) {
+  port::cacheline_aligned_free(memblock);
+}
+
+void LRUCacheShard::operator delete[](void* memblock) {
+  port::cacheline_aligned_free(memblock);
+}
+
 void LRUCacheShard::SetCapacity(size_t capacity) {
   autovector<LRUHandle*> last_reference_list;
   {
@@ -275,7 +285,6 @@ Cache::Handle* LRUCacheShard::Lookup(const Slice& key, uint32_t hash) {
       LRU_Remove(e);
     }
     e->refs++;
-    e->SetHit();
   }
   return reinterpret_cast<Cache::Handle*>(e);
 }
@@ -464,24 +473,15 @@ LRUCache::LRUCache(size_t capacity, int num_shard_bits,
                    bool strict_capacity_limit, double high_pri_pool_ratio)
     : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
   num_shards_ = 1 << num_shard_bits;
-  shards_ = reinterpret_cast<LRUCacheShard*>(
-      port::cacheline_aligned_alloc(sizeof(LRUCacheShard) * num_shards_));
-  size_t per_shard = (capacity + (num_shards_ - 1)) / num_shards_;
+  shards_ = new LRUCacheShard[num_shards_];
+  SetCapacity(capacity);
+  SetStrictCapacityLimit(strict_capacity_limit);
   for (int i = 0; i < num_shards_; i++) {
-    new (&shards_[i])
-        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio);
+    shards_[i].SetHighPriorityPoolRatio(high_pri_pool_ratio);
   }
 }
 
-LRUCache::~LRUCache() {
-  if (shards_ != nullptr) {
-    assert(num_shards_ > 0);
-    for (int i = 0; i < num_shards_; i++) {
-      shards_[i].~LRUCacheShard();
-    }
-    port::cacheline_aligned_free(shards_);
-  }
-}
+LRUCache::~LRUCache() { delete[] shards_; }
 
 CacheShard* LRUCache::GetShard(int shard) {
   return reinterpret_cast<CacheShard*>(&shards_[shard]);
@@ -507,7 +507,6 @@ void LRUCache::DisownData() {
 // Do not drop data if compile with ASAN to suppress leak warning.
 #ifndef __SANITIZE_ADDRESS__
   shards_ = nullptr;
-  num_shards_ = 0;
 #endif  // !__SANITIZE_ADDRESS__
 }
 

cache/lru_cache.h

@@ -77,7 +77,6 @@ struct LRUHandle {
   bool InCache() { return flags & 1; }
   bool IsHighPri() { return flags & 2; }
   bool InHighPriPool() { return flags & 4; }
-  bool HasHit() { return flags & 8; }
 
   void SetInCache(bool in_cache) {
     if (in_cache) {
@@ -103,8 +102,6 @@ struct LRUHandle {
     }
   }
 
-  void SetHit() { flags |= 8; }
-
   void Free() {
     assert((refs == 1 && InCache()) || (refs == 0 && !InCache()));
     if (deleter) {
@@ -159,8 +156,7 @@ class LRUHandleTable {
 // A single shard of sharded cache.
 class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
  public:
-  LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                double high_pri_pool_ratio);
+  LRUCacheShard();
   virtual ~LRUCacheShard();
 
   // Separate from constructor so caller can easily make an array of LRUCache
@@ -209,6 +205,15 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
   //  Retrives high pri pool ratio
   double GetHighPriPoolRatio();
 
+  // Overloading to aligned it to cache line size
+  void* operator new(size_t);
+
+  void* operator new[](size_t);
+
+  void operator delete(void *);
+
+  void operator delete[](void*);
+
  private:
   void LRU_Remove(LRUHandle* e);
   void LRU_Insert(LRUHandle* e);
@@ -295,7 +300,7 @@ class LRUCache : public ShardedCache {
   double GetHighPriPoolRatio();
 
  private:
-  LRUCacheShard* shards_ = nullptr;
+  LRUCacheShard* shards_;
   int num_shards_ = 0;
 };
 

cache/lru_cache_test.cc

@@ -7,7 +7,6 @@
 
 #include <string>
 #include <vector>
-#include "port/port.h"
 #include "util/testharness.h"
 
 namespace rocksdb {
@@ -15,22 +14,22 @@ namespace rocksdb {
 class LRUCacheTest : public testing::Test {
  public:
   LRUCacheTest() {}
-  ~LRUCacheTest() { DeleteCache(); }
-
-  void DeleteCache() {
-    if (cache_ != nullptr) {
-      cache_->~LRUCacheShard();
-      port::cacheline_aligned_free(cache_);
-      cache_ = nullptr;
-    }
-  }
+  ~LRUCacheTest() {}
 
   void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0) {
-    DeleteCache();
-    cache_ = reinterpret_cast<LRUCacheShard*>(
-        port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
-    new (cache_) LRUCacheShard(capacity, false /*strict_capcity_limit*/,
-                               high_pri_pool_ratio);
+    cache_.reset(
+#if defined(_MSC_VER)
+#pragma warning(push)
+#pragma warning(disable: 4316) // We've validated the alignment with the new operators
+#endif
+      new LRUCacheShard()
+#if defined(_MSC_VER)
+#pragma warning(pop)
+#endif
+    );
+    cache_->SetCapacity(capacity);
+    cache_->SetStrictCapacityLimit(false);
+    cache_->SetHighPriorityPoolRatio(high_pri_pool_ratio);
   }
 
   void Insert(const std::string& key,
@@ -86,7 +85,7 @@ class LRUCacheTest : public testing::Test {
   }
 
  private:
-  LRUCacheShard* cache_ = nullptr;
+  std::unique_ptr<LRUCacheShard> cache_;
 };
 
 TEST_F(LRUCacheTest, BasicLRU) {
@@ -115,30 +114,7 @@ TEST_F(LRUCacheTest, BasicLRU) {
   ValidateLRUList({"e", "z", "d", "u", "v"});
 }
 
-TEST_F(LRUCacheTest, MidpointInsertion) {
-  // Allocate 2 cache entries to high-pri pool.
-  NewCache(5, 0.45);
-
-  Insert("a", Cache::Priority::LOW);
-  Insert("b", Cache::Priority::LOW);
-  Insert("c", Cache::Priority::LOW);
-  Insert("x", Cache::Priority::HIGH);
-  Insert("y", Cache::Priority::HIGH);
-  ValidateLRUList({"a", "b", "c", "x", "y"}, 2);
-
-  // Low-pri entries inserted to the tail of low-pri list (the midpoint).
-  // After lookup, it will move to the tail of the full list.
-  Insert("d", Cache::Priority::LOW);
-  ValidateLRUList({"b", "c", "d", "x", "y"}, 2);
-  ASSERT_TRUE(Lookup("d"));
-  ValidateLRUList({"b", "c", "x", "y", "d"}, 2);
-
-  // High-pri entries will be inserted to the tail of full list.
-  Insert("z", Cache::Priority::HIGH);
-  ValidateLRUList({"c", "x", "y", "d", "z"}, 2);
-}
-
-TEST_F(LRUCacheTest, EntriesWithPriority) {
+TEST_F(LRUCacheTest, MidPointInsertion) {
   // Allocate 2 cache entries to high-pri pool.
   NewCache(5, 0.45);
 
@@ -164,15 +140,15 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   Insert("a", Cache::Priority::LOW);
   ValidateLRUList({"v", "X", "a", "Y", "Z"}, 2);
 
-  // Low-pri entries will be inserted to head of high-pri pool after lookup.
+  // Low-pri entries will be inserted to head of low-pri pool after lookup.
   ASSERT_TRUE(Lookup("v"));
-  ValidateLRUList({"X", "a", "Y", "Z", "v"}, 2);
+  ValidateLRUList({"X", "a", "v", "Y", "Z"}, 2);
 
   // High-pri entries will be inserted to the head of the list after lookup.
   ASSERT_TRUE(Lookup("X"));
-  ValidateLRUList({"a", "Y", "Z", "v", "X"}, 2);
+  ValidateLRUList({"a", "v", "Y", "Z", "X"}, 2);
   ASSERT_TRUE(Lookup("Z"));
-  ValidateLRUList({"a", "Y", "v", "X", "Z"}, 2);
+  ValidateLRUList({"a", "v", "Y", "X", "Z"}, 2);
 
   Erase("Y");
   ValidateLRUList({"a", "v", "X", "Z"}, 2);
@@ -185,7 +161,7 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   Insert("g", Cache::Priority::LOW);
   ValidateLRUList({"d", "e", "f", "g", "Z"}, 1);
   ASSERT_TRUE(Lookup("d"));
-  ValidateLRUList({"e", "f", "g", "Z", "d"}, 2);
+  ValidateLRUList({"e", "f", "g", "d", "Z"}, 1);
 }
 
 }  // namespace rocksdb

db/builder.cc

@@ -39,7 +39,7 @@ namespace rocksdb {
 class TableFactory;
 
 TableBuilder* NewTableBuilder(
-    const ImmutableCFOptions& ioptions, const MutableCFOptions& moptions,
+    const ImmutableCFOptions& ioptions,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
@@ -52,20 +52,19 @@ TableBuilder* NewTableBuilder(
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
   return ioptions.table_factory->NewTableBuilder(
-      TableBuilderOptions(ioptions, moptions, internal_comparator,
-                          int_tbl_prop_collector_factories, compression_type,
-                          compression_opts, compression_dict, skip_filters,
-                          column_family_name, level, creation_time,
-                          oldest_key_time),
+      TableBuilderOptions(
+          ioptions, internal_comparator, int_tbl_prop_collector_factories,
+          compression_type, compression_opts, compression_dict, skip_filters,
+          column_family_name, level, creation_time, oldest_key_time),
       column_family_id, file);
 }
 
 Status BuildTable(
     const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
-    TableCache* table_cache, InternalIterator* iter,
-    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
-    const InternalKeyComparator& internal_comparator,
+    const MutableCFOptions& /*mutable_cf_options*/,
+    const EnvOptions& env_options, TableCache* table_cache,
+    InternalIterator* iter, std::unique_ptr<InternalIterator> range_del_iter,
+    FileMetaData* meta, const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
@@ -123,11 +122,10 @@ Status BuildTable(
       file_writer.reset(new WritableFileWriter(std::move(file), env_options,
                                                ioptions.statistics));
       builder = NewTableBuilder(
-          ioptions, mutable_cf_options, internal_comparator,
-          int_tbl_prop_collector_factories, column_family_id,
-          column_family_name, file_writer.get(), compression, compression_opts,
-          level, nullptr /* compression_dict */, false /* skip_filters */,
-          creation_time, oldest_key_time);
+          ioptions, internal_comparator, int_tbl_prop_collector_factories,
+          column_family_id, column_family_name, file_writer.get(), compression,
+          compression_opts, level, nullptr /* compression_dict */,
+          false /* skip_filters */, creation_time, oldest_key_time);
     }
 
     MergeHelper merge(env, internal_comparator.user_comparator(),
@@ -197,8 +195,7 @@ Status BuildTable(
       // to cache it here for further user reads
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
           ReadOptions(), env_options, internal_comparator, meta->fd,
-          nullptr /* range_del_agg */,
-          mutable_cf_options.prefix_extractor.get(), nullptr,
+          nullptr /* range_del_agg */, nullptr,
           (internal_stats == nullptr) ? nullptr
                                       : internal_stats->GetFileReadHist(0),
           false /* for_compaction */, nullptr /* arena */,

db/builder.h

@@ -43,7 +43,7 @@ class InternalIterator;
 // @param compression_dict Data for presetting the compression library's
 //    dictionary, or nullptr.
 TableBuilder* NewTableBuilder(
-    const ImmutableCFOptions& options, const MutableCFOptions& moptions,
+    const ImmutableCFOptions& options,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,

db/c.cc

@@ -90,7 +90,6 @@ using rocksdb::LiveFileMetaData;
 using rocksdb::BackupEngine;
 using rocksdb::BackupableDBOptions;
 using rocksdb::BackupInfo;
-using rocksdb::BackupID;
 using rocksdb::RestoreOptions;
 using rocksdb::CompactRangeOptions;
 using rocksdb::RateLimiter;
@@ -532,18 +531,10 @@ rocksdb_backup_engine_t* rocksdb_backup_engine_open(
 }
 
 void rocksdb_backup_engine_create_new_backup(rocksdb_backup_engine_t* be,
-                                             rocksdb_t* db,
-                                             char** errptr) {
+                                             rocksdb_t* db, char** errptr) {
   SaveError(errptr, be->rep->CreateNewBackup(db->rep));
 }
 
-void rocksdb_backup_engine_create_new_backup_flush(rocksdb_backup_engine_t* be,
-                                                   rocksdb_t* db,
-                                                   unsigned char flush_before_backup,
-                                                   char** errptr) {
-  SaveError(errptr, be->rep->CreateNewBackup(db->rep, flush_before_backup));
-}
-
 void rocksdb_backup_engine_purge_old_backups(rocksdb_backup_engine_t* be,
                                              uint32_t num_backups_to_keep,
                                              char** errptr) {
@@ -563,12 +554,6 @@ void rocksdb_restore_options_set_keep_log_files(rocksdb_restore_options_t* opt,
   opt->rep.keep_log_files = v;
 }
 
-
-void rocksdb_backup_engine_verify_backup(rocksdb_backup_engine_t* be,
-    uint32_t backup_id, char** errptr) {
-  SaveError(errptr, be->rep->VerifyBackup(static_cast<BackupID>(backup_id)));
-}
-
 void rocksdb_backup_engine_restore_db_from_latest_backup(
     rocksdb_backup_engine_t* be, const char* db_dir, const char* wal_dir,
     const rocksdb_restore_options_t* restore_options, char** errptr) {

db/column_family_test.cc

@@ -299,9 +299,6 @@ class ColumnFamilyTest : public testing::Test {
   }
 
   void PutRandomData(int cf, int num, int key_value_size, bool save = false) {
-    if (cf >= static_cast<int>(keys_.size())) {
-      keys_.resize(cf + 1);
-    }
     for (int i = 0; i < num; ++i) {
       // 10 bytes for key, rest is value
       if (!save) {
@@ -309,7 +306,7 @@ class ColumnFamilyTest : public testing::Test {
                       RandomString(&rnd_, key_value_size - 10)));
       } else {
         std::string key = test::RandomKey(&rnd_, 11);
-        keys_[cf].insert(key);
+        keys_.insert(key);
         ASSERT_OK(Put(cf, key, RandomString(&rnd_, key_value_size - 10)));
       }
     }
@@ -509,7 +506,7 @@ class ColumnFamilyTest : public testing::Test {
 
   std::vector<ColumnFamilyHandle*> handles_;
   std::vector<std::string> names_;
-  std::vector<std::set<std::string>> keys_;
+  std::set<std::string> keys_;
   ColumnFamilyOptions column_family_options_;
   DBOptions db_options_;
   std::string dbname_;
@@ -1417,8 +1414,8 @@ TEST_F(ColumnFamilyTest, MultipleManualCompactions) {
   CompactAll(2);
   AssertFilesPerLevel("0,1", 2);
   // Compare against saved keys
-  std::set<std::string>::iterator key_iter = keys_[1].begin();
-  while (key_iter != keys_[1].end()) {
+  std::set<std::string>::iterator key_iter = keys_.begin();
+  while (key_iter != keys_.end()) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
@@ -1511,8 +1508,8 @@ TEST_F(ColumnFamilyTest, AutomaticAndManualCompactions) {
   CompactAll(2);
   AssertFilesPerLevel("0,1", 2);
   // Compare against saved keys
-  std::set<std::string>::iterator key_iter = keys_[1].begin();
-  while (key_iter != keys_[1].end()) {
+  std::set<std::string>::iterator key_iter = keys_.begin();
+  while (key_iter != keys_.end()) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
@@ -1607,8 +1604,8 @@ TEST_F(ColumnFamilyTest, ManualAndAutomaticCompactions) {
   CompactAll(2);
   AssertFilesPerLevel("0,1", 2);
   // Compare against saved keys
-  std::set<std::string>::iterator key_iter = keys_[1].begin();
-  while (key_iter != keys_[1].end()) {
+  std::set<std::string>::iterator key_iter = keys_.begin();
+  while (key_iter != keys_.end()) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
@@ -1706,8 +1703,8 @@ TEST_F(ColumnFamilyTest, SameCFManualManualCompactions) {
   ASSERT_LE(NumTableFilesAtLevel(0, 1), 2);
 
   // Compare against saved keys
-  std::set<std::string>::iterator key_iter = keys_[1].begin();
-  while (key_iter != keys_[1].end()) {
+  std::set<std::string>::iterator key_iter = keys_.begin();
+  while (key_iter != keys_.end()) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
@@ -1796,8 +1793,8 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
   ASSERT_LE(NumTableFilesAtLevel(0, 1), 2);
 
   // Compare against saved keys
-  std::set<std::string>::iterator key_iter = keys_[1].begin();
-  while (key_iter != keys_[1].end()) {
+  std::set<std::string>::iterator key_iter = keys_.begin();
+  while (key_iter != keys_.end()) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
@@ -1886,8 +1883,8 @@ TEST_F(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
   AssertFilesPerLevel("0,1", 1);
 
   // Compare against saved keys
-  std::set<std::string>::iterator key_iter = keys_[1].begin();
-  while (key_iter != keys_[1].end()) {
+  std::set<std::string>::iterator key_iter = keys_.begin();
+  while (key_iter != keys_.end()) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
@@ -1975,8 +1972,8 @@ TEST_F(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
   // VERIFY compaction "one"
   AssertFilesPerLevel("1", 1);
   // Compare against saved keys
-  std::set<std::string>::iterator key_iter = keys_[1].begin();
-  while (key_iter != keys_[1].end()) {
+  std::set<std::string>::iterator key_iter = keys_.begin();
+  while (key_iter != keys_.end()) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
@@ -2837,7 +2834,6 @@ TEST_F(ColumnFamilyTest, CreateDropAndDestroy) {
   ASSERT_OK(db_->DestroyColumnFamilyHandle(cfh));
 }
 
-#ifndef ROCKSDB_LITE
 TEST_F(ColumnFamilyTest, CreateDropAndDestroyWithoutFileDeletion) {
   ColumnFamilyHandle* cfh;
   Open();
@@ -2849,6 +2845,7 @@ TEST_F(ColumnFamilyTest, CreateDropAndDestroyWithoutFileDeletion) {
   ASSERT_OK(db_->DestroyColumnFamilyHandle(cfh));
 }
 
+#ifndef ROCKSDB_LITE
 TEST_F(ColumnFamilyTest, FlushCloseWALFiles) {
   SpecialEnv env(Env::Default());
   db_options_.env = &env;
@@ -3213,38 +3210,19 @@ TEST_F(ColumnFamilyTest, MultipleCFPathsTest) {
   CreateColumnFamilies({"one", "two"}, {cf_opt1, cf_opt2});
   Reopen({ColumnFamilyOptions(), cf_opt1, cf_opt2});
 
-  PutRandomData(1, 100, 100, true /* save */);
+  PutRandomData(1, 100, 100);
   Flush(1);
 
   // Check that files are generated in appropriate paths.
   ASSERT_EQ(1, GetSstFileCount(cf_opt1.cf_paths[0].path));
   ASSERT_EQ(0, GetSstFileCount(dbname_));
 
-  PutRandomData(2, 100, 100, true /* save */);
+  PutRandomData(2, 100, 100);
   Flush(2);
 
   ASSERT_EQ(1, GetSstFileCount(cf_opt2.cf_paths[0].path));
   ASSERT_EQ(0, GetSstFileCount(dbname_));
-
-  // Re-open and verify the keys.
-  Reopen({ColumnFamilyOptions(), cf_opt1, cf_opt2});
-  DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
-  for (int cf = 1; cf != 3; ++cf) {
-    ReadOptions read_options;
-    read_options.readahead_size = 0;
-    auto it = dbi->NewIterator(read_options, handles_[cf]);
-    for (it->SeekToFirst(); it->Valid(); it->Next()) {
-      Slice key(it->key());
-      ASSERT_NE(keys_[cf].end(), keys_[cf].find(key.ToString()));
-    }
-    delete it;
-
-    for (const auto& key : keys_[cf]) {
-      ASSERT_NE("NOT_FOUND", Get(cf, key));
-    }
-  }
 }
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/compacted_db_impl.cc

@@ -49,8 +49,8 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
                          GetContext::kNotFound, key, value, nullptr, nullptr,
                          nullptr, nullptr);
   LookupKey lkey(key, kMaxSequenceNumber);
-  files_.files[FindFile(key)].fd.table_reader->Get(options, lkey.internal_key(),
-                                                   &get_context, nullptr);
+  files_.files[FindFile(key)].fd.table_reader->Get(
+      options, lkey.internal_key(), &get_context);
   if (get_context.State() == GetContext::kFound) {
     return Status::OK();
   }
@@ -82,7 +82,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
                              GetContext::kNotFound, keys[idx], &pinnable_val,
                              nullptr, nullptr, nullptr, nullptr);
       LookupKey lkey(keys[idx], kMaxSequenceNumber);
-      r->Get(options, lkey.internal_key(), &get_context, nullptr);
+      r->Get(options, lkey.internal_key(), &get_context);
       value.assign(pinnable_val.data(), pinnable_val.size());
       if (get_context.State() == GetContext::kFound) {
         statuses[idx] = Status::OK();

db/compaction_job.cc

@@ -1183,9 +1183,7 @@ Status CompactionJob::FinishCompactionOutputFile(
     // to cache it here for further user reads
     InternalIterator* iter = cfd->table_cache()->NewIterator(
         ReadOptions(), env_options_, cfd->internal_comparator(), meta->fd,
-        nullptr /* range_del_agg */,
-        sub_compact->compaction->mutable_cf_options()->prefix_extractor.get(),
-        nullptr,
+        nullptr /* range_del_agg */, nullptr,
         cfd->internal_stats()->GetFileReadHist(
             compact_->compaction->output_level()),
         false, nullptr /* arena */, false /* skip_filters */,
@@ -1388,10 +1386,9 @@ Status CompactionJob::OpenCompactionOutputFile(
   }
 
   sub_compact->builder.reset(NewTableBuilder(
-      *cfd->ioptions(), *(sub_compact->compaction->mutable_cf_options()),
-      cfd->internal_comparator(), cfd->int_tbl_prop_collector_factories(),
-      cfd->GetID(), cfd->GetName(), sub_compact->outfile.get(),
-      sub_compact->compaction->output_compression(),
+      *cfd->ioptions(), cfd->internal_comparator(),
+      cfd->int_tbl_prop_collector_factories(), cfd->GetID(), cfd->GetName(),
+      sub_compact->outfile.get(), sub_compact->compaction->output_compression(),
       cfd->ioptions()->compression_opts,
       sub_compact->compaction->output_level(), &sub_compact->compression_dict,
       skip_filters, output_file_creation_time));

db/compaction_picker.cc

@@ -366,7 +366,7 @@ bool CompactionPicker::IsRangeInCompaction(VersionStorageInfo* vstorage,
   assert(level < NumberLevels());
 
   vstorage->GetOverlappingInputs(level, smallest, largest, &inputs,
-                                 level_index ? *level_index : 0, level_index);
+                                 *level_index, level_index);
   return AreFilesInCompaction(inputs);
 }
 
@@ -947,78 +947,6 @@ void CompactionPicker::UnregisterCompaction(Compaction* c) {
   compactions_in_progress_.erase(c);
 }
 
-void CompactionPicker::PickFilesMarkedForCompaction(
-    const std::string& cf_name, VersionStorageInfo* vstorage, int* start_level,
-    int* output_level, CompactionInputFiles* start_level_inputs) {
-  if (vstorage->FilesMarkedForCompaction().empty()) {
-    return;
-  }
-
-  auto continuation = [&, cf_name](std::pair<int, FileMetaData*> level_file) {
-    // If it's being compacted it has nothing to do here.
-    // If this assert() fails that means that some function marked some
-    // files as being_compacted, but didn't call ComputeCompactionScore()
-    assert(!level_file.second->being_compacted);
-    *start_level = level_file.first;
-    *output_level =
-        (*start_level == 0) ? vstorage->base_level() : *start_level + 1;
-
-    if (*start_level == 0 && !level0_compactions_in_progress()->empty()) {
-      return false;
-    }
-
-    start_level_inputs->files = {level_file.second};
-    start_level_inputs->level = *start_level;
-    return ExpandInputsToCleanCut(cf_name, vstorage, start_level_inputs);
-  };
-
-  // take a chance on a random file first
-  Random64 rnd(/* seed */ reinterpret_cast<uint64_t>(vstorage));
-  size_t random_file_index = static_cast<size_t>(rnd.Uniform(
-      static_cast<uint64_t>(vstorage->FilesMarkedForCompaction().size())));
-
-  if (continuation(vstorage->FilesMarkedForCompaction()[random_file_index])) {
-    // found the compaction!
-    return;
-  }
-
-  for (auto& level_file : vstorage->FilesMarkedForCompaction()) {
-    if (continuation(level_file)) {
-      // found the compaction!
-      return;
-    }
-  }
-  start_level_inputs->files.clear();
-}
-
-bool CompactionPicker::GetOverlappingL0Files(
-    VersionStorageInfo* vstorage, CompactionInputFiles* start_level_inputs,
-    int output_level, int* parent_index) {
-  // Two level 0 compaction won't run at the same time, so don't need to worry
-  // about files on level 0 being compacted.
-  assert(level0_compactions_in_progress()->empty());
-  InternalKey smallest, largest;
-  GetRange(*start_level_inputs, &smallest, &largest);
-  // Note that the next call will discard the file we placed in
-  // c->inputs_[0] earlier and replace it with an overlapping set
-  // which will include the picked file.
-  start_level_inputs->files.clear();
-  vstorage->GetOverlappingInputs(0, &smallest, &largest,
-                                 &(start_level_inputs->files));
-
-  // If we include more L0 files in the same compaction run it can
-  // cause the 'smallest' and 'largest' key to get extended to a
-  // larger range. So, re-invoke GetRange to get the new key range
-  GetRange(*start_level_inputs, &smallest, &largest);
-  if (IsRangeInCompaction(vstorage, &smallest, &largest, output_level,
-                          parent_index)) {
-    return false;
-  }
-  assert(!start_level_inputs->files.empty());
-
-  return true;
-}
-
 bool LevelCompactionPicker::NeedsCompaction(
     const VersionStorageInfo* vstorage) const {
   if (!vstorage->ExpiredTtlFiles().empty()) {
@@ -1090,6 +1018,9 @@ class LevelCompactionBuilder {
   // otherwise, returns false.
   bool PickIntraL0Compaction();
 
+  // If there is any file marked for compaction, put put it into inputs.
+  void PickFilesMarkedForCompaction();
+
   void PickExpiredTtlFiles();
 
   const std::string& cf_name_;
@@ -1118,6 +1049,50 @@ class LevelCompactionBuilder {
   static const int kMinFilesForIntraL0Compaction = 4;
 };
 
+void LevelCompactionBuilder::PickFilesMarkedForCompaction() {
+  if (vstorage_->FilesMarkedForCompaction().empty()) {
+    return;
+  }
+
+  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
+    // If it's being compacted it has nothing to do here.
+    // If this assert() fails that means that some function marked some
+    // files as being_compacted, but didn't call ComputeCompactionScore()
+    assert(!level_file.second->being_compacted);
+    start_level_ = level_file.first;
+    output_level_ =
+        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
+
+    if (start_level_ == 0 &&
+        !compaction_picker_->level0_compactions_in_progress()->empty()) {
+      return false;
+    }
+
+    start_level_inputs_.files = {level_file.second};
+    start_level_inputs_.level = start_level_;
+    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                      &start_level_inputs_);
+  };
+
+  // take a chance on a random file first
+  Random64 rnd(/* seed */ reinterpret_cast<uint64_t>(vstorage_));
+  size_t random_file_index = static_cast<size_t>(rnd.Uniform(
+      static_cast<uint64_t>(vstorage_->FilesMarkedForCompaction().size())));
+
+  if (continuation(vstorage_->FilesMarkedForCompaction()[random_file_index])) {
+    // found the compaction!
+    return;
+  }
+
+  for (auto& level_file : vstorage_->FilesMarkedForCompaction()) {
+    if (continuation(level_file)) {
+      // found the compaction!
+      return;
+    }
+  }
+  start_level_inputs_.files.clear();
+}
+
 void LevelCompactionBuilder::PickExpiredTtlFiles() {
   if (vstorage_->ExpiredTtlFiles().empty()) {
     return;
@@ -1207,9 +1182,7 @@ void LevelCompactionBuilder::SetupInitialFiles() {
   if (start_level_inputs_.empty()) {
     parent_index_ = base_index_ = -1;
 
-    // PickFilesMarkedForCompaction();
-    compaction_picker_->PickFilesMarkedForCompaction(
-        cf_name_, vstorage_, &start_level_, &output_level_, &start_level_inputs_);
+    PickFilesMarkedForCompaction();
     if (!start_level_inputs_.empty()) {
       is_manual_ = true;
       compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
@@ -1247,9 +1220,29 @@ void LevelCompactionBuilder::SetupInitialFiles() {
 
 bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
   if (start_level_ == 0 && output_level_ != 0) {
-    return compaction_picker_->GetOverlappingL0Files(
-        vstorage_, &start_level_inputs_, output_level_, &parent_index_);
+    // Two level 0 compaction won't run at the same time, so don't need to worry
+    // about files on level 0 being compacted.
+    assert(compaction_picker_->level0_compactions_in_progress()->empty());
+    InternalKey smallest, largest;
+    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
+    // Note that the next call will discard the file we placed in
+    // c->inputs_[0] earlier and replace it with an overlapping set
+    // which will include the picked file.
+    start_level_inputs_.files.clear();
+    vstorage_->GetOverlappingInputs(0, &smallest, &largest,
+                                    &start_level_inputs_.files);
+
+    // If we include more L0 files in the same compaction run it can
+    // cause the 'smallest' and 'largest' key to get extended to a
+    // larger range. So, re-invoke GetRange to get the new key range
+    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
+    if (compaction_picker_->IsRangeInCompaction(
+            vstorage_, &smallest, &largest, output_level_, &parent_index_)) {
+      return false;
+    }
   }
+  assert(!start_level_inputs_.files.empty());
+
   return true;
 }
 

db/compaction_picker.h

@@ -175,15 +175,6 @@ class CompactionPicker {
                        const CompactionInputFiles& output_level_inputs,
                        std::vector<FileMetaData*>* grandparents);
 
-  void PickFilesMarkedForCompaction(const std::string& cf_name,
-                                    VersionStorageInfo* vstorage,
-                                    int* start_level, int* output_level,
-                                    CompactionInputFiles* start_level_inputs);
-
-  bool GetOverlappingL0Files(VersionStorageInfo* vstorage,
-                             CompactionInputFiles* start_level_inputs,
-                             int output_level, int* parent_index);
-
   // Register this compaction in the set of running compactions
   void RegisterCompaction(Compaction* c);
 

db/compaction_picker_test.cc

@@ -391,10 +391,10 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
   NewVersionStorage(1, kCompactionStyleUniversal);
   UniversalCompactionPicker universal_compaction_picker(
       ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
             false);
+  UpdateVersionStorageInfo();
 
   // verify the trigger given different number of L0 files.
   for (int i = 1;
@@ -415,7 +415,6 @@ TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
   ioptions_.allow_ingest_behind = true;
   ioptions_.num_levels = 3;
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
             false);
@@ -449,7 +448,6 @@ TEST_F(CompactionPickerTest, CannotTrivialMoveUniversal) {
   mutable_cf_options_.compaction_options_universal.allow_trivial_move = true;
   NewVersionStorage(1, kCompactionStyleUniversal);
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-  UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(universal_compaction_picker.NeedsCompaction(vstorage_.get()),
             false);

db/compaction_picker_universal.cc

@@ -162,13 +162,7 @@ bool UniversalCompactionPicker::IsInputFilesNonOverlapping(Compaction* c) {
 bool UniversalCompactionPicker::NeedsCompaction(
     const VersionStorageInfo* vstorage) const {
   const int kLevel0 = 0;
-  if (vstorage->CompactionScore(kLevel0) >= 1) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  return false;
+  return vstorage->CompactionScore(kLevel0) >= 1;
 }
 
 void UniversalCompactionPicker::SortedRun::Dump(char* out_buf,
@@ -263,9 +257,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
       CalculateSortedRuns(*vstorage, ioptions_, mutable_cf_options);
 
   if (sorted_runs.size() == 0 ||
-      (vstorage->FilesMarkedForCompaction().empty() &&
-       sorted_runs.size() < (unsigned int)mutable_cf_options
-                                .level0_file_num_compaction_trigger)) {
+      sorted_runs.size() <
+          (unsigned int)mutable_cf_options.level0_file_num_compaction_trigger) {
     ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: nothing to do\n",
                      cf_name.c_str());
     TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
@@ -279,73 +272,58 @@ Compaction* UniversalCompactionPicker::PickCompaction(
       cf_name.c_str(), sorted_runs.size(), vstorage->LevelSummary(&tmp));
 
   // Check for size amplification first.
-  Compaction* c = nullptr;
-  if (sorted_runs.size() >=
-      static_cast<size_t>(
-          mutable_cf_options.level0_file_num_compaction_trigger)) {
-    if ((c = PickCompactionToReduceSizeAmp(cf_name, mutable_cf_options,
-                                           vstorage, score, sorted_runs,
-                                           log_buffer)) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: compacting for size amp\n",
+  Compaction* c;
+  if ((c = PickCompactionToReduceSizeAmp(cf_name, mutable_cf_options, vstorage,
+                                         score, sorted_runs, log_buffer)) !=
+      nullptr) {
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: compacting for size amp\n",
+                     cf_name.c_str());
+  } else {
+    // Size amplification is within limits. Try reducing read
+    // amplification while maintaining file size ratios.
+    unsigned int ratio =
+        mutable_cf_options.compaction_options_universal.size_ratio;
+
+    if ((c = PickCompactionToReduceSortedRuns(
+             cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
+             sorted_runs, log_buffer)) != nullptr) {
+      ROCKS_LOG_BUFFER(log_buffer,
+                       "[%s] Universal: compacting for size ratio\n",
                        cf_name.c_str());
     } else {
-      // Size amplification is within limits. Try reducing read
-      // amplification while maintaining file size ratios.
-      unsigned int ratio =
-          mutable_cf_options.compaction_options_universal.size_ratio;
-
-      if ((c = PickCompactionToReduceSortedRuns(
-               cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
-               sorted_runs, log_buffer)) != nullptr) {
-        ROCKS_LOG_BUFFER(log_buffer,
-                         "[%s] Universal: compacting for size ratio\n",
-                         cf_name.c_str());
-      } else {
-        // Size amplification and file size ratios are within configured limits.
-        // If max read amplification is exceeding configured limits, then force
-        // compaction without looking at filesize ratios and try to reduce
-        // the number of files to fewer than level0_file_num_compaction_trigger.
-        // This is guaranteed by NeedsCompaction()
-        assert(sorted_runs.size() >=
-               static_cast<size_t>(
-                   mutable_cf_options.level0_file_num_compaction_trigger));
-        // Get the total number of sorted runs that are not being compacted
-        int num_sr_not_compacted = 0;
-        for (size_t i = 0; i < sorted_runs.size(); i++) {
-          if (sorted_runs[i].being_compacted == false) {
-            num_sr_not_compacted++;
-          }
+      // Size amplification and file size ratios are within configured limits.
+      // If max read amplification is exceeding configured limits, then force
+      // compaction without looking at filesize ratios and try to reduce
+      // the number of files to fewer than level0_file_num_compaction_trigger.
+      // This is guaranteed by NeedsCompaction()
+      assert(sorted_runs.size() >=
+             static_cast<size_t>(
+                 mutable_cf_options.level0_file_num_compaction_trigger));
+      // Get the total number of sorted runs that are not being compacted
+      int num_sr_not_compacted = 0;
+      for (size_t i = 0; i < sorted_runs.size(); i++) {
+        if (sorted_runs[i].being_compacted == false) {
+          num_sr_not_compacted++;
         }
+      }
 
-        // The number of sorted runs that are not being compacted is greater
-        // than the maximum allowed number of sorted runs
-        if (num_sr_not_compacted >
-            mutable_cf_options.level0_file_num_compaction_trigger) {
-          unsigned int num_files =
-              num_sr_not_compacted -
-              mutable_cf_options.level0_file_num_compaction_trigger + 1;
-          if ((c = PickCompactionToReduceSortedRuns(
-                   cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
-                   num_files, sorted_runs, log_buffer)) != nullptr) {
-            ROCKS_LOG_BUFFER(log_buffer,
-                             "[%s] Universal: compacting for file num -- %u\n",
-                             cf_name.c_str(), num_files);
-          }
+      // The number of sorted runs that are not being compacted is greater than
+      // the maximum allowed number of sorted runs
+      if (num_sr_not_compacted >
+          mutable_cf_options.level0_file_num_compaction_trigger) {
+        unsigned int num_files =
+            num_sr_not_compacted -
+            mutable_cf_options.level0_file_num_compaction_trigger + 1;
+        if ((c = PickCompactionToReduceSortedRuns(
+                 cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
+                 num_files, sorted_runs, log_buffer)) != nullptr) {
+          ROCKS_LOG_BUFFER(log_buffer,
+                           "[%s] Universal: compacting for file num -- %u\n",
+                           cf_name.c_str(), num_files);
         }
       }
     }
   }
-
-  if (c == nullptr) {
-    if ((c = PickDeleteTriggeredCompaction(cf_name, mutable_cf_options,
-                                           vstorage, score, sorted_runs,
-                                           log_buffer)) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer,
-                       "[%s] Universal: delete triggered compaction\n",
-                       cf_name.c_str());
-    }
-  }
-
   if (c == nullptr) {
     TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
                              nullptr);
@@ -775,125 +753,6 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
       score, false /* deletion_compaction */,
       CompactionReason::kUniversalSizeAmplification);
 }
-
-// Pick files marked for compaction. Typically, files are marked by
-// CompactOnDeleteCollector due to the presence of tombstones.
-Compaction* UniversalCompactionPicker::PickDeleteTriggeredCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, double score,
-    const std::vector<SortedRun>& /*sorted_runs*/, LogBuffer* /*log_buffer*/) {
-  CompactionInputFiles start_level_inputs;
-  int output_level;
-  std::vector<CompactionInputFiles> inputs;
-
-  if (vstorage->num_levels() == 1) {
-    // This is single level universal. Since we're basically trying to reclaim
-    // space by processing files marked for compaction due to high tombstone
-    // density, let's do the same thing as compaction to reduce size amp which
-    // has the same goals.
-    bool compact = false;
-
-    start_level_inputs.level = 0;
-    start_level_inputs.files.clear();
-    output_level = 0;
-    for (FileMetaData* f : vstorage->LevelFiles(0)) {
-      if (f->marked_for_compaction) {
-        compact = true;
-      }
-      if (compact) {
-        start_level_inputs.files.push_back(f);
-      }
-    }
-    if (start_level_inputs.size() <= 1) {
-      // If only the last file in L0 is marked for compaction, ignore it
-      return nullptr;
-    }
-    inputs.push_back(start_level_inputs);
-  } else {
-    int start_level;
-
-    // For multi-level universal, the strategy is to make this look more like
-    // leveled. We pick one of the files marked for compaction and compact with
-    // overlapping files in the adjacent level.
-    PickFilesMarkedForCompaction(cf_name, vstorage, &start_level, &output_level,
-                                 &start_level_inputs);
-    if (start_level_inputs.empty()) {
-      return nullptr;
-    }
-
-    // Pick the first non-empty level after the start_level
-    for (output_level = start_level + 1; output_level < vstorage->num_levels();
-         output_level++) {
-      if (vstorage->NumLevelFiles(output_level) != 0) {
-        break;
-      }
-    }
-
-    // If all higher levels are empty, pick the highest level as output level
-    if (output_level == vstorage->num_levels()) {
-      if (start_level == 0) {
-        output_level = vstorage->num_levels() - 1;
-      } else {
-        // If start level is non-zero and all higher levels are empty, this
-        // compaction will translate into a trivial move. Since the idea is
-        // to reclaim space and trivial move doesn't help with that, we
-        // skip compaction in this case and return nullptr
-        return nullptr;
-      }
-    }
-    if (ioptions_.allow_ingest_behind &&
-        output_level == vstorage->num_levels() - 1) {
-      assert(output_level > 1);
-      output_level--;
-    }
-
-    if (output_level != 0) {
-      if (start_level == 0) {
-        if (!GetOverlappingL0Files(vstorage, &start_level_inputs, output_level,
-                                   nullptr)) {
-          return nullptr;
-        }
-      }
-
-      CompactionInputFiles output_level_inputs;
-      int parent_index = -1;
-
-      output_level_inputs.level = output_level;
-      if (!SetupOtherInputs(cf_name, mutable_cf_options, vstorage,
-                            &start_level_inputs, &output_level_inputs,
-                            &parent_index, -1)) {
-        return nullptr;
-      }
-      inputs.push_back(start_level_inputs);
-      if (!output_level_inputs.empty()) {
-        inputs.push_back(output_level_inputs);
-      }
-      if (FilesRangeOverlapWithCompaction(inputs, output_level)) {
-        return nullptr;
-      }
-    } else {
-      inputs.push_back(start_level_inputs);
-    }
-  }
-
-  uint64_t estimated_total_size = 0;
-  // Use size of the output level as estimated file size
-  for (FileMetaData* f : vstorage->LevelFiles(output_level)) {
-    estimated_total_size += f->fd.GetFileSize();
-  }
-  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
-  return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
-      MaxFileSizeForLevel(mutable_cf_options, output_level,
-                          kCompactionStyleUniversal),
-      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
-                         1),
-      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ true,
-      score, false /* deletion_compaction */,
-      CompactionReason::kFilesMarkedForCompaction);
-}
 }  // namespace rocksdb
 
 #endif  // !ROCKSDB_LITE

db/compaction_picker_universal.h

@@ -73,11 +73,6 @@ class UniversalCompactionPicker : public CompactionPicker {
       VersionStorageInfo* vstorage, double score,
       const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
 
-  Compaction* PickDeleteTriggeredCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, double score,
-      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
-
   // Used in universal compaction when the enabled_trivial_move
   // option is set. Checks whether there are any overlapping files
   // in the input. Returns true if the input files are non

db/comparator_db_test.cc

@@ -2,7 +2,6 @@
 //  This source code is licensed under both the GPLv2 (found in the
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
-#include <array>
 #include <map>
 #include <string>
 
@@ -434,145 +433,6 @@ TEST_F(ComparatorDBTest, TwoStrComparator) {
   }
 }
 
-TEST_F(ComparatorDBTest, FindShortestSeparator) {
-  std::string s1 = "abc1xyz";
-  std::string s2 = "abc3xy";
-
-  BytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc2", s1);
-
-  s1 = "abc5xyztt";
-
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc5", s1);
-
-  s1 = "abc3";
-  s2 = "abc2xy";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc3", s1);
-
-  s1 = "abc3xyz";
-  s2 = "abc2xy";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc3", s1);
-
-  s1 = "abc3xyz";
-  s2 = "abc2";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_EQ("abc3", s1);
-
-  std::string old_s1 = s1 = "abc2xy";
-  s2 = "abc2";
-  ReverseBytewiseComparator()->FindShortestSeparator(&s1, s2);
-  ASSERT_TRUE(old_s1 >= s1);
-  ASSERT_TRUE(s1 > s2);
-}
-
-TEST_F(ComparatorDBTest, SeparatorSuccessorRandomizeTest) {
-  // Char list for boundary cases.
-  std::array<unsigned char, 6> char_list{{0, 1, 2, 253, 254, 255}};
-  Random rnd(301);
-
-  for (int attempts = 0; attempts < 1000; attempts++) {
-    uint32_t size1 = rnd.Skewed(4);
-    uint32_t size2;
-
-    if (rnd.OneIn(2)) {
-      // size2 to be random size
-      size2 = rnd.Skewed(4);
-    } else {
-      // size1 is within [-2, +2] of size1
-      int diff = static_cast<int>(rnd.Uniform(5)) - 2;
-      int tmp_size2 = static_cast<int>(size1) + diff;
-      if (tmp_size2 < 0) {
-        tmp_size2 = 0;
-      }
-      size2 = static_cast<uint32_t>(tmp_size2);
-    }
-
-    std::string s1;
-    std::string s2;
-    for (uint32_t i = 0; i < size1; i++) {
-      if (rnd.OneIn(2)) {
-        // Use random byte
-        s1 += static_cast<char>(rnd.Uniform(256));
-      } else {
-        // Use one byte in char_list
-        char c = static_cast<char>(char_list[rnd.Uniform(sizeof(char_list))]);
-        s1 += c;
-      }
-    }
-
-    // First set s2 to be the same as s1, and then modify s2.
-    s2 = s1;
-    s2.resize(size2);
-    // We start from the back of the string
-    if (size2 > 0) {
-      uint32_t pos = size2 - 1;
-      do {
-        if (pos >= size1 || rnd.OneIn(4)) {
-          // For 1/4 chance, use random byte
-          s2[pos] = static_cast<char>(rnd.Uniform(256));
-        } else if (rnd.OneIn(4)) {
-          // In 1/4 chance, stop here.
-          break;
-        } else {
-          // Create a char within [-2, +2] of the matching char of s1.
-          int diff = static_cast<int>(rnd.Uniform(5)) - 2;
-          // char may be signed or unsigned based on platform.
-          int s1_char = static_cast<int>(static_cast<unsigned char>(s1[pos]));
-          int s2_char = s1_char + diff;
-          if (s2_char < 0) {
-            s2_char = 0;
-          }
-          if (s2_char > 255) {
-            s2_char = 255;
-          }
-          s2[pos] = static_cast<char>(s2_char);
-        }
-      } while (pos-- != 0);
-    }
-
-    // Test separators
-    for (int rev = 0; rev < 2; rev++) {
-      if (rev == 1) {
-        // switch s1 and s2
-        std::string t = s1;
-        s1 = s2;
-        s2 = t;
-      }
-      std::string separator = s1;
-      BytewiseComparator()->FindShortestSeparator(&separator, s2);
-      std::string rev_separator = s1;
-      ReverseBytewiseComparator()->FindShortestSeparator(&rev_separator, s2);
-
-      if (s1 == s2) {
-        ASSERT_EQ(s1, separator);
-        ASSERT_EQ(s2, rev_separator);
-      } else if (s1 < s2) {
-        ASSERT_TRUE(s1 <= separator);
-        ASSERT_TRUE(s2 > separator);
-        ASSERT_LE(separator.size(), std::max(s1.size(), s2.size()));
-        ASSERT_EQ(s1, rev_separator);
-      } else {
-        ASSERT_TRUE(s1 >= rev_separator);
-        ASSERT_TRUE(s2 < rev_separator);
-        ASSERT_LE(rev_separator.size(), std::max(s1.size(), s2.size()));
-        ASSERT_EQ(s1, separator);
-      }
-    }
-
-    // Test successors
-    std::string succ = s1;
-    BytewiseComparator()->FindShortSuccessor(&succ);
-    ASSERT_TRUE(succ >= s1);
-
-    succ = s1;
-    ReverseBytewiseComparator()->FindShortSuccessor(&succ);
-    ASSERT_TRUE(succ <= s1);
-  }
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/convenience.cc

@@ -50,9 +50,8 @@ Status VerifySstFileChecksum(const Options& options,
   std::unique_ptr<RandomAccessFileReader> file_reader(
       new RandomAccessFileReader(std::move(file), file_path));
   s = ioptions.table_factory->NewTableReader(
-      TableReaderOptions(ioptions, options.prefix_extractor.get(), env_options,
-                         internal_comparator, false /* skip_filters */,
-                         -1 /* level */),
+      TableReaderOptions(ioptions, env_options, internal_comparator,
+                         false /* skip_filters */, -1 /* level */),
       std::move(file_reader), file_size, &table_reader,
       false /* prefetch_index_and_filter_in_cache */);
   if (!s.ok()) {

db/db_block_cache_test.cc

@@ -390,10 +390,7 @@ class MockCache : public LRUCache {
   static uint32_t high_pri_insert_count;
   static uint32_t low_pri_insert_count;
 
-  MockCache()
-      : LRUCache((size_t)1 << 25 /*capacity*/, 0 /*num_shard_bits*/,
-                 false /*strict_capacity_limit*/, 0.0 /*high_pri_pool_ratio*/) {
-  }
+  MockCache() : LRUCache(1 << 25, 0, false, 0.0) {}
 
   virtual Status Insert(const Slice& key, void* value, size_t charge,
                         void (*deleter)(const Slice& key, void* value),

db/db_compaction_filter_test.cc

@@ -45,7 +45,6 @@ class DBTestCompactionFilterWithCompactParam
   }
 };
 
-#ifndef ROCKSDB_VALGRIND_RUN
 INSTANTIATE_TEST_CASE_P(
     DBTestCompactionFilterWithCompactOption,
     DBTestCompactionFilterWithCompactParam,
@@ -54,12 +53,6 @@ INSTANTIATE_TEST_CASE_P(
                       DBTestBase::OptionConfig::kUniversalCompactionMultiLevel,
                       DBTestBase::OptionConfig::kLevelSubcompactions,
                       DBTestBase::OptionConfig::kUniversalSubcompactions));
-#else
-// Run fewer cases in valgrind
-INSTANTIATE_TEST_CASE_P(DBTestCompactionFilterWithCompactOption,
-                        DBTestCompactionFilterWithCompactParam,
-                        ::testing::Values(DBTestBase::OptionConfig::kDefault));
-#endif  // ROCKSDB_VALGRIND_RUN
 
 class KeepFilter : public CompactionFilter {
  public:

db/db_compaction_test.cc

@@ -251,7 +251,6 @@ const SstFileMetaData* PickFileRandomly(
 }
 }  // anonymous namespace
 
-#ifndef ROCKSDB_VALGRIND_RUN
 // All the TEST_P tests run once with sub_compactions disabled (i.e.
 // options.max_subcompactions = 1) and once with it enabled
 TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
@@ -294,7 +293,6 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
     ASSERT_GT(db_size[0] / 3, db_size[1]);
   }
 }
-#endif  // ROCKSDB_VALGRIND_RUN
 
 TEST_P(DBCompactionTestWithParam, CompactionsPreserveDeletes) {
   //  For each options type we test following

db/db_impl.cc

@@ -969,7 +969,7 @@ InternalIterator* DBImpl::NewInternalIterator(
   MergeIteratorBuilder merge_iter_builder(
       &cfd->internal_comparator(), arena,
       !read_options.total_order_seek &&
-          super_version->mutable_cf_options.prefix_extractor != nullptr);
+          cfd->ioptions()->prefix_extractor != nullptr);
   // Collect iterator for mutable mem
   merge_iter_builder.AddIterator(
       super_version->mem->NewIterator(read_options, arena));
@@ -1568,11 +1568,11 @@ Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
 #else
     SuperVersion* sv = cfd->GetReferencedSuperVersion(&mutex_);
     auto iter = new ForwardIterator(this, read_options, cfd, sv);
-    result = NewDBIterator(
-        env_, read_options, *cfd->ioptions(), sv->mutable_cf_options,
-        cfd->user_comparator(), iter, kMaxSequenceNumber,
-        sv->mutable_cf_options.max_sequential_skip_in_iterations,
-        read_callback);
+    result =
+        NewDBIterator(env_, read_options, *cfd->ioptions(),
+                      cfd->user_comparator(), iter, kMaxSequenceNumber,
+                      sv->mutable_cf_options.max_sequential_skip_in_iterations,
+                      read_callback);
 #endif
   } else {
     // Note: no need to consider the special case of
@@ -1637,7 +1637,7 @@ ArenaWrappedDBIter* DBImpl::NewIteratorImpl(const ReadOptions& read_options,
   // likely that any iterator pointer is close to the iterator it points to so
   // that they are likely to be in the same cache line and/or page.
   ArenaWrappedDBIter* db_iter = NewArenaWrappedDbIterator(
-      env_, read_options, *cfd->ioptions(), sv->mutable_cf_options, snapshot,
+      env_, read_options, *cfd->ioptions(), snapshot,
       sv->mutable_cf_options.max_sequential_skip_in_iterations,
       sv->version_number, read_callback,
       ((read_options.snapshot != nullptr) ? nullptr : this), cfd, allow_blob,
@@ -1688,8 +1688,8 @@ Status DBImpl::NewIterators(
       SuperVersion* sv = cfd->GetReferencedSuperVersion(&mutex_);
       auto iter = new ForwardIterator(this, read_options, cfd, sv);
       iterators->push_back(NewDBIterator(
-          env_, read_options, *cfd->ioptions(), sv->mutable_cf_options,
-          cfd->user_comparator(), iter, kMaxSequenceNumber,
+          env_, read_options, *cfd->ioptions(), cfd->user_comparator(), iter,
+          kMaxSequenceNumber,
           sv->mutable_cf_options.max_sequential_skip_in_iterations,
           read_callback));
     }
@@ -2863,9 +2863,7 @@ Status DBImpl::IngestExternalFile(
     pending_output_elem = CaptureCurrentFileNumberInPendingOutputs();
   }
 
-  SuperVersion* super_version = cfd->GetReferencedSuperVersion(&mutex_);
-  status = ingestion_job.Prepare(external_files, super_version);
-  CleanupSuperVersion(super_version);
+  status = ingestion_job.Prepare(external_files);
   if (!status.ok()) {
     return status;
   }

db/db_impl_files.cc

@@ -12,7 +12,6 @@
 #define __STDC_FORMAT_MACROS
 #endif
 #include <inttypes.h>
-#include <set>
 #include <unordered_set>
 #include "db/event_helpers.h"
 #include "db/memtable_list.h"
@@ -100,10 +99,10 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
   if (doing_the_full_scan) {
     InfoLogPrefix info_log_prefix(!immutable_db_options_.db_log_dir.empty(),
         dbname_);
-    std::set<std::string> paths;
+    std::vector<std::string> paths;
     for (size_t path_id = 0; path_id < immutable_db_options_.db_paths.size();
          path_id++) {
-      paths.insert(immutable_db_options_.db_paths[path_id].path);
+      paths.emplace_back(immutable_db_options_.db_paths[path_id].path);
     }
 
     // Note that if cf_paths is not specified in the ColumnFamilyOptions
@@ -114,11 +113,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
     for (auto cfd : *versions_->GetColumnFamilySet()) {
       for (size_t path_id = 0; path_id < cfd->ioptions()->cf_paths.size();
            path_id++) {
-        auto& path = cfd->ioptions()->cf_paths[path_id].path;
-
-        if (paths.find(path) == paths.end()) {
-          paths.insert(path);
-        }
+        paths.emplace_back(cfd->ioptions()->cf_paths[path_id].path);
       }
     }
 

db/db_impl_readonly.cc

@@ -58,7 +58,7 @@ Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
   SequenceNumber latest_snapshot = versions_->LastSequence();
   ReadCallback* read_callback = nullptr;  // No read callback provided.
   auto db_iter = NewArenaWrappedDbIterator(
-      env_, read_options, *cfd->ioptions(), super_version->mutable_cf_options,
+      env_, read_options, *cfd->ioptions(),
       (read_options.snapshot != nullptr
            ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
                  ->number_
@@ -88,7 +88,7 @@ Status DBImplReadOnly::NewIterators(
     auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
     auto* sv = cfd->GetSuperVersion()->Ref();
     auto* db_iter = NewArenaWrappedDbIterator(
-        env_, read_options, *cfd->ioptions(), sv->mutable_cf_options,
+        env_, read_options, *cfd->ioptions(),
         (read_options.snapshot != nullptr
              ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
                    ->number_

db/db_impl_write.cc

@@ -211,7 +211,6 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
   // and protects against concurrent loggers and concurrent writes
   // into memtables
 
-  TEST_SYNC_POINT("DBImpl::WriteImpl:BeforeLeaderEnters");
   last_batch_group_size_ =
       write_thread_.EnterAsBatchGroupLeader(&w, &write_group);
 
@@ -1281,11 +1280,7 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
   // In case of pipelined write is enabled, wait for all pending memtable
   // writers.
   if (immutable_db_options_.enable_pipelined_write) {
-    // Memtable writers may call DB::Get in case max_successive_merges > 0,
-    // which may lock mutex. Unlocking mutex here to avoid deadlock.
-    mutex_.Unlock();
     write_thread_.WaitForMemTableWriters();
-    mutex_.Lock();
   }
 
   // Attempt to switch to a new memtable and trigger flush of old.

db/db_iter.cc

@@ -110,8 +110,7 @@ class DBIter final: public Iterator {
   };
 
   DBIter(Env* _env, const ReadOptions& read_options,
-         const ImmutableCFOptions& cf_options,
-         const MutableCFOptions& mutable_cf_options, const Comparator* cmp,
+         const ImmutableCFOptions& cf_options, const Comparator* cmp,
          InternalIterator* iter, SequenceNumber s, bool arena_mode,
          uint64_t max_sequential_skip_in_iterations,
          ReadCallback* read_callback, bool allow_blob)
@@ -139,7 +138,7 @@ class DBIter final: public Iterator {
         is_blob_(false),
         start_seqnum_(read_options.iter_start_seqnum) {
     RecordTick(statistics_, NO_ITERATORS);
-    prefix_extractor_ = mutable_cf_options.prefix_extractor.get();
+    prefix_extractor_ = cf_options.prefix_extractor;
     max_skip_ = max_sequential_skip_in_iterations;
     max_skippable_internal_keys_ = read_options.max_skippable_internal_keys;
     if (pin_thru_lifetime_) {
@@ -1427,15 +1426,14 @@ void DBIter::SeekToLast() {
 
 Iterator* NewDBIterator(Env* env, const ReadOptions& read_options,
                         const ImmutableCFOptions& cf_options,
-                        const MutableCFOptions& mutable_cf_options,
                         const Comparator* user_key_comparator,
                         InternalIterator* internal_iter,
                         const SequenceNumber& sequence,
                         uint64_t max_sequential_skip_in_iterations,
                         ReadCallback* read_callback, bool allow_blob) {
   DBIter* db_iter =
-      new DBIter(env, read_options, cf_options, mutable_cf_options,
-                 user_key_comparator, internal_iter, sequence, false,
+      new DBIter(env, read_options, cf_options, user_key_comparator,
+                 internal_iter, sequence, false,
                  max_sequential_skip_in_iterations, read_callback, allow_blob);
   return db_iter;
 }
@@ -1479,7 +1477,6 @@ inline Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
 
 void ArenaWrappedDBIter::Init(Env* env, const ReadOptions& read_options,
                               const ImmutableCFOptions& cf_options,
-                              const MutableCFOptions& mutable_cf_options,
                               const SequenceNumber& sequence,
                               uint64_t max_sequential_skip_in_iteration,
                               uint64_t version_number,
@@ -1487,9 +1484,9 @@ void ArenaWrappedDBIter::Init(Env* env, const ReadOptions& read_options,
                               bool allow_refresh) {
   auto mem = arena_.AllocateAligned(sizeof(DBIter));
   db_iter_ = new (mem)
-      DBIter(env, read_options, cf_options, mutable_cf_options,
-             cf_options.user_comparator, nullptr, sequence, true,
-             max_sequential_skip_in_iteration, read_callback, allow_blob);
+      DBIter(env, read_options, cf_options, cf_options.user_comparator, nullptr,
+             sequence, true, max_sequential_skip_in_iteration, read_callback,
+             allow_blob);
   sv_number_ = version_number;
   allow_refresh_ = allow_refresh;
 }
@@ -1511,8 +1508,8 @@ Status ArenaWrappedDBIter::Refresh() {
     new (&arena_) Arena();
 
     SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_->mutex());
-    Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
-         latest_seq, sv->mutable_cf_options.max_sequential_skip_in_iterations,
+    Init(env, read_options_, *(cfd_->ioptions()), latest_seq,
+         sv->mutable_cf_options.max_sequential_skip_in_iterations,
          cur_sv_number, read_callback_, allow_blob_, allow_refresh_);
 
     InternalIterator* internal_iter = db_impl_->NewInternalIterator(
@@ -1527,13 +1524,12 @@ Status ArenaWrappedDBIter::Refresh() {
 
 ArenaWrappedDBIter* NewArenaWrappedDbIterator(
     Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
+    const ImmutableCFOptions& cf_options, const SequenceNumber& sequence,
     uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
     ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
     bool allow_blob, bool allow_refresh) {
   ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
-  iter->Init(env, read_options, cf_options, mutable_cf_options, sequence,
+  iter->Init(env, read_options, cf_options, sequence,
              max_sequential_skip_in_iterations, version_number, read_callback,
              allow_blob, allow_refresh);
   if (db_impl != nullptr && cfd != nullptr && allow_refresh) {

db/db_iter.h

@@ -30,7 +30,6 @@ class InternalIterator;
 // into appropriate user keys.
 extern Iterator* NewDBIterator(Env* env, const ReadOptions& read_options,
                                const ImmutableCFOptions& cf_options,
-                               const MutableCFOptions& mutable_cf_options,
                                const Comparator* user_key_comparator,
                                InternalIterator* internal_iter,
                                const SequenceNumber& sequence,
@@ -72,7 +71,6 @@ class ArenaWrappedDBIter : public Iterator {
 
   void Init(Env* env, const ReadOptions& read_options,
             const ImmutableCFOptions& cf_options,
-            const MutableCFOptions& mutable_cf_options,
             const SequenceNumber& sequence,
             uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
             ReadCallback* read_callback, bool allow_blob, bool allow_refresh);
@@ -104,8 +102,7 @@ class ArenaWrappedDBIter : public Iterator {
 // be supported.
 extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
     Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
+    const ImmutableCFOptions& cf_options, const SequenceNumber& sequence,
     uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
     ReadCallback* read_callback, DBImpl* db_impl = nullptr,
     ColumnFamilyData* cfd = nullptr, bool allow_blob = false,

db/db_iter_stress_test.cc

@@ -173,7 +173,7 @@ struct StressTestIterator : public InternalIterator {
     }
   }
 
-  void SeekToFirst() override {
+  void SeekToFirst() {
     if (MaybeFail()) return;
     MaybeMutate();
 
@@ -181,7 +181,7 @@ struct StressTestIterator : public InternalIterator {
     iter = 0;
     SkipForward();
   }
-  void SeekToLast() override {
+  void SeekToLast() {
     if (MaybeFail()) return;
     MaybeMutate();
 
@@ -190,7 +190,7 @@ struct StressTestIterator : public InternalIterator {
     SkipBackward();
   }
 
-  void Seek(const Slice& target) override {
+  void Seek(const Slice& target) {
     if (MaybeFail()) return;
     MaybeMutate();
 
@@ -202,7 +202,7 @@ struct StressTestIterator : public InternalIterator {
     iter = (int)(it - data->entries.begin());
     SkipForward();
   }
-  void SeekForPrev(const Slice& target) override {
+  void SeekForPrev(const Slice& target) {
     if (MaybeFail()) return;
     MaybeMutate();
 
@@ -216,14 +216,14 @@ struct StressTestIterator : public InternalIterator {
     SkipBackward();
   }
 
-  void Next() override {
+  void Next() {
     assert(Valid());
     if (MaybeFail()) return;
     MaybeMutate();
     ++iter;
     SkipForward();
   }
-  void Prev() override {
+  void Prev() {
     assert(Valid());
     if (MaybeFail()) return;
     MaybeMutate();
@@ -231,11 +231,11 @@ struct StressTestIterator : public InternalIterator {
     SkipBackward();
   }
 
-  Slice key() const override {
+  Slice key() const {
     assert(Valid());
     return data->entries[iter].ikey;
   }
-  Slice value() const override {
+  Slice value() const {
     assert(Valid());
     return data->entries[iter].value;
   }
@@ -404,14 +404,13 @@ TEST_F(DBIteratorStressTest, StressTest) {
   Random64 rnd(826909345792864532ll);
 
   auto gen_key = [&](int max_key) {
-    assert(max_key > 0);
     int len = 0;
     int a = max_key;
     while (a) {
       a /= 10;
       ++len;
     }
-    std::string s = ToString(rnd.Next() % static_cast<uint64_t>(max_key));
+    std::string s = ToString(rnd.Next() % (uint64_t)max_key);
     s.insert(0, len - (int)s.size(), '0');
     return s;
   };
@@ -509,8 +508,7 @@ TEST_F(DBIteratorStressTest, StressTest) {
                   internal_iter->trace = trace;
                   db_iter.reset(NewDBIterator(
                       env_, ropt, ImmutableCFOptions(options),
-                      MutableCFOptions(options), BytewiseComparator(),
-                      internal_iter, sequence,
+                      BytewiseComparator(), internal_iter, sequence,
                       options.max_sequential_skip_in_iterations,
                       nullptr /*read_callback*/));
                 }

db/db_iter_test.cc

@@ -36,7 +36,9 @@ class TestIterator : public InternalIterator {
         valid_(false),
         sequence_number_(0),
         iter_(0),
-        cmp(comparator) {}
+        cmp(comparator) {
+    data_.reserve(16);
+  }
 
   void AddPut(std::string argkey, std::string argvalue) {
     Add(argkey, kTypeValue, argvalue);
@@ -234,7 +236,7 @@ class DBIteratorTest : public testing::Test {
 TEST_F(DBIteratorTest, DBIteratorPrevNext) {
   Options options;
   ImmutableCFOptions cf_options = ImmutableCFOptions(options);
-  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
+
   {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
     internal_iter->AddDeletion("a");
@@ -248,9 +250,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -281,9 +282,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -308,9 +308,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -341,9 +340,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -377,9 +375,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
@@ -407,9 +404,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 7, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 7,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     SetPerfLevel(kEnableCount);
     ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -445,9 +441,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 4, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 4,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -471,9 +466,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
@@ -494,9 +488,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -530,9 +523,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     ro.iterate_upper_bound = &prefix;
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 7, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 7,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     SetPerfLevel(kEnableCount);
     ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -560,9 +552,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -603,9 +594,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 2, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 2,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -635,9 +625,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     ReadOptions ro;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -658,7 +647,6 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 TEST_F(DBIteratorTest, DBIteratorEmpty) {
   Options options;
   ImmutableCFOptions cf_options = ImmutableCFOptions(options);
-  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
   ReadOptions ro;
 
   {
@@ -666,9 +654,8 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 0, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 0,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
   }
@@ -678,9 +665,8 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 0, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 0,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToFirst();
     ASSERT_TRUE(!db_iter->Valid());
   }
@@ -700,10 +686,10 @@ TEST_F(DBIteratorTest, DBIteratorUseSkipCountSkips) {
   }
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 2,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 2, options.max_sequential_skip_in_iterations,
+                    nullptr /*read_callback*/));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -732,7 +718,6 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
   ImmutableCFOptions cf_options = ImmutableCFOptions(options);
-  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
     for (size_t i = 0; i < 200; ++i) {
@@ -746,8 +731,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
 
       options.statistics = rocksdb::CreateDBStatistics();
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
@@ -782,8 +767,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
@@ -811,8 +796,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, 202, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, 202,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
@@ -844,8 +829,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->AddPut("c", "200");
       internal_iter->Finish();
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, i, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, i,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
       db_iter->SeekToLast();
       ASSERT_TRUE(!db_iter->Valid());
@@ -861,9 +846,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
     internal_iter->AddPut("c", "200");
     internal_iter->Finish();
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 200, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 200,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -896,8 +880,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
@@ -931,8 +915,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
@@ -963,7 +947,6 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
 TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
   Options options;
   ImmutableCFOptions cf_options = ImmutableCFOptions(options);
-  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
   ReadOptions ro;
 
   // Basic test case ... Make sure explicityly passing the default value works.
@@ -981,9 +964,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 0;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1028,9 +1010,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1073,9 +1054,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1112,9 +1092,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1148,9 +1127,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -1179,9 +1157,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1217,9 +1194,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
     ro.max_skippable_internal_keys = 2;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -1255,8 +1231,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
 
       ro.max_skippable_internal_keys = i;
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, 2 * i + 1, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, 2 * i + 1,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
 
       db_iter->SeekToFirst();
@@ -1309,8 +1285,8 @@ TEST_F(DBIteratorTest, DBIteratorSkipInternalKeys) {
       options.max_sequential_skip_in_iterations = 1000;
       ro.max_skippable_internal_keys = i;
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-          internal_iter, 2 * i + 1, options.max_sequential_skip_in_iterations,
+          env_, ro, cf_options, BytewiseComparator(), internal_iter, 2 * i + 1,
+          options.max_sequential_skip_in_iterations,
           nullptr /*read_callback*/));
 
       db_iter->SeekToFirst();
@@ -1347,10 +1323,10 @@ TEST_F(DBIteratorTest, DBIterator1) {
   internal_iter->AddMerge("b", "2");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 1,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 1, options.max_sequential_skip_in_iterations,
+                    nullptr /*read_callback*/));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1375,10 +1351,10 @@ TEST_F(DBIteratorTest, DBIterator2) {
   internal_iter->AddMerge("b", "2");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 0,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 0, options.max_sequential_skip_in_iterations,
+                    nullptr /*read_callback*/));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1400,10 +1376,10 @@ TEST_F(DBIteratorTest, DBIterator3) {
   internal_iter->AddMerge("b", "2");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 2,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 2, options.max_sequential_skip_in_iterations,
+                    nullptr /*read_callback*/));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1425,10 +1401,10 @@ TEST_F(DBIteratorTest, DBIterator4) {
   internal_iter->AddMerge("b", "2");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 4,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 4, options.max_sequential_skip_in_iterations,
+                    nullptr /*read_callback*/));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1446,7 +1422,6 @@ TEST_F(DBIteratorTest, DBIterator5) {
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
   ImmutableCFOptions cf_options = ImmutableCFOptions(options);
-  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
@@ -1460,9 +1435,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 0, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 0,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1483,9 +1457,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 1, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 1,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1506,9 +1479,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 2, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 2,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1529,9 +1501,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 3, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 3,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1552,9 +1523,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 4, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 4,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1575,9 +1545,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 5, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 5,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1598,9 +1567,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 6, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 6,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1619,9 +1587,8 @@ TEST_F(DBIteratorTest, DBIterator5) {
     internal_iter->AddPut("b", "val_b");
     internal_iter->Finish();
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 10, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 10,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->Seek("b");
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -1636,7 +1603,6 @@ TEST_F(DBIteratorTest, DBIterator6) {
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
   ImmutableCFOptions cf_options = ImmutableCFOptions(options);
-  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
@@ -1650,9 +1616,8 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 0, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 0,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1673,9 +1638,8 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 1, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 1,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1696,9 +1660,8 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 2, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 2,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1719,9 +1682,8 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 3, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 3,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
   }
@@ -1738,9 +1700,8 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 4, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 4,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1761,9 +1722,8 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 5, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 5,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1784,9 +1744,8 @@ TEST_F(DBIteratorTest, DBIterator6) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 6, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 6,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1801,7 +1760,6 @@ TEST_F(DBIteratorTest, DBIterator7) {
   Options options;
   options.merge_operator = MergeOperators::CreateFromStringId("stringappend");
   ImmutableCFOptions cf_options = ImmutableCFOptions(options);
-  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
 
   {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
@@ -1827,9 +1785,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 0, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 0,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1862,9 +1819,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 2, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 2,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1903,9 +1859,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 4, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 4,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1944,9 +1899,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 5, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 5,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1990,9 +1944,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 6, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 6,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2037,9 +1990,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 7, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 7,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2078,9 +2030,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 9, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 9,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2125,9 +2076,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 13, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 13,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2173,9 +2123,8 @@ TEST_F(DBIteratorTest, DBIterator7) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, cf_options, mutable_cf_options, BytewiseComparator(),
-        internal_iter, 14, options.max_sequential_skip_in_iterations,
-        nullptr /*read_callback*/));
+        env_, ro, cf_options, BytewiseComparator(), internal_iter, 14,
+        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -2204,9 +2153,9 @@ TEST_F(DBIteratorTest, DBIterator8) {
   internal_iter->Finish();
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 10,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+      env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+      internal_iter, 10, options.max_sequential_skip_in_iterations,
+      nullptr /*read_callback*/));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -2235,9 +2184,9 @@ TEST_F(DBIteratorTest, DBIterator9) {
     internal_iter->Finish();
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-        BytewiseComparator(), internal_iter, 10,
-        options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+        env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+        internal_iter, 10, options.max_sequential_skip_in_iterations,
+        nullptr /*read_callback*/));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -2302,9 +2251,9 @@ TEST_F(DBIteratorTest, DBIterator10) {
   internal_iter->Finish();
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 10,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+      env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+      internal_iter, 10, options.max_sequential_skip_in_iterations,
+      nullptr /*read_callback*/));
 
   db_iter->Seek("c");
   ASSERT_TRUE(db_iter->Valid());
@@ -2342,9 +2291,8 @@ TEST_F(DBIteratorTest, SeekToLastOccurrenceSeq0) {
   internal_iter->Finish();
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 10, 0 /* force seek */,
-      nullptr /*read_callback*/));
+      env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+      internal_iter, 10, 0 /* force seek */, nullptr /*read_callback*/));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -2370,10 +2318,10 @@ TEST_F(DBIteratorTest, DBIterator11) {
   internal_iter->AddMerge("b", "2");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 1,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 1, options.max_sequential_skip_in_iterations,
+                    nullptr /*read_callback*/));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -2397,9 +2345,9 @@ TEST_F(DBIteratorTest, DBIterator12) {
   internal_iter->AddSingleDeletion("b");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 10, 0, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 10, 0, nullptr /*read_callback*/));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -2434,9 +2382,9 @@ TEST_F(DBIteratorTest, DBIterator13) {
   internal_iter->AddPut(key, "8");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 2, 3, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 2, 3, nullptr /*read_callback*/));
   db_iter->Seek("b");
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), key);
@@ -2462,9 +2410,9 @@ TEST_F(DBIteratorTest, DBIterator14) {
   internal_iter->AddPut("c", "9");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 4, 1, nullptr /*read_callback*/));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 4, 1, nullptr /*read_callback*/));
   db_iter->Seek("b");
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -2489,10 +2437,10 @@ TEST_F(DBIteratorTest, DBIteratorTestDifferentialSnapshots) {
     }
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-        BytewiseComparator(), internal_iter, 13,
-        options.max_sequential_skip_in_iterations, nullptr));
+    std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 13,
+                    options.max_sequential_skip_in_iterations, nullptr));
     // Expecting InternalKeys in [5,8] range with correct type
     int seqnums[4] = {5,8,11,13};
     std::string user_keys[4] = {"1","2","3","4"};
@@ -2524,10 +2472,10 @@ TEST_F(DBIteratorTest, DBIteratorTestDifferentialSnapshots) {
     }
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-        BytewiseComparator(), internal_iter, 13,
-        options.max_sequential_skip_in_iterations, nullptr));
+    std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 13,
+                    options.max_sequential_skip_in_iterations, nullptr));
     // Expecting InternalKeys in [5,8] range with correct type
     int seqnums[4] = {5,8,11,13};
     EntryType key_types[4] = {EntryType::kEntryDelete,EntryType::kEntryDelete,
@@ -2575,9 +2523,8 @@ class DBIterWithMergeIterTest : public testing::Test {
         NewMergingIterator(&icomp_, &child_iters[0], 2u);
 
     db_iter_.reset(NewDBIterator(
-        env_, ro_, ImmutableCFOptions(options_), MutableCFOptions(options_),
-        BytewiseComparator(), merge_iter,
-        8 /* read data earlier than seqId 8 */,
+        env_, ro_, ImmutableCFOptions(options_), BytewiseComparator(),
+        merge_iter, 8 /* read data earlier than seqId 8 */,
         3 /* max iterators before reseek */, nullptr /*read_callback*/));
   }
 
@@ -2660,7 +2607,7 @@ TEST_F(DBIterWithMergeIterTest, InnerMergeIteratorDataRace1) {
   // MergeIterator::Prev() realized the mem table iterator is at its end
   // and before an SeekToLast() is called.
   rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "MergeIterator::Prev:BeforeSeekToLast",
+      "MergeIterator::Prev:BeforePrev",
       [&](void* /*arg*/) { internal_iter2_->Add("z", kTypeValue, "7", 12u); });
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
@@ -2696,7 +2643,7 @@ TEST_F(DBIterWithMergeIterTest, InnerMergeIteratorDataRace2) {
   // mem table after MergeIterator::Prev() realized the mem tableiterator is at
   // its end and before an SeekToLast() is called.
   rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "MergeIterator::Prev:BeforeSeekToLast", [&](void* /*arg*/) {
+      "MergeIterator::Prev:BeforePrev", [&](void* /*arg*/) {
         internal_iter2_->Add("z", kTypeValue, "7", 12u);
         internal_iter2_->Add("z", kTypeValue, "7", 11u);
       });
@@ -2734,7 +2681,7 @@ TEST_F(DBIterWithMergeIterTest, InnerMergeIteratorDataRace3) {
   // mem table after MergeIterator::Prev() realized the mem table iterator is at
   // its end and before an SeekToLast() is called.
   rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "MergeIterator::Prev:BeforeSeekToLast", [&](void* /*arg*/) {
+      "MergeIterator::Prev:BeforePrev", [&](void* /*arg*/) {
         internal_iter2_->Add("z", kTypeValue, "7", 16u, true);
         internal_iter2_->Add("z", kTypeValue, "7", 15u, true);
         internal_iter2_->Add("z", kTypeValue, "7", 14u, true);
@@ -3015,9 +2962,9 @@ TEST_F(DBIteratorTest, SeekPrefixTombstones) {
 
   ro.prefix_same_as_start = true;
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 10,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+      env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+      internal_iter, 10, options.max_sequential_skip_in_iterations,
+      nullptr /*read_callback*/));
 
   int skipped_keys = 0;
 
@@ -3051,10 +2998,9 @@ TEST_F(DBIteratorTest, SeekToFirstLowerBound) {
     ro.iterate_lower_bound = &lower_bound;
     Options options;
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-        BytewiseComparator(), internal_iter, 10 /* sequence */,
-        options.max_sequential_skip_in_iterations,
-        nullptr /* read_callback */));
+        env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+        internal_iter, 10 /* sequence */,
+        options.max_sequential_skip_in_iterations, nullptr /* read_callback */));
 
     db_iter->SeekToFirst();
     if (i == kNumKeys + 1) {
@@ -3090,8 +3036,8 @@ TEST_F(DBIteratorTest, PrevLowerBound) {
   ro.iterate_lower_bound = &lower_bound;
   Options options;
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 10 /* sequence */,
+      env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+      internal_iter, 10 /* sequence */,
       options.max_sequential_skip_in_iterations, nullptr /* read_callback */));
 
   db_iter->SeekToLast();
@@ -3118,8 +3064,8 @@ TEST_F(DBIteratorTest, SeekLessLowerBound) {
   ro.iterate_lower_bound = &lower_bound;
   Options options;
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ro, ImmutableCFOptions(options), MutableCFOptions(options),
-      BytewiseComparator(), internal_iter, 10 /* sequence */,
+      env_, ro, ImmutableCFOptions(options), BytewiseComparator(),
+      internal_iter, 10 /* sequence */,
       options.max_sequential_skip_in_iterations, nullptr /* read_callback */));
 
   auto before_lower_bound_str = std::to_string(kLowerBound - 1);
@@ -3143,9 +3089,9 @@ TEST_F(DBIteratorTest, ReverseToForwardWithDisappearingKeys) {
   internal_iter->Finish();
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ReadOptions(), ImmutableCFOptions(options),
-      MutableCFOptions(options), BytewiseComparator(), internal_iter, 10,
-      options.max_sequential_skip_in_iterations, nullptr /*read_callback*/));
+      env_, ReadOptions(), ImmutableCFOptions(options), BytewiseComparator(),
+      internal_iter, 10, options.max_sequential_skip_in_iterations,
+      nullptr /*read_callback*/));
 
   db_iter->SeekForPrev("a");
   ASSERT_TRUE(db_iter->Valid());

db/db_iterator_test.cc

@@ -862,8 +862,6 @@ TEST_P(DBIteratorTest, IteratorPinsRef) {
   } while (ChangeCompactOptions());
 }
 
-// SetOptions not defined in ROCKSDB LITE
-#ifndef ROCKSDB_LITE
 TEST_P(DBIteratorTest, DBIteratorBoundTest) {
   Options options = CurrentOptions();
   options.env = env_;
@@ -948,7 +946,9 @@ TEST_P(DBIteratorTest, DBIteratorBoundTest) {
   }
 
   // prefix is the first letter of the key
-  ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:1"}}));
+  options.prefix_extractor.reset(NewFixedPrefixTransform(1));
+
+  DestroyAndReopen(options);
   ASSERT_OK(Put("a", "0"));
   ASSERT_OK(Put("foo", "bar"));
   ASSERT_OK(Put("foo1", "bar1"));
@@ -1035,7 +1035,6 @@ TEST_P(DBIteratorTest, DBIteratorBoundTest) {
     ASSERT_EQ(static_cast<int>(get_perf_context()->internal_delete_skipped_count), 0);
   }
 }
-#endif
 
 TEST_P(DBIteratorTest, DBIteratorBoundOptimizationTest) {
   int upper_bound_hits = 0;
@@ -2044,6 +2043,43 @@ TEST_P(DBIteratorTest, CreationFailure) {
   delete iter;
 }
 
+TEST_P(DBIteratorTest, UpperBoundWithChangeDirection) {
+  Options options = CurrentOptions();
+  options.max_sequential_skip_in_iterations = 3;
+  DestroyAndReopen(options);
+
+  // write a bunch of kvs to the database.
+  ASSERT_OK(Put("a", "1"));
+  ASSERT_OK(Put("y", "1"));
+  ASSERT_OK(Put("y1", "1"));
+  ASSERT_OK(Put("y2", "1"));
+  ASSERT_OK(Put("y3", "1"));
+  ASSERT_OK(Put("z", "1"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put("a", "1"));
+  ASSERT_OK(Put("z", "1"));
+  ASSERT_OK(Put("bar", "1"));
+  ASSERT_OK(Put("foo", "1"));
+
+  std::string upper_bound = "x";
+  Slice ub_slice(upper_bound);
+  ReadOptions ro;
+  ro.iterate_upper_bound = &ub_slice;
+  ro.max_skippable_internal_keys = 1000;
+
+  Iterator* iter = NewIterator(ro);
+  iter->Seek("foo");
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ("foo", iter->key().ToString());
+
+  iter->Prev();
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_OK(iter->status());
+  ASSERT_EQ("bar", iter->key().ToString());
+
+  delete iter;
+}
+
 TEST_P(DBIteratorTest, TableFilter) {
   ASSERT_OK(Put("a", "1"));
   dbfull()->Flush(FlushOptions());
@@ -2110,6 +2146,47 @@ TEST_P(DBIteratorTest, TableFilter) {
   }
 }
 
+TEST_P(DBIteratorTest, UpperBoundWithPrevReseek) {
+  Options options = CurrentOptions();
+  options.max_sequential_skip_in_iterations = 3;
+  DestroyAndReopen(options);
+
+  // write a bunch of kvs to the database.
+  ASSERT_OK(Put("a", "1"));
+  ASSERT_OK(Put("y", "1"));
+  ASSERT_OK(Put("z", "1"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put("a", "1"));
+  ASSERT_OK(Put("z", "1"));
+  ASSERT_OK(Put("bar", "1"));
+  ASSERT_OK(Put("foo", "1"));
+  ASSERT_OK(Put("foo", "2"));
+
+  ASSERT_OK(Put("foo", "3"));
+  ASSERT_OK(Put("foo", "4"));
+  ASSERT_OK(Put("foo", "5"));
+  const Snapshot* snapshot = db_->GetSnapshot();
+  ASSERT_OK(Put("foo", "6"));
+
+  std::string upper_bound = "x";
+  Slice ub_slice(upper_bound);
+  ReadOptions ro;
+  ro.snapshot = snapshot;
+  ro.iterate_upper_bound = &ub_slice;
+
+  Iterator* iter = NewIterator(ro);
+  iter->SeekForPrev("goo");
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ("foo", iter->key().ToString());
+  iter->Prev();
+
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ("bar", iter->key().ToString());
+
+  delete iter;
+  db_->ReleaseSnapshot(snapshot);
+}
+
 TEST_P(DBIteratorTest, SkipStatistics) {
   Options options = CurrentOptions();
   options.statistics = rocksdb::CreateDBStatistics();

db/db_options_test.cc

@@ -242,12 +242,11 @@ TEST_F(DBOptionsTest, WritableFileMaxBufferSize) {
   ASSERT_EQ(unmatch_cnt, 0);
   ASSERT_GE(match_cnt, 11);
 
-  ASSERT_OK(
-      dbfull()->SetDBOptions({{"writable_file_max_buffer_size", "524288"}}));
   buffer_size = 512 * 1024;
   match_cnt = 0;
-  unmatch_cnt = 0;  // SetDBOptions() will create a WriteableFileWriter
-
+  unmatch_cnt = 0;
+  ASSERT_OK(
+      dbfull()->SetDBOptions({{"writable_file_max_buffer_size", "524288"}}));
   ASSERT_EQ(buffer_size,
             dbfull()->GetDBOptions().writable_file_max_buffer_size);
   i = 0;

db/db_properties_test.cc

@@ -177,16 +177,17 @@ void ParseTablePropertiesString(std::string tp_string, TableProperties* tp) {
   std::replace(tp_string.begin(), tp_string.end(), ';', ' ');
   std::replace(tp_string.begin(), tp_string.end(), '=', ' ');
   ResetTableProperties(tp);
+
   sscanf(tp_string.c_str(),
          "# data blocks %" SCNu64 " # entries %" SCNu64 " raw key size %" SCNu64
          " raw average key size %lf "
          " raw value size %" SCNu64
          " raw average value size %lf "
-         " data block size %" SCNu64 " index block size (user-key? %" SCNu64
-         ") %" SCNu64 " filter block size %" SCNu64,
+         " data block size %" SCNu64 " index block size %" SCNu64
+         " filter block size %" SCNu64,
          &tp->num_data_blocks, &tp->num_entries, &tp->raw_key_size,
          &dummy_double, &tp->raw_value_size, &dummy_double, &tp->data_size,
-         &tp->index_key_is_user_key, &tp->index_size, &tp->filter_size);
+         &tp->index_size, &tp->filter_size);
 }
 
 void VerifySimilar(uint64_t a, uint64_t b, double bias) {
@@ -223,8 +224,7 @@ void GetExpectedTableProperties(TableProperties* expected_tp,
                                 const int kKeySize, const int kValueSize,
                                 const int kKeysPerTable, const int kTableCount,
                                 const int kBloomBitsPerKey,
-                                const size_t kBlockSize,
-                                const bool index_key_is_user_key) {
+                                const size_t kBlockSize) {
   const int kKeyCount = kTableCount * kKeysPerTable;
   const int kAvgSuccessorSize = kKeySize / 5;
   const int kEncodingSavePerKey = kKeySize / 4;
@@ -238,8 +238,7 @@ void GetExpectedTableProperties(TableProperties* expected_tp,
   expected_tp->data_size =
       kTableCount * (kKeysPerTable * (kKeySize + 8 + kValueSize));
   expected_tp->index_size =
-      expected_tp->num_data_blocks *
-      (kAvgSuccessorSize + (index_key_is_user_key ? 0 : 8));
+      expected_tp->num_data_blocks * (kAvgSuccessorSize + 8);
   expected_tp->filter_size =
       kTableCount * (kKeysPerTable * kBloomBitsPerKey / 8);
 }
@@ -316,14 +315,14 @@ TEST_F(DBPropertiesTest, AggregatedTableProperties) {
     }
     std::string property;
     db_->GetProperty(DB::Properties::kAggregatedTableProperties, &property);
-    TableProperties output_tp;
-    ParseTablePropertiesString(property, &output_tp);
-    bool index_key_is_user_key = output_tp.index_key_is_user_key > 0;
 
     TableProperties expected_tp;
     GetExpectedTableProperties(&expected_tp, kKeySize, kValueSize,
                                kKeysPerTable, kTableCount, kBloomBitsPerKey,
-                               table_options.block_size, index_key_is_user_key);
+                               table_options.block_size);
+
+    TableProperties output_tp;
+    ParseTablePropertiesString(property, &output_tp);
 
     VerifyTableProperties(expected_tp, output_tp);
   }
@@ -490,7 +489,6 @@ TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
     }
     db_->GetProperty(DB::Properties::kAggregatedTableProperties, &tp_string);
     ParseTablePropertiesString(tp_string, &tp);
-    bool index_key_is_user_key = tp.index_key_is_user_key > 0;
     ASSERT_EQ(sum_tp.data_size, tp.data_size);
     ASSERT_EQ(sum_tp.index_size, tp.index_size);
     ASSERT_EQ(sum_tp.filter_size, tp.filter_size);
@@ -499,9 +497,9 @@ TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
     ASSERT_EQ(sum_tp.num_data_blocks, tp.num_data_blocks);
     ASSERT_EQ(sum_tp.num_entries, tp.num_entries);
     if (table > 3) {
-      GetExpectedTableProperties(
-          &expected_tp, kKeySize, kValueSize, kKeysPerTable, table,
-          kBloomBitsPerKey, table_options.block_size, index_key_is_user_key);
+      GetExpectedTableProperties(&expected_tp, kKeySize, kValueSize,
+                                 kKeysPerTable, table, kBloomBitsPerKey,
+                                 table_options.block_size);
       // Gives larger bias here as index block size, filter block size,
       // and data block size become much harder to estimate in this test.
       VerifyTableProperties(tp, expected_tp, 0.5, 0.4, 0.4, 0.25);

db/db_test.cc

@@ -2153,14 +2153,10 @@ TEST_F(DBTest, GroupCommitTest) {
   do {
     Options options = CurrentOptions();
     options.env = env_;
+    env_->log_write_slowdown_.store(100);
     options.statistics = rocksdb::CreateDBStatistics();
     Reopen(options);
 
-    rocksdb::SyncPoint::GetInstance()->LoadDependency(
-        {{"WriteThread::JoinBatchGroup:BeganWaiting",
-          "DBImpl::WriteImpl:BeforeLeaderEnters"}});
-    rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
     // Start threads
     GCThread thread[kGCNumThreads];
     for (int id = 0; id < kGCNumThreads; id++) {
@@ -2169,7 +2165,13 @@ TEST_F(DBTest, GroupCommitTest) {
       thread[id].done = false;
       env_->StartThread(GCThreadBody, &thread[id]);
     }
-    env_->WaitForJoin();
+
+    for (int id = 0; id < kGCNumThreads; id++) {
+      while (thread[id].done == false) {
+        env_->SleepForMicroseconds(100000);
+      }
+    }
+    env_->log_write_slowdown_.store(0);
 
     ASSERT_GT(TestGetTickerCount(options, WRITE_DONE_BY_OTHER), 0);
 
@@ -2561,7 +2563,6 @@ class ModelDB : public DB {
   std::string name_ = "";
 };
 
-#ifndef ROCKSDB_VALGRIND_RUN
 static std::string RandomKey(Random* rnd, int minimum = 0) {
   int len;
   do {
@@ -2718,7 +2719,6 @@ TEST_P(DBTestRandomized, Randomized) {
   if (model_snap != nullptr) model.ReleaseSnapshot(model_snap);
   if (db_snap != nullptr) db_->ReleaseSnapshot(db_snap);
 }
-#endif  // ROCKSDB_VALGRIND_RUN
 
 TEST_F(DBTest, BlockBasedTablePrefixIndexTest) {
   // create a DB with block prefix index
@@ -4607,181 +4607,6 @@ TEST_F(DBTest, FileCreationRandomFailure) {
 }
 
 #ifndef ROCKSDB_LITE
-int CountIter(Iterator* iter, const Slice& key) {
-  int count = 0;
-  for (iter->Seek(key); iter->Valid() && iter->status() == Status::OK();
-       iter->Next()) {
-    count++;
-  }
-  return count;
-}
-
-// Create multiple SST files each with a different prefix_extractor config,
-// verify iterators can read all SST files using the latest config.
-TEST_F(DBTest, DynamicBloomFilterMultipleSST) {
-  Options options;
-  options.create_if_missing = true;
-  options.prefix_extractor.reset(NewFixedPrefixTransform(1));
-  options.disable_auto_compactions = true;
-  // Enable prefix bloom for SST files
-  BlockBasedTableOptions table_options;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(10, true));
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  DestroyAndReopen(options);
-
-  ReadOptions read_options;
-  read_options.prefix_same_as_start = true;
-
-  // first SST with fixed:1 BF
-  ASSERT_OK(Put("foo2", "bar2"));
-  ASSERT_OK(Put("foo", "bar"));
-  ASSERT_OK(Put("foq1", "bar1"));
-  ASSERT_OK(Put("fpa", "0"));
-  dbfull()->Flush(FlushOptions());
-  Iterator* iter_old = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter_old, "foo"), 4);
-
-  ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
-  ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                      "rocksdb.CappedPrefix.3"));
-  Iterator* iter = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter, "foo"), 2);
-
-  // second SST with capped:3 BF
-  ASSERT_OK(Put("foo3", "bar3"));
-  ASSERT_OK(Put("foo4", "bar4"));
-  ASSERT_OK(Put("foq5", "bar5"));
-  ASSERT_OK(Put("fpb", "1"));
-  dbfull()->Flush(FlushOptions());
-  // BF is cappped:3 now
-  Iterator* iter_tmp = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter_tmp, "foo"), 4);
-  delete iter_tmp;
-
-  ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:2"}}));
-  ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                      "rocksdb.FixedPrefix.2"));
-  // third SST with fixed:2 BF
-  ASSERT_OK(Put("foo6", "bar6"));
-  ASSERT_OK(Put("foo7", "bar7"));
-  ASSERT_OK(Put("foq8", "bar8"));
-  ASSERT_OK(Put("fpc", "2"));
-  dbfull()->Flush(FlushOptions());
-  // BF is fixed:2 now
-  iter_tmp = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter_tmp, "foo"), 9);
-  delete iter_tmp;
-
-  // TODO(Zhongyi): verify existing iterator cannot see newly inserted keys
-  ASSERT_EQ(CountIter(iter_old, "foo"), 4);
-  ASSERT_EQ(CountIter(iter, "foo"), 2);
-  delete iter;
-  delete iter_old;
-
-  // keys in all three SSTs are visible to iterator
-  Iterator* iter_all = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter_all, "foo"), 9);
-  delete iter_all;
-  ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
-  ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                      "rocksdb.CappedPrefix.3"));
-  iter_all = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter_all, "foo"), 6);
-  delete iter_all;
-  // TODO(Zhongyi): add test for cases where certain SST are skipped
-  // Also verify BF related counters like BLOOM_FILTER_USEFUL
-}
-
-// Create a new column family in a running DB, change prefix_extractor
-// dynamically, verify the iterator created on the new column family behaves
-// as expected
-TEST_F(DBTest, DynamicBloomFilterNewColumnFamily) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.prefix_extractor.reset(NewFixedPrefixTransform(1));
-  options.disable_auto_compactions = true;
-  // Enable prefix bloom for SST files
-  BlockBasedTableOptions table_options;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(10, true));
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  CreateAndReopenWithCF({"pikachu"}, options);
-  ReadOptions read_options;
-  read_options.prefix_same_as_start = true;
-  // create a new CF and set prefix_extractor dynamically
-  options.prefix_extractor.reset(NewCappedPrefixTransform(3));
-  CreateColumnFamilies({"ramen_dojo"}, options);
-  ASSERT_EQ(0,
-            strcmp(dbfull()->GetOptions(handles_[2]).prefix_extractor->Name(),
-                   "rocksdb.CappedPrefix.3"));
-  ASSERT_OK(Put(2, "foo3", "bar3"));
-  ASSERT_OK(Put(2, "foo4", "bar4"));
-  ASSERT_OK(Put(2, "foo5", "bar5"));
-  ASSERT_OK(Put(2, "foq6", "bar6"));
-  ASSERT_OK(Put(2, "fpq7", "bar7"));
-  dbfull()->Flush(FlushOptions());
-  Iterator* iter = db_->NewIterator(read_options, handles_[2]);
-  ASSERT_EQ(CountIter(iter, "foo"), 3);
-  delete iter;
-  ASSERT_OK(
-      dbfull()->SetOptions(handles_[2], {{"prefix_extractor", "fixed:2"}}));
-  ASSERT_EQ(0,
-            strcmp(dbfull()->GetOptions(handles_[2]).prefix_extractor->Name(),
-                   "rocksdb.FixedPrefix.2"));
-  iter = db_->NewIterator(read_options, handles_[2]);
-  ASSERT_EQ(CountIter(iter, "foo"), 4);
-  delete iter;
-}
-
-// Verify it's possible to change prefix_extractor at runtime and iterators
-// behaves as expected
-TEST_F(DBTest, DynamicBloomFilterOptions) {
-  Options options;
-  options.create_if_missing = true;
-  options.prefix_extractor.reset(NewFixedPrefixTransform(1));
-  options.disable_auto_compactions = true;
-  // Enable prefix bloom for SST files
-  BlockBasedTableOptions table_options;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(10, true));
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  DestroyAndReopen(options);
-
-  ASSERT_OK(Put("foo2", "bar2"));
-  ASSERT_OK(Put("foo", "bar"));
-  ASSERT_OK(Put("foo1", "bar1"));
-  ASSERT_OK(Put("fpa", "0"));
-  dbfull()->Flush(FlushOptions());
-  ASSERT_OK(Put("foo3", "bar3"));
-  ASSERT_OK(Put("foo4", "bar4"));
-  ASSERT_OK(Put("foo5", "bar5"));
-  ASSERT_OK(Put("fpb", "1"));
-  dbfull()->Flush(FlushOptions());
-  ASSERT_OK(Put("foo6", "bar6"));
-  ASSERT_OK(Put("foo7", "bar7"));
-  ASSERT_OK(Put("foo8", "bar8"));
-  ASSERT_OK(Put("fpc", "2"));
-  dbfull()->Flush(FlushOptions());
-
-  ReadOptions read_options;
-  read_options.prefix_same_as_start = true;
-  Iterator* iter = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter, "foo"), 12);
-  delete iter;
-  Iterator* iter_old = db_->NewIterator(read_options);
-  ASSERT_EQ(CountIter(iter_old, "foo"), 12);
-
-  ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
-  ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                      "rocksdb.CappedPrefix.3"));
-  iter = db_->NewIterator(read_options);
-  // "fp*" should be skipped
-  ASSERT_EQ(CountIter(iter, "foo"), 9);
-  delete iter;
-
-  // iterator created before should not be affected and see all keys
-  ASSERT_EQ(CountIter(iter_old, "foo"), 12);
-  delete iter_old;
-}
-
 TEST_F(DBTest, DynamicMiscOptions) {
   // Test max_sequential_skip_in_iterations
   Options options;
@@ -5620,17 +5445,18 @@ TEST_F(DBTest, HardLimit) {
 #if !defined(ROCKSDB_LITE) && !defined(ROCKSDB_DISABLE_STALL_NOTIFICATION)
 class WriteStallListener : public EventListener {
  public:
-  WriteStallListener()
-      : cond_(&mutex_),
-        condition_(WriteStallCondition::kNormal),
-        expected_(WriteStallCondition::kNormal),
-        expected_set_(false) {}
+  WriteStallListener() : cond_(&mutex_), 
+    condition_(WriteStallCondition::kNormal),
+    expected_(WriteStallCondition::kNormal),
+    expected_set_(false) 
+  {}
   void OnStallConditionsChanged(const WriteStallInfo& info) override {
     MutexLock l(&mutex_);
     condition_ = info.condition.cur;
-    if (expected_set_ && condition_ == expected_) {
-      cond_.Signal();
-      expected_set_ = false;
+    if (expected_set_ && 
+      condition_ == expected_) {
+        cond_.Signal();
+        expected_set_ = false;
     }
   }
   bool CheckCondition(WriteStallCondition expected) {

db/db_universal_compaction_test.cc

@@ -10,7 +10,6 @@
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
 #if !defined(ROCKSDB_LITE)
-#include "rocksdb/utilities/table_properties_collectors.h"
 #include "util/sync_point.h"
 
 namespace rocksdb {
@@ -41,12 +40,6 @@ class DBTestUniversalCompaction : public DBTestUniversalCompactionBase {
       DBTestUniversalCompactionBase("/db_universal_compaction_test") {}
 };
 
-class DBTestUniversalDeleteTrigCompaction : public DBTestBase {
- public:
-  DBTestUniversalDeleteTrigCompaction()
-      : DBTestBase("/db_universal_compaction_test") {}
-};
-
 namespace {
 void VerifyCompactionResult(
     const ColumnFamilyMetaData& cf_meta,
@@ -662,7 +655,7 @@ TEST_P(DBTestUniversalCompaction, UniversalCompactionTargetLevel) {
   ASSERT_EQ("0,0,0,0,1", FilesPerLevel(0));
 }
 
-#ifndef ROCKSDB_VALGRIND_RUN
+
 class DBTestUniversalCompactionMultiLevels
     : public DBTestUniversalCompactionBase {
  public:
@@ -698,7 +691,6 @@ TEST_P(DBTestUniversalCompactionMultiLevels, UniversalCompactionMultiLevels) {
     ASSERT_EQ(Get(1, Key(i % num_keys)), Key(i));
   }
 }
-
 // Tests universal compaction with trivial move enabled
 TEST_P(DBTestUniversalCompactionMultiLevels, UniversalCompactionTrivialMove) {
   int32_t trivial_move = 0;
@@ -941,7 +933,6 @@ INSTANTIATE_TEST_CASE_P(DBTestUniversalCompactionParallel,
                         DBTestUniversalCompactionParallel,
                         ::testing::Combine(::testing::Values(1, 10),
                                            ::testing::Values(false)));
-#endif  // ROCKSDB_VALGRIND_RUN
 
 TEST_P(DBTestUniversalCompaction, UniversalCompactionOptions) {
   Options options = CurrentOptions();
@@ -1157,7 +1148,6 @@ TEST_P(DBTestUniversalCompaction, UniversalCompactionCompressRatio2) {
   ASSERT_LT(TotalSize(), 120000U * 12 * 0.8 + 120000 * 2);
 }
 
-#ifndef ROCKSDB_VALGRIND_RUN
 // Test that checks trivial move in universal compaction
 TEST_P(DBTestUniversalCompaction, UniversalCompactionTrivialMoveTest1) {
   int32_t trivial_move = 0;
@@ -1250,7 +1240,6 @@ TEST_P(DBTestUniversalCompaction, UniversalCompactionTrivialMoveTest2) {
 
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
-#endif  // ROCKSDB_VALGRIND_RUN
 
 TEST_P(DBTestUniversalCompaction, UniversalCompactionFourPaths) {
   Options options = CurrentOptions();
@@ -1856,241 +1845,6 @@ INSTANTIATE_TEST_CASE_P(DBTestUniversalManualCompactionOutputPathId,
                         ::testing::Combine(::testing::Values(1, 8),
                                            ::testing::Bool()));
 
-TEST_F(DBTestUniversalDeleteTrigCompaction, BasicL0toL1) {
-  const int kNumKeys = 3000;
-  const int kWindowSize = 100;
-  const int kNumDelsTrigger = 90;
-
-  Options opts = CurrentOptions();
-  opts.table_properties_collector_factories.emplace_back(
-      NewCompactOnDeletionCollectorFactory(kWindowSize, kNumDelsTrigger));
-  opts.compaction_style = kCompactionStyleUniversal;
-  opts.level0_file_num_compaction_trigger = 2;
-  opts.compression = kNoCompression;
-  opts.compaction_options_universal.size_ratio = 10;
-  opts.compaction_options_universal.min_merge_width = 2;
-  opts.compaction_options_universal.max_size_amplification_percent = 200;
-  Reopen(opts);
-
-  // add an L1 file to prevent tombstones from dropping due to obsolescence
-  // during flush
-  int i;
-  for (i = 0; i < 2000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  //  MoveFilesToLevel(6);
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-
-  for (i = 1999; i < kNumKeys; ++i) {
-    if (i >= kNumKeys - kWindowSize &&
-        i < kNumKeys - kWindowSize + kNumDelsTrigger) {
-      Delete(Key(i));
-    } else {
-      Put(Key(i), "val");
-    }
-  }
-  Flush();
-
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
-  ASSERT_GT(NumTableFilesAtLevel(6), 0);
-}
-
-TEST_F(DBTestUniversalDeleteTrigCompaction, SingleLevel) {
-  const int kNumKeys = 3000;
-  const int kWindowSize = 100;
-  const int kNumDelsTrigger = 90;
-
-  Options opts = CurrentOptions();
-  opts.table_properties_collector_factories.emplace_back(
-      NewCompactOnDeletionCollectorFactory(kWindowSize, kNumDelsTrigger));
-  opts.compaction_style = kCompactionStyleUniversal;
-  opts.level0_file_num_compaction_trigger = 2;
-  opts.compression = kNoCompression;
-  opts.num_levels = 1;
-  opts.compaction_options_universal.size_ratio = 10;
-  opts.compaction_options_universal.min_merge_width = 2;
-  opts.compaction_options_universal.max_size_amplification_percent = 200;
-  Reopen(opts);
-
-  // add an L1 file to prevent tombstones from dropping due to obsolescence
-  // during flush
-  int i;
-  for (i = 0; i < 2000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-
-  for (i = 1999; i < kNumKeys; ++i) {
-    if (i >= kNumKeys - kWindowSize &&
-        i < kNumKeys - kWindowSize + kNumDelsTrigger) {
-      Delete(Key(i));
-    } else {
-      Put(Key(i), "val");
-    }
-  }
-  Flush();
-
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(1, NumTableFilesAtLevel(0));
-}
-
-TEST_F(DBTestUniversalDeleteTrigCompaction, MultipleLevels) {
-  const int kWindowSize = 100;
-  const int kNumDelsTrigger = 90;
-
-  Options opts = CurrentOptions();
-  opts.table_properties_collector_factories.emplace_back(
-      NewCompactOnDeletionCollectorFactory(kWindowSize, kNumDelsTrigger));
-  opts.compaction_style = kCompactionStyleUniversal;
-  opts.level0_file_num_compaction_trigger = 4;
-  opts.compression = kNoCompression;
-  opts.compaction_options_universal.size_ratio = 10;
-  opts.compaction_options_universal.min_merge_width = 2;
-  opts.compaction_options_universal.max_size_amplification_percent = 200;
-  Reopen(opts);
-
-  // add an L1 file to prevent tombstones from dropping due to obsolescence
-  // during flush
-  int i;
-  for (i = 0; i < 500; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 500; i < 1000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 1000; i < 1500; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 1500; i < 2000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
-  ASSERT_GT(NumTableFilesAtLevel(6), 0);
-
-  for (i = 1999; i < 2333; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 2333; i < 2666; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 2666; i < 2999; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
-  ASSERT_GT(NumTableFilesAtLevel(6), 0);
-  ASSERT_GT(NumTableFilesAtLevel(5), 0);
-
-  for (i = 1900; i < 2100; ++i) {
-    Delete(Key(i));
-  }
-  Flush();
-
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
-  ASSERT_EQ(0, NumTableFilesAtLevel(1));
-  ASSERT_EQ(0, NumTableFilesAtLevel(2));
-  ASSERT_EQ(0, NumTableFilesAtLevel(3));
-  ASSERT_EQ(0, NumTableFilesAtLevel(4));
-  ASSERT_EQ(0, NumTableFilesAtLevel(5));
-  ASSERT_GT(NumTableFilesAtLevel(6), 0);
-}
-
-TEST_F(DBTestUniversalDeleteTrigCompaction, OverlappingL0) {
-  const int kWindowSize = 100;
-  const int kNumDelsTrigger = 90;
-
-  Options opts = CurrentOptions();
-  opts.table_properties_collector_factories.emplace_back(
-      NewCompactOnDeletionCollectorFactory(kWindowSize, kNumDelsTrigger));
-  opts.compaction_style = kCompactionStyleUniversal;
-  opts.level0_file_num_compaction_trigger = 5;
-  opts.compression = kNoCompression;
-  opts.compaction_options_universal.size_ratio = 10;
-  opts.compaction_options_universal.min_merge_width = 2;
-  opts.compaction_options_universal.max_size_amplification_percent = 200;
-  Reopen(opts);
-
-  // add an L1 file to prevent tombstones from dropping due to obsolescence
-  // during flush
-  int i;
-  for (i = 0; i < 2000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 2000; i < 3000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 3500; i < 4000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  for (i = 2900; i < 3100; ++i) {
-    Delete(Key(i));
-  }
-  Flush();
-
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(2, NumTableFilesAtLevel(0));
-  ASSERT_GT(NumTableFilesAtLevel(6), 0);
-}
-
-TEST_F(DBTestUniversalDeleteTrigCompaction, IngestBehind) {
-  const int kNumKeys = 3000;
-  const int kWindowSize = 100;
-  const int kNumDelsTrigger = 90;
-
-  Options opts = CurrentOptions();
-  opts.table_properties_collector_factories.emplace_back(
-      NewCompactOnDeletionCollectorFactory(kWindowSize, kNumDelsTrigger));
-  opts.compaction_style = kCompactionStyleUniversal;
-  opts.level0_file_num_compaction_trigger = 2;
-  opts.compression = kNoCompression;
-  opts.allow_ingest_behind = true;
-  opts.compaction_options_universal.size_ratio = 10;
-  opts.compaction_options_universal.min_merge_width = 2;
-  opts.compaction_options_universal.max_size_amplification_percent = 200;
-  Reopen(opts);
-
-  // add an L1 file to prevent tombstones from dropping due to obsolescence
-  // during flush
-  int i;
-  for (i = 0; i < 2000; ++i) {
-    Put(Key(i), "val");
-  }
-  Flush();
-  //  MoveFilesToLevel(6);
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-
-  for (i = 1999; i < kNumKeys; ++i) {
-    if (i >= kNumKeys - kWindowSize &&
-        i < kNumKeys - kWindowSize + kNumDelsTrigger) {
-      Delete(Key(i));
-    } else {
-      Put(Key(i), "val");
-    }
-  }
-  Flush();
-
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
-  ASSERT_EQ(0, NumTableFilesAtLevel(6));
-  ASSERT_GT(NumTableFilesAtLevel(5), 0);
-}
-
 }  // namespace rocksdb
 
 #endif  // !defined(ROCKSDB_LITE)

db/external_sst_file_ingestion_job.cc

@@ -29,13 +29,13 @@
 namespace rocksdb {
 
 Status ExternalSstFileIngestionJob::Prepare(
-    const std::vector<std::string>& external_files_paths, SuperVersion* sv) {
+    const std::vector<std::string>& external_files_paths) {
   Status status;
 
   // Read the information of files we are ingesting
   for (const std::string& file_path : external_files_paths) {
     IngestedFileInfo file_to_ingest;
-    status = GetIngestedFileInfo(file_path, &file_to_ingest, sv);
+    status = GetIngestedFileInfo(file_path, &file_to_ingest);
     if (!status.ok()) {
       return status;
     }
@@ -284,8 +284,7 @@ void ExternalSstFileIngestionJob::Cleanup(const Status& status) {
 }
 
 Status ExternalSstFileIngestionJob::GetIngestedFileInfo(
-    const std::string& external_file, IngestedFileInfo* file_to_ingest,
-    SuperVersion* sv) {
+    const std::string& external_file, IngestedFileInfo* file_to_ingest) {
   file_to_ingest->external_file_path = external_file;
 
   // Get external file size
@@ -307,9 +306,8 @@ Status ExternalSstFileIngestionJob::GetIngestedFileInfo(
                                                    external_file));
 
   status = cfd_->ioptions()->table_factory->NewTableReader(
-      TableReaderOptions(*cfd_->ioptions(),
-                         sv->mutable_cf_options.prefix_extractor.get(),
-                         env_options_, cfd_->internal_comparator()),
+      TableReaderOptions(*cfd_->ioptions(), env_options_,
+                         cfd_->internal_comparator()),
       std::move(sst_file_reader), file_to_ingest->file_size, &table_reader);
   if (!status.ok()) {
     return status;
@@ -365,8 +363,7 @@ Status ExternalSstFileIngestionJob::GetIngestedFileInfo(
   // We need to disable fill_cache so that we read from the file without
   // updating the block cache.
   ro.fill_cache = false;
-  std::unique_ptr<InternalIterator> iter(table_reader->NewIterator(
-      ro, sv->mutable_cf_options.prefix_extractor.get()));
+  std::unique_ptr<InternalIterator> iter(table_reader->NewIterator(ro));
 
   // Get first (smallest) key from file
   iter->SeekToFirst();

db/external_sst_file_ingestion_job.h

@@ -86,8 +86,7 @@ class ExternalSstFileIngestionJob {
         job_start_time_(env_->NowMicros()) {}
 
   // Prepare the job by copying external files into the DB.
-  Status Prepare(const std::vector<std::string>& external_files_paths,
-                 SuperVersion* sv);
+  Status Prepare(const std::vector<std::string>& external_files_paths);
 
   // Check if we need to flush the memtable before running the ingestion job
   // This will be true if the files we are ingesting are overlapping with any
@@ -120,8 +119,7 @@ class ExternalSstFileIngestionJob {
   // Open the external file and populate `file_to_ingest` with all the
   // external information we need to ingest this file.
   Status GetIngestedFileInfo(const std::string& external_file,
-                             IngestedFileInfo* file_to_ingest,
-                             SuperVersion* sv);
+                             IngestedFileInfo* file_to_ingest);
 
   // Assign `file_to_ingest` the appropriate sequence number and  the lowest
   // possible level that it can be ingested to according to compaction_style.

db/forward_iterator.cc

@@ -33,16 +33,14 @@ class ForwardLevelIterator : public InternalIterator {
  public:
   ForwardLevelIterator(const ColumnFamilyData* const cfd,
                        const ReadOptions& read_options,
-                       const std::vector<FileMetaData*>& files,
-                       const SliceTransform* prefix_extractor)
+                       const std::vector<FileMetaData*>& files)
       : cfd_(cfd),
         read_options_(read_options),
         files_(files),
         valid_(false),
         file_index_(std::numeric_limits<uint32_t>::max()),
         file_iter_(nullptr),
-        pinned_iters_mgr_(nullptr),
-        prefix_extractor_(prefix_extractor) {}
+        pinned_iters_mgr_(nullptr) {}
 
   ~ForwardLevelIterator() {
     // Reset current pointer
@@ -77,7 +75,7 @@ class ForwardLevelIterator : public InternalIterator {
         read_options_, *(cfd_->soptions()), cfd_->internal_comparator(),
         files_[file_index_]->fd,
         read_options_.ignore_range_deletions ? nullptr : &range_del_agg,
-        prefix_extractor_, nullptr /* table_reader_ptr */, nullptr, false);
+        nullptr /* table_reader_ptr */, nullptr, false);
     file_iter_->SetPinnedItersMgr(pinned_iters_mgr_);
     valid_ = false;
     if (!range_del_agg.IsEmpty()) {
@@ -190,7 +188,6 @@ class ForwardLevelIterator : public InternalIterator {
   Status status_;
   InternalIterator* file_iter_;
   PinnedIteratorsManager* pinned_iters_mgr_;
-  const SliceTransform* prefix_extractor_;
 };
 
 ForwardIterator::ForwardIterator(DBImpl* db, const ReadOptions& read_options,
@@ -199,7 +196,7 @@ ForwardIterator::ForwardIterator(DBImpl* db, const ReadOptions& read_options,
     : db_(db),
       read_options_(read_options),
       cfd_(cfd),
-      prefix_extractor_(current_sv->mutable_cf_options.prefix_extractor.get()),
+      prefix_extractor_(cfd->ioptions()->prefix_extractor),
       user_comparator_(cfd->user_comparator()),
       immutable_min_heap_(MinIterComparator(&cfd_->internal_comparator())),
       sv_(current_sv),
@@ -636,8 +633,7 @@ void ForwardIterator::RebuildIterators(bool refresh_sv) {
     }
     l0_iters_.push_back(cfd_->table_cache()->NewIterator(
         read_options_, *cfd_->soptions(), cfd_->internal_comparator(), l0->fd,
-        read_options_.ignore_range_deletions ? nullptr : &range_del_agg,
-        sv_->mutable_cf_options.prefix_extractor.get()));
+        read_options_.ignore_range_deletions ? nullptr : &range_del_agg));
   }
   BuildLevelIterators(vstorage);
   current_ = nullptr;
@@ -707,8 +703,7 @@ void ForwardIterator::RenewIterators() {
     l0_iters_new.push_back(cfd_->table_cache()->NewIterator(
         read_options_, *cfd_->soptions(), cfd_->internal_comparator(),
         l0_files_new[inew]->fd,
-        read_options_.ignore_range_deletions ? nullptr : &range_del_agg,
-        svnew->mutable_cf_options.prefix_extractor.get()));
+        read_options_.ignore_range_deletions ? nullptr : &range_del_agg));
   }
 
   for (auto* f : l0_iters_) {
@@ -749,9 +744,8 @@ void ForwardIterator::BuildLevelIterators(const VersionStorageInfo* vstorage) {
         has_iter_trimmed_for_upper_bound_ = true;
       }
     } else {
-      level_iters_.push_back(new ForwardLevelIterator(
-          cfd_, read_options_, level_files,
-          sv_->mutable_cf_options.prefix_extractor.get()));
+      level_iters_.push_back(
+          new ForwardLevelIterator(cfd_, read_options_, level_files));
     }
   }
 }
@@ -766,8 +760,7 @@ void ForwardIterator::ResetIncompleteIterators() {
     DeleteIterator(l0_iters_[i]);
     l0_iters_[i] = cfd_->table_cache()->NewIterator(
         read_options_, *cfd_->soptions(), cfd_->internal_comparator(),
-        l0_files[i]->fd, nullptr /* range_del_agg */,
-        sv_->mutable_cf_options.prefix_extractor.get());
+        l0_files[i]->fd, nullptr /* range_del_agg */);
     l0_iters_[i]->SetPinnedItersMgr(pinned_iters_mgr_);
   }
 

db/internal_stats.cc

@@ -788,8 +788,8 @@ bool InternalStats::HandleEstimateTableReadersMem(uint64_t* value,
 }
 
 bool InternalStats::HandleEstimateLiveDataSize(uint64_t* value, DBImpl* /*db*/,
-                                               Version* version) {
-  const auto* vstorage = version->storage_info();
+                                               Version* /*version*/) {
+  const auto* vstorage = cfd_->current()->storage_info();
   *value = vstorage->EstimateLiveDataSize();
   return true;
 }

db/memtable.cc

@@ -74,8 +74,8 @@ MemTable::MemTable(const InternalKeyComparator& cmp,
               : nullptr,
           mutable_cf_options.memtable_huge_page_size),
       table_(ioptions.memtable_factory->CreateMemTableRep(
-          comparator_, &arena_, mutable_cf_options.prefix_extractor.get(),
-          ioptions.info_log, column_family_id)),
+          comparator_, &arena_, ioptions.prefix_extractor, ioptions.info_log,
+          column_family_id)),
       range_del_table_(SkipListFactory().CreateMemTableRep(
           comparator_, &arena_, nullptr /* transform */, ioptions.info_log,
           column_family_id)),
@@ -95,7 +95,7 @@ MemTable::MemTable(const InternalKeyComparator& cmp,
       locks_(moptions_.inplace_update_support
                  ? moptions_.inplace_update_num_locks
                  : 0),
-      prefix_extractor_(mutable_cf_options.prefix_extractor.get()),
+      prefix_extractor_(ioptions.prefix_extractor),
       flush_state_(FLUSH_NOT_REQUESTED),
       env_(ioptions.env),
       insert_with_hint_prefix_extractor_(

db/plain_table_db_test.cc

@@ -262,13 +262,11 @@ class TestPlainTableReader : public PlainTableReader {
                        const TableProperties* table_properties,
                        unique_ptr<RandomAccessFileReader>&& file,
                        const ImmutableCFOptions& ioptions,
-                       const SliceTransform* prefix_extractor,
                        bool* expect_bloom_not_match, bool store_index_in_file,
                        uint32_t column_family_id,
                        const std::string& column_family_name)
       : PlainTableReader(ioptions, std::move(file), env_options, icomparator,
-                         encoding_type, file_size, table_properties,
-                         prefix_extractor),
+                         encoding_type, file_size, table_properties),
         expect_bloom_not_match_(expect_bloom_not_match) {
     Status s = MmapDataIfNeeded();
     EXPECT_TRUE(s.ok());
@@ -362,8 +360,7 @@ class TestPlainTableFactory : public PlainTableFactory {
         table_reader_options.env_options,
         table_reader_options.internal_comparator, encoding_type, file_size,
         bloom_bits_per_key_, hash_table_ratio_, index_sparseness_, props,
-        std::move(file), table_reader_options.ioptions,
-        table_reader_options.prefix_extractor, expect_bloom_not_match_,
+        std::move(file), table_reader_options.ioptions, expect_bloom_not_match_,
         store_index_in_file_, column_family_id_, column_family_name_));
 
     *table = std::move(new_reader);

db/range_del_aggregator.cc

@@ -195,10 +195,6 @@ Status RangeDelAggregator::AddTombstones(
   input->SeekToFirst();
   bool first_iter = true;
   while (input->Valid()) {
-    // The tombstone map holds slices into the iterator's memory. This assert
-    // ensures pinning the iterator also pins the keys/values.
-    assert(input->IsKeyPinned() && input->IsValuePinned());
-
     if (first_iter) {
       if (rep_ == nullptr) {
         InitRep({upper_bound_});

db/repair.cc

@@ -501,8 +501,7 @@ class Repairer {
     if (status.ok()) {
       InternalIterator* iter = table_cache_->NewIterator(
           ReadOptions(), env_options_, cfd->internal_comparator(), t->meta.fd,
-          nullptr /* range_del_agg */,
-          cfd->GetLatestMutableCFOptions()->prefix_extractor.get());
+          nullptr /* range_del_agg */);
       bool empty = true;
       ParsedInternalKey parsed;
       t->min_sequence = 0;

db/table_cache.cc

@@ -89,8 +89,8 @@ Status TableCache::GetTableReader(
     const InternalKeyComparator& internal_comparator, const FileDescriptor& fd,
     bool sequential_mode, size_t readahead, bool record_read_stats,
     HistogramImpl* file_read_hist, unique_ptr<TableReader>* table_reader,
-    const SliceTransform* prefix_extractor, bool skip_filters, int level,
-    bool prefetch_index_and_filter_in_cache, bool for_compaction) {
+    bool skip_filters, int level, bool prefetch_index_and_filter_in_cache,
+    bool for_compaction) {
   std::string fname =
       TableFileName(ioptions_.cf_paths, fd.GetNumber(), fd.GetPathId());
   unique_ptr<RandomAccessFile> file;
@@ -115,8 +115,8 @@ Status TableCache::GetTableReader(
             record_read_stats ? ioptions_.statistics : nullptr, SST_READ_MICROS,
             file_read_hist, ioptions_.rate_limiter, for_compaction));
     s = ioptions_.table_factory->NewTableReader(
-        TableReaderOptions(ioptions_, prefix_extractor, env_options,
-                           internal_comparator, skip_filters, level),
+        TableReaderOptions(ioptions_, env_options, internal_comparator,
+                           skip_filters, level),
         std::move(file_reader), fd.GetFileSize(), table_reader,
         prefetch_index_and_filter_in_cache);
     TEST_SYNC_POINT("TableCache::GetTableReader:0");
@@ -134,7 +134,6 @@ void TableCache::EraseHandle(const FileDescriptor& fd, Cache::Handle* handle) {
 Status TableCache::FindTable(const EnvOptions& env_options,
                              const InternalKeyComparator& internal_comparator,
                              const FileDescriptor& fd, Cache::Handle** handle,
-                             const SliceTransform* prefix_extractor,
                              const bool no_io, bool record_read_stats,
                              HistogramImpl* file_read_hist, bool skip_filters,
                              int level,
@@ -155,8 +154,7 @@ Status TableCache::FindTable(const EnvOptions& env_options,
     s = GetTableReader(env_options, internal_comparator, fd,
                        false /* sequential mode */, 0 /* readahead */,
                        record_read_stats, file_read_hist, &table_reader,
-                       prefix_extractor, skip_filters, level,
-                       prefetch_index_and_filter_in_cache);
+                       skip_filters, level, prefetch_index_and_filter_in_cache);
     if (!s.ok()) {
       assert(table_reader == nullptr);
       RecordTick(ioptions_.statistics, NO_FILE_ERRORS);
@@ -177,9 +175,9 @@ Status TableCache::FindTable(const EnvOptions& env_options,
 InternalIterator* TableCache::NewIterator(
     const ReadOptions& options, const EnvOptions& env_options,
     const InternalKeyComparator& icomparator, const FileDescriptor& fd,
-    RangeDelAggregator* range_del_agg, const SliceTransform* prefix_extractor,
-    TableReader** table_reader_ptr, HistogramImpl* file_read_hist,
-    bool for_compaction, Arena* arena, bool skip_filters, int level) {
+    RangeDelAggregator* range_del_agg, TableReader** table_reader_ptr,
+    HistogramImpl* file_read_hist, bool for_compaction, Arena* arena,
+    bool skip_filters, int level) {
   PERF_TIMER_GUARD(new_table_iterator_nanos);
 
   Status s;
@@ -212,7 +210,7 @@ InternalIterator* TableCache::NewIterator(
     s = GetTableReader(
         env_options, icomparator, fd, true /* sequential_mode */, readahead,
         !for_compaction /* record stats */, nullptr, &table_reader_unique_ptr,
-        prefix_extractor, false /* skip_filters */, level,
+        false /* skip_filters */, level,
         true /* prefetch_index_and_filter_in_cache */, for_compaction);
     if (s.ok()) {
       table_reader = table_reader_unique_ptr.release();
@@ -220,7 +218,7 @@ InternalIterator* TableCache::NewIterator(
   } else {
     table_reader = fd.table_reader;
     if (table_reader == nullptr) {
-      s = FindTable(env_options, icomparator, fd, &handle, prefix_extractor,
+      s = FindTable(env_options, icomparator, fd, &handle,
                     options.read_tier == kBlockCacheTier /* no_io */,
                     !for_compaction /* record read_stats */, file_read_hist,
                     skip_filters, level);
@@ -235,8 +233,7 @@ InternalIterator* TableCache::NewIterator(
         !options.table_filter(*table_reader->GetTableProperties())) {
       result = NewEmptyInternalIterator(arena);
     } else {
-      result = table_reader->NewIterator(options, prefix_extractor, arena,
-                                         skip_filters);
+      result = table_reader->NewIterator(options, arena, skip_filters);
     }
     if (create_new_table_reader) {
       assert(handle == nullptr);
@@ -279,13 +276,12 @@ InternalIterator* TableCache::NewIterator(
 InternalIterator* TableCache::NewRangeTombstoneIterator(
     const ReadOptions& options, const EnvOptions& env_options,
     const InternalKeyComparator& icomparator, const FileDescriptor& fd,
-    HistogramImpl* file_read_hist, bool skip_filters, int level,
-    const SliceTransform* prefix_extractor) {
+    HistogramImpl* file_read_hist, bool skip_filters, int level) {
   Status s;
   Cache::Handle* handle = nullptr;
   TableReader* table_reader = fd.table_reader;
   if (table_reader == nullptr) {
-    s = FindTable(env_options, icomparator, fd, &handle, prefix_extractor,
+    s = FindTable(env_options, icomparator, fd, &handle,
                   options.read_tier == kBlockCacheTier /* no_io */,
                   true /* record read_stats */, file_read_hist, skip_filters,
                   level);
@@ -317,10 +313,8 @@ InternalIterator* TableCache::NewRangeTombstoneIterator(
 Status TableCache::Get(const ReadOptions& options,
                        const InternalKeyComparator& internal_comparator,
                        const FileDescriptor& fd, const Slice& k,
-                       GetContext* get_context,
-                       const SliceTransform* prefix_extractor,
-                       HistogramImpl* file_read_hist, bool skip_filters,
-                       int level) {
+                       GetContext* get_context, HistogramImpl* file_read_hist,
+                       bool skip_filters, int level) {
   std::string* row_cache_entry = nullptr;
   bool done = false;
 #ifndef ROCKSDB_LITE
@@ -384,10 +378,10 @@ Status TableCache::Get(const ReadOptions& options,
   Cache::Handle* handle = nullptr;
   if (!done && s.ok()) {
     if (t == nullptr) {
-      s = FindTable(
-          env_options_, internal_comparator, fd, &handle, prefix_extractor,
-          options.read_tier == kBlockCacheTier /* no_io */,
-          true /* record_read_stats */, file_read_hist, skip_filters, level);
+      s = FindTable(env_options_, internal_comparator, fd, &handle,
+                    options.read_tier == kBlockCacheTier /* no_io */,
+                    true /* record_read_stats */, file_read_hist, skip_filters,
+                    level);
       if (s.ok()) {
         t = GetTableReaderFromHandle(handle);
       }
@@ -406,7 +400,7 @@ Status TableCache::Get(const ReadOptions& options,
     }
     if (s.ok()) {
       get_context->SetReplayLog(row_cache_entry);  // nullptr if no cache.
-      s = t->Get(options, k, get_context, prefix_extractor, skip_filters);
+      s = t->Get(options, k, get_context, skip_filters);
       get_context->SetReplayLog(nullptr);
     } else if (options.read_tier == kBlockCacheTier && s.IsIncomplete()) {
       // Couldn't find Table in cache but treat as kFound if no_io set
@@ -436,8 +430,7 @@ Status TableCache::Get(const ReadOptions& options,
 Status TableCache::GetTableProperties(
     const EnvOptions& env_options,
     const InternalKeyComparator& internal_comparator, const FileDescriptor& fd,
-    std::shared_ptr<const TableProperties>* properties,
-    const SliceTransform* prefix_extractor, bool no_io) {
+    std::shared_ptr<const TableProperties>* properties, bool no_io) {
   Status s;
   auto table_reader = fd.table_reader;
   // table already been pre-loaded?
@@ -448,8 +441,7 @@ Status TableCache::GetTableProperties(
   }
 
   Cache::Handle* table_handle = nullptr;
-  s = FindTable(env_options, internal_comparator, fd, &table_handle,
-                prefix_extractor, no_io);
+  s = FindTable(env_options, internal_comparator, fd, &table_handle, no_io);
   if (!s.ok()) {
     return s;
   }
@@ -462,8 +454,8 @@ Status TableCache::GetTableProperties(
 
 size_t TableCache::GetMemoryUsageByTableReader(
     const EnvOptions& env_options,
-    const InternalKeyComparator& internal_comparator, const FileDescriptor& fd,
-    const SliceTransform* prefix_extractor) {
+    const InternalKeyComparator& internal_comparator,
+    const FileDescriptor& fd) {
   Status s;
   auto table_reader = fd.table_reader;
   // table already been pre-loaded?
@@ -472,8 +464,7 @@ size_t TableCache::GetMemoryUsageByTableReader(
   }
 
   Cache::Handle* table_handle = nullptr;
-  s = FindTable(env_options, internal_comparator, fd, &table_handle,
-                prefix_extractor, true);
+  s = FindTable(env_options, internal_comparator, fd, &table_handle, true);
   if (!s.ok()) {
     return 0;
   }

db/table_cache.h

@@ -54,7 +54,6 @@ class TableCache {
       const ReadOptions& options, const EnvOptions& toptions,
       const InternalKeyComparator& internal_comparator,
       const FileDescriptor& file_fd, RangeDelAggregator* range_del_agg,
-      const SliceTransform* prefix_extractor = nullptr,
       TableReader** table_reader_ptr = nullptr,
       HistogramImpl* file_read_hist = nullptr, bool for_compaction = false,
       Arena* arena = nullptr, bool skip_filters = false, int level = -1);
@@ -63,8 +62,7 @@ class TableCache {
       const ReadOptions& options, const EnvOptions& toptions,
       const InternalKeyComparator& internal_comparator,
       const FileDescriptor& file_fd, HistogramImpl* file_read_hist,
-      bool skip_filters, int level,
-      const SliceTransform* prefix_extractor = nullptr);
+      bool skip_filters, int level);
 
   // If a seek to internal key "k" in specified file finds an entry,
   // call (*handle_result)(arg, found_key, found_value) repeatedly until
@@ -77,10 +75,8 @@ class TableCache {
   Status Get(const ReadOptions& options,
              const InternalKeyComparator& internal_comparator,
              const FileDescriptor& file_fd, const Slice& k,
-             GetContext* get_context,
-             const SliceTransform* prefix_extractor = nullptr,
-             HistogramImpl* file_read_hist = nullptr, bool skip_filters = false,
-             int level = -1);
+             GetContext* get_context, HistogramImpl* file_read_hist = nullptr,
+             bool skip_filters = false, int level = -1);
 
   // Evict any entry for the specified file number
   static void Evict(Cache* cache, uint64_t file_number);
@@ -95,7 +91,6 @@ class TableCache {
   Status FindTable(const EnvOptions& toptions,
                    const InternalKeyComparator& internal_comparator,
                    const FileDescriptor& file_fd, Cache::Handle**,
-                   const SliceTransform* prefix_extractor = nullptr,
                    const bool no_io = false, bool record_read_stats = true,
                    HistogramImpl* file_read_hist = nullptr,
                    bool skip_filters = false, int level = -1,
@@ -114,7 +109,6 @@ class TableCache {
                             const InternalKeyComparator& internal_comparator,
                             const FileDescriptor& file_meta,
                             std::shared_ptr<const TableProperties>* properties,
-                            const SliceTransform* prefix_extractor = nullptr,
                             bool no_io = false);
 
   // Return total memory usage of the table reader of the file.
@@ -122,8 +116,7 @@ class TableCache {
   size_t GetMemoryUsageByTableReader(
       const EnvOptions& toptions,
       const InternalKeyComparator& internal_comparator,
-      const FileDescriptor& fd,
-      const SliceTransform* prefix_extractor = nullptr);
+      const FileDescriptor& fd);
 
   // Release the handle from a cache
   void ReleaseHandle(Cache::Handle* handle);
@@ -140,7 +133,6 @@ class TableCache {
                         size_t readahead, bool record_read_stats,
                         HistogramImpl* file_read_hist,
                         unique_ptr<TableReader>* table_reader,
-                        const SliceTransform* prefix_extractor = nullptr,
                         bool skip_filters = false, int level = -1,
                         bool prefetch_index_and_filter_in_cache = true,
                         bool for_compaction = false);

db/table_properties_collector_test.cc

@@ -39,7 +39,6 @@ static const uint32_t kTestColumnFamilyId = 66;
 static const std::string kTestColumnFamilyName = "test_column_fam";
 
 void MakeBuilder(const Options& options, const ImmutableCFOptions& ioptions,
-                 const MutableCFOptions& moptions,
                  const InternalKeyComparator& internal_comparator,
                  const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
                      int_tbl_prop_collector_factories,
@@ -49,9 +48,10 @@ void MakeBuilder(const Options& options, const ImmutableCFOptions& ioptions,
   writable->reset(new WritableFileWriter(std::move(wf), EnvOptions()));
   int unknown_level = -1;
   builder->reset(NewTableBuilder(
-      ioptions, moptions, internal_comparator, int_tbl_prop_collector_factories,
-      kTestColumnFamilyId, kTestColumnFamilyName, writable->get(),
-      options.compression, options.compression_opts, unknown_level));
+      ioptions, internal_comparator, int_tbl_prop_collector_factories,
+      kTestColumnFamilyId, kTestColumnFamilyName,
+      writable->get(), options.compression, options.compression_opts,
+      unknown_level));
 }
 }  // namespace
 
@@ -251,7 +251,6 @@ void TestCustomizedTablePropertiesCollector(
   std::unique_ptr<TableBuilder> builder;
   std::unique_ptr<WritableFileWriter> writer;
   const ImmutableCFOptions ioptions(options);
-  const MutableCFOptions moptions(options);
   std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
       int_tbl_prop_collector_factories;
   if (test_int_tbl_prop_collector) {
@@ -260,7 +259,7 @@ void TestCustomizedTablePropertiesCollector(
   } else {
     GetIntTblPropCollectorFactory(ioptions, &int_tbl_prop_collector_factories);
   }
-  MakeBuilder(options, ioptions, moptions, internal_comparator,
+  MakeBuilder(options, ioptions, internal_comparator,
               &int_tbl_prop_collector_factories, &writer, &builder);
 
   SequenceNumber seqNum = 0U;
@@ -402,11 +401,10 @@ void TestInternalKeyPropertiesCollector(
         new InternalKeyPropertiesCollectorFactory);
   }
   const ImmutableCFOptions ioptions(options);
-  MutableCFOptions moptions(options);
 
   for (int iter = 0; iter < 2; ++iter) {
-    MakeBuilder(options, ioptions, moptions, pikc,
-                &int_tbl_prop_collector_factories, &writable, &builder);
+    MakeBuilder(options, ioptions, pikc, &int_tbl_prop_collector_factories,
+                &writable, &builder);
     for (const auto& k : keys) {
       builder->Add(k.Encode(), "val");
     }

db/version_builder.cc

@@ -368,8 +368,7 @@ class VersionBuilder::Rep {
   }
 
   void LoadTableHandlers(InternalStats* internal_stats, int max_threads,
-                         bool prefetch_index_and_filter_in_cache,
-                         const SliceTransform* prefix_extractor) {
+                         bool prefetch_index_and_filter_in_cache) {
     assert(table_cache_ != nullptr);
     // <file metadata, level>
     std::vector<std::pair<FileMetaData*, int>> files_meta;
@@ -391,12 +390,12 @@ class VersionBuilder::Rep {
 
         auto* file_meta = files_meta[file_idx].first;
         int level = files_meta[file_idx].second;
-        table_cache_->FindTable(
-            env_options_, *(base_vstorage_->InternalComparator()),
-            file_meta->fd, &file_meta->table_reader_handle, prefix_extractor,
-            false /*no_io */, true /* record_read_stats */,
-            internal_stats->GetFileReadHist(level), false, level,
-            prefetch_index_and_filter_in_cache);
+        table_cache_->FindTable(env_options_,
+                                *(base_vstorage_->InternalComparator()),
+                                file_meta->fd, &file_meta->table_reader_handle,
+                                false /*no_io */, true /* record_read_stats */,
+                                internal_stats->GetFileReadHist(level), false,
+                                level, prefetch_index_and_filter_in_cache);
         if (file_meta->table_reader_handle != nullptr) {
           // Load table_reader
           file_meta->fd.table_reader = table_cache_->GetTableReaderFromHandle(
@@ -456,12 +455,11 @@ void VersionBuilder::SaveTo(VersionStorageInfo* vstorage) {
   rep_->SaveTo(vstorage);
 }
 
-void VersionBuilder::LoadTableHandlers(InternalStats* internal_stats,
-                                       int max_threads,
-                                       bool prefetch_index_and_filter_in_cache,
-                                       const SliceTransform* prefix_extractor) {
+void VersionBuilder::LoadTableHandlers(
+    InternalStats* internal_stats, int max_threads,
+    bool prefetch_index_and_filter_in_cache) {
   rep_->LoadTableHandlers(internal_stats, max_threads,
-                          prefetch_index_and_filter_in_cache, prefix_extractor);
+                          prefetch_index_and_filter_in_cache);
 }
 
 void VersionBuilder::MaybeAddFile(VersionStorageInfo* vstorage, int level,

db/version_builder.h

@@ -9,7 +9,6 @@
 //
 #pragma once
 #include "rocksdb/env.h"
-#include "rocksdb/slice_transform.h"
 
 namespace rocksdb {
 
@@ -34,8 +33,7 @@ class VersionBuilder {
   void Apply(VersionEdit* edit);
   void SaveTo(VersionStorageInfo* vstorage);
   void LoadTableHandlers(InternalStats* internal_stats, int max_threads,
-                         bool prefetch_index_and_filter_in_cache,
-                         const SliceTransform* prefix_extractor);
+                         bool prefetch_index_and_filter_in_cache);
   void MaybeAddFile(VersionStorageInfo* vstorage, int level, FileMetaData* f);
 
  private:

db/version_edit.cc

@@ -20,7 +20,7 @@ namespace rocksdb {
 
 // Tag numbers for serialized VersionEdit.  These numbers are written to
 // disk and should not be changed.
-enum Tag : uint32_t {
+enum Tag {
   kComparator = 1,
   kLogNumber = 2,
   kNextFileNumber = 3,
@@ -42,7 +42,7 @@ enum Tag : uint32_t {
   kMaxColumnFamily = 203,
 };
 
-enum CustomTag : uint32_t {
+enum CustomTag {
   kTerminate = 1,  // The end of customized fields
   kNeedCompaction = 2,
   // Since Manifest is not entirely currently forward-compatible, and the only

db/version_set.cc

@@ -463,8 +463,7 @@ class LevelIterator final : public InternalIterator {
   LevelIterator(TableCache* table_cache, const ReadOptions& read_options,
                 const EnvOptions& env_options,
                 const InternalKeyComparator& icomparator,
-                const LevelFilesBrief* flevel,
-                const SliceTransform* prefix_extractor, bool should_sample,
+                const LevelFilesBrief* flevel, bool should_sample,
                 HistogramImpl* file_read_hist, bool for_compaction,
                 bool skip_filters, int level, RangeDelAggregator* range_del_agg)
       : table_cache_(table_cache),
@@ -472,7 +471,6 @@ class LevelIterator final : public InternalIterator {
         env_options_(env_options),
         icomparator_(icomparator),
         flevel_(flevel),
-        prefix_extractor_(prefix_extractor),
         file_read_hist_(file_read_hist),
         should_sample_(should_sample),
         for_compaction_(for_compaction),
@@ -549,9 +547,8 @@ class LevelIterator final : public InternalIterator {
 
     return table_cache_->NewIterator(
         read_options_, env_options_, icomparator_, file_meta.fd, range_del_agg_,
-        prefix_extractor_, nullptr /* don't need reference to table */,
-        file_read_hist_, for_compaction_, nullptr /* arena */, skip_filters_,
-        level_);
+        nullptr /* don't need reference to table */, file_read_hist_,
+        for_compaction_, nullptr /* arena */, skip_filters_, level_);
   }
 
   TableCache* table_cache_;
@@ -560,7 +557,6 @@ class LevelIterator final : public InternalIterator {
   const InternalKeyComparator& icomparator_;
   const LevelFilesBrief* flevel_;
   mutable FileDescriptor current_value_;
-  const SliceTransform* prefix_extractor_;
 
   HistogramImpl* file_read_hist_;
   bool should_sample_;
@@ -726,8 +722,8 @@ Status Version::GetTableProperties(std::shared_ptr<const TableProperties>* tp,
   auto table_cache = cfd_->table_cache();
   auto ioptions = cfd_->ioptions();
   Status s = table_cache->GetTableProperties(
-      env_options_, cfd_->internal_comparator(), file_meta->fd, tp,
-      mutable_cf_options_.prefix_extractor.get(), true /* no io */);
+      env_options_, cfd_->internal_comparator(), file_meta->fd,
+      tp, true /* no io */);
   if (s.ok()) {
     return s;
   }
@@ -861,8 +857,8 @@ size_t Version::GetMemoryUsageByTableReaders() {
   for (auto& file_level : storage_info_.level_files_brief_) {
     for (size_t i = 0; i < file_level.num_files; i++) {
       total_usage += cfd_->table_cache()->GetMemoryUsageByTableReader(
-          env_options_, cfd_->internal_comparator(), file_level.files[i].fd,
-          mutable_cf_options_.prefix_extractor.get());
+          env_options_, cfd_->internal_comparator(),
+          file_level.files[i].fd);
     }
   }
   return total_usage;
@@ -1000,9 +996,8 @@ void Version::AddIteratorsForLevel(const ReadOptions& read_options,
       const auto& file = storage_info_.LevelFilesBrief(0).files[i];
       merge_iter_builder->AddIterator(cfd_->table_cache()->NewIterator(
           read_options, soptions, cfd_->internal_comparator(), file.fd,
-          range_del_agg, mutable_cf_options_.prefix_extractor.get(), nullptr,
-          cfd_->internal_stats()->GetFileReadHist(0), false, arena,
-          false /* skip_filters */, 0 /* level */));
+          range_del_agg, nullptr, cfd_->internal_stats()->GetFileReadHist(0),
+          false, arena, false /* skip_filters */, 0 /* level */));
     }
     if (should_sample) {
       // Count ones for every L0 files. This is done per iterator creation
@@ -1021,7 +1016,7 @@ void Version::AddIteratorsForLevel(const ReadOptions& read_options,
     merge_iter_builder->AddIterator(new (mem) LevelIterator(
         cfd_->table_cache(), read_options, soptions,
         cfd_->internal_comparator(), &storage_info_.LevelFilesBrief(level),
-        mutable_cf_options_.prefix_extractor.get(), should_sample_file_read(),
+        should_sample_file_read(),
         cfd_->internal_stats()->GetFileReadHist(level),
         false /* for_compaction */, IsFilterSkipped(level), level,
         range_del_agg));
@@ -1053,9 +1048,8 @@ Status Version::OverlapWithLevelIterator(const ReadOptions& read_options,
       }
       ScopedArenaIterator iter(cfd_->table_cache()->NewIterator(
           read_options, env_options, cfd_->internal_comparator(), file->fd,
-          &range_del_agg, mutable_cf_options_.prefix_extractor.get(), nullptr,
-          cfd_->internal_stats()->GetFileReadHist(0), false, &arena,
-          false /* skip_filters */, 0 /* level */));
+          &range_del_agg, nullptr, cfd_->internal_stats()->GetFileReadHist(0),
+          false, &arena, false /* skip_filters */, 0 /* level */));
       status = OverlapWithIterator(
           ucmp, smallest_user_key, largest_user_key, iter.get(), overlap);
       if (!status.ok() || *overlap) {
@@ -1067,7 +1061,7 @@ Status Version::OverlapWithLevelIterator(const ReadOptions& read_options,
     ScopedArenaIterator iter(new (mem) LevelIterator(
         cfd_->table_cache(), read_options, env_options,
         cfd_->internal_comparator(), &storage_info_.LevelFilesBrief(level),
-        mutable_cf_options_.prefix_extractor.get(), should_sample_file_read(),
+        should_sample_file_read(),
         cfd_->internal_stats()->GetFileReadHist(level),
         false /* for_compaction */, IsFilterSkipped(level), level,
         &range_del_agg));
@@ -1128,9 +1122,7 @@ VersionStorageInfo::VersionStorageInfo(
 }
 
 Version::Version(ColumnFamilyData* column_family_data, VersionSet* vset,
-                 const EnvOptions& env_opt,
-                 const MutableCFOptions mutable_cf_options,
-                 uint64_t version_number)
+                 const EnvOptions& env_opt, uint64_t version_number)
     : env_(vset->env_),
       cfd_(column_family_data),
       info_log_((cfd_ == nullptr) ? nullptr : cfd_->ioptions()->info_log),
@@ -1154,7 +1146,6 @@ Version::Version(ColumnFamilyData* column_family_data, VersionSet* vset,
       prev_(this),
       refs_(0),
       env_options_(env_opt),
-      mutable_cf_options_(mutable_cf_options),
       version_number_(version_number) {}
 
 void Version::Get(const ReadOptions& read_options, const LookupKey& k,
@@ -1198,7 +1189,6 @@ void Version::Get(const ReadOptions& read_options, const LookupKey& k,
 
     *status = table_cache_->Get(
         read_options, *internal_comparator(), f->fd, ikey, &get_context,
-        mutable_cf_options_.prefix_extractor.get(),
         cfd_->internal_stats()->GetFileReadHist(fp.GetHitFileLevel()),
         IsFilterSkipped(static_cast<int>(fp.GetHitFileLevel()),
                         fp.IsHitFileLastInLevel()),
@@ -2785,7 +2775,7 @@ Status VersionSet::LogAndApply(ColumnFamilyData* column_family_data,
     LogAndApplyCFHelper(w.edit_list.front());
     batch_edits.push_back(w.edit_list.front());
   } else {
-    v = new Version(column_family_data, this, env_options_, mutable_cf_options,
+    v = new Version(column_family_data, this, env_options_,
                     current_version_number_++);
     builder_guard.reset(new BaseReferencedVersionBuilder(column_family_data));
     auto* builder = builder_guard->version_builder();
@@ -2846,8 +2836,7 @@ Status VersionSet::LogAndApply(ColumnFamilyData* column_family_data,
       builder_guard->version_builder()->LoadTableHandlers(
           column_family_data->internal_stats(),
           column_family_data->ioptions()->optimize_filters_for_hits,
-          true /* prefetch_index_and_filter_in_cache */,
-          mutable_cf_options.prefix_extractor.get());
+          true /* prefetch_index_and_filter_in_cache */);
     }
 
     // This is fine because everything inside of this block is serialized --
@@ -3338,13 +3327,11 @@ Status VersionSet::Recover(
         // Need to do it out of the mutex.
         builder->LoadTableHandlers(
             cfd->internal_stats(), db_options_->max_file_opening_threads,
-            false /* prefetch_index_and_filter_in_cache */,
-            cfd->GetLatestMutableCFOptions()->prefix_extractor.get());
+            false /* prefetch_index_and_filter_in_cache */);
       }
 
-      Version* v = new Version(cfd, this, env_options_,
-                               *cfd->GetLatestMutableCFOptions(),
-                               current_version_number_++);
+      Version* v =
+          new Version(cfd, this, env_options_, current_version_number_++);
       builder->SaveTo(v->storage_info());
 
       // Install recovered version
@@ -3709,9 +3696,8 @@ Status VersionSet::DumpManifest(Options& options, std::string& dscname,
       assert(builders_iter != builders.end());
       auto builder = builders_iter->second->version_builder();
 
-      Version* v = new Version(cfd, this, env_options_,
-                               *cfd->GetLatestMutableCFOptions(),
-                               current_version_number_++);
+      Version* v =
+          new Version(cfd, this, env_options_, current_version_number_++);
       builder->SaveTo(v->storage_info());
       v->PrepareApply(*cfd->GetLatestMutableCFOptions(), false);
 
@@ -3934,8 +3920,7 @@ uint64_t VersionSet::ApproximateSize(Version* v, const FdWithKeyRange& f,
     TableReader* table_reader_ptr;
     InternalIterator* iter = v->cfd_->table_cache()->NewIterator(
         ReadOptions(), v->env_options_, v->cfd_->internal_comparator(), f.fd,
-        nullptr /* range_del_agg */,
-        v->GetMutableCFOptions().prefix_extractor.get(), &table_reader_ptr);
+        nullptr /* range_del_agg */, &table_reader_ptr);
     if (table_reader_ptr != nullptr) {
       result = table_reader_ptr->ApproximateOffsetOf(key);
     }
@@ -4015,7 +4000,6 @@ InternalIterator* VersionSet::MakeInputIterator(
           list[num++] = cfd->table_cache()->NewIterator(
               read_options, env_options_compactions, cfd->internal_comparator(),
               flevel->files[i].fd, range_del_agg,
-              c->mutable_cf_options()->prefix_extractor.get(),
               nullptr /* table_reader_ptr */,
               nullptr /* no per level latency histogram */,
               true /* for_compaction */, nullptr /* arena */,
@@ -4026,7 +4010,6 @@ InternalIterator* VersionSet::MakeInputIterator(
         list[num++] = new LevelIterator(
             cfd->table_cache(), read_options, env_options_compactions,
             cfd->internal_comparator(), c->input_levels(which),
-            c->mutable_cf_options()->prefix_extractor.get(),
             false /* should_sample */,
             nullptr /* no per level latency histogram */,
             true /* for_compaction */, false /* skip_filters */,
@@ -4166,9 +4149,7 @@ ColumnFamilyData* VersionSet::CreateColumnFamily(
     const ColumnFamilyOptions& cf_options, VersionEdit* edit) {
   assert(edit->is_column_family_add_);
 
-  MutableCFOptions dummy_cf_options;
-  Version* dummy_versions =
-      new Version(nullptr, this, env_options_, dummy_cf_options);
+  Version* dummy_versions = new Version(nullptr, this, env_options_);
   // Ref() dummy version once so that later we can call Unref() to delete it
   // by avoiding calling "delete" explicitly (~Version is private)
   dummy_versions->Ref();
@@ -4176,9 +4157,8 @@ ColumnFamilyData* VersionSet::CreateColumnFamily(
       edit->column_family_name_, edit->column_family_, dummy_versions,
       cf_options);
 
-  Version* v = new Version(new_cfd, this, env_options_,
-                           *new_cfd->GetLatestMutableCFOptions(),
-                           current_version_number_++);
+  Version* v =
+      new Version(new_cfd, this, env_options_, current_version_number_++);
 
   // Fill level target base information.
   v->storage_info()->CalculateBaseBytes(*new_cfd->ioptions(),

db/version_set.h

@@ -633,8 +633,6 @@ class Version {
 
   uint64_t GetSstFilesSize();
 
-  MutableCFOptions GetMutableCFOptions() { return mutable_cf_options_; }
-
  private:
   Env* env_;
   friend class VersionSet;
@@ -682,14 +680,13 @@ class Version {
   Version* prev_;               // Previous version in linked list
   int refs_;                    // Number of live refs to this version
   const EnvOptions env_options_;
-  const MutableCFOptions mutable_cf_options_;
 
   // A version number that uniquely represents this version. This is
   // used for debugging and logging purposes only.
   uint64_t version_number_;
 
   Version(ColumnFamilyData* cfd, VersionSet* vset, const EnvOptions& env_opt,
-          MutableCFOptions mutable_cf_options, uint64_t version_number = 0);
+          uint64_t version_number = 0);
 
   ~Version();
 

db/write_batch.cc

@@ -39,7 +39,6 @@
 #include <stdexcept>
 #include <type_traits>
 #include <vector>
-#include <csignal>
 
 #include "db/column_family.h"
 #include "db/db_impl.h"
@@ -514,7 +513,6 @@ Status WriteBatch::Iterate(Handler* handler) const {
         handler->MarkBeginPrepare();
         empty_batch = false;
         if (handler->WriteAfterCommit()) {
-          std::raise(SIGINT);
           s = Status::NotSupported(
               "WritePrepared txn tag when write_after_commit_ is enabled (in "
               "default WriteCommitted mode). If it is not due to corruption, "

db/write_thread.cc

@@ -318,7 +318,6 @@ void WriteThread::JoinBatchGroup(Writer* w) {
      * 3.2) an existing memtable writer group leader tell us to finish memtable
      *      writes in parallel.
      */
-    TEST_SYNC_POINT_CALLBACK("WriteThread::JoinBatchGroup:BeganWaiting", w);
     AwaitState(w, STATE_GROUP_LEADER | STATE_MEMTABLE_WRITER_LEADER |
                       STATE_PARALLEL_MEMTABLE_WRITER | STATE_COMPLETED,
                &jbg_ctx);

env/env_posix.cc

@@ -241,9 +241,9 @@ class PosixEnv : public Env {
                                                   size, options));
         } else {
           s = IOError("while mmap file for read", fname, errno);
-          close(fd);
         }
       }
+      close(fd);
     } else {
       if (options.use_direct_reads && !options.use_mmap_reads) {
 #ifdef OS_MACOSX

env/env_test.cc

@@ -232,10 +232,10 @@ TEST_F(EnvPosixTest, MemoryMappedFileBuffer) {
 
   ASSERT_OK(status);
   ASSERT_NE(nullptr, mmap_buffer.get());
-  ASSERT_NE(nullptr, mmap_buffer->GetBase());
-  ASSERT_EQ(kFileBytes, mmap_buffer->GetLen());
-  std::string actual_data(reinterpret_cast<const char*>(mmap_buffer->GetBase()),
-                          mmap_buffer->GetLen());
+  ASSERT_NE(nullptr, mmap_buffer->base);
+  ASSERT_EQ(kFileBytes, mmap_buffer->length);
+  std::string actual_data(static_cast<char*>(mmap_buffer->base),
+                          mmap_buffer->length);
   ASSERT_EQ(expected_data, actual_data);
 }
 
@@ -1437,8 +1437,10 @@ TEST_P(EnvPosixTestWithParam, PosixRandomRWFile) {
 
   std::unique_ptr<RandomRWFile> file;
 
+#ifdef OS_LINUX
   // Cannot open non-existing file.
   ASSERT_NOK(env_->NewRandomRWFile(path, &file, EnvOptions()));
+#endif
 
   // Create the file using WriteableFile
   {

env/io_posix.cc

@@ -456,7 +456,6 @@ PosixMmapReadableFile::~PosixMmapReadableFile() {
     fprintf(stdout, "failed to munmap %p length %" ROCKSDB_PRIszt " \n",
             mmapped_region_, length_);
   }
-  close(fd_);
 }
 
 Status PosixMmapReadableFile::Read(uint64_t offset, size_t n, Slice* result,
@@ -1055,7 +1054,7 @@ Status PosixRandomRWFile::Close() {
 
 PosixMemoryMappedFileBuffer::~PosixMemoryMappedFileBuffer() {
   // TODO should have error handling though not much we can do...
-  munmap(this->base_, length_);
+  munmap(this->base, length);
 }
 
 /*

include/rocksdb/advanced_options.h

@@ -87,14 +87,6 @@ struct CompactionOptionsFIFO {
 
 // Compression options for different compression algorithms like Zlib
 struct CompressionOptions {
-  // RocksDB's generic default compression level. Internally it'll be translated
-  // to the default compression level specific to the library being used (see
-  // comment above `ColumnFamilyOptions::compression`).
-  //
-  // The default value is the max 16-bit int as it'll be written out in OPTIONS
-  // file, which should be portable.
-  const static int kDefaultCompressionLevel = 32767;
-
   int window_bits;
   int level;
   int strategy;
@@ -128,7 +120,7 @@ struct CompressionOptions {
 
   CompressionOptions()
       : window_bits(-14),
-        level(kDefaultCompressionLevel),
+        level(-1),
         strategy(0),
         max_dict_bytes(0),
         zstd_max_train_bytes(0) {}

include/rocksdb/c.h

@@ -145,10 +145,6 @@ extern ROCKSDB_LIBRARY_API rocksdb_backup_engine_t* rocksdb_backup_engine_open(
 extern ROCKSDB_LIBRARY_API void rocksdb_backup_engine_create_new_backup(
     rocksdb_backup_engine_t* be, rocksdb_t* db, char** errptr);
 
-extern ROCKSDB_LIBRARY_API void rocksdb_backup_engine_create_new_backup_flush(
-    rocksdb_backup_engine_t* be, rocksdb_t* db, unsigned char flush_before_backup,
-    char** errptr);
-
 extern ROCKSDB_LIBRARY_API void rocksdb_backup_engine_purge_old_backups(
     rocksdb_backup_engine_t* be, uint32_t num_backups_to_keep, char** errptr);
 
@@ -159,10 +155,6 @@ extern ROCKSDB_LIBRARY_API void rocksdb_restore_options_destroy(
 extern ROCKSDB_LIBRARY_API void rocksdb_restore_options_set_keep_log_files(
     rocksdb_restore_options_t* opt, int v);
 
-extern ROCKSDB_LIBRARY_API void
-rocksdb_backup_engine_verify_backup(rocksdb_backup_engine_t* be,
-    uint32_t backup_id, char** errptr);
-
 extern ROCKSDB_LIBRARY_API void
 rocksdb_backup_engine_restore_db_from_latest_backup(
     rocksdb_backup_engine_t* be, const char* db_dir, const char* wal_dir,

include/rocksdb/cache.h

@@ -47,15 +47,6 @@ struct LRUCacheOptions {
   bool strict_capacity_limit = false;
 
   // Percentage of cache reserved for high priority entries.
-  // If greater than zero, the LRU list will be split into a high-pri
-  // list and a low-pri list. High-pri entries will be insert to the
-  // tail of high-pri list, while low-pri entries will be first inserted to
-  // the low-pri list (the midpoint). This is refered to as
-  // midpoint insertion strategy to make entries never get hit in cache
-  // age out faster.
-  //
-  // See also
-  // BlockBasedTableOptions::cache_index_and_filter_blocks_with_high_priority.
   double high_pri_pool_ratio = 0.0;
 
   LRUCacheOptions() {}

include/rocksdb/env.h

@@ -42,7 +42,7 @@ class SequentialFile;
 class Slice;
 class WritableFile;
 class RandomRWFile;
-class MemoryMappedFileBuffer;
+struct MemoryMappedFileBuffer;
 class Directory;
 struct DBOptions;
 struct ImmutableDBOptions;
@@ -822,24 +822,13 @@ class RandomRWFile {
 
 // MemoryMappedFileBuffer object represents a memory-mapped file's raw buffer.
 // Subclasses should release the mapping upon destruction.
-class MemoryMappedFileBuffer {
-public:
+struct MemoryMappedFileBuffer {
   MemoryMappedFileBuffer(void* _base, size_t _length)
-      : base_(_base), length_(_length) {}
-
+      : base(_base), length(_length) {}
   virtual ~MemoryMappedFileBuffer() = 0;
 
-  // We do not want to unmap this twice. We can make this class
-  // movable if desired, however, since
-  MemoryMappedFileBuffer(const MemoryMappedFileBuffer&) = delete;
-  MemoryMappedFileBuffer& operator=(const MemoryMappedFileBuffer&) = delete;
-
-  void*       GetBase() const { return base_;   }
-  size_t      GetLen() const  { return length_; }
-
-protected:
-  void*        base_;
-  const size_t length_;
+  void* const base;
+  const size_t length;
 };
 
 // Directory object represents collection of files and implements

include/rocksdb/options.h

@@ -198,21 +198,11 @@ struct ColumnFamilyOptions : public AdvancedColumnFamilyOptions {
   // Typical speeds of kSnappyCompression on an Intel(R) Core(TM)2 2.4GHz:
   //    ~200-500MB/s compression
   //    ~400-800MB/s decompression
-  //
   // Note that these speeds are significantly faster than most
   // persistent storage speeds, and therefore it is typically never
   // worth switching to kNoCompression.  Even if the input data is
   // incompressible, the kSnappyCompression implementation will
   // efficiently detect that and will switch to uncompressed mode.
-  //
-  // If you do not set `compression_opts.level`, or set it to
-  // `CompressionOptions::kDefaultCompressionLevel`, we will attempt to pick the
-  // default corresponding to `compression` as follows:
-  //
-  // - kZSTD: 3
-  // - kZlibCompression: Z_DEFAULT_COMPRESSION (currently -1)
-  // - kLZ4HCCompression: 0
-  // - For all others, we do not specify a compression level
   CompressionType compression;
 
   // Compression algorithm that will be used for the bottommost level that
@@ -281,7 +271,7 @@ struct ColumnFamilyOptions : public AdvancedColumnFamilyOptions {
   // later in the vector.
   // Note that, if a path is supplied to multiple column
   // families, it would have files and total size from all
-  // the column families combined. User should provision for the
+  // the column families combined. User should privision for the
   // total size(from all the column families) in such cases.
   //
   // If left empty, db_paths will be used.
@@ -568,9 +558,8 @@ struct DBOptions {
 
   // manifest file is rolled over on reaching this limit.
   // The older manifest file be deleted.
-  // The default value is 1GB so that the manifest file can grow, but not
-  // reach the limit of storage capacity.
-  uint64_t max_manifest_file_size = 1024 * 1024 * 1024;
+  // The default value is MAX_INT so that roll-over does not take place.
+  uint64_t max_manifest_file_size = std::numeric_limits<uint64_t>::max();
 
   // Number of shards used for table cache.
   int table_cache_numshardbits = 6;

include/rocksdb/slice.h

@@ -43,9 +43,7 @@ class Slice {
 
   // Create a slice that refers to s[0,strlen(s)-1]
   /* implicit */
-  Slice(const char* s) : data_(s) {
-    size_ = (s == nullptr) ? 0 : strlen(s);
-  }
+  Slice(const char* s) : data_(s), size_(strlen(s)) { }
 
   // Create a single slice from SliceParts using buf as storage.
   // buf must exist as long as the returned Slice exists.

include/rocksdb/sst_file_manager.h

@@ -98,12 +98,13 @@ class SstFileManager {
 //    DeleteScheduler immediately
 // @param bytes_max_delete_chunk: if a single file is larger than delete chunk,
 //    ftruncate the file by this size each time, rather than dropping the whole
-//    file. 0 means to always delete the whole file.
+//    file. 0 means to always delete the whole file. NOTE this options may not
+//    work well with checkpoints, which relies on file system hard links.
 extern SstFileManager* NewSstFileManager(
     Env* env, std::shared_ptr<Logger> info_log = nullptr,
     std::string trash_dir = "", int64_t rate_bytes_per_sec = 0,
     bool delete_existing_trash = true, Status* status = nullptr,
     double max_trash_db_ratio = 0.25,
-    uint64_t bytes_max_delete_chunk = 64 * 1024 * 1024);
+    uint64_t bytes_max_delete_chunk = 0);
 
 }  // namespace rocksdb

include/rocksdb/statistics.h

@@ -619,8 +619,6 @@ struct HistogramData {
   // zero-initialize new members since old Statistics::histogramData()
   // implementations won't write them.
   double max = 0.0;
-  uint64_t count = 0;
-  uint64_t sum = 0;
 };
 
 enum StatsLevel {

include/rocksdb/table.h

@@ -214,11 +214,8 @@ struct BlockBasedTableOptions {
   // encode compressed blocks with LZ4, BZip2 and Zlib compression. If you
   // don't plan to run RocksDB before version 3.10, you should probably use
   // this.
-  // 3 -- Can be read by RocksDB's versions since 5.15. Changes the way we
-  // encode the keys in index blocks. If you don't plan to run RocksDB before
-  // version 5.15, you should probably use this.
-  // This option only affects newly written tables. When reading existing
-  // tables, the information about version is read from the footer.
+  // This option only affects newly written tables. When reading existing tables,
+  // the information about version is read from the footer.
   uint32_t format_version = 2;
 
   // Store index blocks on disk in compressed format. Changing this option to

include/rocksdb/table_properties.h

@@ -33,7 +33,6 @@ struct TablePropertiesNames {
   static const std::string kIndexSize;
   static const std::string kIndexPartitions;
   static const std::string kTopLevelIndexSize;
-  static const std::string kIndexKeyIsUserKey;
   static const std::string kFilterSize;
   static const std::string kRawKeySize;
   static const std::string kRawValueSize;
@@ -135,9 +134,6 @@ struct TableProperties {
   uint64_t index_partitions = 0;
   // Size of the top-level index if kTwoLevelIndexSearch is used
   uint64_t top_level_index_size = 0;
-  // Whether the index key is user key. Otherwise it includes 8 byte of sequence
-  // number added by internal key format.
-  uint64_t index_key_is_user_key = 0;
   // the size of filter block.
   uint64_t filter_size = 0;
   // total raw key size

include/rocksdb/version.h

@@ -6,7 +6,7 @@
 
 #define ROCKSDB_MAJOR 5
 #define ROCKSDB_MINOR 14
-#define ROCKSDB_PATCH 0
+#define ROCKSDB_PATCH 2
 
 // Do not use these. We made the mistake of declaring macros starting with
 // double underscore. Now we have to live with our choice. We'll deprecate these

java/rocksjni/options.cc

@@ -3230,7 +3230,7 @@ Java_org_rocksdb_ColumnFamilyOptions_setCompactionFilterFactoryHandle(
     JNIEnv* /*env*/, jobject /*jobj*/, jlong jopt_handle,
     jlong jcompactionfilterfactory_handle) {
   auto* cff_factory =
-      reinterpret_cast<std::shared_ptr<rocksdb::CompactionFilterFactory>*>(
+      reinterpret_cast<std::shared_ptr<rocksdb::CompactionFilterFactoryJniCallback>*>(
           jcompactionfilterfactory_handle);
   reinterpret_cast<rocksdb::ColumnFamilyOptions*>(jopt_handle)
       ->compaction_filter_factory = *cff_factory;

java/rocksjni/portal.h

@@ -4292,25 +4292,12 @@ class JniUtil {
      * @param bytes The bytes to copy
      *
      * @return the Java byte[] or nullptr if an exception occurs
+     * 
+     * @throws RocksDBException thrown 
+     *   if memory size to copy exceeds general java specific array size limitation.
      */
     static jbyteArray copyBytes(JNIEnv* env, std::string bytes) {
-      const jsize jlen = static_cast<jsize>(bytes.size());
-
-      jbyteArray jbytes = env->NewByteArray(jlen);
-      if(jbytes == nullptr) {
-        // exception thrown: OutOfMemoryError
-        return nullptr;
-      }
-
-      env->SetByteArrayRegion(jbytes, 0, jlen,
-        const_cast<jbyte*>(reinterpret_cast<const jbyte*>(bytes.c_str())));
-      if(env->ExceptionCheck()) {
-        // exception thrown: ArrayIndexOutOfBoundsException
-        env->DeleteLocalRef(jbytes);
-        return nullptr;
-      }
-
-      return jbytes;
+      return createJavaByteArrayWithSizeCheck(env, bytes.c_str(), bytes.size());
     }
 
     /**
@@ -4473,6 +4460,47 @@ class JniUtil {
 
       return jbyte_strings;
     }
+    
+    /**
+      * Copies bytes to a new jByteArray with the check of java array size limitation.
+      *
+      * @param bytes pointer to memory to copy to a new jByteArray
+      * @param size number of bytes to copy
+      *
+      * @return the Java byte[] or nullptr if an exception occurs
+      * 
+      * @throws RocksDBException thrown 
+      *   if memory size to copy exceeds general java array size limitation to avoid overflow.
+      */
+    static jbyteArray createJavaByteArrayWithSizeCheck(JNIEnv* env, const char* bytes, const size_t size) {
+      // Limitation for java array size is vm specific
+      // In general it cannot exceed Integer.MAX_VALUE (2^31 - 1)
+      // Current HotSpot VM limitation for array size is Integer.MAX_VALUE - 5 (2^31 - 1 - 5)
+      // It means that the next call to env->NewByteArray can still end with 
+      // OutOfMemoryError("Requested array size exceeds VM limit") coming from VM
+      static const size_t MAX_JARRAY_SIZE = (static_cast<size_t>(1)) << 31;
+      if(size > MAX_JARRAY_SIZE) {
+        rocksdb::RocksDBExceptionJni::ThrowNew(env, "Requested array size exceeds VM limit");
+        return nullptr;
+      }
+      
+      const jsize jlen = static_cast<jsize>(size);
+      jbyteArray jbytes = env->NewByteArray(jlen);
+      if(jbytes == nullptr) {
+        // exception thrown: OutOfMemoryError	
+        return nullptr;
+      }
+      
+      env->SetByteArrayRegion(jbytes, 0, jlen,
+        const_cast<jbyte*>(reinterpret_cast<const jbyte*>(bytes)));
+      if(env->ExceptionCheck()) {
+        // exception thrown: ArrayIndexOutOfBoundsException
+        env->DeleteLocalRef(jbytes);
+        return nullptr;
+      }
+
+      return jbytes;
+    }
 
     /**
      * Copies bytes from a rocksdb::Slice to a jByteArray
@@ -4481,25 +4509,12 @@ class JniUtil {
      * @param bytes The bytes to copy
      *
      * @return the Java byte[] or nullptr if an exception occurs
+     * 
+     * @throws RocksDBException thrown 
+     *   if memory size to copy exceeds general java specific array size limitation.
      */
     static jbyteArray copyBytes(JNIEnv* env, const Slice& bytes) {
-      const jsize jlen = static_cast<jsize>(bytes.size());
-
-      jbyteArray jbytes = env->NewByteArray(jlen);
-      if(jbytes == nullptr) {
-        // exception thrown: OutOfMemoryError
-        return nullptr;
-      }
-
-      env->SetByteArrayRegion(jbytes, 0, jlen,
-        const_cast<jbyte*>(reinterpret_cast<const jbyte*>(bytes.data())));
-      if(env->ExceptionCheck()) {
-        // exception thrown: ArrayIndexOutOfBoundsException
-        env->DeleteLocalRef(jbytes);
-        return nullptr;
-      }
-
-      return jbytes;
+      return createJavaByteArrayWithSizeCheck(env, bytes.data(), bytes.size());
     }
 
     /*

java/rocksjni/sst_file_manager.cc

@@ -138,7 +138,7 @@ jobject Java_org_rocksdb_SstFileManager_getTrackedFiles(JNIEnv* env,
 
   const rocksdb::HashMapJni::FnMapKV<const std::string, const uint64_t>
       fn_map_kv =
-          [env, &tracked_files](
+          [env](
               const std::pair<const std::string, const uint64_t>& pair) {
             const jstring jtracked_file_path =
                 env->NewStringUTF(pair.first.c_str());

java/rocksjni/transaction.cc

@@ -48,7 +48,7 @@ void Java_org_rocksdb_Transaction_setSnapshotOnNextOperation__JJ(
     jlong jtxn_notifier_handle) {
   auto* txn = reinterpret_cast<rocksdb::Transaction*>(jhandle);
   auto* txn_notifier =
-      reinterpret_cast<std::shared_ptr<rocksdb::TransactionNotifier>*>(
+      reinterpret_cast<std::shared_ptr<rocksdb::TransactionNotifierJniCallback>*>(
           jtxn_notifier_handle);
   txn->SetSnapshotOnNextOperation(*txn_notifier);
 }

java/src/main/java/org/rocksdb/ColumnFamilyHandle.java

@@ -28,8 +28,10 @@ public class ColumnFamilyHandle extends RocksObject {
    * Gets the name of the Column Family.
    *
    * @return The name of the Column Family.
+   *
+   * @throws RocksDBException if an error occurs whilst retrieving the name.
    */
-  public byte[] getName() {
+  public byte[] getName() throws RocksDBException {
     return getName(nativeHandle_);
   }
 
@@ -71,14 +73,22 @@ public class ColumnFamilyHandle extends RocksObject {
     }
 
     final ColumnFamilyHandle that = (ColumnFamilyHandle) o;
-    return rocksDB_.nativeHandle_ == that.rocksDB_.nativeHandle_ &&
-        getID() == that.getID() &&
-        Arrays.equals(getName(), that.getName());
+    try {
+      return rocksDB_.nativeHandle_ == that.rocksDB_.nativeHandle_ &&
+          getID() == that.getID() &&
+          Arrays.equals(getName(), that.getName());
+    } catch (RocksDBException e) {
+      throw new RuntimeException("Cannot compare column family handles", e);
+    }
   }
 
   @Override
   public int hashCode() {
-    return Objects.hash(getName(), getID(), rocksDB_.nativeHandle_);
+    try {
+      return Objects.hash(getName(), getID(), rocksDB_.nativeHandle_);
+    } catch (RocksDBException e) {
+      throw new RuntimeException("Cannot calculate hash code of column family handle", e);
+    }
   }
 
   /**
@@ -96,7 +106,7 @@ public class ColumnFamilyHandle extends RocksObject {
     }
   }
 
-  private native byte[] getName(final long handle);
+  private native byte[] getName(final long handle) throws RocksDBException;
   private native int getID(final long handle);
   private native ColumnFamilyDescriptor getDescriptor(final long handle) throws RocksDBException;
   @Override protected final native void disposeInternal(final long handle);

java/src/main/java/org/rocksdb/WriteBatch.java

@@ -65,8 +65,11 @@ public class WriteBatch extends AbstractWriteBatch {
    * Retrieve the serialized version of this batch.
    *
    * @return the serialized representation of this write batch.
+   *
+   * @throws RocksDBException if an error occurs whilst retrieving
+   *   the serialized batch data.
    */
-  public byte[] data() {
+  public byte[] data() throws RocksDBException {
     return data(nativeHandle_);
   }
 
@@ -253,7 +256,7 @@ public class WriteBatch extends AbstractWriteBatch {
       final int serializedLength);
   private native void iterate(final long handle, final long handlerHandle)
       throws RocksDBException;
-  private native byte[] data(final long nativeHandle);
+  private native byte[] data(final long nativeHandle) throws RocksDBException;
   private native long getDataSize(final long nativeHandle);
   private native boolean hasPut(final long nativeHandle);
   private native boolean hasDelete(final long nativeHandle);

java/src/test/java/org/rocksdb/RocksDBTest.java

@@ -4,9 +4,11 @@
 //  (found in the LICENSE.Apache file in the root directory).
 package org.rocksdb;
 
+import org.junit.Assume;
 import org.junit.ClassRule;
 import org.junit.Rule;
 import org.junit.Test;
+import org.junit.rules.ExpectedException;
 import org.junit.rules.TemporaryFolder;
 
 import java.util.*;
@@ -143,6 +145,39 @@ public class RocksDBTest {
     }
   }
 
+  @Rule
+  public ExpectedException thrown = ExpectedException.none();
+
+  @Test
+  public void getOutOfArrayMaxSizeValue() throws RocksDBException {
+    final int numberOfValueSplits = 10;
+    final int splitSize = Integer.MAX_VALUE / numberOfValueSplits;
+
+    Runtime runtime = Runtime.getRuntime();
+    long neededMemory = ((long)(splitSize)) * (((long)numberOfValueSplits) + 3);
+    boolean isEnoughMemory = runtime.maxMemory() - runtime.totalMemory() > neededMemory;
+    Assume.assumeTrue(isEnoughMemory);
+
+    final byte[] valueSplit = new byte[splitSize];
+    final byte[] key = "key".getBytes();
+
+    thrown.expect(RocksDBException.class);
+    thrown.expectMessage("Requested array size exceeds VM limit");
+
+    // merge (numberOfValueSplits + 1) valueSplit's to get value size exceeding Integer.MAX_VALUE
+    try (final StringAppendOperator stringAppendOperator = new StringAppendOperator();
+         final Options opt = new Options()
+                 .setCreateIfMissing(true)
+                 .setMergeOperator(stringAppendOperator);
+         final RocksDB db = RocksDB.open(opt, dbFolder.getRoot().getAbsolutePath())) {
+      db.put(key, valueSplit);
+      for (int i = 0; i < numberOfValueSplits; i++) {
+        db.merge(key, valueSplit);
+      }
+      db.get(key);
+    }
+  }
+
   @Test
   public void multiGet() throws RocksDBException, InterruptedException {
     try (final RocksDB db = RocksDB.open(dbFolder.getRoot().getAbsolutePath());

memtable/inlineskiplist.h

@@ -184,9 +184,10 @@ class InlineSkipList {
   const uint16_t kBranching_;
   const uint32_t kScaledInverseBranching_;
 
-  Allocator* const allocator_;  // Allocator used for allocations of nodes
   // Immutable after construction
   Comparator const compare_;
+  Allocator* const allocator_;  // Allocator used for allocations of nodes
+
   Node* const head_;
 
   // Modified only by Insert().  Read racily by readers, but stale
@@ -586,8 +587,8 @@ InlineSkipList<Comparator>::InlineSkipList(const Comparator cmp,
     : kMaxHeight_(static_cast<uint16_t>(max_height)),
       kBranching_(static_cast<uint16_t>(branching_factor)),
       kScaledInverseBranching_((Random::kMaxNext + 1) / kBranching_),
-      allocator_(allocator),
       compare_(cmp),
+      allocator_(allocator),
       head_(AllocateNode(0, max_height)),
       max_height_(1),
       seq_splice_(AllocateSplice()) {

memtable/inlineskiplist_test.cc

@@ -309,7 +309,6 @@ TEST_F(InlineSkipTest, InsertWithHint_CompatibleWithInsertWithoutHint) {
   Validate(&list);
 }
 
-#ifndef ROCKSDB_VALGRIND_RUN
 // We want to make sure that with a single writer and multiple
 // concurrent readers (with no synchronization other than when a
 // reader's iterator is created), the reader always observes all the
@@ -636,7 +635,6 @@ TEST_F(InlineSkipTest, ConcurrentInsert1) { RunConcurrentInsert(1); }
 TEST_F(InlineSkipTest, ConcurrentInsert2) { RunConcurrentInsert(2); }
 TEST_F(InlineSkipTest, ConcurrentInsert3) { RunConcurrentInsert(3); }
 
-#endif  // ROCKSDB_VALGRIND_RUN
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

monitoring/histogram.cc

@@ -235,8 +235,6 @@ void HistogramStat::Data(HistogramData * const data) const {
   data->max = static_cast<double>(max());
   data->average = Average();
   data->standard_deviation = StandardDeviation();
-  data->count = num();
-  data->sum = sum();
 }
 
 void HistogramImpl::Clear() {

monitoring/statistics.cc

@@ -169,17 +169,11 @@ std::string StatisticsImpl::ToString() const {
       char buffer[kTmpStrBufferSize];
       HistogramData hData;
       getHistogramImplLocked(h.first)->Data(&hData);
-      // don't handle failures - buffer should always be big enough and arguments
-      // should be provided correctly
-      int ret = snprintf(
+      snprintf(
           buffer, kTmpStrBufferSize,
-          "%s P50 : %f P95 : %f P99 : %f P100 : %f COUNT : %" PRIu64 " SUM : %"
-          PRIu64 "\n", h.second.c_str(), hData.median, hData.percentile95,
-          hData.percentile99, hData.max, hData.count, hData.sum);
-      if (ret < 0 || ret >= kTmpStrBufferSize) {
-        assert(false);
-        continue;
-      }
+          "%s statistics Percentiles :=> 50 : %f 95 : %f 99 : %f 100 : %f\n",
+          h.second.c_str(), hData.median, hData.percentile95,
+          hData.percentile99, hData.max);
       res.append(buffer);
     }
   }

options/cf_options.cc

@@ -27,6 +27,7 @@ ImmutableCFOptions::ImmutableCFOptions(const ImmutableDBOptions& db_options,
                                        const ColumnFamilyOptions& cf_options)
     : compaction_style(cf_options.compaction_style),
       compaction_pri(cf_options.compaction_pri),
+      prefix_extractor(cf_options.prefix_extractor.get()),
       user_comparator(cf_options.comparator),
       internal_comparator(InternalKeyComparator(cf_options.comparator)),
       merge_operator(cf_options.merge_operator.get()),
@@ -142,9 +143,6 @@ void MutableCFOptions::Dump(Logger* log) const {
   ROCKS_LOG_INFO(log,
                  "                 inplace_update_num_locks: %" ROCKSDB_PRIszt,
                  inplace_update_num_locks);
-  ROCKS_LOG_INFO(
-      log, "                         prefix_extractor: %s",
-      prefix_extractor == nullptr ? "nullptr" : prefix_extractor->Name());
   ROCKS_LOG_INFO(log, "                 disable_auto_compactions: %d",
                  disable_auto_compactions);
   ROCKS_LOG_INFO(log, "      soft_pending_compaction_bytes_limit: %" PRIu64,
@@ -191,7 +189,4 @@ void MutableCFOptions::Dump(Logger* log) const {
                  static_cast<int>(compression));
 }
 
-MutableCFOptions::MutableCFOptions(const Options& options)
-    : MutableCFOptions(ColumnFamilyOptions(options)) {}
-
 }  // namespace rocksdb

options/cf_options.h

@@ -30,6 +30,8 @@ struct ImmutableCFOptions {
 
   CompactionPri compaction_pri;
 
+  const SliceTransform* prefix_extractor;
+
   const Comparator* user_comparator;
   InternalKeyComparator internal_comparator;
 
@@ -132,7 +134,6 @@ struct MutableCFOptions {
         memtable_huge_page_size(options.memtable_huge_page_size),
         max_successive_merges(options.max_successive_merges),
         inplace_update_num_locks(options.inplace_update_num_locks),
-        prefix_extractor(options.prefix_extractor),
         disable_auto_compactions(options.disable_auto_compactions),
         soft_pending_compaction_bytes_limit(
             options.soft_pending_compaction_bytes_limit),
@@ -167,7 +168,6 @@ struct MutableCFOptions {
         memtable_huge_page_size(0),
         max_successive_merges(0),
         inplace_update_num_locks(0),
-        prefix_extractor(nullptr),
         disable_auto_compactions(false),
         soft_pending_compaction_bytes_limit(0),
         hard_pending_compaction_bytes_limit(0),
@@ -185,8 +185,6 @@ struct MutableCFOptions {
         report_bg_io_stats(false),
         compression(Snappy_Supported() ? kSnappyCompression : kNoCompression) {}
 
-  explicit MutableCFOptions(const Options& options);
-
   // Must be called after any change to MutableCFOptions
   void RefreshDerivedOptions(int num_levels, CompactionStyle compaction_style);
 
@@ -212,7 +210,6 @@ struct MutableCFOptions {
   size_t memtable_huge_page_size;
   size_t max_successive_merges;
   size_t inplace_update_num_locks;
-  std::shared_ptr<const SliceTransform> prefix_extractor;
 
   // Compaction related options
   bool disable_auto_compactions;

options/options_helper.cc

@@ -145,7 +145,6 @@ ColumnFamilyOptions BuildColumnFamilyOptions(
   cf_opts.max_successive_merges = mutable_cf_options.max_successive_merges;
   cf_opts.inplace_update_num_locks =
       mutable_cf_options.inplace_update_num_locks;
-  cf_opts.prefix_extractor = mutable_cf_options.prefix_extractor;
 
   // Compaction related options
   cf_opts.disable_auto_compactions =
@@ -384,8 +383,7 @@ bool ParseSliceTransformHelper(
     const std::string& kFixedPrefixName, const std::string& kCappedPrefixName,
     const std::string& value,
     std::shared_ptr<const SliceTransform>* slice_transform) {
-  const char* no_op_name = "rocksdb.Noop";
-  size_t no_op_length = strlen(no_op_name);
+
   auto& pe_value = value;
   if (pe_value.size() > kFixedPrefixName.size() &&
       pe_value.compare(0, kFixedPrefixName.size(), kFixedPrefixName) == 0) {
@@ -397,10 +395,6 @@ bool ParseSliceTransformHelper(
     int prefix_length =
         ParseInt(trim(pe_value.substr(kCappedPrefixName.size())));
     slice_transform->reset(NewCappedPrefixTransform(prefix_length));
-  } else if (pe_value.size() == no_op_length &&
-             pe_value.compare(0, no_op_length, no_op_name) == 0) {
-    const SliceTransform* no_op_transform = NewNoopTransform();
-    slice_transform->reset(no_op_transform);
   } else if (value == kNullptrString) {
     slice_transform->reset();
   } else {
@@ -1797,7 +1791,7 @@ std::unordered_map<std::string, OptionTypeInfo>
         {"prefix_extractor",
          {offset_of(&ColumnFamilyOptions::prefix_extractor),
           OptionType::kSliceTransform, OptionVerificationType::kByNameAllowNull,
-          true, offsetof(struct MutableCFOptions, prefix_extractor)}},
+          false, 0}},
         {"memtable_insert_with_hint_prefix_extractor",
          {offset_of(
               &ColumnFamilyOptions::memtable_insert_with_hint_prefix_extractor),

options/options_parser.cc

@@ -17,7 +17,6 @@
 #include "rocksdb/convenience.h"
 #include "rocksdb/db.h"
 #include "util/cast_util.h"
-#include "util/file_reader_writer.h"
 #include "util/string_util.h"
 #include "util/sync_point.h"
 
@@ -42,16 +41,12 @@ Status PersistRocksDBOptions(const DBOptions& db_opt,
     return Status::InvalidArgument(
         "cf_names.size() and cf_opts.size() must be the same");
   }
-  std::unique_ptr<WritableFile> wf;
+  std::unique_ptr<WritableFile> writable;
 
-  Status s = env->NewWritableFile(file_name, &wf, EnvOptions());
+  Status s = env->NewWritableFile(file_name, &writable, EnvOptions());
   if (!s.ok()) {
     return s;
   }
-  unique_ptr<WritableFileWriter> writable;
-  writable.reset(new WritableFileWriter(std::move(wf), EnvOptions(),
-                                        nullptr /* statistics */));
-
   std::string options_file_content;
 
   writable->Append(option_file_header + "[" +
@@ -98,7 +93,8 @@ Status PersistRocksDBOptions(const DBOptions& db_opt,
       writable->Append(options_file_content + "\n");
     }
   }
-  writable->Sync(true /* use_fsync */);
+  writable->Flush();
+  writable->Fsync();
   writable->Close();
 
   return RocksDBOptionsParser::VerifyRocksDBOptionsFromFile(

port/port_posix.cc

@@ -188,6 +188,8 @@ int GetMaxOpenFiles() {
 void *cacheline_aligned_alloc(size_t size) {
 #if __GNUC__ < 5 && defined(__SANITIZE_ADDRESS__)
   return malloc(size);
+#elif defined(_ISOC11_SOURCE)
+  return aligned_alloc(CACHE_LINE_SIZE, size);
 #elif ( _POSIX_C_SOURCE >= 200112L || _XOPEN_SOURCE >= 600 || defined(__APPLE__))
   void *m;
   errno = posix_memalign(&m, CACHE_LINE_SIZE, size);

port/win/env_win.cc

@@ -112,15 +112,6 @@ Status WinEnvIO::DeleteFile(const std::string& fname) {
   return result;
 }
 
-Status WinEnvIO::Truncate(const std::string& fname, size_t size) {
-  Status s;
-  int result = truncate(fname.c_str(), size);
-  if (result != 0) {
-    s = IOError("Failed to truncate: " + fname, errno);
-  }
-  return s;
-}
-
 Status WinEnvIO::GetCurrentTime(int64_t* unix_time) {
   time_t time = std::time(nullptr);
   if (time == (time_t)(-1)) {
@@ -353,7 +344,7 @@ Status WinEnvIO::NewRandomRWFile(const std::string & fname,
   // Random access is to disable read-ahead as the system reads too much data
   DWORD desired_access = GENERIC_READ | GENERIC_WRITE;
   DWORD shared_mode = FILE_SHARE_READ | FILE_SHARE_WRITE | FILE_SHARE_DELETE;
-  DWORD creation_disposition = OPEN_EXISTING; // Fail if file does not exist
+  DWORD creation_disposition = OPEN_ALWAYS; // Create if necessary or open existing
   DWORD file_flags = FILE_FLAG_RANDOM_ACCESS;
 
   if (options.use_direct_reads && options.use_direct_writes) {
@@ -389,84 +380,6 @@ Status WinEnvIO::NewRandomRWFile(const std::string & fname,
   return s;
 }
 
-Status WinEnvIO::NewMemoryMappedFileBuffer(const std::string & fname,
-  std::unique_ptr<MemoryMappedFileBuffer>* result) {
-  Status s;
-  result->reset();
-
-  DWORD fileFlags = FILE_ATTRIBUTE_READONLY;
-
-  HANDLE hFile = INVALID_HANDLE_VALUE;
-  {
-    IOSTATS_TIMER_GUARD(open_nanos);
-    hFile = CreateFileA(
-      fname.c_str(), GENERIC_READ | GENERIC_WRITE,
-      FILE_SHARE_READ | FILE_SHARE_WRITE | FILE_SHARE_DELETE,
-      NULL,
-      OPEN_EXISTING,  // Open only if it exists
-      fileFlags,
-      NULL);
-  }
-
-  if (INVALID_HANDLE_VALUE == hFile) {
-    auto lastError = GetLastError();
-    s = IOErrorFromWindowsError("Failed to open NewMemoryMappedFileBuffer: " + fname,
-      lastError);
-    return s;
-  }
-  UniqueCloseHandlePtr fileGuard(hFile, CloseHandleFunc);
-
-  uint64_t fileSize = 0;
-  s = GetFileSize(fname, &fileSize);
-  if (!s.ok()) {
-    return s;
-  }
-  // Will not map empty files
-  if (fileSize == 0) {
-    return Status::NotSupported("NewMemoryMappedFileBuffer can not map zero length files: " + fname);
-  }
-
-  // size_t is 32-bit with 32-bit builds
-  if (fileSize > std::numeric_limits<size_t>::max()) {
-    return Status::NotSupported(
-      "The specified file size does not fit into 32-bit memory addressing: " + fname);
-  }
-
-  HANDLE hMap = CreateFileMappingA(hFile, NULL, PAGE_READWRITE,
-      0,  // Whole file at its present length
-      0,
-      NULL);  // Mapping name
-
-  if (!hMap) {
-    auto lastError = GetLastError();
-    return IOErrorFromWindowsError(
-      "Failed to create file mapping for NewMemoryMappedFileBuffer: " + fname,
-      lastError);
-  }
-  UniqueCloseHandlePtr mapGuard(hMap, CloseHandleFunc);
-
-  void* base = MapViewOfFileEx(hMap, FILE_MAP_WRITE,
-    0,  // High DWORD of access start
-    0,  // Low DWORD
-    fileSize,
-    NULL);  // Let the OS choose the mapping
-
-  if (!base) {
-    auto lastError = GetLastError();
-    return IOErrorFromWindowsError(
-      "Failed to MapViewOfFile for NewMemoryMappedFileBuffer: " + fname,
-      lastError);
-  }
-
-  result->reset(new WinMemoryMappedBuffer(hFile, hMap, 
-    base, static_cast<size_t>(fileSize)));
-
-  mapGuard.release();
-  fileGuard.release();
-
-  return s;
-}
-
 Status WinEnvIO::NewDirectory(const std::string& name,
   std::unique_ptr<Directory>* result) {
   Status s;
@@ -1015,33 +928,27 @@ std::string WinEnvIO::TimeToString(uint64_t secondsSince1970) {
 
 EnvOptions WinEnvIO::OptimizeForLogWrite(const EnvOptions& env_options,
   const DBOptions& db_options) const {
-  EnvOptions optimized(env_options);
-  // These two the same as default optimizations
+  EnvOptions optimized = env_options;
   optimized.bytes_per_sync = db_options.wal_bytes_per_sync;
+  optimized.use_mmap_writes = false;
+  // This is because we flush only whole pages on unbuffered io and
+  // the last records are not guaranteed to be flushed.
+  optimized.use_direct_writes = false;
+  // TODO(icanadi) it's faster if fallocate_with_keep_size is false, but it
+  // breaks TransactionLogIteratorStallAtLastRecord unit test. Fix the unit
+  // test and make this false
+  optimized.fallocate_with_keep_size = true;
   optimized.writable_file_max_buffer_size =
       db_options.writable_file_max_buffer_size;
-
-  // This adversely affects %999 on windows
-  optimized.use_mmap_writes = false;
-  // Direct writes will produce a huge perf impact on
-  // Windows. Pre-allocate space for WAL.
-  optimized.use_direct_writes = false;
   return optimized;
 }
 
 EnvOptions WinEnvIO::OptimizeForManifestWrite(
   const EnvOptions& env_options) const {
-  EnvOptions optimized(env_options);
+  EnvOptions optimized = env_options;
   optimized.use_mmap_writes = false;
-  optimized.use_direct_reads = false;
-  return optimized;
-}
-
-EnvOptions WinEnvIO::OptimizeForManifestRead(
-  const EnvOptions& env_options) const {
-  EnvOptions optimized(env_options);
-  optimized.use_mmap_writes = false;
-  optimized.use_direct_reads = false;
+  optimized.use_direct_writes = false;
+  optimized.fallocate_with_keep_size = true;
   return optimized;
 }
 
@@ -1238,10 +1145,6 @@ Status WinEnv::DeleteFile(const std::string& fname) {
   return winenv_io_.DeleteFile(fname);
 }
 
-Status WinEnv::Truncate(const std::string& fname, size_t size) {
-  return winenv_io_.Truncate(fname, size);
-}
-
 Status WinEnv::GetCurrentTime(int64_t* unix_time) {
   return winenv_io_.GetCurrentTime(unix_time);
 }
@@ -1270,15 +1173,10 @@ Status WinEnv::ReopenWritableFile(const std::string& fname,
 }
 
 Status WinEnv::NewRandomRWFile(const std::string & fname,
-  std::unique_ptr<RandomRWFile>* result, const EnvOptions & options) {
+  unique_ptr<RandomRWFile>* result, const EnvOptions & options) {
   return winenv_io_.NewRandomRWFile(fname, result, options);
 }
 
-Status WinEnv::NewMemoryMappedFileBuffer(const std::string& fname,
-  std::unique_ptr<MemoryMappedFileBuffer>* result) {
-  return winenv_io_.NewMemoryMappedFileBuffer(fname, result);
-}
-
 Status WinEnv::NewDirectory(const std::string& name,
   std::unique_ptr<Directory>* result) {
   return winenv_io_.NewDirectory(name, result);
@@ -1412,11 +1310,6 @@ void  WinEnv::IncBackgroundThreadsIfNeeded(int num, Env::Priority pri) {
   return winenv_threads_.IncBackgroundThreadsIfNeeded(num, pri);
 }
 
-EnvOptions WinEnv::OptimizeForManifestRead(
-  const EnvOptions& env_options) const {
-  return winenv_io_.OptimizeForManifestRead(env_options);
-}
-
 EnvOptions WinEnv::OptimizeForLogWrite(const EnvOptions& env_options,
   const DBOptions& db_options) const {
   return winenv_io_.OptimizeForLogWrite(env_options, db_options);

port/win/env_win.h

@@ -89,8 +89,6 @@ public:
 
   virtual Status DeleteFile(const std::string& fname);
 
-  Status Truncate(const std::string& fname, size_t size);
-
   virtual Status GetCurrentTime(int64_t* unix_time);
 
   virtual Status NewSequentialFile(const std::string& fname,
@@ -112,10 +110,6 @@ public:
     unique_ptr<RandomRWFile>* result,
     const EnvOptions& options);
 
-  virtual Status NewMemoryMappedFileBuffer(
-    const std::string& fname,
-    std::unique_ptr<MemoryMappedFileBuffer>* result);
-
   virtual Status NewDirectory(const std::string& name,
     std::unique_ptr<Directory>* result);
 
@@ -174,9 +168,6 @@ public:
   virtual EnvOptions OptimizeForManifestWrite(
     const EnvOptions& env_options) const;
 
-  virtual EnvOptions OptimizeForManifestRead(
-    const EnvOptions& env_options) const;
-
   size_t GetPageSize() const { return page_size_; }
 
   size_t GetAllocationGranularity() const { return allocation_granularity_; }
@@ -206,8 +197,6 @@ public:
 
   Status DeleteFile(const std::string& fname) override;
 
-  Status Truncate(const std::string& fname, size_t size) override;
-
   Status GetCurrentTime(int64_t* unix_time) override;
 
   Status NewSequentialFile(const std::string& fname,
@@ -235,13 +224,9 @@ public:
 
   // The returned file will only be accessed by one thread at a time.
   Status NewRandomRWFile(const std::string& fname,
-    std::unique_ptr<RandomRWFile>* result,
+    unique_ptr<RandomRWFile>* result,
     const EnvOptions& options) override;
 
-  Status NewMemoryMappedFileBuffer(
-    const std::string& fname,
-    std::unique_ptr<MemoryMappedFileBuffer>* result) override;
-
   Status NewDirectory(const std::string& name,
     std::unique_ptr<Directory>* result) override;
 
@@ -317,16 +302,12 @@ public:
 
   void IncBackgroundThreadsIfNeeded(int num, Env::Priority pri) override;
 
-  EnvOptions OptimizeForManifestRead(
-    const EnvOptions& env_options) const override;
-
   EnvOptions OptimizeForLogWrite(const EnvOptions& env_options,
     const DBOptions& db_options) const override;
 
   EnvOptions OptimizeForManifestWrite(
     const EnvOptions& env_options) const override;
 
-
 private:
 
   WinEnvIO      winenv_io_;

port/win/io_win.cc

@@ -1061,27 +1061,6 @@ Status WinRandomRWFile::Close() {
   return CloseImpl();
 }
 
-//////////////////////////////////////////////////////////////////////////
-/// WinMemoryMappedBufer
-WinMemoryMappedBuffer::~WinMemoryMappedBuffer() {
-  BOOL ret = FALSE;
-  if (base_ != nullptr) {
-    ret = ::UnmapViewOfFile(base_);
-    assert(ret);
-    base_ = nullptr;
-  }
-  if (map_handle_ != NULL && map_handle_ != INVALID_HANDLE_VALUE) {
-    ret = ::CloseHandle(map_handle_);
-    assert(ret);
-    map_handle_ = NULL;
-  }
-  if (file_handle_ != NULL && file_handle_ != INVALID_HANDLE_VALUE) {
-    ret = ::CloseHandle(file_handle_);
-    assert(ret);
-    file_handle_ = NULL;
-  }
-}
-
 //////////////////////////////////////////////////////////////////////////
 /// WinDirectory
 

port/win/io_win.h

@@ -411,18 +411,6 @@ class WinRandomRWFile : private WinFileData,
   virtual Status Close() override;
 };
 
-class WinMemoryMappedBuffer : public MemoryMappedFileBuffer {
-private:
-  HANDLE  file_handle_;
-  HANDLE  map_handle_;
-public:
-  WinMemoryMappedBuffer(HANDLE file_handle, HANDLE map_handle, void* base, size_t size) :
-    MemoryMappedFileBuffer(base, size),
-    file_handle_(file_handle),
-    map_handle_(map_handle) {}
-  ~WinMemoryMappedBuffer() override;
-};
-
 class WinDirectory : public Directory {
   HANDLE handle_;
  public:

src.mk

@@ -208,8 +208,6 @@ LIB_SOURCES =                                                   \
   utilities/transactions/transaction_util.cc                    \
   utilities/transactions/write_prepared_txn.cc                  \
   utilities/transactions/write_prepared_txn_db.cc               \
-  utilities/transactions/write_unprepared_txn.cc                \
-  utilities/transactions/write_unprepared_txn_db.cc             \
   utilities/ttl/db_ttl_impl.cc                                  \
   utilities/write_batch_with_index/write_batch_with_index.cc    \
   utilities/write_batch_with_index/write_batch_with_index_internal.cc    \
@@ -252,8 +250,6 @@ MAIN_SOURCES =                                                          \
   cache/cache_bench.cc                                                  \
   cache/cache_test.cc                                                   \
   db/column_family_test.cc                                              \
-  db/compact_files_test.cc                                              \
-  db/compaction_iterator_test.cc                                        \
   db/compaction_job_stats_test.cc                                       \
   db/compaction_job_test.cc                                             \
   db/compaction_picker_test.cc                                          \
@@ -261,7 +257,6 @@ MAIN_SOURCES =                                                          \
   db/corruption_test.cc                                                 \
   db/cuckoo_table_db_test.cc                                            \
   db/db_basic_test.cc                                                   \
-  db/db_blob_index_test.cc                                              \
   db/db_block_cache_test.cc                                             \
   db/db_bloom_filter_test.cc                                            \
   db/db_compaction_filter_test.cc                                       \
@@ -278,50 +273,33 @@ MAIN_SOURCES =                                                          \
   db/db_memtable_test.cc                                                \
   db/db_merge_operator_test.cc                                          \
   db/db_options_test.cc                                                 \
-  db/db_properties_test.cc                                              \
   db/db_range_del_test.cc                                               \
   db/db_sst_test.cc                                                     \
   db/db_statistics_test.cc                                              \
   db/db_table_properties_test.cc                                        \
   db/db_tailing_iter_test.cc                                            \
   db/db_test.cc                                                         \
-  db/db_test2.cc                                                        \
   db/db_universal_compaction_test.cc                                    \
   db/db_wal_test.cc                                                     \
   db/db_write_test.cc                                                   \
   db/dbformat_test.cc                                                   \
   db/deletefile_test.cc                                                 \
-  db/env_timed_test.cc                                                  \
+  db/obsolete_files_test.cc						\
   db/external_sst_file_basic_test.cc                                    \
   db/external_sst_file_test.cc                                          \
   db/fault_injection_test.cc                                            \
   db/file_indexer_test.cc                                               \
-  db/file_reader_writer_test.cc                                         \
   db/filename_test.cc                                                   \
   db/flush_job_test.cc                                                  \
-  db/hash_table_test.cc                                                 \
-  db/hash_test.cc                                                       \
-  db/heap_test.cc                                                       \
   db/listener_test.cc                                                   \
   db/log_test.cc                                                        \
-  db/lru_cache_test.cc                                                  \
   db/manual_compaction_test.cc                                          \
-  db/memtable_list_test.cc                                              \
-  db/merge_helper_test.cc                                               \
   db/merge_test.cc                                                      \
-  db/obsolete_files_test.cc						\
-  db/options_settable_test.cc                                           \
   db/options_file_test.cc                                               \
-  db/partitioned_filter_block_test.cc                                   \
   db/perf_context_test.cc                                               \
-  db/persistent_cache_test.cc                                           \
   db/plain_table_db_test.cc                                             \
   db/prefix_test.cc                                                     \
-  db/redis_test.cc                                                      \
-  db/repair_test.cc                                                     \
-  db/range_del_aggregator_test.cc                                       \
   db/table_properties_collector_test.cc                                 \
-  db/util_merge_operators_test.cc                                       \
   db/version_builder_test.cc                                            \
   db/version_edit_test.cc                                               \
   db/version_set_test.cc                                                \

table/block.cc

@@ -87,11 +87,7 @@ void BlockIter::Prev() {
     const Slice current_key(key_ptr, current_prev_entry.key_size);
 
     current_ = current_prev_entry.offset;
-    if (key_includes_seq_) {
-      key_.SetInternalKey(current_key, false /* copy */);
-    } else {
-      key_.SetUserKey(current_key, false /* copy */);
-    }
+    key_.SetInternalKey(current_key, false /* copy */);
     value_ = current_prev_entry.value;
 
     return;
@@ -140,10 +136,6 @@ void BlockIter::Prev() {
 }
 
 void BlockIter::Seek(const Slice& target) {
-  Slice seek_key = target;
-  if (!key_includes_seq_) {
-    seek_key = ExtractUserKey(target);
-  }
   PERF_TIMER_GUARD(block_seek_nanos);
   if (data_ == nullptr) {  // Not init yet
     return;
@@ -153,7 +145,7 @@ void BlockIter::Seek(const Slice& target) {
   if (prefix_index_) {
     ok = PrefixSeek(target, &index);
   } else {
-    ok = BinarySeek(seek_key, 0, num_restarts_ - 1, &index);
+    ok = BinarySeek(target, 0, num_restarts_ - 1, &index);
   }
 
   if (!ok) {
@@ -163,7 +155,7 @@ void BlockIter::Seek(const Slice& target) {
   // Linear search (within restart block) for first key >= target
 
   while (true) {
-    if (!ParseNextKey() || Compare(key_, seek_key) >= 0) {
+    if (!ParseNextKey() || Compare(key_.GetInternalKey(), target) >= 0) {
       return;
     }
   }
@@ -171,28 +163,24 @@ void BlockIter::Seek(const Slice& target) {
 
 void BlockIter::SeekForPrev(const Slice& target) {
   PERF_TIMER_GUARD(block_seek_nanos);
-  Slice seek_key = target;
-  if (!key_includes_seq_) {
-    seek_key = ExtractUserKey(target);
-  }
   if (data_ == nullptr) {  // Not init yet
     return;
   }
   uint32_t index = 0;
-  bool ok = BinarySeek(seek_key, 0, num_restarts_ - 1, &index);
+  bool ok = BinarySeek(target, 0, num_restarts_ - 1, &index);
 
   if (!ok) {
     return;
   }
   SeekToRestartPoint(index);
-  // Linear search (within restart block) for first key >= seek_key
+  // Linear search (within restart block) for first key >= target
 
-  while (ParseNextKey() && Compare(key_, seek_key) < 0) {
+  while (ParseNextKey() && Compare(key_.GetInternalKey(), target) < 0) {
   }
   if (!Valid()) {
     SeekToLast();
   } else {
-    while (Valid() && Compare(key_, seek_key) > 0) {
+    while (Valid() && Compare(key_.GetInternalKey(), target) > 0) {
       Prev();
     }
   }
@@ -245,11 +233,7 @@ bool BlockIter::ParseNextKey() {
     if (shared == 0) {
       // If this key dont share any bytes with prev key then we dont need
       // to decode it and can use it's address in the block directly.
-      if (key_includes_seq_) {
-        key_.SetInternalKey(Slice(p, non_shared), false /* copy */);
-      } else {
-        key_.SetUserKey(Slice(p, non_shared), false /* copy */);
-      }
+      key_.SetInternalKey(Slice(p, non_shared), false /* copy */);
       key_pinned_ = true;
     } else {
       // This key share `shared` bytes with prev key, we need to decode it
@@ -396,10 +380,6 @@ bool BlockIter::BinaryBlockIndexSeek(const Slice& target, uint32_t* block_ids,
 
 bool BlockIter::PrefixSeek(const Slice& target, uint32_t* index) {
   assert(prefix_index_);
-  Slice seek_key = target;
-  if (!key_includes_seq_) {
-    seek_key = ExtractUserKey(target);
-  }
   uint32_t* block_ids = nullptr;
   uint32_t num_blocks = prefix_index_->GetBlocks(target, &block_ids);
 
@@ -407,7 +387,7 @@ bool BlockIter::PrefixSeek(const Slice& target, uint32_t* index) {
     current_ = restarts_;
     return false;
   } else  {
-    return BinaryBlockIndexSeek(seek_key, block_ids, 0, num_blocks - 1, index);
+    return BinaryBlockIndexSeek(target, block_ids, 0, num_blocks - 1, index);
   }
 }
 
@@ -422,14 +402,12 @@ Block::Block(BlockContents&& contents, SequenceNumber _global_seqno,
       data_(contents_.data.data()),
       size_(contents_.data.size()),
       restart_offset_(0),
-      num_restarts_(0),
       global_seqno_(_global_seqno) {
   if (size_ < sizeof(uint32_t)) {
     size_ = 0;  // Error marker
   } else {
-    num_restarts_ = NumRestarts();
     restart_offset_ =
-        static_cast<uint32_t>(size_) - (1 + num_restarts_) * sizeof(uint32_t);
+        static_cast<uint32_t>(size_) - (1 + NumRestarts()) * sizeof(uint32_t);
     if (restart_offset_ > size_ - sizeof(uint32_t)) {
       // The size is too small for NumRestarts() and therefore
       // restart_offset_ wrapped around.
@@ -442,9 +420,8 @@ Block::Block(BlockContents&& contents, SequenceNumber _global_seqno,
   }
 }
 
-BlockIter* Block::NewIterator(const Comparator* cmp, const Comparator* ucmp,
-                              BlockIter* iter, bool total_order_seek,
-                              Statistics* stats, bool key_includes_seq) {
+BlockIter* Block::NewIterator(const Comparator* cmp, BlockIter* iter,
+                              bool total_order_seek, Statistics* stats) {
   BlockIter* ret_iter;
   if (iter != nullptr) {
     ret_iter = iter;
@@ -455,16 +432,17 @@ BlockIter* Block::NewIterator(const Comparator* cmp, const Comparator* ucmp,
     ret_iter->Invalidate(Status::Corruption("bad block contents"));
     return ret_iter;
   }
-  if (num_restarts_ == 0) {
+  const uint32_t num_restarts = NumRestarts();
+  if (num_restarts == 0) {
     // Empty block.
     ret_iter->Invalidate(Status::OK());
     return ret_iter;
   } else {
     BlockPrefixIndex* prefix_index_ptr =
         total_order_seek ? nullptr : prefix_index_.get();
-    ret_iter->Initialize(cmp, ucmp, data_, restart_offset_, num_restarts_,
+    ret_iter->Initialize(cmp, data_, restart_offset_, num_restarts,
                          prefix_index_ptr, global_seqno_,
-                         read_amp_bitmap_.get(), key_includes_seq);
+                         read_amp_bitmap_.get());
 
     if (read_amp_bitmap_) {
       if (read_amp_bitmap_->GetStatistics() != stats) {

table/block.h

@@ -162,9 +162,6 @@ class Block {
   // the iterator will simply be set as "invalid", rather than returning
   // the key that is just pass the target key.
   //
-  // If comparator is InternalKeyComparator, user_comparator is its user
-  // comparator; they are equal otherwise.
-  //
   // If iter is null, return new Iterator
   // If iter is not null, update this one and return it as Iterator*
   //
@@ -172,11 +169,9 @@ class Block {
   // This option only applies for index block. For data block, hash_index_
   // and prefix_index_ are null, so this option does not matter.
   BlockIter* NewIterator(const Comparator* comparator,
-                         const Comparator* user_comparator,
                          BlockIter* iter = nullptr,
                          bool total_order_seek = true,
-                         Statistics* stats = nullptr,
-                         bool key_includes_seq = true);
+                         Statistics* stats = nullptr);
   void SetBlockPrefixIndex(BlockPrefixIndex* prefix_index);
 
   // Report an approximation of how much memory has been used.
@@ -189,7 +184,6 @@ class Block {
   const char* data_;            // contents_.data.data()
   size_t size_;                 // contents_.data.size()
   uint32_t restart_offset_;     // Offset in data_ of restart array
-  uint32_t num_restarts_;
   std::unique_ptr<BlockPrefixIndex> prefix_index_;
   std::unique_ptr<BlockReadAmpBitmap> read_amp_bitmap_;
   // All keys in the block will have seqno = global_seqno_, regardless of
@@ -208,7 +202,6 @@ class BlockIter final : public InternalIterator {
   // and status() is OK.
   BlockIter()
       : comparator_(nullptr),
-        user_comparator_(nullptr),
         data_(nullptr),
         restarts_(0),
         num_restarts_(0),
@@ -217,30 +210,26 @@ class BlockIter final : public InternalIterator {
         status_(Status::OK()),
         prefix_index_(nullptr),
         key_pinned_(false),
-        key_includes_seq_(true),
         global_seqno_(kDisableGlobalSequenceNumber),
         read_amp_bitmap_(nullptr),
         last_bitmap_offset_(0) {}
 
-  BlockIter(const Comparator* comparator, const Comparator* user_comparator,
-            const char* data, uint32_t restarts, uint32_t num_restarts,
-            BlockPrefixIndex* prefix_index, SequenceNumber global_seqno,
-            BlockReadAmpBitmap* read_amp_bitmap, bool key_includes_seq)
+  BlockIter(const Comparator* comparator, const char* data, uint32_t restarts,
+            uint32_t num_restarts, BlockPrefixIndex* prefix_index,
+            SequenceNumber global_seqno, BlockReadAmpBitmap* read_amp_bitmap)
       : BlockIter() {
-    Initialize(comparator, user_comparator, data, restarts, num_restarts,
-               prefix_index, global_seqno, read_amp_bitmap, key_includes_seq);
+    Initialize(comparator, data, restarts, num_restarts, prefix_index,
+               global_seqno, read_amp_bitmap);
   }
 
-  void Initialize(const Comparator* comparator,
-                  const Comparator* user_comparator, const char* data,
+  void Initialize(const Comparator* comparator, const char* data,
                   uint32_t restarts, uint32_t num_restarts,
                   BlockPrefixIndex* prefix_index, SequenceNumber global_seqno,
-                  BlockReadAmpBitmap* read_amp_bitmap, bool key_includes_seq) {
+                  BlockReadAmpBitmap* read_amp_bitmap) {
     assert(data_ == nullptr);           // Ensure it is called only once
     assert(num_restarts > 0);           // Ensure the param is valid
 
     comparator_ = comparator;
-    user_comparator_ = user_comparator;
     data_ = data;
     restarts_ = restarts;
     num_restarts_ = num_restarts;
@@ -250,11 +239,10 @@ class BlockIter final : public InternalIterator {
     global_seqno_ = global_seqno;
     read_amp_bitmap_ = read_amp_bitmap;
     last_bitmap_offset_ = current_ + 1;
-    key_includes_seq_ = key_includes_seq;
   }
 
   // Makes Valid() return false, status() return `s`, and Seek()/Prev()/etc do
-  // nothing.
+  // nothing. Calls cleanup functions.
   void Invalidate(Status s) {
     // Assert that the BlockIter is never deleted while Pinning is Enabled.
     assert(!pinned_iters_mgr_ ||
@@ -264,6 +252,9 @@ class BlockIter final : public InternalIterator {
     current_ = restarts_;
     status_ = s;
 
+    // Call cleanup callbacks.
+    Cleanable::Reset();
+
     // Clear prev entries cache.
     prev_entries_keys_buff_.clear();
     prev_entries_.clear();
@@ -274,7 +265,7 @@ class BlockIter final : public InternalIterator {
   virtual Status status() const override { return status_; }
   virtual Slice key() const override {
     assert(Valid());
-    return key_includes_seq_ ? key_.GetInternalKey() : key_.GetUserKey();
+    return key_.GetInternalKey();
   }
   virtual Slice value() const override {
     assert(Valid());
@@ -323,11 +314,7 @@ class BlockIter final : public InternalIterator {
   }
 
  private:
-  // Note: The type could be changed to InternalKeyComparator but we see a weird
-  // performance drop by that.
   const Comparator* comparator_;
-  // Same as comparator_ if comparator_ is not InernalKeyComparator
-  const Comparator* user_comparator_;
   const char* data_;       // underlying block contents
   uint32_t restarts_;      // Offset of restart array (list of fixed32)
   uint32_t num_restarts_;  // Number of uint32_t entries in restart array
@@ -340,11 +327,8 @@ class BlockIter final : public InternalIterator {
   Status status_;
   BlockPrefixIndex* prefix_index_;
   bool key_pinned_;
-  // Key is in InternalKey format
-  bool key_includes_seq_;
   SequenceNumber global_seqno_;
 
- public:
   // read-amp bitmap
   BlockReadAmpBitmap* read_amp_bitmap_;
   // last `current_` value we report to read-amp bitmp
@@ -375,19 +359,7 @@ class BlockIter final : public InternalIterator {
   int32_t prev_entries_idx_ = -1;
 
   inline int Compare(const Slice& a, const Slice& b) const {
-    if (key_includes_seq_) {
-      return comparator_->Compare(a, b);
-    } else {
-      return user_comparator_->Compare(a, b);
-    }
-  }
-
-  inline int Compare(const IterKey& ikey, const Slice& b) const {
-    if (key_includes_seq_) {
-      return comparator_->Compare(ikey.GetInternalKey(), b);
-    } else {
-      return user_comparator_->Compare(ikey.GetUserKey(), b);
-    }
+    return comparator_->Compare(a, b);
   }
 
   // Return the offset in data_ just past the end of the current entry.

table/block_based_filter_block.cc

@@ -186,8 +186,7 @@ BlockBasedFilterBlockReader::BlockBasedFilterBlockReader(
 }
 
 bool BlockBasedFilterBlockReader::KeyMayMatch(
-    const Slice& key, const SliceTransform* /* prefix_extractor */,
-    uint64_t block_offset, const bool /*no_io*/,
+    const Slice& key, uint64_t block_offset, const bool /*no_io*/,
     const Slice* const /*const_ikey_ptr*/) {
   assert(block_offset != kNotValid);
   if (!whole_key_filtering_) {
@@ -197,8 +196,7 @@ bool BlockBasedFilterBlockReader::KeyMayMatch(
 }
 
 bool BlockBasedFilterBlockReader::PrefixMayMatch(
-    const Slice& prefix, const SliceTransform* /* prefix_extractor */,
-    uint64_t block_offset, const bool /*no_io*/,
+    const Slice& prefix, uint64_t block_offset, const bool /*no_io*/,
     const Slice* const /*const_ikey_ptr*/) {
   assert(block_offset != kNotValid);
   if (!prefix_extractor_) {

table/block_based_filter_block.h

@@ -83,14 +83,13 @@ class BlockBasedFilterBlockReader : public FilterBlockReader {
                               bool whole_key_filtering,
                               BlockContents&& contents, Statistics* statistics);
   virtual bool IsBlockBased() override { return true; }
-
   virtual bool KeyMayMatch(
-      const Slice& key, const SliceTransform* prefix_extractor,
-      uint64_t block_offset = kNotValid, const bool no_io = false,
+      const Slice& key, uint64_t block_offset = kNotValid,
+      const bool no_io = false,
       const Slice* const const_ikey_ptr = nullptr) override;
   virtual bool PrefixMayMatch(
-      const Slice& prefix, const SliceTransform* prefix_extractor,
-      uint64_t block_offset = kNotValid, const bool no_io = false,
+      const Slice& prefix, uint64_t block_offset = kNotValid,
+      const bool no_io = false,
       const Slice* const const_ikey_ptr = nullptr) override;
   virtual size_t ApproximateMemoryUsage() const override;
 

table/block_based_filter_block_test.cc

@@ -59,8 +59,8 @@ TEST_F(FilterBlockTest, EmptyBuilder) {
   ASSERT_EQ("\\x00\\x00\\x00\\x00\\x0b", EscapeString(block.data));
   BlockBasedFilterBlockReader reader(nullptr, table_options_, true,
                                      std::move(block), nullptr);
-  ASSERT_TRUE(reader.KeyMayMatch("foo", nullptr, uint64_t{0}));
-  ASSERT_TRUE(reader.KeyMayMatch("foo", nullptr, 100000));
+  ASSERT_TRUE(reader.KeyMayMatch("foo", 0));
+  ASSERT_TRUE(reader.KeyMayMatch("foo", 100000));
 }
 
 TEST_F(FilterBlockTest, SingleChunk) {
@@ -78,13 +78,13 @@ TEST_F(FilterBlockTest, SingleChunk) {
   BlockContents block(builder.Finish(), false, kNoCompression);
   BlockBasedFilterBlockReader reader(nullptr, table_options_, true,
                                      std::move(block), nullptr);
-  ASSERT_TRUE(reader.KeyMayMatch("foo", nullptr, 100));
-  ASSERT_TRUE(reader.KeyMayMatch("bar", nullptr, 100));
-  ASSERT_TRUE(reader.KeyMayMatch("box", nullptr, 100));
-  ASSERT_TRUE(reader.KeyMayMatch("hello", nullptr, 100));
-  ASSERT_TRUE(reader.KeyMayMatch("foo", nullptr, 100));
-  ASSERT_TRUE(!reader.KeyMayMatch("missing", nullptr, 100));
-  ASSERT_TRUE(!reader.KeyMayMatch("other", nullptr, 100));
+  ASSERT_TRUE(reader.KeyMayMatch("foo", 100));
+  ASSERT_TRUE(reader.KeyMayMatch("bar", 100));
+  ASSERT_TRUE(reader.KeyMayMatch("box", 100));
+  ASSERT_TRUE(reader.KeyMayMatch("hello", 100));
+  ASSERT_TRUE(reader.KeyMayMatch("foo", 100));
+  ASSERT_TRUE(!reader.KeyMayMatch("missing", 100));
+  ASSERT_TRUE(!reader.KeyMayMatch("other", 100));
 }
 
 TEST_F(FilterBlockTest, MultiChunk) {
@@ -112,28 +112,28 @@ TEST_F(FilterBlockTest, MultiChunk) {
                                      std::move(block), nullptr);
 
   // Check first filter
-  ASSERT_TRUE(reader.KeyMayMatch("foo", nullptr, uint64_t{0}));
-  ASSERT_TRUE(reader.KeyMayMatch("bar", nullptr, 2000));
-  ASSERT_TRUE(!reader.KeyMayMatch("box", nullptr, uint64_t{0}));
-  ASSERT_TRUE(!reader.KeyMayMatch("hello", nullptr, uint64_t{0}));
+  ASSERT_TRUE(reader.KeyMayMatch("foo", 0));
+  ASSERT_TRUE(reader.KeyMayMatch("bar", 2000));
+  ASSERT_TRUE(!reader.KeyMayMatch("box", 0));
+  ASSERT_TRUE(!reader.KeyMayMatch("hello", 0));
 
   // Check second filter
-  ASSERT_TRUE(reader.KeyMayMatch("box", nullptr, 3100));
-  ASSERT_TRUE(!reader.KeyMayMatch("foo", nullptr, 3100));
-  ASSERT_TRUE(!reader.KeyMayMatch("bar", nullptr, 3100));
-  ASSERT_TRUE(!reader.KeyMayMatch("hello", nullptr, 3100));
+  ASSERT_TRUE(reader.KeyMayMatch("box", 3100));
+  ASSERT_TRUE(!reader.KeyMayMatch("foo", 3100));
+  ASSERT_TRUE(!reader.KeyMayMatch("bar", 3100));
+  ASSERT_TRUE(!reader.KeyMayMatch("hello", 3100));
 
   // Check third filter (empty)
-  ASSERT_TRUE(!reader.KeyMayMatch("foo", nullptr, 4100));
-  ASSERT_TRUE(!reader.KeyMayMatch("bar", nullptr, 4100));
-  ASSERT_TRUE(!reader.KeyMayMatch("box", nullptr, 4100));
-  ASSERT_TRUE(!reader.KeyMayMatch("hello", nullptr, 4100));
+  ASSERT_TRUE(!reader.KeyMayMatch("foo", 4100));
+  ASSERT_TRUE(!reader.KeyMayMatch("bar", 4100));
+  ASSERT_TRUE(!reader.KeyMayMatch("box", 4100));
+  ASSERT_TRUE(!reader.KeyMayMatch("hello", 4100));
 
   // Check last filter
-  ASSERT_TRUE(reader.KeyMayMatch("box", nullptr, 9000));
-  ASSERT_TRUE(reader.KeyMayMatch("hello", nullptr, 9000));
-  ASSERT_TRUE(!reader.KeyMayMatch("foo", nullptr, 9000));
-  ASSERT_TRUE(!reader.KeyMayMatch("bar", nullptr, 9000));
+  ASSERT_TRUE(reader.KeyMayMatch("box", 9000));
+  ASSERT_TRUE(reader.KeyMayMatch("hello", 9000));
+  ASSERT_TRUE(!reader.KeyMayMatch("foo", 9000));
+  ASSERT_TRUE(!reader.KeyMayMatch("bar", 9000));
 }
 
 // Test for block based filter block
@@ -156,8 +156,8 @@ TEST_F(BlockBasedFilterBlockTest, BlockBasedEmptyBuilder) {
   ASSERT_EQ("\\x00\\x00\\x00\\x00\\x0b", EscapeString(block.data));
   FilterBlockReader* reader = new BlockBasedFilterBlockReader(
       nullptr, table_options_, true, std::move(block), nullptr);
-  ASSERT_TRUE(reader->KeyMayMatch("foo", nullptr, uint64_t{0}));
-  ASSERT_TRUE(reader->KeyMayMatch("foo", nullptr, 100000));
+  ASSERT_TRUE(reader->KeyMayMatch("foo", 0));
+  ASSERT_TRUE(reader->KeyMayMatch("foo", 100000));
 
   delete builder;
   delete reader;
@@ -177,13 +177,13 @@ TEST_F(BlockBasedFilterBlockTest, BlockBasedSingleChunk) {
   BlockContents block(builder->Finish(), false, kNoCompression);
   FilterBlockReader* reader = new BlockBasedFilterBlockReader(
       nullptr, table_options_, true, std::move(block), nullptr);
-  ASSERT_TRUE(reader->KeyMayMatch("foo", nullptr, 100));
-  ASSERT_TRUE(reader->KeyMayMatch("bar", nullptr, 100));
-  ASSERT_TRUE(reader->KeyMayMatch("box", nullptr, 100));
-  ASSERT_TRUE(reader->KeyMayMatch("hello", nullptr, 100));
-  ASSERT_TRUE(reader->KeyMayMatch("foo", nullptr, 100));
-  ASSERT_TRUE(!reader->KeyMayMatch("missing", nullptr, 100));
-  ASSERT_TRUE(!reader->KeyMayMatch("other", nullptr, 100));
+  ASSERT_TRUE(reader->KeyMayMatch("foo", 100));
+  ASSERT_TRUE(reader->KeyMayMatch("bar", 100));
+  ASSERT_TRUE(reader->KeyMayMatch("box", 100));
+  ASSERT_TRUE(reader->KeyMayMatch("hello", 100));
+  ASSERT_TRUE(reader->KeyMayMatch("foo", 100));
+  ASSERT_TRUE(!reader->KeyMayMatch("missing", 100));
+  ASSERT_TRUE(!reader->KeyMayMatch("other", 100));
 
   delete builder;
   delete reader;
@@ -215,28 +215,28 @@ TEST_F(BlockBasedFilterBlockTest, BlockBasedMultiChunk) {
       nullptr, table_options_, true, std::move(block), nullptr);
 
   // Check first filter
-  ASSERT_TRUE(reader->KeyMayMatch("foo", nullptr, uint64_t{0}));
-  ASSERT_TRUE(reader->KeyMayMatch("bar", nullptr, 2000));
-  ASSERT_TRUE(!reader->KeyMayMatch("box", nullptr, uint64_t{0}));
-  ASSERT_TRUE(!reader->KeyMayMatch("hello", nullptr, uint64_t{0}));
+  ASSERT_TRUE(reader->KeyMayMatch("foo", 0));
+  ASSERT_TRUE(reader->KeyMayMatch("bar", 2000));
+  ASSERT_TRUE(!reader->KeyMayMatch("box", 0));
+  ASSERT_TRUE(!reader->KeyMayMatch("hello", 0));
 
   // Check second filter
-  ASSERT_TRUE(reader->KeyMayMatch("box", nullptr, 3100));
-  ASSERT_TRUE(!reader->KeyMayMatch("foo", nullptr, 3100));
-  ASSERT_TRUE(!reader->KeyMayMatch("bar", nullptr, 3100));
-  ASSERT_TRUE(!reader->KeyMayMatch("hello", nullptr, 3100));
+  ASSERT_TRUE(reader->KeyMayMatch("box", 3100));
+  ASSERT_TRUE(!reader->KeyMayMatch("foo", 3100));
+  ASSERT_TRUE(!reader->KeyMayMatch("bar", 3100));
+  ASSERT_TRUE(!reader->KeyMayMatch("hello", 3100));
 
   // Check third filter (empty)
-  ASSERT_TRUE(!reader->KeyMayMatch("foo", nullptr, 4100));
-  ASSERT_TRUE(!reader->KeyMayMatch("bar", nullptr, 4100));
-  ASSERT_TRUE(!reader->KeyMayMatch("box", nullptr, 4100));
-  ASSERT_TRUE(!reader->KeyMayMatch("hello", nullptr, 4100));
+  ASSERT_TRUE(!reader->KeyMayMatch("foo", 4100));
+  ASSERT_TRUE(!reader->KeyMayMatch("bar", 4100));
+  ASSERT_TRUE(!reader->KeyMayMatch("box", 4100));
+  ASSERT_TRUE(!reader->KeyMayMatch("hello", 4100));
 
   // Check last filter
-  ASSERT_TRUE(reader->KeyMayMatch("box", nullptr, 9000));
-  ASSERT_TRUE(reader->KeyMayMatch("hello", nullptr, 9000));
-  ASSERT_TRUE(!reader->KeyMayMatch("foo", nullptr, 9000));
-  ASSERT_TRUE(!reader->KeyMayMatch("bar", nullptr, 9000));
+  ASSERT_TRUE(reader->KeyMayMatch("box", 9000));
+  ASSERT_TRUE(reader->KeyMayMatch("hello", 9000));
+  ASSERT_TRUE(!reader->KeyMayMatch("foo", 9000));
+  ASSERT_TRUE(!reader->KeyMayMatch("bar", 9000));
 
   delete builder;
   delete reader;

table/block_based_table_builder.cc

@@ -62,16 +62,14 @@ namespace {
 
 // Create a filter block builder based on its type.
 FilterBlockBuilder* CreateFilterBlockBuilder(
-    const ImmutableCFOptions& /*opt*/, const MutableCFOptions& mopt,
-    const BlockBasedTableOptions& table_opt,
+    const ImmutableCFOptions& opt, const BlockBasedTableOptions& table_opt,
     PartitionedIndexBuilder* const p_index_builder) {
   if (table_opt.filter_policy == nullptr) return nullptr;
 
   FilterBitsBuilder* filter_bits_builder =
       table_opt.filter_policy->GetFilterBitsBuilder();
   if (filter_bits_builder == nullptr) {
-    return new BlockBasedFilterBlockBuilder(mopt.prefix_extractor.get(),
-                                            table_opt);
+    return new BlockBasedFilterBlockBuilder(opt.prefix_extractor, table_opt);
   } else {
     if (table_opt.partition_filters) {
       assert(p_index_builder != nullptr);
@@ -84,11 +82,11 @@ FilterBlockBuilder* CreateFilterBlockBuilder(
           (100 - table_opt.block_size_deviation)) + 99) / 100);
       partition_size = std::max(partition_size, static_cast<uint32_t>(1));
       return new PartitionedFilterBlockBuilder(
-          mopt.prefix_extractor.get(), table_opt.whole_key_filtering,
+          opt.prefix_extractor, table_opt.whole_key_filtering,
           filter_bits_builder, table_opt.index_block_restart_interval,
           p_index_builder, partition_size);
     } else {
-      return new FullFilterBlockBuilder(mopt.prefix_extractor.get(),
+      return new FullFilterBlockBuilder(opt.prefix_extractor,
                                         table_opt.whole_key_filtering,
                                         filter_bits_builder);
     }
@@ -246,7 +244,6 @@ class BlockBasedTableBuilder::BlockBasedTablePropertiesCollector
 
 struct BlockBasedTableBuilder::Rep {
   const ImmutableCFOptions ioptions;
-  const MutableCFOptions moptions;
   const BlockBasedTableOptions table_options;
   const InternalKeyComparator& internal_comparator;
   WritableFileWriter* file;
@@ -283,7 +280,7 @@ struct BlockBasedTableBuilder::Rep {
 
   std::vector<std::unique_ptr<IntTblPropCollector>> table_properties_collectors;
 
-  Rep(const ImmutableCFOptions& _ioptions, const MutableCFOptions& _moptions,
+  Rep(const ImmutableCFOptions& _ioptions,
       const BlockBasedTableOptions& table_opt,
       const InternalKeyComparator& icomparator,
       const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
@@ -295,7 +292,6 @@ struct BlockBasedTableBuilder::Rep {
       const std::string& _column_family_name, const uint64_t _creation_time,
       const uint64_t _oldest_key_time)
       : ioptions(_ioptions),
-        moptions(_moptions),
         table_options(table_opt),
         internal_comparator(icomparator),
         file(f),
@@ -304,8 +300,8 @@ struct BlockBasedTableBuilder::Rep {
                       : 0),
         data_block(table_options.block_restart_interval,
                    table_options.use_delta_encoding),
-        range_del_block(1 /* block_restart_interval */),
-        internal_prefix_transform(_moptions.prefix_extractor.get()),
+        range_del_block(1),  // TODO(andrewkr): restart_interval unnecessary
+        internal_prefix_transform(_ioptions.prefix_extractor),
         compression_type(_compression_type),
         compression_opts(_compression_opts),
         compression_dict(_compression_dict),
@@ -330,8 +326,8 @@ struct BlockBasedTableBuilder::Rep {
     if (skip_filters) {
       filter_builder = nullptr;
     } else {
-      filter_builder.reset(CreateFilterBlockBuilder(
-          _ioptions, _moptions, table_options, p_index_builder_));
+      filter_builder.reset(
+          CreateFilterBlockBuilder(_ioptions, table_options, p_index_builder_));
     }
 
     for (auto& collector_factories : *int_tbl_prop_collector_factories) {
@@ -341,12 +337,12 @@ struct BlockBasedTableBuilder::Rep {
     table_properties_collectors.emplace_back(
         new BlockBasedTablePropertiesCollector(
             table_options.index_type, table_options.whole_key_filtering,
-            _moptions.prefix_extractor != nullptr));
+            _ioptions.prefix_extractor != nullptr));
   }
 };
 
 BlockBasedTableBuilder::BlockBasedTableBuilder(
-    const ImmutableCFOptions& ioptions, const MutableCFOptions& moptions,
+    const ImmutableCFOptions& ioptions,
     const BlockBasedTableOptions& table_options,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
@@ -369,11 +365,11 @@ BlockBasedTableBuilder::BlockBasedTableBuilder(
     sanitized_table_options.format_version = 1;
   }
 
-  rep_ =
-      new Rep(ioptions, moptions, sanitized_table_options, internal_comparator,
-              int_tbl_prop_collector_factories, column_family_id, file,
-              compression_type, compression_opts, compression_dict,
-              skip_filters, column_family_name, creation_time, oldest_key_time);
+  rep_ = new Rep(ioptions, sanitized_table_options, internal_comparator,
+                 int_tbl_prop_collector_factories, column_family_id, file,
+                 compression_type, compression_opts, compression_dict,
+                 skip_filters, column_family_name, creation_time,
+                 oldest_key_time);
 
   if (rep_->filter_builder != nullptr) {
     rep_->filter_builder->StartBlock(0);
@@ -741,8 +737,8 @@ Status BlockBasedTableBuilder::Finish() {
                                          : "nullptr";
       r->props.compression_name = CompressionTypeToString(r->compression_type);
       r->props.prefix_extractor_name =
-          r->moptions.prefix_extractor != nullptr
-              ? r->moptions.prefix_extractor->Name()
+          r->ioptions.prefix_extractor != nullptr
+              ? r->ioptions.prefix_extractor->Name()
               : "nullptr";
 
       std::string property_collectors_names = "[";
@@ -763,8 +759,6 @@ Status BlockBasedTableBuilder::Finish() {
         r->props.top_level_index_size =
             r->p_index_builder_->EstimateTopLevelIndexSize(r->offset);
       }
-      r->props.index_key_is_user_key =
-          !r->index_builder->seperator_is_key_plus_seq();
       r->props.creation_time = r->creation_time;
       r->props.oldest_key_time = r->oldest_key_time;
 

table/block_based_table_builder.h

@@ -38,7 +38,7 @@ class BlockBasedTableBuilder : public TableBuilder {
   // @param compression_dict Data for presetting the compression library's
   //    dictionary, or nullptr.
   BlockBasedTableBuilder(
-      const ImmutableCFOptions& ioptions, const MutableCFOptions& moptions,
+      const ImmutableCFOptions& ioptions,
       const BlockBasedTableOptions& table_options,
       const InternalKeyComparator& internal_comparator,
       const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*

table/block_based_table_factory.cc

@@ -69,17 +69,16 @@ Status BlockBasedTableFactory::NewTableReader(
   return BlockBasedTable::Open(
       table_reader_options.ioptions, table_reader_options.env_options,
       table_options_, table_reader_options.internal_comparator, std::move(file),
-      file_size, table_reader, table_reader_options.prefix_extractor,
-      prefetch_index_and_filter_in_cache, table_reader_options.skip_filters,
-      table_reader_options.level);
+      file_size, table_reader, prefetch_index_and_filter_in_cache,
+      table_reader_options.skip_filters, table_reader_options.level);
 }
 
 TableBuilder* BlockBasedTableFactory::NewTableBuilder(
     const TableBuilderOptions& table_builder_options, uint32_t column_family_id,
     WritableFileWriter* file) const {
   auto table_builder = new BlockBasedTableBuilder(
-      table_builder_options.ioptions, table_builder_options.moptions,
-      table_options_, table_builder_options.internal_comparator,
+      table_builder_options.ioptions, table_options_,
+      table_builder_options.internal_comparator,
       table_builder_options.int_tbl_prop_collector_factories, column_family_id,
       file, table_builder_options.compression_type,
       table_builder_options.compression_opts,

table/block_based_table_reader.cc

@@ -173,29 +173,6 @@ Cache::Handle* GetEntryFromCache(Cache* block_cache, const Slice& key,
   return cache_handle;
 }
 
-// For hash based index, return true if prefix_extractor and
-// prefix_extractor_block mismatch, false otherwise. This flag will be used
-// as total_order_seek via NewIndexIterator
-bool PrefixExtractorChanged(
-    std::shared_ptr<const TableProperties> table_properties,
-    const SliceTransform* prefix_extractor) {
-  // BlockBasedTableOptions::kHashSearch requires prefix_extractor to be set.
-  // Turn off hash index in prefix_extractor is not set; if  prefix_extractor
-  // is set but prefix_extractor_block is not set, also disable hash index
-  if (prefix_extractor == nullptr || table_properties == nullptr ||
-      table_properties->prefix_extractor_name.empty()) {
-    return true;
-  }
-
-  // prefix_extractor and prefix_extractor_block are both non-empty
-  if (table_properties->prefix_extractor_name.compare(
-          prefix_extractor->Name()) != 0) {
-    return true;
-  } else {
-    return false;
-  }
-}
-
 }  // namespace
 
 // Index that allows binary search lookup in a two-level index structure.
@@ -212,7 +189,7 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
                        const InternalKeyComparator* icomparator,
                        IndexReader** index_reader,
                        const PersistentCacheOptions& cache_options,
-                       const int level, const bool index_key_includes_seq) {
+                       const int level) {
     std::unique_ptr<Block> index_block;
     auto s = ReadBlockFromFile(
         file, prefetch_buffer, footer, ReadOptions(), index_handle,
@@ -221,9 +198,9 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
         kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */);
 
     if (s.ok()) {
-      *index_reader = new PartitionIndexReader(
-          table, icomparator, std::move(index_block), ioptions.statistics,
-          level, index_key_includes_seq);
+      *index_reader =
+          new PartitionIndexReader(table, icomparator, std::move(index_block),
+                                   ioptions.statistics, level);
     }
 
     return s;
@@ -237,19 +214,14 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
     if (!partition_map_.empty()) {
       return NewTwoLevelIterator(
           new BlockBasedTable::PartitionedIndexIteratorState(
-              table_, &partition_map_, index_key_includes_seq_),
-          index_block_->NewIterator(
-              icomparator_, icomparator_->user_comparator(), nullptr, true));
+              table_, partition_map_.size() ? &partition_map_ : nullptr),
+          index_block_->NewIterator(icomparator_, nullptr, true));
     } else {
       auto ro = ReadOptions();
       ro.fill_cache = fill_cache;
-      bool kIsIndex = true;
       return new BlockBasedTableIterator(
           table_, ro, *icomparator_,
-          index_block_->NewIterator(
-              icomparator_, icomparator_->user_comparator(), nullptr, true),
-          false,
-          /* prefix_extractor */ nullptr, kIsIndex, index_key_includes_seq_);
+          index_block_->NewIterator(icomparator_, nullptr, true), false);
     }
     // TODO(myabandeh): Update TwoLevelIterator to be able to make use of
     // on-stack BlockIter while the state is on heap. Currentlly it assumes
@@ -262,8 +234,7 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
     auto rep = table_->rep_;
     BlockIter biter;
     BlockHandle handle;
-    index_block_->NewIterator(icomparator_, icomparator_->user_comparator(),
-                              &biter, true);
+    index_block_->NewIterator(icomparator_, &biter, true);
     // Index partitions are assumed to be consecuitive. Prefetch them all.
     // Read the first block offset
     biter.SeekToFirst();
@@ -352,18 +323,16 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
   PartitionIndexReader(BlockBasedTable* table,
                        const InternalKeyComparator* icomparator,
                        std::unique_ptr<Block>&& index_block, Statistics* stats,
-                       const int /*level*/, const bool index_key_includes_seq)
+                       const int /*level*/)
       : IndexReader(icomparator, stats),
         table_(table),
-        index_block_(std::move(index_block)),
-        index_key_includes_seq_(index_key_includes_seq) {
+        index_block_(std::move(index_block)) {
     assert(index_block_ != nullptr);
   }
   BlockBasedTable* table_;
   std::unique_ptr<Block> index_block_;
   std::unordered_map<uint64_t, BlockBasedTable::CachableEntry<Block>>
       partition_map_;
-  const bool index_key_includes_seq_;
 };
 
 // Index that allows binary search lookup for the first key of each block.
@@ -381,8 +350,7 @@ class BinarySearchIndexReader : public IndexReader {
                        const ImmutableCFOptions& ioptions,
                        const InternalKeyComparator* icomparator,
                        IndexReader** index_reader,
-                       const PersistentCacheOptions& cache_options,
-                       const bool index_key_includes_seq) {
+                       const PersistentCacheOptions& cache_options) {
     std::unique_ptr<Block> index_block;
     auto s = ReadBlockFromFile(
         file, prefetch_buffer, footer, ReadOptions(), index_handle,
@@ -392,8 +360,7 @@ class BinarySearchIndexReader : public IndexReader {
 
     if (s.ok()) {
       *index_reader = new BinarySearchIndexReader(
-          icomparator, std::move(index_block), ioptions.statistics,
-          index_key_includes_seq);
+          icomparator, std::move(index_block), ioptions.statistics);
     }
 
     return s;
@@ -402,9 +369,7 @@ class BinarySearchIndexReader : public IndexReader {
   virtual InternalIterator* NewIterator(BlockIter* iter = nullptr,
                                         bool /*dont_care*/ = true,
                                         bool /*dont_care*/ = true) override {
-    return index_block_->NewIterator(icomparator_,
-                                     icomparator_->user_comparator(), iter,
-                                     true, nullptr, index_key_includes_seq_);
+    return index_block_->NewIterator(icomparator_, iter, true);
   }
 
   virtual size_t size() const override { return index_block_->size(); }
@@ -420,14 +385,11 @@ class BinarySearchIndexReader : public IndexReader {
  private:
   BinarySearchIndexReader(const InternalKeyComparator* icomparator,
                           std::unique_ptr<Block>&& index_block,
-                          Statistics* stats, const bool index_key_includes_seq)
-      : IndexReader(icomparator, stats),
-        index_block_(std::move(index_block)),
-        index_key_includes_seq_(index_key_includes_seq) {
+                          Statistics* stats)
+      : IndexReader(icomparator, stats), index_block_(std::move(index_block)) {
     assert(index_block_ != nullptr);
   }
   std::unique_ptr<Block> index_block_;
-  const bool index_key_includes_seq_;
 };
 
 // Index that leverages an internal hash table to quicken the lookup for a given
@@ -443,8 +405,7 @@ class HashIndexReader : public IndexReader {
                        InternalIterator* meta_index_iter,
                        IndexReader** index_reader,
                        bool /*hash_index_allow_collision*/,
-                       const PersistentCacheOptions& cache_options,
-                       const bool index_key_includes_seq) {
+                       const PersistentCacheOptions& cache_options) {
     std::unique_ptr<Block> index_block;
     auto s = ReadBlockFromFile(
         file, prefetch_buffer, footer, ReadOptions(), index_handle,
@@ -462,7 +423,7 @@ class HashIndexReader : public IndexReader {
 
     auto new_index_reader =
         new HashIndexReader(icomparator, std::move(index_block),
-                            ioptions.statistics, index_key_includes_seq);
+          ioptions.statistics);
     *index_reader = new_index_reader;
 
     // Get prefixes block
@@ -499,7 +460,7 @@ class HashIndexReader : public IndexReader {
         file, prefetch_buffer, footer, ReadOptions(), prefixes_meta_handle,
         &prefixes_meta_contents, ioptions, true /* decompress */,
         dummy_comp_dict /*compression dict*/, cache_options);
-    s = prefixes_meta_block_fetcher.ReadBlockContents();
+    prefixes_meta_block_fetcher.ReadBlockContents();
     if (!s.ok()) {
       // TODO: log error
       return Status::OK();
@@ -519,9 +480,7 @@ class HashIndexReader : public IndexReader {
   virtual InternalIterator* NewIterator(BlockIter* iter = nullptr,
                                         bool total_order_seek = true,
                                         bool /*dont_care*/ = true) override {
-    return index_block_->NewIterator(
-        icomparator_, icomparator_->user_comparator(), iter, total_order_seek,
-        nullptr, index_key_includes_seq_);
+    return index_block_->NewIterator(icomparator_, iter, total_order_seek);
   }
 
   virtual size_t size() const override { return index_block_->size(); }
@@ -537,11 +496,8 @@ class HashIndexReader : public IndexReader {
 
  private:
   HashIndexReader(const InternalKeyComparator* icomparator,
-                  std::unique_ptr<Block>&& index_block, Statistics* stats,
-                  const bool index_key_includes_seq)
-      : IndexReader(icomparator, stats),
-        index_block_(std::move(index_block)),
-        index_key_includes_seq_(index_key_includes_seq) {
+                  std::unique_ptr<Block>&& index_block, Statistics* stats)
+      : IndexReader(icomparator, stats), index_block_(std::move(index_block)) {
     assert(index_block_ != nullptr);
   }
 
@@ -550,7 +506,6 @@ class HashIndexReader : public IndexReader {
 
   std::unique_ptr<Block> index_block_;
   BlockContents prefixes_contents_;
-  const bool index_key_includes_seq_;
 };
 
 // Helper function to setup the cache key's prefix for the Table.
@@ -691,7 +646,6 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
                              unique_ptr<RandomAccessFileReader>&& file,
                              uint64_t file_size,
                              unique_ptr<TableReader>* table_reader,
-                             const SliceTransform* prefix_extractor,
                              const bool prefetch_index_and_filter_in_cache,
                              const bool skip_filters, const int level) {
   table_reader->reset();
@@ -743,7 +697,7 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
   // We need to wrap data with internal_prefix_transform to make sure it can
   // handle prefix correctly.
   rep->internal_prefix_transform.reset(
-      new InternalKeySliceTransform(prefix_extractor));
+      new InternalKeySliceTransform(rep->ioptions.prefix_extractor));
   SetupCacheKeyPrefix(rep, file_size);
   unique_ptr<BlockBasedTable> new_table(new BlockBasedTable(rep));
 
@@ -909,14 +863,8 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
       // block_cache
 
       CachableEntry<IndexReader> index_entry;
-      bool prefix_extractor_changed = false;
-      // check prefix_extractor match only if hash based index is used
-      if (rep->index_type == BlockBasedTableOptions::kHashSearch) {
-        prefix_extractor_changed =
-            PrefixExtractorChanged(rep->table_properties, prefix_extractor);
-      }
-      unique_ptr<InternalIterator> iter(new_table->NewIndexIterator(
-          ReadOptions(), prefix_extractor_changed, nullptr, &index_entry));
+      unique_ptr<InternalIterator> iter(
+          new_table->NewIndexIterator(ReadOptions(), nullptr, &index_entry));
       s = iter->status();
       if (s.ok()) {
         // This is the first call to NewIndexIterator() since we're in Open().
@@ -931,9 +879,9 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
         }
 
         // Hack: Call GetFilter() to implicitly add filter to the block_cache
-        auto filter_entry = new_table->GetFilter(prefix_extractor);
+        auto filter_entry = new_table->GetFilter();
         if (filter_entry.value != nullptr) {
-          filter_entry.value->CacheDependencies(pin, prefix_extractor);
+          filter_entry.value->CacheDependencies(pin);
         }
         // if pin_l0_filter_and_index_blocks_in_cache is true, and this is
         // a level0 file, then save it in rep_->filter_entry; it will be
@@ -965,14 +913,13 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
       // Set filter block
       if (rep->filter_policy) {
         const bool is_a_filter_partition = true;
-        auto filter =
-            new_table->ReadFilter(prefetch_buffer.get(), rep->filter_handle,
-                                  !is_a_filter_partition, prefix_extractor);
+        auto filter = new_table->ReadFilter(
+            prefetch_buffer.get(), rep->filter_handle, !is_a_filter_partition);
         rep->filter.reset(filter);
         // Refer to the comment above about paritioned indexes always being
         // cached
         if (filter && (prefetch_index_and_filter_in_cache || level == 0)) {
-          filter->CacheDependencies(pin, prefix_extractor);
+          filter->CacheDependencies(pin);
         }
       }
     } else {
@@ -1047,8 +994,7 @@ Status BlockBasedTable::ReadMetaBlock(Rep* rep,
 
   *meta_block = std::move(meta);
   // meta block uses bytewise comparator.
-  iter->reset(meta_block->get()->NewIterator(BytewiseComparator(),
-                                             BytewiseComparator()));
+  iter->reset(meta_block->get()->NewIterator(BytewiseComparator()));
   return Status::OK();
 }
 
@@ -1269,8 +1215,7 @@ Status BlockBasedTable::PutDataBlockToCache(
 
 FilterBlockReader* BlockBasedTable::ReadFilter(
     FilePrefetchBuffer* prefetch_buffer, const BlockHandle& filter_handle,
-    const bool is_a_filter_partition,
-    const SliceTransform* prefix_extractor) const {
+    const bool is_a_filter_partition) const {
   auto& rep = rep_;
   // TODO: We might want to unify with ReadBlockFromFile() if we start
   // requiring checksum verification in Table::Open.
@@ -1303,14 +1248,14 @@ FilterBlockReader* BlockBasedTable::ReadFilter(
   switch (filter_type) {
     case Rep::FilterType::kPartitionedFilter: {
       return new PartitionedFilterBlockReader(
-          rep->prefix_filtering ? prefix_extractor : nullptr,
+          rep->prefix_filtering ? rep->ioptions.prefix_extractor : nullptr,
           rep->whole_key_filtering, std::move(block), nullptr,
           rep->ioptions.statistics, rep->internal_comparator, this);
     }
 
     case Rep::FilterType::kBlockFilter:
       return new BlockBasedFilterBlockReader(
-          rep->prefix_filtering ? prefix_extractor : nullptr,
+          rep->prefix_filtering ? rep->ioptions.prefix_extractor : nullptr,
           rep->table_options, rep->whole_key_filtering, std::move(block),
           rep->ioptions.statistics);
 
@@ -1319,7 +1264,7 @@ FilterBlockReader* BlockBasedTable::ReadFilter(
           rep->filter_policy->GetFilterBitsReader(block.data);
       assert(filter_bits_reader != nullptr);
       return new FullFilterBlockReader(
-          rep->prefix_filtering ? prefix_extractor : nullptr,
+          rep->prefix_filtering ? rep->ioptions.prefix_extractor : nullptr,
           rep->whole_key_filtering, std::move(block), filter_bits_reader,
           rep->ioptions.statistics);
     }
@@ -1333,18 +1278,18 @@ FilterBlockReader* BlockBasedTable::ReadFilter(
 }
 
 BlockBasedTable::CachableEntry<FilterBlockReader> BlockBasedTable::GetFilter(
-    const SliceTransform* prefix_extractor, FilePrefetchBuffer* prefetch_buffer,
-    bool no_io, GetContext* get_context) const {
+    FilePrefetchBuffer* prefetch_buffer, bool no_io,
+    GetContext* get_context) const {
   const BlockHandle& filter_blk_handle = rep_->filter_handle;
   const bool is_a_filter_partition = true;
   return GetFilter(prefetch_buffer, filter_blk_handle, !is_a_filter_partition,
-                   no_io, get_context, prefix_extractor);
+                   no_io, get_context);
 }
 
 BlockBasedTable::CachableEntry<FilterBlockReader> BlockBasedTable::GetFilter(
     FilePrefetchBuffer* prefetch_buffer, const BlockHandle& filter_blk_handle,
-    const bool is_a_filter_partition, bool no_io, GetContext* get_context,
-    const SliceTransform* prefix_extractor) const {
+    const bool is_a_filter_partition, bool no_io,
+    GetContext* get_context) const {
   // If cache_index_and_filter_blocks is false, filter should be pre-populated.
   // We will return rep_->filter anyway. rep_->filter can be nullptr if filter
   // read fails at Open() time. We don't want to reload again since it will
@@ -1384,8 +1329,8 @@ BlockBasedTable::CachableEntry<FilterBlockReader> BlockBasedTable::GetFilter(
     // Do not invoke any io.
     return CachableEntry<FilterBlockReader>();
   } else {
-    filter = ReadFilter(prefetch_buffer, filter_blk_handle,
-                        is_a_filter_partition, prefix_extractor);
+    filter =
+        ReadFilter(prefetch_buffer, filter_blk_handle, is_a_filter_partition);
     if (filter != nullptr) {
       Status s = block_cache->Insert(
           key, filter, filter->size(), &DeleteCachedFilterEntry, &cache_handle,
@@ -1417,23 +1362,18 @@ BlockBasedTable::CachableEntry<FilterBlockReader> BlockBasedTable::GetFilter(
   return { filter, cache_handle };
 }
 
-// disable_prefix_seek should be set to true when prefix_extractor found in SST
-// differs from the one in mutable_cf_options and index type is HashBasedIndex
 InternalIterator* BlockBasedTable::NewIndexIterator(
-    const ReadOptions& read_options, bool disable_prefix_seek,
-    BlockIter* input_iter, CachableEntry<IndexReader>* index_entry,
-    GetContext* get_context) {
+    const ReadOptions& read_options, BlockIter* input_iter,
+    CachableEntry<IndexReader>* index_entry, GetContext* get_context) {
   // index reader has already been pre-populated.
   if (rep_->index_reader) {
     return rep_->index_reader->NewIterator(
-        input_iter, read_options.total_order_seek || disable_prefix_seek,
-        read_options.fill_cache);
+        input_iter, read_options.total_order_seek, read_options.fill_cache);
   }
   // we have a pinned index block
   if (rep_->index_entry.IsSet()) {
     return rep_->index_entry.value->NewIterator(
-        input_iter, read_options.total_order_seek || disable_prefix_seek,
-        read_options.fill_cache);
+        input_iter, read_options.total_order_seek, read_options.fill_cache);
   }
 
   PERF_TIMER_GUARD(read_index_block_nanos);
@@ -1509,7 +1449,7 @@ InternalIterator* BlockBasedTable::NewIndexIterator(
 
   assert(cache_handle);
   auto* iter = index_reader->NewIterator(
-      input_iter, read_options.total_order_seek || disable_prefix_seek);
+      input_iter, read_options.total_order_seek);
 
   // the caller would like to take ownership of the index block
   // don't call RegisterCleanup() in this case, the caller will take care of it
@@ -1524,15 +1464,14 @@ InternalIterator* BlockBasedTable::NewIndexIterator(
 
 BlockIter* BlockBasedTable::NewDataBlockIterator(
     Rep* rep, const ReadOptions& ro, const Slice& index_value,
-    BlockIter* input_iter, bool is_index, bool key_includes_seq,
-    GetContext* get_context) {
+    BlockIter* input_iter, bool is_index, GetContext* get_context) {
   BlockHandle handle;
   Slice input = index_value;
   // We intentionally allow extra stuff in index_value so that we
   // can add more features in the future.
   Status s = handle.DecodeFrom(&input);
   return NewDataBlockIterator(rep, ro, handle, input_iter, is_index,
-                              key_includes_seq, get_context, s);
+                              get_context, s);
 }
 
 // Convert an index iterator value (i.e., an encoded BlockHandle)
@@ -1541,8 +1480,7 @@ BlockIter* BlockBasedTable::NewDataBlockIterator(
 // If input_iter is not null, update this iter and return it
 BlockIter* BlockBasedTable::NewDataBlockIterator(
     Rep* rep, const ReadOptions& ro, const BlockHandle& handle,
-    BlockIter* input_iter, bool is_index, bool key_includes_seq,
-    GetContext* get_context, Status s) {
+    BlockIter* input_iter, bool is_index, GetContext* get_context, Status s) {
   PERF_TIMER_GUARD(new_table_block_iter_nanos);
 
   const bool no_io = (ro.read_tier == kBlockCacheTier);
@@ -1588,9 +1526,8 @@ BlockIter* BlockBasedTable::NewDataBlockIterator(
 
   if (s.ok()) {
     assert(block.value != nullptr);
-    iter = block.value->NewIterator(
-        &rep->internal_comparator, rep->internal_comparator.user_comparator(),
-        iter, true, rep->ioptions.statistics, key_includes_seq);
+    iter = block.value->NewIterator(&rep->internal_comparator, iter, true,
+                                    rep->ioptions.statistics);
     if (block.cache_handle != nullptr) {
       iter->RegisterCleanup(&ReleaseCachedEntry, block_cache,
                             block.cache_handle);
@@ -1702,11 +1639,8 @@ Status BlockBasedTable::MaybeLoadDataBlockToCache(
 
 BlockBasedTable::PartitionedIndexIteratorState::PartitionedIndexIteratorState(
     BlockBasedTable* table,
-    std::unordered_map<uint64_t, CachableEntry<Block>>* block_map,
-    bool index_key_includes_seq)
-    : table_(table),
-      block_map_(block_map),
-      index_key_includes_seq_(index_key_includes_seq) {}
+    std::unordered_map<uint64_t, CachableEntry<Block>>* block_map)
+    : table_(table), block_map_(block_map) {}
 
 const size_t BlockBasedTableIterator::kMaxReadaheadSize = 256 * 1024;
 
@@ -1729,9 +1663,8 @@ BlockBasedTable::PartitionedIndexIteratorState::NewSecondaryIterator(
     assert(block_cache);
     RecordTick(rep->ioptions.statistics, BLOCK_CACHE_BYTES_READ,
                block_cache->GetUsage(block->second.cache_handle));
-    return block->second.value->NewIterator(
-        &rep->internal_comparator, rep->internal_comparator.user_comparator(),
-        nullptr, true, rep->ioptions.statistics, index_key_includes_seq_);
+    return block->second.value->NewIterator(&rep->internal_comparator, nullptr,
+                                            true, rep->ioptions.statistics);
   }
   // Create an empty iterator
   return new BlockIter();
@@ -1749,32 +1682,31 @@ BlockBasedTable::PartitionedIndexIteratorState::NewSecondaryIterator(
 // Otherwise, this method guarantees no I/O will be incurred.
 //
 // REQUIRES: this method shouldn't be called while the DB lock is held.
-bool BlockBasedTable::PrefixMayMatch(const Slice& internal_key,
-                                     const SliceTransform* prefix_extractor) {
+bool BlockBasedTable::PrefixMayMatch(const Slice& internal_key) {
   if (!rep_->filter_policy) {
     return true;
   }
 
-  assert(prefix_extractor != nullptr);
+  assert(rep_->ioptions.prefix_extractor != nullptr);
   auto user_key = ExtractUserKey(internal_key);
-  if (!prefix_extractor->InDomain(user_key)) {
+  if (!rep_->ioptions.prefix_extractor->InDomain(user_key) ||
+      rep_->table_properties->prefix_extractor_name.compare(
+          rep_->ioptions.prefix_extractor->Name()) != 0) {
     return true;
   }
-  assert(rep_->table_properties->prefix_extractor_name.compare(
-             prefix_extractor->Name()) == 0);
-  auto prefix = prefix_extractor->Transform(user_key);
+  auto prefix = rep_->ioptions.prefix_extractor->Transform(user_key);
 
   bool may_match = true;
   Status s;
 
   // First, try check with full filter
-  auto filter_entry = GetFilter(prefix_extractor);
+  auto filter_entry = GetFilter();
   FilterBlockReader* filter = filter_entry.value;
   if (filter != nullptr) {
     if (!filter->IsBlockBased()) {
       const Slice* const const_ikey_ptr = &internal_key;
-      may_match = filter->PrefixMayMatch(prefix, prefix_extractor, kNotValid,
-                                         false, const_ikey_ptr);
+      may_match =
+          filter->PrefixMayMatch(prefix, kNotValid, false, const_ikey_ptr);
     } else {
       InternalKey internal_key_prefix(prefix, kMaxSequenceNumber, kTypeValue);
       auto internal_prefix = internal_key_prefix.Encode();
@@ -1786,11 +1718,7 @@ bool BlockBasedTable::PrefixMayMatch(const Slice& internal_key,
       no_io_read_options.read_tier = kBlockCacheTier;
 
       // Then, try find it within each block
-      // we already know prefix_extractor and prefix_extractor_name must match
-      // because `CheckPrefixMayMatch` first checks `check_filter_ == true`
-      bool prefix_extractor_changed = false;
-      unique_ptr<InternalIterator> iiter(
-          NewIndexIterator(no_io_read_options, prefix_extractor_changed));
+      unique_ptr<InternalIterator> iiter(NewIndexIterator(no_io_read_options));
       iiter->Seek(internal_prefix);
 
       if (!iiter->Valid()) {
@@ -1799,10 +1727,7 @@ bool BlockBasedTable::PrefixMayMatch(const Slice& internal_key,
         // and we're not really sure that we're past the end
         // of the file
         may_match = iiter->status().IsIncomplete();
-      } else if ((rep_->table_properties &&
-                          rep_->table_properties->index_key_is_user_key
-                      ? iiter->key()
-                      : ExtractUserKey(iiter->key()))
+      } else if (ExtractUserKey(iiter->key())
                      .starts_with(ExtractUserKey(internal_prefix))) {
         // we need to check for this subtle case because our only
         // guarantee is that "the key is a string >= last key in that data
@@ -1825,8 +1750,7 @@ bool BlockBasedTable::PrefixMayMatch(const Slice& internal_key,
         BlockHandle handle;
         s = handle.DecodeFrom(&handle_value);
         assert(s.ok());
-        may_match =
-            filter->PrefixMayMatch(prefix, prefix_extractor, handle.offset());
+        may_match = filter->PrefixMayMatch(prefix, handle.offset());
       }
     }
   }
@@ -1848,7 +1772,7 @@ bool BlockBasedTable::PrefixMayMatch(const Slice& internal_key,
 }
 
 void BlockBasedTableIterator::Seek(const Slice& target) {
-  if (!CheckPrefixMayMatch(target, prefix_extractor_)) {
+  if (!CheckPrefixMayMatch(target)) {
     ResetDataIter();
     return;
   }
@@ -1868,15 +1792,11 @@ void BlockBasedTableIterator::Seek(const Slice& target) {
 
   FindKeyForward();
   assert(!data_block_iter_.Valid() ||
-         (key_includes_seq_ &&
-          icomp_.Compare(target, data_block_iter_.key()) <= 0) ||
-         (!key_includes_seq_ &&
-          icomp_.user_comparator()->Compare(ExtractUserKey(target),
-                                            data_block_iter_.key()) <= 0));
+         icomp_.Compare(target, data_block_iter_.key()) <= 0);
 }
 
 void BlockBasedTableIterator::SeekForPrev(const Slice& target) {
-  if (!CheckPrefixMayMatch(target, prefix_extractor_)) {
+  if (!CheckPrefixMayMatch(target)) {
     ResetDataIter();
     return;
   }
@@ -1988,8 +1908,7 @@ void BlockBasedTableIterator::InitDataBlock() {
     }
 
     BlockBasedTable::NewDataBlockIterator(rep, read_options_, data_block_handle,
-                                          &data_block_iter_, is_index_,
-                                          key_includes_seq_,
+                                          &data_block_iter_, false,
                                           /* get_context */ nullptr, s);
     block_iter_points_to_real_block_ = true;
   }
@@ -2056,30 +1975,22 @@ void BlockBasedTableIterator::FindKeyBackward() {
   // code simplicity.
 }
 
-InternalIterator* BlockBasedTable::NewIterator(
-    const ReadOptions& read_options, const SliceTransform* prefix_extractor,
-    Arena* arena, bool skip_filters) {
-  bool prefix_extractor_changed =
-      PrefixExtractorChanged(rep_->table_properties, prefix_extractor);
-  const bool kIsNotIndex = false;
+InternalIterator* BlockBasedTable::NewIterator(const ReadOptions& read_options,
+                                               Arena* arena,
+                                               bool skip_filters) {
   if (arena == nullptr) {
     return new BlockBasedTableIterator(
         this, read_options, rep_->internal_comparator,
-        NewIndexIterator(
-            read_options,
-            prefix_extractor_changed &&
-                rep_->index_type == BlockBasedTableOptions::kHashSearch),
+        NewIndexIterator(read_options),
         !skip_filters && !read_options.total_order_seek &&
-            prefix_extractor != nullptr && !prefix_extractor_changed,
-        prefix_extractor, kIsNotIndex);
+            rep_->ioptions.prefix_extractor != nullptr);
   } else {
     auto* mem = arena->AllocateAligned(sizeof(BlockBasedTableIterator));
     return new (mem) BlockBasedTableIterator(
         this, read_options, rep_->internal_comparator,
-        NewIndexIterator(read_options, prefix_extractor_changed),
+        NewIndexIterator(read_options),
         !skip_filters && !read_options.total_order_seek &&
-            prefix_extractor != nullptr && !prefix_extractor_changed,
-        prefix_extractor, kIsNotIndex);
+            rep_->ioptions.prefix_extractor != nullptr);
   }
 }
 
@@ -2099,8 +2010,7 @@ InternalIterator* BlockBasedTable::NewRangeTombstoneIterator(
     assert(block_cache != nullptr);
     if (block_cache->Ref(rep_->range_del_entry.cache_handle)) {
       auto iter = rep_->range_del_entry.value->NewIterator(
-          &rep_->internal_comparator,
-          rep_->internal_comparator.user_comparator(), nullptr /* iter */,
+          &rep_->internal_comparator, nullptr /* iter */,
           true /* total_order_seek */, rep_->ioptions.statistics);
       iter->RegisterCleanup(&ReleaseCachedEntry, block_cache,
                             rep_->range_del_entry.cache_handle);
@@ -2114,10 +2024,10 @@ InternalIterator* BlockBasedTable::NewRangeTombstoneIterator(
   return NewDataBlockIterator(rep_, read_options, Slice(str));
 }
 
-bool BlockBasedTable::FullFilterKeyMayMatch(
-    const ReadOptions& read_options, FilterBlockReader* filter,
-    const Slice& internal_key, const bool no_io,
-    const SliceTransform* prefix_extractor) const {
+bool BlockBasedTable::FullFilterKeyMayMatch(const ReadOptions& read_options,
+                                            FilterBlockReader* filter,
+                                            const Slice& internal_key,
+                                            const bool no_io) const {
   if (filter == nullptr || filter->IsBlockBased()) {
     return true;
   }
@@ -2125,15 +2035,15 @@ bool BlockBasedTable::FullFilterKeyMayMatch(
   const Slice* const const_ikey_ptr = &internal_key;
   bool may_match = true;
   if (filter->whole_key_filtering()) {
-    may_match = filter->KeyMayMatch(user_key, prefix_extractor, kNotValid,
-                                    no_io, const_ikey_ptr);
-  } else if (!read_options.total_order_seek && prefix_extractor &&
+    may_match = filter->KeyMayMatch(user_key, kNotValid, no_io, const_ikey_ptr);
+  } else if (!read_options.total_order_seek &&
+             rep_->ioptions.prefix_extractor &&
              rep_->table_properties->prefix_extractor_name.compare(
-                 prefix_extractor->Name()) == 0 &&
-             prefix_extractor->InDomain(user_key) &&
-             !filter->PrefixMayMatch(prefix_extractor->Transform(user_key),
-                                     prefix_extractor, kNotValid, false,
-                                     const_ikey_ptr)) {
+                 rep_->ioptions.prefix_extractor->Name()) == 0 &&
+             rep_->ioptions.prefix_extractor->InDomain(user_key) &&
+             !filter->PrefixMayMatch(
+                 rep_->ioptions.prefix_extractor->Transform(user_key),
+                 kNotValid, false, const_ikey_ptr)) {
     may_match = false;
   }
   if (may_match) {
@@ -2143,37 +2053,25 @@ bool BlockBasedTable::FullFilterKeyMayMatch(
 }
 
 Status BlockBasedTable::Get(const ReadOptions& read_options, const Slice& key,
-                            GetContext* get_context,
-                            const SliceTransform* prefix_extractor,
-                            bool skip_filters) {
-  assert(key.size() >= 8);  // key must be internal key
+                            GetContext* get_context, bool skip_filters) {
   Status s;
   const bool no_io = read_options.read_tier == kBlockCacheTier;
   CachableEntry<FilterBlockReader> filter_entry;
   if (!skip_filters) {
     filter_entry =
-        GetFilter(prefix_extractor, /*prefetch_buffer*/ nullptr,
+        GetFilter(/*prefetch_buffer*/ nullptr,
                   read_options.read_tier == kBlockCacheTier, get_context);
   }
   FilterBlockReader* filter = filter_entry.value;
 
   // First check the full filter
   // If full filter not useful, Then go into each block
-  if (!FullFilterKeyMayMatch(read_options, filter, key, no_io,
-                             prefix_extractor)) {
+  if (!FullFilterKeyMayMatch(read_options, filter, key, no_io)) {
     RecordTick(rep_->ioptions.statistics, BLOOM_FILTER_USEFUL);
   } else {
     BlockIter iiter_on_stack;
-    // if prefix_extractor found in block differs from options, disable
-    // BlockPrefixIndex. Only do this check when index_type is kHashSearch.
-    bool prefix_extractor_changed = false;
-    if (rep_->index_type == BlockBasedTableOptions::kHashSearch) {
-      prefix_extractor_changed =
-          PrefixExtractorChanged(rep_->table_properties, prefix_extractor);
-    }
-    auto iiter = NewIndexIterator(read_options, prefix_extractor_changed,
-                                  &iiter_on_stack, /* index_entry */ nullptr,
-                                  get_context);
+    auto iiter = NewIndexIterator(read_options, &iiter_on_stack,
+                                  /* index_entry */ nullptr, get_context);
     std::unique_ptr<InternalIterator> iiter_unique_ptr;
     if (iiter != &iiter_on_stack) {
       iiter_unique_ptr.reset(iiter);
@@ -2188,8 +2086,7 @@ Status BlockBasedTable::Get(const ReadOptions& read_options, const Slice& key,
       bool not_exist_in_filter =
           filter != nullptr && filter->IsBlockBased() == true &&
           handle.DecodeFrom(&handle_value).ok() &&
-          !filter->KeyMayMatch(ExtractUserKey(key), prefix_extractor,
-                               handle.offset(), no_io);
+          !filter->KeyMayMatch(ExtractUserKey(key), handle.offset(), no_io);
 
       if (not_exist_in_filter) {
         // Not found
@@ -2255,14 +2152,13 @@ Status BlockBasedTable::Get(const ReadOptions& read_options, const Slice& key,
 Status BlockBasedTable::Prefetch(const Slice* const begin,
                                  const Slice* const end) {
   auto& comparator = rep_->internal_comparator;
-  auto user_comparator = comparator.user_comparator();
   // pre-condition
   if (begin && end && comparator.Compare(*begin, *end) > 0) {
     return Status::InvalidArgument(*begin, *end);
   }
 
   BlockIter iiter_on_stack;
-  auto iiter = NewIndexIterator(ReadOptions(), false, &iiter_on_stack);
+  auto iiter = NewIndexIterator(ReadOptions(), &iiter_on_stack);
   std::unique_ptr<InternalIterator> iiter_unique_ptr;
   if (iiter != &iiter_on_stack) {
     iiter_unique_ptr = std::unique_ptr<InternalIterator>(iiter);
@@ -2279,12 +2175,8 @@ Status BlockBasedTable::Prefetch(const Slice* const begin,
   for (begin ? iiter->Seek(*begin) : iiter->SeekToFirst(); iiter->Valid();
        iiter->Next()) {
     Slice block_handle = iiter->value();
-    const bool is_user_key = rep_->table_properties &&
-                             rep_->table_properties->index_key_is_user_key > 0;
-    if (end &&
-        ((!is_user_key && comparator.Compare(iiter->key(), *end) >= 0) ||
-         (is_user_key &&
-          user_comparator->Compare(iiter->key(), ExtractUserKey(*end)) >= 0))) {
+
+    if (end && comparator.Compare(iiter->key(), *end) >= 0) {
       if (prefetching_boundary_page) {
         break;
       }
@@ -2323,8 +2215,7 @@ Status BlockBasedTable::VerifyChecksum() {
   }
   // Check Data blocks
   BlockIter iiter_on_stack;
-  InternalIterator* iiter =
-      NewIndexIterator(ReadOptions(), false, &iiter_on_stack);
+  InternalIterator* iiter = NewIndexIterator(ReadOptions(), &iiter_on_stack);
   std::unique_ptr<InternalIterator> iiter_unique_ptr;
   if (iiter != &iiter_on_stack) {
     iiter_unique_ptr = std::unique_ptr<InternalIterator>(iiter);
@@ -2417,36 +2308,32 @@ Status BlockBasedTable::CreateIndexReader(
     if (pos != props.end()) {
       index_type_on_file = static_cast<BlockBasedTableOptions::IndexType>(
           DecodeFixed32(pos->second.c_str()));
-      // update index_type with the true type
-      rep_->index_type = index_type_on_file;
     }
   }
 
   auto file = rep_->file.get();
   const InternalKeyComparator* icomparator = &rep_->internal_comparator;
   const Footer& footer = rep_->footer;
-
-  // kHashSearch requires non-empty prefix_extractor but bypass checking
-  // prefix_extractor here since we have no access to MutableCFOptions.
-  // Add prefix_extractor_changed flag in  BlockBasedTable::NewIndexIterator.
-  // If prefix_extractor does not match prefix_extractor_name from table
-  // properties, turn off Hash Index by setting total_order_seek to true
+  if (index_type_on_file == BlockBasedTableOptions::kHashSearch &&
+      rep_->ioptions.prefix_extractor == nullptr) {
+    ROCKS_LOG_WARN(rep_->ioptions.info_log,
+                   "BlockBasedTableOptions::kHashSearch requires "
+                   "options.prefix_extractor to be set."
+                   " Fall back to binary search index.");
+    index_type_on_file = BlockBasedTableOptions::kBinarySearch;
+  }
 
   switch (index_type_on_file) {
     case BlockBasedTableOptions::kTwoLevelIndexSearch: {
       return PartitionIndexReader::Create(
           this, file, prefetch_buffer, footer, footer.index_handle(),
           rep_->ioptions, icomparator, index_reader,
-          rep_->persistent_cache_options, level,
-          rep_->table_properties == nullptr ||
-              rep_->table_properties->index_key_is_user_key == 0);
+          rep_->persistent_cache_options, level);
     }
     case BlockBasedTableOptions::kBinarySearch: {
       return BinarySearchIndexReader::Create(
           file, prefetch_buffer, footer, footer.index_handle(), rep_->ioptions,
-          icomparator, index_reader, rep_->persistent_cache_options,
-          rep_->table_properties == nullptr ||
-              rep_->table_properties->index_key_is_user_key == 0);
+          icomparator, index_reader, rep_->persistent_cache_options);
     }
     case BlockBasedTableOptions::kHashSearch: {
       std::unique_ptr<Block> meta_guard;
@@ -2464,9 +2351,7 @@ Status BlockBasedTable::CreateIndexReader(
           return BinarySearchIndexReader::Create(
               file, prefetch_buffer, footer, footer.index_handle(),
               rep_->ioptions, icomparator, index_reader,
-              rep_->persistent_cache_options,
-              rep_->table_properties == nullptr ||
-                  rep_->table_properties->index_key_is_user_key == 0);
+              rep_->persistent_cache_options);
         }
         meta_index_iter = meta_iter_guard.get();
       }
@@ -2475,9 +2360,7 @@ Status BlockBasedTable::CreateIndexReader(
           rep_->internal_prefix_transform.get(), footer, file, prefetch_buffer,
           rep_->ioptions, icomparator, footer.index_handle(), meta_index_iter,
           index_reader, rep_->hash_index_allow_collision,
-          rep_->persistent_cache_options,
-          rep_->table_properties == nullptr ||
-              rep_->table_properties->index_key_is_user_key == 0);
+          rep_->persistent_cache_options);
     }
     default: {
       std::string error_message =
@@ -2578,8 +2461,7 @@ Status BlockBasedTable::GetKVPairsFromDataBlocks(
   return Status::OK();
 }
 
-Status BlockBasedTable::DumpTable(WritableFile* out_file,
-                                  const SliceTransform* prefix_extractor) {
+Status BlockBasedTable::DumpTable(WritableFile* out_file) {
   // Output Footer
   out_file->Append(
       "Footer Details:\n"
@@ -2660,7 +2542,7 @@ Status BlockBasedTable::DumpTable(WritableFile* out_file,
         s = block_fetcher.ReadBlockContents();
         if (!s.ok()) {
           rep_->filter.reset(new BlockBasedFilterBlockReader(
-              prefix_extractor, table_options,
+              rep_->ioptions.prefix_extractor, table_options,
               table_options.whole_key_filtering, std::move(block),
               rep_->ioptions.statistics));
         }
@@ -2745,6 +2627,7 @@ Status BlockBasedTable::DumpIndexBlock(WritableFile* out_file) {
   out_file->Append(
       "Index Details:\n"
       "--------------------------------------\n");
+
   std::unique_ptr<InternalIterator> blockhandles_iter(
       NewIndexIterator(ReadOptions()));
   Status s = blockhandles_iter->status();
@@ -2762,23 +2645,16 @@ Status BlockBasedTable::DumpIndexBlock(WritableFile* out_file) {
       break;
     }
     Slice key = blockhandles_iter->key();
-    Slice user_key;
     InternalKey ikey;
-    if (rep_->table_properties &&
-        rep_->table_properties->index_key_is_user_key != 0) {
-      user_key = key;
-    } else {
-      ikey.DecodeFrom(key);
-      user_key = ikey.user_key();
-    }
+    ikey.DecodeFrom(key);
 
     out_file->Append("  HEX    ");
-    out_file->Append(user_key.ToString(true).c_str());
+    out_file->Append(ikey.user_key().ToString(true).c_str());
     out_file->Append(": ");
     out_file->Append(blockhandles_iter->value().ToString(true).c_str());
     out_file->Append("\n");
 
-    std::string str_key = user_key.ToString();
+    std::string str_key = ikey.user_key().ToString();
     std::string res_key("");
     char cspace = ' ';
     for (size_t i = 0; i < str_key.size(); i++) {

table/block_based_table_reader.h

@@ -90,29 +90,25 @@ class BlockBasedTable : public TableReader {
                      const InternalKeyComparator& internal_key_comparator,
                      unique_ptr<RandomAccessFileReader>&& file,
                      uint64_t file_size, unique_ptr<TableReader>* table_reader,
-                     const SliceTransform* prefix_extractor = nullptr,
                      bool prefetch_index_and_filter_in_cache = true,
                      bool skip_filters = false, int level = -1);
 
-  bool PrefixMayMatch(const Slice& internal_key,
-                      const SliceTransform* prefix_extractor = nullptr);
+  bool PrefixMayMatch(const Slice& internal_key);
 
   // Returns a new iterator over the table contents.
   // The result of NewIterator() is initially invalid (caller must
   // call one of the Seek methods on the iterator before using it).
   // @param skip_filters Disables loading/accessing the filter block
-  InternalIterator* NewIterator(const ReadOptions&,
-                                const SliceTransform* prefix_extractor,
-                                Arena* arena = nullptr,
-                                bool skip_filters = false) override;
+  InternalIterator* NewIterator(
+      const ReadOptions&, Arena* arena = nullptr,
+      bool skip_filters = false) override;
 
   InternalIterator* NewRangeTombstoneIterator(
       const ReadOptions& read_options) override;
 
   // @param skip_filters Disables loading/accessing the filter block
   Status Get(const ReadOptions& readOptions, const Slice& key,
-             GetContext* get_context, const SliceTransform* prefix_extractor,
-             bool skip_filters = false) override;
+             GetContext* get_context, bool skip_filters = false) override;
 
   // Pre-fetch the disk blocks that correspond to the key range specified by
   // (kbegin, kend). The call will return error status in the event of
@@ -140,8 +136,7 @@ class BlockBasedTable : public TableReader {
   size_t ApproximateMemoryUsage() const override;
 
   // convert SST file to a human readable form
-  Status DumpTable(WritableFile* out_file,
-                   const SliceTransform* prefix_extractor = nullptr) override;
+  Status DumpTable(WritableFile* out_file) override;
 
   Status VerifyChecksum() override;
 
@@ -217,13 +212,11 @@ class BlockBasedTable : public TableReader {
                                          const Slice& index_value,
                                          BlockIter* input_iter = nullptr,
                                          bool is_index = false,
-                                         bool key_includes_seq = true,
                                          GetContext* get_context = nullptr);
   static BlockIter* NewDataBlockIterator(Rep* rep, const ReadOptions& ro,
                                          const BlockHandle& block_hanlde,
                                          BlockIter* input_iter = nullptr,
                                          bool is_index = false,
-                                         bool key_includes_seq = true,
                                          GetContext* get_context = nullptr,
                                          Status s = Status());
 
@@ -260,13 +253,12 @@ class BlockBasedTable : public TableReader {
   // if `no_io == true`, we will not try to read filter/index from sst file
   // were they not present in cache yet.
   CachableEntry<FilterBlockReader> GetFilter(
-      const SliceTransform* prefix_extractor = nullptr,
       FilePrefetchBuffer* prefetch_buffer = nullptr, bool no_io = false,
       GetContext* get_context = nullptr) const;
   virtual CachableEntry<FilterBlockReader> GetFilter(
       FilePrefetchBuffer* prefetch_buffer, const BlockHandle& filter_blk_handle,
-      const bool is_a_filter_partition, bool no_io, GetContext* get_context,
-      const SliceTransform* prefix_extractor = nullptr) const;
+      const bool is_a_filter_partition, bool no_io,
+      GetContext* get_context) const;
 
   // Get the iterator from the index reader.
   // If input_iter is not set, return new Iterator
@@ -279,8 +271,7 @@ class BlockBasedTable : public TableReader {
   //  3. We disallowed any io to be performed, that is, read_options ==
   //     kBlockCacheTier
   InternalIterator* NewIndexIterator(
-      const ReadOptions& read_options, bool prefix_extractor_changed = false,
-      BlockIter* input_iter = nullptr,
+      const ReadOptions& read_options, BlockIter* input_iter = nullptr,
       CachableEntry<IndexReader>* index_entry = nullptr,
       GetContext* get_context = nullptr);
 
@@ -334,10 +325,9 @@ class BlockBasedTable : public TableReader {
       InternalIterator* preloaded_meta_index_iter = nullptr,
       const int level = -1);
 
-  bool FullFilterKeyMayMatch(
-      const ReadOptions& read_options, FilterBlockReader* filter,
-      const Slice& user_key, const bool no_io,
-      const SliceTransform* prefix_extractor = nullptr) const;
+  bool FullFilterKeyMayMatch(const ReadOptions& read_options,
+                             FilterBlockReader* filter, const Slice& user_key,
+                             const bool no_io) const;
 
   // Read the meta block from sst.
   static Status ReadMetaBlock(Rep* rep, FilePrefetchBuffer* prefetch_buffer,
@@ -347,10 +337,9 @@ class BlockBasedTable : public TableReader {
   Status VerifyChecksumInBlocks(InternalIterator* index_iter);
 
   // Create the filter from the filter block.
-  FilterBlockReader* ReadFilter(
-      FilePrefetchBuffer* prefetch_buffer, const BlockHandle& filter_handle,
-      const bool is_a_filter_partition,
-      const SliceTransform* prefix_extractor = nullptr) const;
+  FilterBlockReader* ReadFilter(FilePrefetchBuffer* prefetch_buffer,
+                                const BlockHandle& filter_handle,
+                                const bool is_a_filter_partition) const;
 
   static void SetupCacheKeyPrefix(Rep* rep, uint64_t file_size);
 
@@ -380,15 +369,13 @@ class BlockBasedTable::PartitionedIndexIteratorState
  public:
   PartitionedIndexIteratorState(
       BlockBasedTable* table,
-      std::unordered_map<uint64_t, CachableEntry<Block>>* block_map,
-      const bool index_key_includes_seq);
+      std::unordered_map<uint64_t, CachableEntry<Block>>* block_map = nullptr);
   InternalIterator* NewSecondaryIterator(const Slice& index_value) override;
 
  private:
   // Don't own table_
   BlockBasedTable* table_;
   std::unordered_map<uint64_t, CachableEntry<Block>>* block_map_;
-  bool index_key_includes_seq_;
 };
 
 // CachableEntry represents the entries that *may* be fetched from block cache.
@@ -512,19 +499,14 @@ class BlockBasedTableIterator : public InternalIterator {
   BlockBasedTableIterator(BlockBasedTable* table,
                           const ReadOptions& read_options,
                           const InternalKeyComparator& icomp,
-                          InternalIterator* index_iter, bool check_filter,
-                          const SliceTransform* prefix_extractor, bool is_index,
-                          bool key_includes_seq = true)
+                          InternalIterator* index_iter, bool check_filter)
       : table_(table),
         read_options_(read_options),
         icomp_(icomp),
         index_iter_(index_iter),
         pinned_iters_mgr_(nullptr),
         block_iter_points_to_real_block_(false),
-        check_filter_(check_filter),
-        is_index_(is_index),
-        key_includes_seq_(key_includes_seq),
-        prefix_extractor_(prefix_extractor) {}
+        check_filter_(check_filter) {}
 
   ~BlockBasedTableIterator() { delete index_iter_; }
 
@@ -570,9 +552,8 @@ class BlockBasedTableIterator : public InternalIterator {
            block_iter_points_to_real_block_;
   }
 
-  bool CheckPrefixMayMatch(const Slice& ikey,
-                           const SliceTransform* prefix_extractor = nullptr) {
-    if (check_filter_ && !table_->PrefixMayMatch(ikey, prefix_extractor)) {
+  bool CheckPrefixMayMatch(const Slice& ikey) {
+    if (check_filter_ && !table_->PrefixMayMatch(ikey)) {
       // TODO remember the iterator is invalidated because of prefix
       // match. This can avoid the upper level file iterator to falsely
       // believe the position is the end of the SST file and move to
@@ -616,13 +597,8 @@ class BlockBasedTableIterator : public InternalIterator {
   bool block_iter_points_to_real_block_;
   bool is_out_of_bound_ = false;
   bool check_filter_;
-  // If the blocks over which we iterate are index blocks
-  bool is_index_;
-  // If the keys in the blocks over which we iterate include 8 byte sequence
-  bool key_includes_seq_;
   // TODO use block offset instead
   std::string prev_index_value_;
-  const SliceTransform* prefix_extractor_;
 
   static const size_t kInitReadaheadSize = 8 * 1024;
   // Found that 256 KB readahead size provides the best performance, based on