Disable error as warning

Add one more #include<functional>
Add some include<functional>
2026-11-06 02:52:35 -05:00 · 2019-11-05 11:03:42 -08:00 · 2019-11-05 11:03:40 -08:00 · 2019-10-31 14:30:44 -07:00 · 2019-10-31 14:30:43 -07:00 · 2017-07-17 22:21:57 -07:00
667 changed files with 5411 additions and 1778 deletions
@@ -42,6 +42,7 @@ unity.a
 tags
 rocksdb_dump
 rocksdb_undump
+db_test2

 java/out
 java/target
@@ -177,7 +177,6 @@ set(SOURCES
        table/merger.cc
        table/sst_file_writer.cc
        table/meta_blocks.cc
-        table/mock_table.cc
        table/plain_table_builder.cc
        table/plain_table_factory.cc
        table/plain_table_index.cc
@@ -186,6 +185,7 @@ set(SOURCES
        table/table_properties.cc
        table/two_level_iterator.cc
        tools/sst_dump_tool.cc
+        tools/db_bench_tool.cc
        tools/dump/db_dump_tool.cc
        util/arena.cc
        util/bloom.cc
@@ -214,7 +214,6 @@ set(SOURCES
        util/logging.cc
        util/log_buffer.cc
        util/memenv.cc
-        util/mock_env.cc
        util/murmurhash.cc
        util/mutable_cf_options.cc
        util/options.cc
@@ -277,6 +276,8 @@ set(SOURCES
 # and linked to tests. Add test only code that is not #ifdefed for Release here.
 set(TESTUTIL_SOURCE
    db/db_test_util.cc
+    table/mock_table.cc
+    util/mock_env.cc
    util/thread_status_updater_debug.cc
 )

@@ -301,7 +302,7 @@ else()
 endif()

 set(APPS
-        db/db_bench.cc
+        tools/db_bench.cc
        db/memtablerep_bench.cc
        table/table_reader_bench.cc
        tools/db_stress.cc
@@ -336,6 +337,8 @@ set(TESTS
        db/db_table_properties_test.cc
        db/db_tailing_iter_test.cc
        db/db_test.cc
+        db/db_test2.cc
+        db/db_block_cache_test.cc
        db/db_universal_compaction_test.cc
        db/db_wal_test.cc
        db/dbformat_test.cc
@@ -390,6 +393,7 @@ set(TESTS
        util/file_reader_writer_test.cc
        util/heap_test.cc
        util/histogram_test.cc
+        util/iostats_context_test.cc
        util/memenv_test.cc
        util/mock_env_test.cc
        util/options_test.cc
@@ -1,12 +1,23 @@
 # Rocksdb Change Log
-## Unreleased
+## 4.6.0 (3/10/2016)
 ### Public API Changes
-* Add a new perf context level between kEnableCount and kEnableTime. Level 2 now doesn't include timers for mutexes.
+* Change default of BlockBasedTableOptions.format_version to 2. It means default DB created by 4.6 or up cannot be opened by RocksDB version 3.9 or earlier.
+* Added strict_capacity_limit option to NewLRUCache. If the flag is set to true, insert to cache will fail if no enough capacity can be free. Signiture of Cache::Insert() is updated accordingly.
+* Tickers [NUMBER_DB_NEXT, NUMBER_DB_PREV, NUMBER_DB_NEXT_FOUND, NUMBER_DB_PREV_FOUND, ITER_BYTES_READ] are not updated immediately. The are updated when the Iterator is deleted.  
+* Add monotonically increasing counter (DB property "rocksdb.current-super-version-number") that increments upon any change to the LSM tree.
+### New Features
+* Add CompactionPri::kMinOverlappingRatio, a compaction picking mode friendly to write amplification.
+* Deprecate Iterator::IsKeyPinned() and replace it with Iterator::GetProperty() with prop_name="rocksdb.iterator.is.key.pinned"
+
+## 4.5.0 (2/5/2016)
+### Public API Changes
+* Add a new perf context level between kEnableCount and kEnableTime. Level 2 now does not include timers for mutexes.
 * Statistics of mutex operation durations will not be measured by default. If you want to have them enabled, you need to set Statistics::stats_level_ to kAll.
 * DBOptions::delete_scheduler and NewDeleteScheduler() are removed, please use DBOptions::sst_file_manager and NewSstFileManager() instead

 ### New Features
 * ldb tool now supports operations to non-default column families.
+* Add kPersistedTier to ReadTier.  This option allows Get and MultiGet to read only the persited data and skip mem-tables if writes were done with disableWAL = true.
 * Add DBOptions::sst_file_manager. Use NewSstFileManager() in include/rocksdb/sst_file_manager.h to create a SstFileManager that can be used to track the total size of SST files and control the SST files deletion rate.  

 ## 4.4.0 (1/14/2016)
@@ -2,7 +2,7 @@ BSD License

 For rocksdb software

-Copyright (c) 2014, Facebook, Inc.
+Copyright (c) 2011-present, Facebook, Inc.
 All rights reserved.
 ---------------------------------------------------------------------

@@ -84,12 +84,11 @@ endif
 # compile with -O2 if debug level is not 2
 ifneq ($(DEBUG_LEVEL), 2)
 OPT += -O2 -fno-omit-frame-pointer
-ifeq (,$(findstring ppc64,$(MACHINE))) # ppc64[le] doesn't support -momit-leaf-frame-pointer
-ifneq ($(MACHINE),armv7l)
+# Skip for archs that don't support -momit-leaf-frame-pointer
+ifeq (,$(shell $(CXX) -fsyntax-only -momit-leaf-frame-pointer -xc /dev/null 2>&1))
 OPT += -momit-leaf-frame-pointer
 endif
 endif
-endif

 # if we're compiling for release, compile without debug code (-DNDEBUG) and
 # don't treat warnings as errors
@@ -192,10 +191,6 @@ default: all
 WARNING_FLAGS = -W -Wextra -Wall -Wsign-compare -Wshadow \
  -Wno-unused-parameter

-ifndef DISABLE_WARNING_AS_ERROR
-	WARNING_FLAGS += -Werror
-endif
-
 CFLAGS += $(WARNING_FLAGS) -I. -I./include $(PLATFORM_CCFLAGS) $(OPT)
 CXXFLAGS += $(WARNING_FLAGS) -I. -I./include $(PLATFORM_CXXFLAGS) $(OPT) -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers

@@ -242,8 +237,12 @@ VALGRIND_VER := $(join $(VALGRIND_VER),valgrind)

 VALGRIND_OPTS = --error-exitcode=$(VALGRIND_ERROR) --leak-check=full

+BENCHTOOLOBJECTS = $(BENCH_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)
+
 TESTS = \
 	db_test \
+	db_test2 \
+	db_block_cache_test \
 	db_iter_test \
 	db_log_iter_test \
 	db_compaction_filter_test \
@@ -338,7 +337,8 @@ TESTS = \
 	compact_on_deletion_collector_test \
 	compaction_job_stats_test \
 	transaction_test \
-	ldb_cmd_test
+	ldb_cmd_test \
+	iostats_context_test

 SUBSET :=  $(shell echo $(TESTS) |sed s/^.*$(ROCKSDBTESTS_START)/$(ROCKSDBTESTS_START)/)

@@ -644,8 +644,6 @@ parloop:
 	exit $$ret_bad;
 endif

-all_tests:=$(shell $(test_names))
-
 parallel_check: $(TESTS)
 	$(AM_V_GEN)if test "$(J)" > 1                                  \
 	    && (parallel --gnu --help 2>/dev/null) |                    \
@@ -659,7 +657,7 @@ parallel_check: $(TESTS)
 	echo $(J);\
 	echo Test Dir: $(TMPD); \
        seq $(J) | parallel --gnu 's=$(TMPD)/rdb-{}; rm -rf $$s; mkdir $$s'; \
-	$(MAKE)  PAR_TEST="$(all_tests)" TMPD=$(TMPD) \
+	$(MAKE)  PAR_TEST="$(shell $(test_names))" TMPD=$(TMPD) \
 		J=$(J) db_test=1 parloop; \
 	$(MAKE) PAR_TEST="$(filter-out db_test, $(TESTS))" \
 		TMPD=$(TMPD) J=$(J) db_test=0 parloop;
@@ -715,7 +713,7 @@ $(LIBRARY): $(LIBOBJECTS)
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $(LIBOBJECTS)

-db_bench: db/db_bench.o $(LIBOBJECTS) $(TESTUTIL)
+db_bench: tools/db_bench.o $(BENCHTOOLOBJECTS)
 	$(AM_LINK)

 cache_bench: util/cache_bench.o $(LIBOBJECTS) $(TESTUTIL)
@@ -790,6 +788,12 @@ slice_transform_test: util/slice_transform_test.o $(LIBOBJECTS) $(TESTHARNESS)
 db_test: db/db_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

+db_test2: db/db_test2.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+db_block_cache_test: db/db_block_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 db_log_iter_test: db/db_log_iter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1045,6 +1049,9 @@ ldb_cmd_test: tools/ldb_cmd_test.o $(LIBOBJECTS) $(TESTHARNESS)
 ldb: tools/ldb.o $(LIBOBJECTS)
 	$(AM_LINK)

+iostats_context_test: util/iostats_context_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_V_CCLD)$(CXX) $^ $(EXEC_LDFLAGS) -o $@ $(LDFLAGS)
+
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -1207,7 +1214,7 @@ jdb_bench:

 commit_prereq: build_tools/rocksdb-lego-determinator \
               build_tools/precommit_checker.py
-	build_tools/precommit_checker.py unit unit_481 clang_unit tsan asan lite
+	J=$(J) build_tools/precommit_checker.py unit unit_481 clang_unit tsan asan lite
 	$(MAKE) clean && $(MAKE) jclean && $(MAKE) rocksdbjava;

 xfunc:
@@ -1,5 +1,5 @@
 #!/usr/bin/python
-# Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+# Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree. An additional grant
 # of patent rights can be found in the PATENTS file in the same directory.
@@ -52,12 +52,7 @@ if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
    FBCODE_BUILD="true"
    # If we're compiling with TSAN we need pic build
    PIC_BUILD=$COMPILE_WITH_TSAN
-    if [ -z "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
-      source "$PWD/build_tools/fbcode_config.sh"
-    else
-      # we need this to build with MySQL. Don't use for other purposes.
-      source "$PWD/build_tools/fbcode_config4.8.1.sh"
-    fi
+    source "$PWD/build_tools/fbcode_config.sh"
 fi

 # Delete existing output, if it exists
@@ -189,17 +184,19 @@ if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
    # Also don't need any compilation tests if compiling on fbcode
    true
 else
-    # Test whether fallocate is available
-    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      #include <fcntl.h>
-      #include <linux/falloc.h>
-      int main() {
-	int fd = open("/dev/null", 0);
-  fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
-      }
+    if ! test $ROCKSDB_DISABLE_FALLOCATE; then
+        # Test whether fallocate is available
+        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+          #include <fcntl.h>
+          #include <linux/falloc.h>
+          int main() {
+      int fd = open("/dev/null", 0);
+      fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
+          }
 EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_FALLOCATE_PRESENT"
+        if [ "$?" = 0 ]; then
+            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_FALLOCATE_PRESENT"
+        fi
    fi

    # Test whether Snappy library is installed
@@ -363,6 +360,8 @@ elif test -z "$PORTABLE"; then
    # Tune for this POWER processor, treating '+' models as base models
    POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
    COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
+  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
+    COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
  else
    COMMON_FLAGS="$COMMON_FLAGS -march=native "
  fi
@@ -1,16 +1,19 @@
-GCC_BASE=/mnt/vol/engshare/fbcode/third-party2/gcc/4.9.x/centos6-native/1317bc4/
-CLANG_BASE=/mnt/vol/engshare/fbcode/third-party2/clang/3.7.1/centos6-native/9d9ecb9/
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/5710d6a0fb0d12820aac0bffcd7fcb8646e7fff7/4.9.x/gcc-4.9-glibc-2.20/024dbc3
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/0600c95b31226b5e535614c590677d87c62d8016/2.20/gcc-4.9-glibc-2.20/500e281
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/cbf6f1f209e5bd160bdc5d971744e039f36b1566/1.1.3/gcc-4.9-glibc-2.20/e9936bf
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/6d39cb54708049f527e713ad19f2aadb9d3667e8/1.2.8/gcc-4.9-glibc-2.20/e9936bf
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/2ddd45f0853bfc8bb1c27f0f447236a1a26c338a/1.0.6/gcc-4.9-glibc-2.20/e9936bf
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/6858fac689e0f92e584224d91bdb0e39f6c8320d/r131/gcc-4.9-glibc-2.20/e9936bf
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/69d56740ffb89d8bc81ded8ec428c01a813ea948/0.4.7/gcc-4.9-glibc-2.20/e9936bf
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/c7275a4ceae0aca0929e56964a31dafc53c1ee96/2.1.1/gcc-4.8.1-glibc-2.17/c3f970a
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/5f0be745ddc0f86f22c8c8bb64b6b1163c93df91/4.0.3/gcc-4.9-glibc-2.20/a6c5e1e
-NUMA_BASE=/mnt/gvfs/third-party2/numa/ae54a5ed22cdabb1c6446dce4e8ffae5b4446d73/2.0.8/gcc-4.9-glibc-2.20/e9936bf
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/121f1a75c4414683aea8c70b761bfaf187f7c1a3/trunk/gcc-4.9-glibc-2.20/12266b1
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/1a48835975c66d30e47770ec419758ed3b9ba010/3.10.62-62_fbk17_03959_ge29cc63/gcc-4.9-glibc-2.20/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/75670d0d8ef4891fd1ec2a7513ef01cd002c823b/2.25/centos6-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/af85c56f424cd5edfc2c97588299b44ecdec96bb/3.10.0/gcc-4.9-glibc-2.20/e9936bf
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/7.x/centos7-native/b2ef2b6
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/963d9aeda70cc4779885b1277484fe7544a04e3e/9.0.0/platform007/9e92d53/
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/7.x/platform007/5620abc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.26/platform007/f259413
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/platform007/ca4da3d
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/platform007/ca4da3d
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/platform007/15a3614
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/platform007/c26c002
+NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/platform007/ca4da3d
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/platform007/6f3e0a9
+TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/platform007/ca4da3d
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/fb/platform007/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/ab9f09bba370e7066cafd4eb59752db93f2e8312/2.29.1/platform007/15a3614
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/platform007/ca4da3d
+LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.3.4/platform007/5007832
@@ -1,16 +1,16 @@
-GCC_BASE=/mnt/vol/engshare/fbcode/third-party2/gcc/4.8.1/centos6-native/cc6c9dc/
-CLANG_BASE=/mnt/vol/engshare/fbcode/third-party2/clang/3.7.1/centos6-native/9d9ecb9/
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/5710d6a0fb0d12820aac0bffcd7fcb8646e7fff7/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/0600c95b31226b5e535614c590677d87c62d8016/2.17/gcc-4.8.1-glibc-2.17/99df8fc
+GCC_BASE=/mnt/gvfs/third-party2/gcc/ebc96bc2fb751b5a0300b8d91a95bdf24ac1d88b/4.8.1/centos6-native/cc6c9dc
+CLANG_BASE=/mnt/gvfs/third-party2/clang/fc904e50a9266b9d7b98cae1993afa0c5aae1440/3.7.1/centos6-native/9d9ecb9/
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/ea2fd1278810d3af2ea52218d2767e09d786dbd0/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/f5484f168c0e4d19823d41df052c5870c6e575a4/2.17/gcc-4.8.1-glibc-2.17/99df8fc
 SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/cbf6f1f209e5bd160bdc5d971744e039f36b1566/1.1.3/gcc-4.8.1-glibc-2.17/c3f970a
 ZLIB_BASE=/mnt/gvfs/third-party2/zlib/6d39cb54708049f527e713ad19f2aadb9d3667e8/1.2.8/gcc-4.8.1-glibc-2.17/c3f970a
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/2ddd45f0853bfc8bb1c27f0f447236a1a26c338a/1.0.6/gcc-4.8.1-glibc-2.17/c3f970a
 LZ4_BASE=/mnt/gvfs/third-party2/lz4/6858fac689e0f92e584224d91bdb0e39f6c8320d/r131/gcc-4.8.1-glibc-2.17/c3f970a
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/69d56740ffb89d8bc81ded8ec428c01a813ea948/0.4.7/gcc-4.8.1-glibc-2.17/c3f970a
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/cb6c4880fcb4fee471574ba6af63a3882155a16a/0.5.1/gcc-4.8.1-glibc-2.17/c3f970a
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/c7275a4ceae0aca0929e56964a31dafc53c1ee96/2.1.1/gcc-4.8.1-glibc-2.17/c3f970a
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/5f0be745ddc0f86f22c8c8bb64b6b1163c93df91/4.0.3/gcc-4.8.1-glibc-2.17/8d31e51
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/40791a3fef9206a77f2c4bc51f8169e5bf10d68e/master/gcc-4.8.1-glibc-2.17/8d31e51
 NUMA_BASE=/mnt/gvfs/third-party2/numa/ae54a5ed22cdabb1c6446dce4e8ffae5b4446d73/2.0.8/gcc-4.8.1-glibc-2.17/c3f970a
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/121f1a75c4414683aea8c70b761bfaf187f7c1a3/trunk/gcc-4.8.1-glibc-2.17/675d945
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/303048f72efc92ae079e62dfc84823401aecfd94/trunk/gcc-4.8.1-glibc-2.17/675d945
 KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/1a48835975c66d30e47770ec419758ed3b9ba010/3.10.62-62_fbk17_03959_ge29cc63/gcc-4.8.1-glibc-2.17/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/75670d0d8ef4891fd1ec2a7513ef01cd002c823b/2.25/centos6-native/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/a5b8152b2a15ce8a98808cf954fbccec825a97bc/2.25/centos6-native/da39a3e
 VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/af85c56f424cd5edfc2c97588299b44ecdec96bb/3.8.1/gcc-4.8.1-glibc-2.17/c3f970a
@@ -13,12 +13,12 @@ source "$BASEDIR/dependencies.sh"
 CFLAGS=""

 # libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/libs"
+LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/7.3.0"
+LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"

 # glibc
 GLIBC_INCLUDE="$GLIBC_BASE/include"
-GLIBC_LIBS=" -L $GLIB_BASE/lib"
+GLIBC_LIBS=" -L $GLIBC_BASE/lib"

 # snappy
 SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
@@ -43,12 +43,16 @@ if test -z $PIC_BUILD; then
  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
  CFLAGS+=" -DLZ4"
-
-  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-  CFLAGS+=" -DZSTD"
 fi

+ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
+if test -z $PIC_BUILD; then
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
+else
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
+fi
+CFLAGS+=" -DZSTD"
+
 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
 if test -z $PIC_BUILD; then
@@ -56,7 +60,7 @@ if test -z $PIC_BUILD; then
 else
  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags_pic.a"
 fi
-CFLAGS+=" -DGFLAGS=google"
+CFLAGS+=" -DGFLAGS=gflags"

 # location of jemalloc
 JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
@@ -72,13 +76,22 @@ if test -z $PIC_BUILD; then
  LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
 fi

+# location of TBB
+TBB_INCLUDE=" -isystem $TBB_BASE/include/"
+if test -z $PIC_BUILD; then
+  TBB_LIBS="$TBB_BASE/lib/libtbb.a"
+else
+  TBB_LIBS="$TBB_BASE/lib/libtbb_pic.a"
+fi
+CFLAGS+=" -DTBB"
+
 # use Intel SSE support for checksum calculations
 export USE_SSE=1

 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"

-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE"
+DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE"

 STDLIBS="-L $GCC_BASE/lib64"

@@ -87,7 +100,7 @@ CLANG_LIB="$CLANG_BASE/lib"
 CLANG_SRC="$CLANG_BASE/../../src"

 CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_SRC/clang/tools/scan-build/scan-build"
+CLANG_SCAN_BUILD="$CLANG_SRC/llvm/tools/clang/tools/scan-build/bin/scan-build"

 if [ -z "$USE_CLANG" ]; then
  # gcc
@@ -95,40 +108,45 @@ if [ -z "$USE_CLANG" ]; then
  CXX="$GCC_BASE/bin/g++"

  CFLAGS+=" -B$BINUTILS/gold"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
+  CFLAGS+=" -isystem $GLIBC_INCLUDE"
+  JEMALLOC=1
 else
  # clang
-  CLANG_INCLUDE="$CLANG_LIB/clang/*/include"
+  CLANG_INCLUDE="$CLANG_LIB/clang/stable/include"
  CC="$CLANG_BIN/clang"
  CXX="$CLANG_BIN/clang++"

  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"

  CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.9.x "
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.9.x/x86_64-facebook-linux "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x/x86_64-facebook-linux "
  CFLAGS+=" -isystem $GLIBC_INCLUDE"
  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
  CFLAGS+=" -isystem $CLANG_INCLUDE"
  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
+  CFLAGS+=" -Wno-expansion-to-defined "
  CXXFLAGS="-nostdinc++"
 fi

 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
 CXXFLAGS+=" $CFLAGS"

-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB"
-EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-4.9-glibc-2.20/lib/ld.so"
+EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
+EXEC_LDFLAGS+=" -B$BINUTILS/gold"
+EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform007/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-4.9-glibc-2.20/lib"
+EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform007/lib"
+# required by libtbb
+EXEC_LDFLAGS+=" -ldl"

 PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"

-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS"
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS"

 VALGRIND_VER="$VALGRIND_BASE/bin/"

-export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD
+export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD 
@@ -1,5 +1,5 @@
 #!/bin/bash
-#  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+#  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 #  This source code is licensed under the BSD-style license found in the
 #  LICENSE file in the root directory of this source tree. An additional grant
 #  of patent rights can be found in the PATENTS file in the same directory.
@@ -10,7 +10,7 @@ then
  GIT="git"
 fi

-# Print out the colored progress info so that it can be brainlessly 
+# Print out the colored progress info so that it can be brainlessly
 # distinguished by users.
 function title() {
  echo -e "\033[1;32m$*\033[0m"
@@ -64,8 +64,8 @@ touch "$OUTPUT"
 echo "Writing dependencies to $OUTPUT"

 # Compilers locations
-GCC_BASE=`ls -d1 $TP2_LATEST/gcc/4.9.x/centos6-native/*/ | head -n1`
-CLANG_BASE=`ls -d1 $TP2_LATEST/clang/3.7.1/centos6-native/*/ | head -n1`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.9.x/centos6-native/*/`
+CLANG_BASE=`ls -d1 /mnt/gvfs/third-party2/clang/fc904e50a9266b9d7b98cae1993afa0c5aae1440/3.7.1/centos6-native/*/ | head -n1`

 log_variable GCC_BASE
 log_variable CLANG_BASE
@@ -101,8 +101,8 @@ touch "$OUTPUT"
 echo "Writing 4.8.1 dependencies to $OUTPUT"

 # Compilers locations
-GCC_BASE=`ls -d1 $TP2_LATEST/gcc/4.8.1/centos6-native/*/ | head -n1`
-CLANG_BASE=`ls -d1 $TP2_LATEST/clang/3.7.1/centos6-native/*/ | head -n1`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.8.1/centos6-native/*/`
+CLANG_BASE=`ls -d1 /mnt/gvfs/third-party2/clang/fc904e50a9266b9d7b98cae1993afa0c5aae1440/3.7.1/centos6-native/*/ | head -n1`

 log_variable GCC_BASE
 log_variable CLANG_BASE
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -12,7 +12,9 @@ namespace rocksdb {

 // -- AutoRollLogger
 Status AutoRollLogger::ResetLogger() {
+  TEST_SYNC_POINT("AutoRollLogger::ResetLogger:BeforeNewLogger");
  status_ = env_->NewLogger(log_fname_, &logger_);
+  TEST_SYNC_POINT("AutoRollLogger::ResetLogger:AfterNewLogger");

  if (!status_.ok()) {
    return status_;
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -13,6 +13,8 @@
 #include "db/filename.h"
 #include "port/port.h"
 #include "port/util_logger.h"
+#include "util/sync_point.h"
+#include "util/mutexlock.h"

 namespace rocksdb {

@@ -53,11 +55,26 @@ class AutoRollLogger : public Logger {
    return status_;
  }

-  size_t GetLogFileSize() const override { return logger_->GetLogFileSize(); }
+  size_t GetLogFileSize() const override {
+    std::shared_ptr<Logger> logger;
+    {
+      MutexLock l(&mutex_);
+      // pin down the current logger_ instance before releasing the mutex.
+      logger = logger_;
+    }
+    return logger->GetLogFileSize();
+  }

  void Flush() override {
-    if (logger_) {
-      logger_->Flush();
+    std::shared_ptr<Logger> logger;
+    {
+      MutexLock l(&mutex_);
+      // pin down the current logger_ instance before releasing the mutex.
+      logger = logger_;
+    }
+    TEST_SYNC_POINT("AutoRollLogger::Flush:PinnedLogger");
+    if (logger) {
+      logger->Flush();
    }
  }

@@ -101,7 +118,7 @@ class AutoRollLogger : public Logger {
  uint64_t ctime_;
  uint64_t cached_now_access_count;
  uint64_t call_NowMicros_every_N_records_;
-  port::Mutex mutex_;
+  mutable port::Mutex mutex_;
 };

 // Facade to craete logger automatically
@@ -1,9 +1,10 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
 //
 #include <string>
+#include <thread>
 #include <vector>
 #include <cmath>
 #include <iostream>
@@ -11,6 +12,8 @@
 #include <iterator>
 #include <algorithm>
 #include "db/auto_roll_logger.h"
+#include "port/port.h"
+#include "util/sync_point.h"
 #include "util/testharness.h"
 #include "rocksdb/db.h"
 #include <sys/stat.h>
@@ -260,7 +263,60 @@ TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
      auto_roll_logger, options.log_file_time_to_roll,
      kSampleMessage + ":CreateLoggerFromOptions - both");
 }
-#endif
+
+TEST_F(AutoRollLoggerTest, LogFlushWhileRolling) {
+  DBOptions options;
+  shared_ptr<Logger> logger;
+
+  InitTestDb();
+  options.max_log_file_size = 1024 * 5;
+  ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
+  AutoRollLogger* auto_roll_logger =
+      dynamic_cast<AutoRollLogger*>(logger.get());
+  ASSERT_TRUE(auto_roll_logger);
+  std::thread flush_thread;
+
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
+      // Need to pin the old logger before beginning the roll, as rolling grabs
+      // the mutex, which would prevent us from accessing the old logger.
+      {"AutoRollLogger::Flush:PinnedLogger",
+       "AutoRollLoggerTest::LogFlushWhileRolling:PreRollAndPostThreadInit"},
+      // Need to finish the flush thread init before this callback because the
+      // callback accesses flush_thread.get_id() in order to apply certain sync
+      // points only to the flush thread.
+      {"AutoRollLoggerTest::LogFlushWhileRolling:PreRollAndPostThreadInit",
+       "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallbackBegin"},
+      // Need to reset logger at this point in Flush() to exercise a race
+      // condition case, which is executing the flush with the pinned (old)
+      // logger after the roll has cut over to a new logger.
+      {"AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback1",
+       "AutoRollLogger::ResetLogger:BeforeNewLogger"},
+      {"AutoRollLogger::ResetLogger:AfterNewLogger",
+       "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback2"},
+  });
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "PosixLogger::Flush:BeginCallback", [&](void* arg) {
+        TEST_SYNC_POINT(
+            "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallbackBegin");
+        if (std::this_thread::get_id() == flush_thread.get_id()) {
+          TEST_SYNC_POINT(
+              "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback1");
+          TEST_SYNC_POINT(
+              "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback2");
+        }
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  flush_thread = std::thread([&]() { auto_roll_logger->Flush(); });
+  TEST_SYNC_POINT(
+      "AutoRollLoggerTest::LogFlushWhileRolling:PreRollAndPostThreadInit");
+  RollLogFileBySizeTest(auto_roll_logger, options.max_log_file_size,
+                        kSampleMessage + ":LogFlushWhileRolling");
+  flush_thread.join();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+}
+
+#endif  // OS_WIN

 TEST_F(AutoRollLoggerTest, InfoLogLevel) {
  InitTestDb();
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -135,6 +135,10 @@ Status CheckConcurrentWritesSupported(const ColumnFamilyOptions& cf_options) {
        "Delete filtering (filter_deletes) is not compatible with concurrent "
        "memtable writes (allow_concurrent_memtable_writes)");
  }
+  if (!cf_options.memtable_factory->IsInsertConcurrentlySupported()) {
+    return Status::InvalidArgument(
+        "Memtable doesn't concurrent writes (allow_concurrent_memtable_write)");
+  }
  return Status::OK();
 }

@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1952,13 +1952,27 @@ TEST_F(ColumnFamilyTest, ReadDroppedColumnFamily) {
    PutRandomData(1, kKeysNum, 100);
    PutRandomData(2, kKeysNum, 100);

-    if (iter == 0) {
-      // Drop CF two
-      ASSERT_OK(db_->DropColumnFamily(handles_[2]));
-    } else {
-      // delete CF two
-      delete handles_[2];
-      handles_[2] = nullptr;
+    {
+      std::unique_ptr<Iterator> iterator(
+          db_->NewIterator(ReadOptions(), handles_[2]));
+      iterator->SeekToFirst();
+
+      if (iter == 0) {
+        // Drop CF two
+        ASSERT_OK(db_->DropColumnFamily(handles_[2]));
+      } else {
+        // delete CF two
+        delete handles_[2];
+        handles_[2] = nullptr;
+      }
+      // Make sure iterator created can still be used.
+      int count = 0;
+      for (; iterator->Valid(); iterator->Next()) {
+        ASSERT_OK(iterator->status());
+        ++count;
+      }
+      ASSERT_OK(iterator->status());
+      ASSERT_EQ(count, kKeysNum);
    }

    // Add bunch more data to other CFs
@@ -2542,6 +2556,36 @@ TEST_F(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
  cfd->RecalculateWriteStallConditions(mutable_cf_options);
  ASSERT_EQ(2, dbfull()->BGCompactionsAllowed());
 }
+
+TEST_F(ColumnFamilyTest, LogSyncConflictFlush) {
+  Open();
+  CreateColumnFamiliesAndReopen({"one", "two"});
+
+  Put(0, "", "");
+  Put(1, "foo", "bar");
+
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::SyncWAL:BeforeMarkLogsSynced:1",
+        "ColumnFamilyTest::LogSyncConflictFlush:1"},
+       {"ColumnFamilyTest::LogSyncConflictFlush:2",
+        "DBImpl::SyncWAL:BeforeMarkLogsSynced:2"}});
+
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  std::thread thread([&] { db_->SyncWAL(); });
+
+  TEST_SYNC_POINT("ColumnFamilyTest::LogSyncConflictFlush:1");
+  Flush(1);
+  Put(1, "foo", "bar");
+  Flush(1);
+
+  TEST_SYNC_POINT("ColumnFamilyTest::LogSyncConflictFlush:2");
+
+  thread.join();
+
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  Close();
+}
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -1,4 +1,4 @@
-//  Copyright (c) 2014, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -7,6 +7,7 @@

 #include <mutex>
 #include <string>
+#include <thread>
 #include <vector>

 #include "rocksdb/db.h"
@@ -142,9 +143,6 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {
  }

  auto l0_files = collector->GetFlushedFiles();
-  CompactionOptions compact_opt;
-  compact_opt.compression = kNoCompression;
-  compact_opt.output_file_size_limit = kWriteBufferSize * 5;
  ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1));

  // verify all compaction input files are deleted
@@ -154,6 +152,62 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {
  delete db;
 }

+TEST_F(CompactFilesTest, CapturingPendingFiles) {
+  Options options;
+  options.create_if_missing = true;
+  // Disable RocksDB background compaction.
+  options.compaction_style = kCompactionStyleNone;
+  // Always do full scans for obsolete files (needed to reproduce the issue).
+  options.delete_obsolete_files_period_micros = 0;
+
+  // Add listener.
+  FlushedFileCollector* collector = new FlushedFileCollector();
+  options.listeners.emplace_back(collector);
+
+  DB* db = nullptr;
+  DestroyDB(db_name_, options);
+  Status s = DB::Open(options, db_name_, &db);
+  assert(s.ok());
+  assert(db);
+
+  // Create 5 files.
+  for (int i = 0; i < 5; ++i) {
+    db->Put(WriteOptions(), "key" + ToString(i), "value");
+    db->Flush(FlushOptions());
+  }
+
+  auto l0_files = collector->GetFlushedFiles();
+  EXPECT_EQ(5, l0_files.size());
+
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
+      {"CompactFilesImpl:2", "CompactFilesTest.CapturingPendingFiles:0"},
+      {"CompactFilesTest.CapturingPendingFiles:1", "CompactFilesImpl:3"},
+  });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  // Start compacting files.
+  std::thread compaction_thread(
+      [&] { EXPECT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1)); });
+
+  // In the meantime flush another file.
+  TEST_SYNC_POINT("CompactFilesTest.CapturingPendingFiles:0");
+  db->Put(WriteOptions(), "key5", "value");
+  db->Flush(FlushOptions());
+  TEST_SYNC_POINT("CompactFilesTest.CapturingPendingFiles:1");
+
+  compaction_thread.join();
+
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+
+  delete db;
+
+  // Make sure we can reopen the DB.
+  s = DB::Open(options, db_name_, &db);
+  ASSERT_TRUE(s.ok());
+  assert(db);
+  delete db;
+}
+
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -1,4 +1,4 @@
-//  Copyright (c) 2014, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2014, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -138,6 +138,8 @@ class Compaction {

  // Clear all files to indicate that they are not being compacted
  // Delete this compaction from the list of running compactions.
+  //
+  // Requirement: DB mutex held
  void ReleaseCompactionFiles(Status status);

  // Returns the summary of the compaction in "output" with maximum "len"
@@ -1,6 +1,6 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,6 +1,6 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -212,6 +212,7 @@ CompactionJob::CompactionJob(
    const EnvOptions& env_options, VersionSet* versions,
    std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
    Directory* db_directory, Directory* output_directory, Statistics* stats,
+    InstrumentedMutex* db_mutex, Status* db_bg_error,
    std::vector<SequenceNumber> existing_snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
    std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
@@ -231,6 +232,8 @@ CompactionJob::CompactionJob(
      db_directory_(db_directory),
      output_directory_(output_directory),
      stats_(stats),
+      db_mutex_(db_mutex),
+      db_bg_error_(db_bg_error),
      existing_snapshots_(std::move(existing_snapshots)),
      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
      table_cache_(std::move(table_cache)),
@@ -360,7 +363,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
      size_t num_files = flevel->num_files;

      if (num_files == 0) {
-        break;
+        continue;
      }

      if (lvl == 0) {
@@ -499,16 +502,11 @@ Status CompactionJob::Run() {
  }

  TablePropertiesCollection tp;
-  auto sfm =
-      static_cast<SstFileManagerImpl*>(db_options_.sst_file_manager.get());
  for (const auto& state : compact_->sub_compact_states) {
    for (const auto& output : state.outputs) {
      auto fn = TableFileName(db_options_.db_paths, output.meta.fd.GetNumber(),
                              output.meta.fd.GetPathId());
      tp[fn] = output.table_properties;
-      if (sfm && output.meta.fd.GetPathId() == 0) {
-        sfm->OnAddFile(fn);
-      }
    }
  }
  compact_->compaction->SetOutputTableProperties(std::move(tp));
@@ -524,18 +522,17 @@ Status CompactionJob::Run() {
  return status;
 }

-Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options,
-                              InstrumentedMutex* db_mutex) {
+Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
  AutoThreadOperationStageUpdater stage_updater(
      ThreadStatus::STAGE_COMPACTION_INSTALL);
-  db_mutex->AssertHeld();
+  db_mutex_->AssertHeld();
  Status status = compact_->status;
  ColumnFamilyData* cfd = compact_->compaction->column_family_data();
  cfd->internal_stats()->AddCompactionStats(
      compact_->compaction->output_level(), compaction_stats_);

  if (status.ok()) {
-    status = InstallCompactionResults(mutable_cf_options, db_mutex);
+    status = InstallCompactionResults(mutable_cf_options);
  }
  VersionStorageInfo::LevelSummaryStorage tmp;
  auto vstorage = cfd->current()->storage_info();
@@ -861,13 +858,33 @@ Status CompactionJob::FinishCompactionOutputFile(
          event_logger_, cfd->ioptions()->listeners, meta->fd, info);
    }
  }
+
+  // Report new file to SstFileManagerImpl
+  auto sfm =
+      static_cast<SstFileManagerImpl*>(db_options_.sst_file_manager.get());
+  if (sfm && meta->fd.GetPathId() == 0) {
+    ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
+    auto fn = TableFileName(cfd->ioptions()->db_paths, meta->fd.GetNumber(),
+                            meta->fd.GetPathId());
+    sfm->OnAddFile(fn);
+    if (sfm->IsMaxAllowedSpaceReached()) {
+      InstrumentedMutexLock l(db_mutex_);
+      if (db_bg_error_->ok()) {
+        s = Status::IOError("Max allowed space was reached");
+        *db_bg_error_ = s;
+        TEST_SYNC_POINT(
+            "CompactionJob::FinishCompactionOutputFile:MaxAllowedSpaceReached");
+      }
+    }
+  }
+
  sub_compact->builder.reset();
  return s;
 }

 Status CompactionJob::InstallCompactionResults(
-    const MutableCFOptions& mutable_cf_options, InstrumentedMutex* db_mutex) {
-  db_mutex->AssertHeld();
+    const MutableCFOptions& mutable_cf_options) {
+  db_mutex_->AssertHeld();

  auto* compaction = compact_->compaction;
  // paranoia: verify that the files that we started with
@@ -902,7 +919,7 @@ Status CompactionJob::InstallCompactionResults(
  }
  return versions_->LogAndApply(compaction->column_family_data(),
                                mutable_cf_options, compaction->edit(),
-                                db_mutex, db_directory_);
+                                db_mutex_, db_directory_);
 }

 void CompactionJob::RecordCompactionIOStats() {
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -56,7 +56,8 @@ class CompactionJob {
                const EnvOptions& env_options, VersionSet* versions,
                std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
                Directory* db_directory, Directory* output_directory,
-                Statistics* stats,
+                Statistics* stats, InstrumentedMutex* db_mutex,
+                Status* db_bg_error,
                std::vector<SequenceNumber> existing_snapshots,
                SequenceNumber earliest_write_conflict_snapshot,
                std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
@@ -77,8 +78,7 @@ class CompactionJob {
  Status Run();

  // REQUIRED: mutex held
-  Status Install(const MutableCFOptions& mutable_cf_options,
-                 InstrumentedMutex* db_mutex);
+  Status Install(const MutableCFOptions& mutable_cf_options);

 private:
  struct SubcompactionState;
@@ -95,8 +95,7 @@ class CompactionJob {

  Status FinishCompactionOutputFile(const Status& input_status,
                                    SubcompactionState* sub_compact);
-  Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options,
-                                  InstrumentedMutex* db_mutex);
+  Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options);
  void RecordCompactionIOStats();
  Status OpenCompactionOutputFile(SubcompactionState* sub_compact);
  void CleanupCompaction();
@@ -130,6 +129,8 @@ class CompactionJob {
  Directory* db_directory_;
  Directory* output_directory_;
  Statistics* stats_;
+  InstrumentedMutex* db_mutex_;
+  Status* db_bg_error_;
  // If there were two snapshots with seq numbers s1 and
  // s2 and s1 < s2, and if we find two instances of a key k1 then lies
  // entirely within s1 and s2, then the earlier version of k1 can be safely
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -250,9 +250,9 @@ class CompactionJobTest : public testing::Test {
    EventLogger event_logger(db_options_.info_log.get());
    CompactionJob compaction_job(
        0, &compaction, db_options_, env_options_, versions_.get(),
-        &shutting_down_, &log_buffer, nullptr, nullptr, nullptr, snapshots,
-        earliest_write_conflict_snapshot, table_cache_, &event_logger, false,
-        false, dbname_, &compaction_job_stats_);
+        &shutting_down_, &log_buffer, nullptr, nullptr, nullptr, &mutex_,
+        &bg_error_, snapshots, earliest_write_conflict_snapshot, table_cache_,
+        &event_logger, false, false, dbname_, &compaction_job_stats_);

    VerifyInitializationOfCompactionJobStats(compaction_job_stats_);

@@ -262,8 +262,7 @@ class CompactionJobTest : public testing::Test {
    s = compaction_job.Run();
    ASSERT_OK(s);
    mutex_.Lock();
-    ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions(),
-                                     &mutex_));
+    ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions()));
    mutex_.Unlock();

    if (expected_results.size() == 0) {
@@ -295,6 +294,7 @@ class CompactionJobTest : public testing::Test {
  ColumnFamilyData* cfd_;
  std::unique_ptr<CompactionFilter> compaction_filter_;
  std::shared_ptr<MergeOperator> merge_op_;
+  Status bg_error_;
 };

 TEST_F(CompactionJobTest, Simple) {
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -141,7 +141,8 @@ CompactionPicker::~CompactionPicker() {}

 // Delete this compaction from the list of running compactions.
 void CompactionPicker::ReleaseCompactionFiles(Compaction* c, Status status) {
-  if (c->start_level() == 0) {
+  if (c->start_level() == 0 ||
+      ioptions_.compaction_style == kCompactionStyleUniversal) {
    level0_compactions_in_progress_.erase(c);
  }
  if (!status.ok()) {
@@ -612,6 +613,17 @@ Compaction* CompactionPicker::CompactRange(
  if (input_level == 0) {
    level0_compactions_in_progress_.insert(compaction);
  }
+
+  // Creating a compaction influences the compaction score because the score
+  // takes running compactions into account (by skipping files that are already
+  // being compacted). Since we just changed compaction score, we recalculate it
+  // here
+  {  // this piece of code recomputes compaction score
+    CompactionOptionsFIFO dummy_compaction_options_fifo;
+    vstorage->ComputeCompactionScore(mutable_cf_options,
+                                     dummy_compaction_options_fifo);
+  }
+
  return compaction;
 }

@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -83,6 +83,8 @@ class CompactionPicker {
 #endif  // ROCKSDB_LITE

  // Free up the files that participated in a compaction
+  //
+  // Requirement: DB mutex held
  void ReleaseCompactionFiles(Compaction* c, Status status);

  // Returns true if any one of the specified files are being compacted
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -487,6 +487,87 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
 }
 #endif  // ROCKSDB_LITE

+TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
+  NewVersionStorage(6, kCompactionStyleLevel);
+  mutable_cf_options_.target_file_size_base = 10000000;
+  mutable_cf_options_.target_file_size_multiplier = 10;
+  mutable_cf_options_.compaction_pri = kMinOverlappingRatio;
+
+  Add(2, 6U, "150", "179", 50000000U);
+  Add(2, 7U, "180", "220", 50000000U);
+  Add(2, 8U, "321", "400", 50000000U);  // File not overlapping
+  Add(2, 9U, "721", "800", 50000000U);
+
+  Add(3, 26U, "150", "170", 260000000U);
+  Add(3, 27U, "171", "179", 260000000U);
+  Add(3, 28U, "191", "220", 260000000U);
+  Add(3, 29U, "221", "300", 260000000U);
+  Add(3, 30U, "750", "900", 260000000U);
+  UpdateVersionStorageInfo();
+
+  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1U, compaction->num_input_files(0));
+  // Pick file 8 because it overlaps with 0 files on level 3.
+  ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, CompactionPriMinOverlapping2) {
+  NewVersionStorage(6, kCompactionStyleLevel);
+  mutable_cf_options_.target_file_size_base = 10000000;
+  mutable_cf_options_.target_file_size_multiplier = 10;
+  mutable_cf_options_.compaction_pri = kMinOverlappingRatio;
+
+  Add(2, 6U, "150", "175",
+      60000000U);  // Overlaps with file 26, 27, total size 521M
+  Add(2, 7U, "176", "200", 60000000U);  // Overlaps with file 27, 28, total size
+                                        // 520M, the smalelst overlapping
+  Add(2, 8U, "201", "300",
+      60000000U);  // Overlaps with file 28, 29, total size 521M
+
+  Add(3, 26U, "100", "110", 261000000U);
+  Add(3, 26U, "150", "170", 261000000U);
+  Add(3, 27U, "171", "179", 260000000U);
+  Add(3, 28U, "191", "220", 260000000U);
+  Add(3, 29U, "221", "300", 261000000U);
+  Add(3, 30U, "321", "400", 261000000U);
+  UpdateVersionStorageInfo();
+
+  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1U, compaction->num_input_files(0));
+  // Picking file 7 because overlapping ratio is the biggest.
+  ASSERT_EQ(7U, compaction->input(0, 0)->fd.GetNumber());
+}
+
+TEST_F(CompactionPickerTest, CompactionPriMinOverlapping3) {
+  NewVersionStorage(6, kCompactionStyleLevel);
+  mutable_cf_options_.target_file_size_base = 10000000;
+  mutable_cf_options_.target_file_size_multiplier = 10;
+  mutable_cf_options_.compaction_pri = kMinOverlappingRatio;
+
+  // file 7 and 8 over lap with the same file, but file 8 is smaller so
+  // it will be picked.
+  Add(2, 6U, "150", "175", 60000000U);  // Overlaps with file 26, 27
+  Add(2, 7U, "176", "200", 60000000U);  // Overlaps with file 27
+  Add(2, 8U, "201", "300", 61000000U);  // Overlaps with file 27
+
+  Add(3, 26U, "160", "165", 260000000U);
+  Add(3, 26U, "166", "170", 260000000U);
+  Add(3, 27U, "180", "400", 260000000U);
+  Add(3, 28U, "401", "500", 260000000U);
+  UpdateVersionStorageInfo();
+
+  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(1U, compaction->num_input_files(0));
+  // Picking file 8 because overlapping ratio is the biggest.
+  ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
+}
+
 // This test exhibits the bug where we don't properly reset parent_index in
 // PickCompaction()
 TEST_F(CompactionPickerTest, ParentIndexResetBug) {
@@ -1,6 +1,6 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2014, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -0,0 +1,237 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+#include <cstdlib>
+#include "db/db_test_util.h"
+#include "port/stack_trace.h"
+
+namespace rocksdb {
+
+static uint64_t TestGetTickerCount(const Options& options,
+                                   Tickers ticker_type) {
+  return options.statistics->getTickerCount(ticker_type);
+}
+
+class DBBlockCacheTest : public DBTestBase {
+ private:
+  size_t miss_count_ = 0;
+  size_t hit_count_ = 0;
+  size_t insert_count_ = 0;
+  size_t failure_count_ = 0;
+  size_t compressed_miss_count_ = 0;
+  size_t compressed_hit_count_ = 0;
+  size_t compressed_insert_count_ = 0;
+  size_t compressed_failure_count_ = 0;
+
+ public:
+  const size_t kNumBlocks = 10;
+  const size_t kValueSize = 100;
+
+  DBBlockCacheTest() : DBTestBase("/db_block_cache_test") {}
+
+  BlockBasedTableOptions GetTableOptions() {
+    BlockBasedTableOptions table_options;
+    // Set a small enough block size so that each key-value get its own block.
+    table_options.block_size = 1;
+    return table_options;
+  }
+
+  Options GetOptions(const BlockBasedTableOptions& table_options) {
+    Options options = CurrentOptions();
+    options.create_if_missing = true;
+    // options.compression = kNoCompression;
+    options.statistics = rocksdb::CreateDBStatistics();
+    options.table_factory.reset(new BlockBasedTableFactory(table_options));
+    return options;
+  }
+
+  void InitTable(const Options& options) {
+    std::string value(kValueSize, 'a');
+    for (size_t i = 0; i < kNumBlocks; i++) {
+      ASSERT_OK(Put(ToString(i), value.c_str()));
+    }
+  }
+
+  void RecordCacheCounters(const Options& options) {
+    miss_count_ = TestGetTickerCount(options, BLOCK_CACHE_MISS);
+    hit_count_ = TestGetTickerCount(options, BLOCK_CACHE_HIT);
+    insert_count_ = TestGetTickerCount(options, BLOCK_CACHE_ADD);
+    failure_count_ = TestGetTickerCount(options, BLOCK_CACHE_ADD_FAILURES);
+    compressed_miss_count_ =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS);
+    compressed_hit_count_ =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT);
+    compressed_insert_count_ =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD);
+    compressed_failure_count_ =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
+  }
+
+  void CheckCacheCounters(const Options& options, size_t expected_misses,
+                          size_t expected_hits, size_t expected_inserts,
+                          size_t expected_failures) {
+    size_t new_miss_count = TestGetTickerCount(options, BLOCK_CACHE_MISS);
+    size_t new_hit_count = TestGetTickerCount(options, BLOCK_CACHE_HIT);
+    size_t new_insert_count = TestGetTickerCount(options, BLOCK_CACHE_ADD);
+    size_t new_failure_count =
+        TestGetTickerCount(options, BLOCK_CACHE_ADD_FAILURES);
+    ASSERT_EQ(miss_count_ + expected_misses, new_miss_count);
+    ASSERT_EQ(hit_count_ + expected_hits, new_hit_count);
+    ASSERT_EQ(insert_count_ + expected_inserts, new_insert_count);
+    ASSERT_EQ(failure_count_ + expected_failures, new_failure_count);
+    miss_count_ = new_miss_count;
+    hit_count_ = new_hit_count;
+    insert_count_ = new_insert_count;
+    failure_count_ = new_failure_count;
+  }
+
+  void CheckCompressedCacheCounters(const Options& options,
+                                    size_t expected_misses,
+                                    size_t expected_hits,
+                                    size_t expected_inserts,
+                                    size_t expected_failures) {
+    size_t new_miss_count =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS);
+    size_t new_hit_count =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT);
+    size_t new_insert_count =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD);
+    size_t new_failure_count =
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
+    ASSERT_EQ(compressed_miss_count_ + expected_misses, new_miss_count);
+    ASSERT_EQ(compressed_hit_count_ + expected_hits, new_hit_count);
+    ASSERT_EQ(compressed_insert_count_ + expected_inserts, new_insert_count);
+    ASSERT_EQ(compressed_failure_count_ + expected_failures, new_failure_count);
+    compressed_miss_count_ = new_miss_count;
+    compressed_hit_count_ = new_hit_count;
+    compressed_insert_count_ = new_insert_count;
+    compressed_failure_count_ = new_failure_count;
+  }
+};
+
+TEST_F(DBBlockCacheTest, TestWithoutCompressedBlockCache) {
+  ReadOptions read_options;
+  auto table_options = GetTableOptions();
+  auto options = GetOptions(table_options);
+  InitTable(options);
+
+  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
+  table_options.block_cache = cache;
+  options.table_factory.reset(new BlockBasedTableFactory(table_options));
+  Reopen(options);
+  RecordCacheCounters(options);
+
+  std::vector<std::unique_ptr<Iterator>> iterators(kNumBlocks - 1);
+  Iterator* iter = nullptr;
+
+  // Load blocks into cache.
+  for (size_t i = 0; i < kNumBlocks - 1; i++) {
+    iter = db_->NewIterator(read_options);
+    iter->Seek(ToString(i));
+    ASSERT_OK(iter->status());
+    CheckCacheCounters(options, 1, 0, 1, 0);
+    iterators[i].reset(iter);
+  }
+  size_t usage = cache->GetUsage();
+  ASSERT_LT(0, usage);
+  cache->SetCapacity(usage);
+  ASSERT_EQ(usage, cache->GetPinnedUsage());
+
+  // Test with strict capacity limit.
+  cache->SetStrictCapacityLimit(true);
+  iter = db_->NewIterator(read_options);
+  iter->Seek(ToString(kNumBlocks - 1));
+  ASSERT_TRUE(iter->status().IsIncomplete());
+  CheckCacheCounters(options, 1, 0, 0, 1);
+  delete iter;
+  iter = nullptr;
+
+  // Release interators and access cache again.
+  for (size_t i = 0; i < kNumBlocks - 1; i++) {
+    iterators[i].reset();
+    CheckCacheCounters(options, 0, 0, 0, 0);
+  }
+  ASSERT_EQ(0, cache->GetPinnedUsage());
+  for (size_t i = 0; i < kNumBlocks - 1; i++) {
+    iter = db_->NewIterator(read_options);
+    iter->Seek(ToString(i));
+    ASSERT_OK(iter->status());
+    CheckCacheCounters(options, 0, 1, 0, 0);
+    iterators[i].reset(iter);
+  }
+}
+
+TEST_F(DBBlockCacheTest, TestWithCompressedBlockCache) {
+  ReadOptions read_options;
+  auto table_options = GetTableOptions();
+  auto options = GetOptions(table_options);
+  InitTable(options);
+
+  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
+  std::shared_ptr<Cache> compressed_cache = NewLRUCache(0, 0, false);
+  table_options.block_cache = cache;
+  table_options.block_cache_compressed = compressed_cache;
+  options.table_factory.reset(new BlockBasedTableFactory(table_options));
+  Reopen(options);
+  RecordCacheCounters(options);
+
+  std::vector<std::unique_ptr<Iterator>> iterators(kNumBlocks - 1);
+  Iterator* iter = nullptr;
+
+  // Load blocks into cache.
+  for (size_t i = 0; i < kNumBlocks - 1; i++) {
+    iter = db_->NewIterator(read_options);
+    iter->Seek(ToString(i));
+    ASSERT_OK(iter->status());
+    CheckCacheCounters(options, 1, 0, 1, 0);
+    CheckCompressedCacheCounters(options, 1, 0, 1, 0);
+    iterators[i].reset(iter);
+  }
+  size_t usage = cache->GetUsage();
+  ASSERT_LT(0, usage);
+  ASSERT_EQ(usage, cache->GetPinnedUsage());
+  size_t compressed_usage = compressed_cache->GetUsage();
+  ASSERT_LT(0, compressed_usage);
+  // Compressed block cache cannot be pinned.
+  ASSERT_EQ(0, compressed_cache->GetPinnedUsage());
+
+  // Set strict capacity limit flag. Now block will only load into compressed
+  // block cache.
+  cache->SetCapacity(usage);
+  cache->SetStrictCapacityLimit(true);
+  ASSERT_EQ(usage, cache->GetPinnedUsage());
+  // compressed_cache->SetCapacity(compressed_usage);
+  compressed_cache->SetCapacity(0);
+  // compressed_cache->SetStrictCapacityLimit(true);
+  iter = db_->NewIterator(read_options);
+  iter->Seek(ToString(kNumBlocks - 1));
+  ASSERT_TRUE(iter->status().IsIncomplete());
+  CheckCacheCounters(options, 1, 0, 0, 1);
+  CheckCompressedCacheCounters(options, 1, 0, 1, 0);
+  delete iter;
+  iter = nullptr;
+
+  // Clear strict capacity limit flag. This time we shall hit compressed block
+  // cache.
+  cache->SetStrictCapacityLimit(false);
+  iter = db_->NewIterator(read_options);
+  iter->Seek(ToString(kNumBlocks - 1));
+  ASSERT_OK(iter->status());
+  CheckCacheCounters(options, 1, 0, 1, 0);
+  CheckCompressedCacheCounters(options, 0, 1, 0, 0);
+  delete iter;
+  iter = nullptr;
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -2507,8 +2507,12 @@ TEST_P(CompactionPriTest, Test) {
  }
 }

-INSTANTIATE_TEST_CASE_P(CompactionPriTest, CompactionPriTest,
-                        ::testing::Values(0, 1, 2));
+INSTANTIATE_TEST_CASE_P(
+    CompactionPriTest, CompactionPriTest,
+    ::testing::Values(CompactionPri::kByCompensatedSize,
+                      CompactionPri::kOldestLargestSeqFirst,
+                      CompactionPri::kOldestSmallestSeqFirst,
+                      CompactionPri::kMinOverlappingRatio));

 #endif // !defined(ROCKSDB_LITE)
 }  // namespace rocksdb
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -275,13 +275,14 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname)
          db_options_.delete_obsolete_files_period_micros),
      last_stats_dump_time_microsec_(0),
      next_job_id_(1),
-      flush_on_destroy_(false),
+      has_unpersisted_data_(false),
      env_options_(db_options_),
 #ifndef ROCKSDB_LITE
      wal_manager_(db_options_, env_options_),
 #endif  // ROCKSDB_LITE
      event_logger_(db_options_.info_log.get()),
      bg_work_paused_(0),
+      bg_compaction_paused_(0),
      refitting_level_(false),
      opened_successfully_(false) {
  env_->GetAbsolutePath(dbname, &db_absolute_path_);
@@ -322,7 +323,8 @@ void DBImpl::CancelAllBackgroundWork(bool wait) {
 DBImpl::~DBImpl() {
  mutex_.Lock();

-  if (!shutting_down_.load(std::memory_order_acquire) && flush_on_destroy_) {
+  if (!shutting_down_.load(std::memory_order_acquire) &&
+      has_unpersisted_data_) {
    for (auto cfd : *versions_->GetColumnFamilySet()) {
      if (!cfd->IsDropped() && !cfd->mem()->IsEmpty()) {
        cfd->Ref();
@@ -570,6 +572,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
  // Get obsolete files.  This function will also update the list of
  // pending files in VersionSet().
  versions_->GetObsoleteFiles(&job_context->sst_delete_files,
+                              &job_context->manifest_delete_files,
                              job_context->min_pending_output);

  // store the current filenum, lognum, etc
@@ -687,9 +690,9 @@ void DBImpl::PurgeObsoleteFiles(const JobContext& state) {
  }

  auto candidate_files = state.full_scan_candidate_files;
-  candidate_files.reserve(candidate_files.size() +
-                          state.sst_delete_files.size() +
-                          state.log_delete_files.size());
+  candidate_files.reserve(
+      candidate_files.size() + state.sst_delete_files.size() +
+      state.log_delete_files.size() + state.manifest_delete_files.size());
  // We may ignore the dbname when generating the file names.
  const char* kDumbDbName = "";
  for (auto file : state.sst_delete_files) {
@@ -705,6 +708,9 @@ void DBImpl::PurgeObsoleteFiles(const JobContext& state) {
                                   0);
    }
  }
+  for (const auto& filename : state.manifest_delete_files) {
+    candidate_files.emplace_back(filename, 0);
+  }

  // dedup state.candidate_files so we don't try to delete the same
  // file twice
@@ -1385,9 +1391,9 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
  mutex_.AssertHeld();
  const uint64_t start_micros = env_->NowMicros();
  FileMetaData meta;
-  meta.fd = FileDescriptor(versions_->NewFileNumber(), 0, 0);
  auto pending_outputs_inserted_elem =
      CaptureCurrentFileNumberInPendingOutputs();
+  meta.fd = FileDescriptor(versions_->NewFileNumber(), 0, 0);
  ReadOptions ro;
  ro.total_order_seek = true;
  Arena arena;
@@ -1509,11 +1515,12 @@ Status DBImpl::FlushMemTableToOutputFile(
    bg_error_ = s;
  }
  RecordFlushIOStats();
-#ifndef ROCKSDB_LITE
  if (s.ok()) {
+#ifndef ROCKSDB_LITE
    // may temporarily unlock and lock the mutex.
    NotifyOnFlushCompleted(cfd, &file_meta, mutable_cf_options,
                           job_context->job_id, flush_job.GetTableProperties());
+#endif  // ROCKSDB_LITE
    auto sfm =
        static_cast<SstFileManagerImpl*>(db_options_.sst_file_manager.get());
    if (sfm) {
@@ -1521,9 +1528,13 @@ Status DBImpl::FlushMemTableToOutputFile(
      std::string file_path = MakeTableFileName(db_options_.db_paths[0].path,
                                                file_meta.fd.GetNumber());
      sfm->OnAddFile(file_path);
+      if (sfm->IsMaxAllowedSpaceReached() && bg_error_.ok()) {
+        bg_error_ = Status::IOError("Max allowed space was reached");
+        TEST_SYNC_POINT(
+            "DBImpl::FlushMemTableToOutputFile:MaxAllowedSpaceReached");
+      }
    }
  }
-#endif  // ROCKSDB_LITE
  return s;
 }

@@ -1813,13 +1824,16 @@ Status DBImpl::CompactFilesImpl(
  std::vector<SequenceNumber> snapshot_seqs =
      snapshots_.GetAll(&earliest_write_conflict_snapshot);

+  auto pending_outputs_inserted_elem =
+      CaptureCurrentFileNumberInPendingOutputs();
+
  assert(is_snapshot_supported_ || snapshots_.empty());
  CompactionJob compaction_job(
      job_context->job_id, c.get(), db_options_, env_options_, versions_.get(),
      &shutting_down_, log_buffer, directories_.GetDbDir(),
-      directories_.GetDataDir(c->output_path_id()), stats_, snapshot_seqs,
-      earliest_write_conflict_snapshot, table_cache_, &event_logger_,
-      c->mutable_cf_options()->paranoid_file_checks,
+      directories_.GetDataDir(c->output_path_id()), stats_, &mutex_, &bg_error_,
+      snapshot_seqs, earliest_write_conflict_snapshot, table_cache_,
+      &event_logger_, c->mutable_cf_options()->paranoid_file_checks,
      c->mutable_cf_options()->compaction_measure_io_stats, dbname_,
      nullptr);  // Here we pass a nullptr for CompactionJobStats because
                 // CompactFiles does not trigger OnCompactionCompleted(),
@@ -1834,21 +1848,35 @@ Status DBImpl::CompactFilesImpl(
                 // support for CompactFiles, we should have CompactFiles API
                 // pass a pointer of CompactionJobStats as the out-value
                 // instead of using EventListener.
+
+  // Creating a compaction influences the compaction score because the score
+  // takes running compactions into account (by skipping files that are already
+  // being compacted). Since we just changed compaction score, we recalculate it
+  // here.
+  {
+    CompactionOptionsFIFO dummy_compaction_options_fifo;
+    version->storage_info()->ComputeCompactionScore(
+        *c->mutable_cf_options(), dummy_compaction_options_fifo);
+  }
+
  compaction_job.Prepare();

  mutex_.Unlock();
  TEST_SYNC_POINT("CompactFilesImpl:0");
  TEST_SYNC_POINT("CompactFilesImpl:1");
  compaction_job.Run();
+  TEST_SYNC_POINT("CompactFilesImpl:2");
+  TEST_SYNC_POINT("CompactFilesImpl:3");
  mutex_.Lock();

-  Status status = compaction_job.Install(*c->mutable_cf_options(), &mutex_);
+  Status status = compaction_job.Install(*c->mutable_cf_options());
  if (status.ok()) {
    InstallSuperVersionAndScheduleWorkWrapper(
        c->column_family_data(), job_context, *c->mutable_cf_options());
  }
  c->ReleaseCompactionFiles(s);
-  c.reset();
+
+  ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);

  if (status.ok()) {
    // Done
@@ -1864,6 +1892,8 @@ Status DBImpl::CompactFilesImpl(
    }
  }

+  c.reset();
+
  bg_compaction_scheduled_--;
  if (bg_compaction_scheduled_ == 0) {
    bg_cv_.SignalAll();
@@ -1875,10 +1905,11 @@ Status DBImpl::CompactFilesImpl(

 Status DBImpl::PauseBackgroundWork() {
  InstrumentedMutexLock guard_lock(&mutex_);
-  bg_work_paused_++;
+  bg_compaction_paused_++;
  while (bg_compaction_scheduled_ > 0 || bg_flush_scheduled_ > 0) {
    bg_cv_.Wait();
  }
+  bg_work_paused_++;
  return Status::OK();
 }

@@ -1888,7 +1919,11 @@ Status DBImpl::ContinueBackgroundWork() {
    return Status::InvalidArgument();
  }
  assert(bg_work_paused_ > 0);
+  assert(bg_compaction_paused_ > 0);
+  bg_compaction_paused_--;
  bg_work_paused_--;
+  // It's sufficient to check just bg_work_paused_ here since
+  // bg_work_paused_ is always no greater than bg_compaction_paused_
  if (bg_work_paused_ == 0) {
    MaybeScheduleFlushOrCompaction();
  }
@@ -2188,6 +2223,9 @@ Status DBImpl::SyncWAL() {
    status = directories_.GetWalDir()->Fsync();
  }

+  TEST_SYNC_POINT("DBImpl::SyncWAL:BeforeMarkLogsSynced:1");
+  TEST_SYNC_POINT("DBImpl::SyncWAL:BeforeMarkLogsSynced:2");
+
  {
    InstrumentedMutexLock l(&mutex_);
    MarkLogsSynced(current_log_number, need_log_dir_sync, status);
@@ -2215,7 +2253,8 @@ void DBImpl::MarkLogsSynced(
      ++it;
    }
  }
-  assert(logs_.empty() || (logs_.size() == 1 && !logs_[0].getting_synced));
+  assert(logs_.empty() || logs_[0].number > up_to ||
+         (logs_.size() == 1 && !logs_[0].getting_synced));
  log_sync_cv_.SignalAll();
 }

@@ -2467,6 +2506,11 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
    }
  }

+  if (bg_compaction_paused_ > 0) {
+    // we paused the background compaction
+    return;
+  }
+
  if (HasExclusiveManualCompaction()) {
    // only manual compactions are allowed to run. don't schedule automatic
    // compactions
@@ -2992,8 +3036,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
    CompactionJob compaction_job(
        job_context->job_id, c.get(), db_options_, env_options_,
        versions_.get(), &shutting_down_, log_buffer, directories_.GetDbDir(),
-        directories_.GetDataDir(c->output_path_id()), stats_, snapshot_seqs,
-        earliest_write_conflict_snapshot, table_cache_, &event_logger_,
+        directories_.GetDataDir(c->output_path_id()), stats_, &mutex_,
+        &bg_error_, snapshot_seqs, earliest_write_conflict_snapshot,
+        table_cache_, &event_logger_,
        c->mutable_cf_options()->paranoid_file_checks,
        c->mutable_cf_options()->compaction_measure_io_stats, dbname_,
        &compaction_job_stats);
@@ -3004,7 +3049,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
    TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
    mutex_.Lock();

-    status = compaction_job.Install(*c->mutable_cf_options(), &mutex_);
+    status = compaction_job.Install(*c->mutable_cf_options());
    if (status.ok()) {
      InstallSuperVersionAndScheduleWorkWrapper(
          c->column_family_data(), job_context, *c->mutable_cf_options());
@@ -3306,13 +3351,19 @@ Status DBImpl::GetImpl(const ReadOptions& read_options,
  LookupKey lkey(key, snapshot);
  PERF_TIMER_STOP(get_snapshot_time);

-  if (sv->mem->Get(lkey, value, &s, &merge_context)) {
-    // Done
-    RecordTick(stats_, MEMTABLE_HIT);
-  } else if (sv->imm->Get(lkey, value, &s, &merge_context)) {
-    // Done
-    RecordTick(stats_, MEMTABLE_HIT);
-  } else {
+  bool skip_memtable =
+      (read_options.read_tier == kPersistedTier && has_unpersisted_data_);
+  bool done = false;
+  if (!skip_memtable) {
+    if (sv->mem->Get(lkey, value, &s, &merge_context)) {
+      done = true;
+      RecordTick(stats_, MEMTABLE_HIT);
+    } else if (sv->imm->Get(lkey, value, &s, &merge_context)) {
+      done = true;
+      RecordTick(stats_, MEMTABLE_HIT);
+    }
+  }
+  if (!done) {
    PERF_TIMER_GUARD(get_from_output_files_time);
    sv->current->Get(read_options, lkey, value, &s, &merge_context,
                     value_found);
@@ -3397,14 +3448,23 @@ std::vector<Status> DBImpl::MultiGet(
    assert(mgd_iter != multiget_cf_data.end());
    auto mgd = mgd_iter->second;
    auto super_version = mgd->super_version;
-    if (super_version->mem->Get(lkey, value, &s, &merge_context)) {
-      // Done
-    } else if (super_version->imm->Get(lkey, value, &s, &merge_context)) {
-      // Done
-    } else {
+    bool skip_memtable =
+        (read_options.read_tier == kPersistedTier && has_unpersisted_data_);
+    bool done = false;
+    if (!skip_memtable) {
+      if (super_version->mem->Get(lkey, value, &s, &merge_context)) {
+        done = true;
+        // TODO(?): RecordTick(stats_, MEMTABLE_HIT)?
+      } else if (super_version->imm->Get(lkey, value, &s, &merge_context)) {
+        done = true;
+        // TODO(?): RecordTick(stats_, MEMTABLE_HIT)?
+      }
+    }
+    if (!done) {
      PERF_TIMER_GUARD(get_from_output_files_time);
      super_version->current->Get(read_options, lkey, value, &s,
                                  &merge_context);
+      // TODO(?): RecordTick(stats_, MEMTABLE_MISS)?
    }

    if (s.ok()) {
@@ -3553,8 +3613,16 @@ Status DBImpl::AddFile(ColumnFamilyHandle* column_family,
    return Status::InvalidArgument(
        "Non zero sequence numbers are not supported");
  }
+
  // Generate a location for the new table
-  meta.fd = FileDescriptor(versions_->NewFileNumber(), 0, file_info->file_size);
+  std::list<uint64_t>::iterator pending_outputs_inserted_elem;
+  {
+    InstrumentedMutexLock l(&mutex_);
+    pending_outputs_inserted_elem = CaptureCurrentFileNumberInPendingOutputs();
+    meta.fd =
+        FileDescriptor(versions_->NewFileNumber(), 0, file_info->file_size);
+  }
+
  std::string db_fname = TableFileName(
      db_options_.db_paths, meta.fd.GetNumber(), meta.fd.GetPathId());

@@ -3567,6 +3635,7 @@ Status DBImpl::AddFile(ColumnFamilyHandle* column_family,
  } else {
    status = CopyFile(env_, file_info->file_path, db_fname, 0);
  }
+  TEST_SYNC_POINT("DBImpl::AddFile:FileCopied");
  if (!status.ok()) {
    return status;
  }
@@ -3630,6 +3699,7 @@ Status DBImpl::AddFile(ColumnFamilyHandle* column_family,
      delete InstallSuperVersionAndScheduleWork(cfd, nullptr,
                                                mutable_cf_options);
    }
+    ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);
  }

  if (!status.ok()) {
@@ -3843,6 +3913,10 @@ bool DBImpl::KeyMayExist(const ReadOptions& read_options,

 Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
                              ColumnFamilyHandle* column_family) {
+  if (read_options.read_tier == kPersistedTier) {
+    return NewErrorIterator(Status::NotSupported(
+        "ReadTier::kPersistedData is not yet supported in iterators."));
+  }
  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
  auto cfd = cfh->cfd();

@@ -3874,8 +3948,8 @@ Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
        env_, *cfd->ioptions(), cfd->user_comparator(), iter,
        kMaxSequenceNumber,
        sv->mutable_cf_options.max_sequential_skip_in_iterations,
-        read_options.iterate_upper_bound, read_options.prefix_same_as_start,
-        read_options.pin_data);
+        sv->version_number, read_options.iterate_upper_bound,
+        read_options.prefix_same_as_start, read_options.pin_data);
 #endif
  } else {
    SequenceNumber latest_snapshot = versions_->LastSequence();
@@ -3932,8 +4006,8 @@ Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
    ArenaWrappedDBIter* db_iter = NewArenaWrappedDbIterator(
        env_, *cfd->ioptions(), cfd->user_comparator(), snapshot,
        sv->mutable_cf_options.max_sequential_skip_in_iterations,
-        read_options.iterate_upper_bound, read_options.prefix_same_as_start,
-        read_options.pin_data);
+        sv->version_number, read_options.iterate_upper_bound,
+        read_options.prefix_same_as_start, read_options.pin_data);

    InternalIterator* internal_iter =
        NewInternalIterator(read_options, cfd, sv, db_iter->GetArena());
@@ -3949,6 +4023,10 @@ Status DBImpl::NewIterators(
    const ReadOptions& read_options,
    const std::vector<ColumnFamilyHandle*>& column_families,
    std::vector<Iterator*>* iterators) {
+  if (read_options.read_tier == kPersistedTier) {
+    return Status::NotSupported(
+        "ReadTier::kPersistedData is not yet supported in iterators.");
+  }
  iterators->clear();
  iterators->reserve(column_families.size());
  XFUNC_TEST("", "managed_new", managed_new1, xf_manage_new,
@@ -3982,8 +4060,8 @@ Status DBImpl::NewIterators(
      iterators->push_back(NewDBIterator(
          env_, *cfd->ioptions(), cfd->user_comparator(), iter,
          kMaxSequenceNumber,
-          sv->mutable_cf_options.max_sequential_skip_in_iterations, nullptr,
-          false, read_options.pin_data));
+          sv->mutable_cf_options.max_sequential_skip_in_iterations,
+          sv->version_number, nullptr, false, read_options.pin_data));
    }
 #endif
  } else {
@@ -4002,8 +4080,8 @@ Status DBImpl::NewIterators(

      ArenaWrappedDBIter* db_iter = NewArenaWrappedDbIterator(
          env_, *cfd->ioptions(), cfd->user_comparator(), snapshot,
-          sv->mutable_cf_options.max_sequential_skip_in_iterations, nullptr,
-          false, read_options.pin_data);
+          sv->mutable_cf_options.max_sequential_skip_in_iterations,
+          sv->version_number, nullptr, false, read_options.pin_data);
      InternalIterator* internal_iter =
          NewInternalIterator(read_options, cfd, sv, db_iter->GetArena());
      db_iter->SetIterUnderDBIter(internal_iter);
@@ -4095,7 +4173,6 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
  }

  Status status;
-  bool callback_failed = false;

  bool xfunc_attempted_write = false;
  XFUNC_TEST("transaction", "transaction_xftest_write_impl",
@@ -4113,7 +4190,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
  w.sync = write_options.sync;
  w.disableWAL = write_options.disableWAL;
  w.in_batch_group = false;
-  w.has_callback = (callback != nullptr) ? true : false;
+  w.callback = callback;

  if (!write_options.disableWAL) {
    RecordTick(stats_, WRITE_WITH_WAL);
@@ -4126,30 +4203,32 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
    // we are a non-leader in a parallel group
    PERF_TIMER_GUARD(write_memtable_time);

-    ColumnFamilyMemTablesImpl column_family_memtables(
-        versions_->GetColumnFamilySet());
-    WriteBatchInternal::SetSequence(w.batch, w.sequence);
-    w.status = WriteBatchInternal::InsertInto(
-        w.batch, &column_family_memtables, &flush_scheduler_,
-        write_options.ignore_missing_column_families, 0 /*log_number*/, this,
-        true /*dont_filter_deletes*/, true /*concurrent_memtable_writes*/);
+    if (!w.CallbackFailed()) {
+      ColumnFamilyMemTablesImpl column_family_memtables(
+          versions_->GetColumnFamilySet());
+      WriteBatchInternal::SetSequence(w.batch, w.sequence);
+      w.status = WriteBatchInternal::InsertInto(
+          w.batch, &column_family_memtables, &flush_scheduler_,
+          write_options.ignore_missing_column_families, 0 /*log_number*/, this,
+          true /*dont_filter_deletes*/, true /*concurrent_memtable_writes*/);
+    }

    if (write_thread_.CompleteParallelWorker(&w)) {
      // we're responsible for early exit
-      auto last_sequence =
-          w.parallel_group->last_writer->sequence +
-          WriteBatchInternal::Count(w.parallel_group->last_writer->batch) - 1;
+      auto last_sequence = w.parallel_group->last_sequence;
      SetTickerCount(stats_, SEQUENCE_NUMBER, last_sequence);
      versions_->SetLastSequence(last_sequence);
      write_thread_.EarlyExitParallelGroup(&w);
    }
    assert(w.state == WriteThread::STATE_COMPLETED);
    // STATE_COMPLETED conditional below handles exit
+
+    status = w.FinalStatus();
  }
  if (w.state == WriteThread::STATE_COMPLETED) {
    // write is complete and leader has updated sequence
    RecordTick(stats_, WRITE_DONE_BY_OTHER);
-    return w.status;
+    return w.FinalStatus();
  }
  // else we are the leader of the write batch group
  assert(w.state == WriteThread::STATE_GROUP_LEADER);
@@ -4255,7 +4334,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,

  uint64_t last_sequence = versions_->LastSequence();
  WriteThread::Writer* last_writer = &w;
-  autovector<WriteBatch*> write_batch_group;
+  autovector<WriteThread::Writer*> write_group;
  bool need_log_sync = !write_options.disableWAL && write_options.sync;
  bool need_log_dir_sync = need_log_sync && !log_dir_synced_;

@@ -4274,24 +4353,15 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
    // during this phase since &w is currently responsible for logging
    // and protects against concurrent loggers and concurrent writes
    // into memtables
-
-    mutex_.Unlock();
-
-    if (callback != nullptr) {
-      // If this write has a validation callback, check to see if this write
-      // is able to be written.  Must be called on the write thread.
-      status = callback->Callback(this);
-      callback_failed = true;
-    }
-  } else {
-    mutex_.Unlock();
  }

+  mutex_.Unlock();
+
  // At this point the mutex is unlocked

  bool exit_completed_early = false;
-  last_batch_group_size_ = write_thread_.EnterAsBatchGroupLeader(
-      &w, &last_writer, &write_batch_group);
+  last_batch_group_size_ =
+      write_thread_.EnterAsBatchGroupLeader(&w, &last_writer, &write_group);

  if (status.ok()) {
    // Rules for when we can update the memtable concurrently
@@ -4307,15 +4377,17 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
    // assumed to be true.  Rule 4 is checked for each batch.  We could
    // relax rules 2 and 3 if we could prevent write batches from referring
    // more than once to a particular key.
-    bool parallel = db_options_.allow_concurrent_memtable_write &&
-                    write_batch_group.size() > 1;
+    bool parallel =
+        db_options_.allow_concurrent_memtable_write && write_group.size() > 1;
    int total_count = 0;
    uint64_t total_byte_size = 0;
-    for (auto b : write_batch_group) {
-      total_count += WriteBatchInternal::Count(b);
-      total_byte_size = WriteBatchInternal::AppendedByteSize(
-          total_byte_size, WriteBatchInternal::ByteSize(b));
-      parallel = parallel && !b->HasMerge();
+    for (auto writer : write_group) {
+      if (writer->CheckCallback(this)) {
+        total_count += WriteBatchInternal::Count(writer->batch);
+        total_byte_size = WriteBatchInternal::AppendedByteSize(
+            total_byte_size, WriteBatchInternal::ByteSize(writer->batch));
+        parallel = parallel && !writer->batch->HasMerge();
+      }
    }

    const SequenceNumber current_sequence = last_sequence + 1;
@@ -4328,7 +4400,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
    PERF_TIMER_STOP(write_pre_and_post_process_time);

    if (write_options.disableWAL) {
-      flush_on_destroy_ = true;
+      has_unpersisted_data_ = true;
    }

    uint64_t log_size = 0;
@@ -4336,21 +4408,22 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
      PERF_TIMER_GUARD(write_wal_time);

      WriteBatch* merged_batch = nullptr;
-      if (write_batch_group.size() == 1) {
-        merged_batch = write_batch_group[0];
+      if (write_group.size() == 1 && !write_group[0]->CallbackFailed()) {
+        merged_batch = write_group[0]->batch;
      } else {
        // WAL needs all of the batches flattened into a single batch.
        // We could avoid copying here with an iov-like AddRecord
        // interface
        merged_batch = &tmp_batch_;
-        for (auto b : write_batch_group) {
-          WriteBatchInternal::Append(merged_batch, b);
+        for (auto writer : write_group) {
+          if (!writer->CallbackFailed()) {
+            WriteBatchInternal::Append(merged_batch, writer->batch);
+          }
        }
      }
      WriteBatchInternal::SetSequence(merged_batch, current_sequence);

      assert(WriteBatchInternal::Count(merged_batch) == total_count);
-      assert(WriteBatchInternal::ByteSize(merged_batch) == total_byte_size);

      Slice log_entry = WriteBatchInternal::Contents(merged_batch);
      status = logs_.back().writer->AddRecord(log_entry);
@@ -4405,7 +4478,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
          }
          stats->AddDBStats(InternalStats::WAL_FILE_BYTES, log_size);
        }
-        uint64_t for_other = write_batch_group.size() - 1;
+        uint64_t for_other = write_group.size() - 1;
        if (for_other > 0) {
          stats->AddDBStats(InternalStats::WRITE_DONE_BY_OTHER, for_other);
          if (!write_options.disableWAL) {
@@ -4416,43 +4489,50 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,

      if (!parallel) {
        status = WriteBatchInternal::InsertInto(
-            write_batch_group, current_sequence, column_family_memtables_.get(),
+            write_group, current_sequence, column_family_memtables_.get(),
            &flush_scheduler_, write_options.ignore_missing_column_families,
            0 /*log_number*/, this, false /*dont_filter_deletes*/);
+
+        if (status.ok()) {
+          // There were no write failures. Set leader's status
+          // in case the write callback returned a non-ok status.
+          status = w.FinalStatus();
+        }
+
      } else {
        WriteThread::ParallelGroup pg;
        pg.leader = &w;
        pg.last_writer = last_writer;
+        pg.last_sequence = last_sequence;
        pg.early_exit_allowed = !need_log_sync;
-        pg.running.store(static_cast<uint32_t>(write_batch_group.size()),
+        pg.running.store(static_cast<uint32_t>(write_group.size()),
                         std::memory_order_relaxed);
        write_thread_.LaunchParallelFollowers(&pg, current_sequence);

-        ColumnFamilyMemTablesImpl column_family_memtables(
-            versions_->GetColumnFamilySet());
-        assert(w.sequence == current_sequence);
-        WriteBatchInternal::SetSequence(w.batch, w.sequence);
-        w.status = WriteBatchInternal::InsertInto(
-            w.batch, &column_family_memtables, &flush_scheduler_,
-            write_options.ignore_missing_column_families, 0 /*log_number*/,
-            this, true /*dont_filter_deletes*/,
-            true /*concurrent_memtable_writes*/);
+        if (!w.CallbackFailed()) {
+          // do leader write
+          ColumnFamilyMemTablesImpl column_family_memtables(
+              versions_->GetColumnFamilySet());
+          assert(w.sequence == current_sequence);
+          WriteBatchInternal::SetSequence(w.batch, w.sequence);
+          w.status = WriteBatchInternal::InsertInto(
+              w.batch, &column_family_memtables, &flush_scheduler_,
+              write_options.ignore_missing_column_families, 0 /*log_number*/,
+              this, true /*dont_filter_deletes*/,
+              true /*concurrent_memtable_writes*/);
+        }

-        assert(last_writer->sequence +
-                   WriteBatchInternal::Count(last_writer->batch) - 1 ==
-               last_sequence);
        // CompleteParallelWorker returns true if this thread should
        // handle exit, false means somebody else did
        exit_completed_early = !write_thread_.CompleteParallelWorker(&w);
-        status = w.status;
-        assert(status.ok() || !exit_completed_early);
+        status = w.FinalStatus();
      }

-      if (status.ok() && !exit_completed_early) {
+      if (!exit_completed_early && w.status.ok()) {
        SetTickerCount(stats_, SEQUENCE_NUMBER, last_sequence);
        versions_->SetLastSequence(last_sequence);
        if (!need_log_sync) {
-          write_thread_.ExitAsBatchGroupLeader(&w, last_writer, status);
+          write_thread_.ExitAsBatchGroupLeader(&w, last_writer, w.status);
          exit_completed_early = true;
        }
      }
@@ -4465,14 +4545,14 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
      //
      // Is setting bg_error_ enough here?  This will at least stop
      // compaction and fail any further writes.
-      if (!status.ok() && bg_error_.ok()) {
+      if (!status.ok() && bg_error_.ok() && !w.CallbackFailed()) {
        bg_error_ = status;
      }
    }
  }
  PERF_TIMER_START(write_pre_and_post_process_time);

-  if (db_options_.paranoid_checks && !status.ok() && !callback_failed &&
+  if (db_options_.paranoid_checks && !status.ok() && !w.CallbackFailed() &&
      !status.IsBusy()) {
    mutex_.Lock();
    if (bg_error_.ok()) {
@@ -4488,7 +4568,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
  }

  if (!exit_completed_early) {
-    write_thread_.ExitAsBatchGroupLeader(&w, last_writer, status);
+    write_thread_.ExitAsBatchGroupLeader(&w, last_writer, w.status);
  }

  return status;
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -494,10 +494,11 @@ class DBImpl : public DB {

  // Background process needs to call
  //     auto x = CaptureCurrentFileNumberInPendingOutputs()
+  //     auto file_num = versions_->NewFileNumber();
  //     <do something>
  //     ReleaseFileNumberFromPendingOutputs(x)
-  // This will protect any temporary files created while <do something> is
-  // executing from being deleted.
+  // This will protect any file with number `file_num` or greater from being
+  // deleted while <do something> is running.
  // -----------
  // This function will capture current file number and append it to
  // pending_outputs_. This will prevent any background process to delete any
@@ -822,7 +823,10 @@ class DBImpl : public DB {
  // they're unique
  std::atomic<int> next_job_id_;

-  bool flush_on_destroy_; // Used when disableWAL is true.
+  // A flag indicating whether the current rocksdb database has any
+  // data that is not yet persisted into either WAL or SST file.
+  // Used when disableWAL is true.
+  bool has_unpersisted_data_;

  static const int KEEP_LOG_FILE_NUM = 1000;
  // MSVC version 1800 still does not have constexpr for ::max()
@@ -840,9 +844,12 @@ class DBImpl : public DB {
  // Unified interface for logging events
  EventLogger event_logger_;

-  // A value of >0 temporarily disables scheduling of background work
+  // A value of > 0 temporarily disables scheduling of background work
  int bg_work_paused_;

+  // A value of > 0 temporarily disables scheduling of background compaction
+  int bg_compaction_paused_;
+
  // Guard against multiple concurrent refitting
  bool refitting_level_;

@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -54,10 +54,11 @@ Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
  auto db_iter = NewArenaWrappedDbIterator(
      env_, *cfd->ioptions(), cfd->user_comparator(),
      (read_options.snapshot != nullptr
-           ? reinterpret_cast<const SnapshotImpl*>(
-                read_options.snapshot)->number_
+           ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
+                 ->number_
           : latest_snapshot),
-      super_version->mutable_cf_options.max_sequential_skip_in_iterations);
+      super_version->mutable_cf_options.max_sequential_skip_in_iterations,
+      super_version->version_number);
  auto internal_iter = NewInternalIterator(
      read_options, cfd, super_version, db_iter->GetArena());
  db_iter->SetIterUnderDBIter(internal_iter);
@@ -81,10 +82,11 @@ Status DBImplReadOnly::NewIterators(
    auto* db_iter = NewArenaWrappedDbIterator(
        env_, *cfd->ioptions(), cfd->user_comparator(),
        (read_options.snapshot != nullptr
-            ? reinterpret_cast<const SnapshotImpl*>(
-                  read_options.snapshot)->number_
-            : latest_snapshot),
-        sv->mutable_cf_options.max_sequential_skip_in_iterations);
+             ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
+                   ->number_
+             : latest_snapshot),
+        sv->mutable_cf_options.max_sequential_skip_in_iterations,
+        sv->version_number);
    auto* internal_iter = NewInternalIterator(
        read_options, cfd, sv, db_iter->GetArena());
    db_iter->SetIterUnderDBIter(internal_iter);
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -13,18 +13,19 @@
 #include <string>
 #include <limits>

-#include "db/filename.h"
 #include "db/dbformat.h"
+#include "db/filename.h"
 #include "port/port.h"
 #include "rocksdb/env.h"
-#include "rocksdb/options.h"
 #include "rocksdb/iterator.h"
 #include "rocksdb/merge_operator.h"
+#include "rocksdb/options.h"
 #include "table/internal_iterator.h"
 #include "util/arena.h"
 #include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/perf_context_imp.h"
+#include "util/string_util.h"

 namespace rocksdb {

@@ -59,9 +60,47 @@ class DBIter: public Iterator {
    kReverse
  };

+  // LocalStatistics contain Statistics counters that will be aggregated per
+  // each iterator instance and then will be sent to the global statistics when
+  // the iterator is destroyed.
+  //
+  // The purpose of this approach is to avoid perf regression happening
+  // when multiple threads bump the atomic counters from a DBIter::Next().
+  struct LocalStatistics {
+    explicit LocalStatistics() { ResetCounters(); }
+
+    void ResetCounters() {
+      next_count_ = 0;
+      next_found_count_ = 0;
+      prev_count_ = 0;
+      prev_found_count_ = 0;
+      bytes_read_ = 0;
+    }
+
+    void BumpGlobalStatistics(Statistics* global_statistics) {
+      RecordTick(global_statistics, NUMBER_DB_NEXT, next_count_);
+      RecordTick(global_statistics, NUMBER_DB_NEXT_FOUND, next_found_count_);
+      RecordTick(global_statistics, NUMBER_DB_PREV, prev_count_);
+      RecordTick(global_statistics, NUMBER_DB_PREV_FOUND, prev_found_count_);
+      RecordTick(global_statistics, ITER_BYTES_READ, bytes_read_);
+      ResetCounters();
+    }
+
+    // Map to Tickers::NUMBER_DB_NEXT
+    uint64_t next_count_;
+    // Map to Tickers::NUMBER_DB_NEXT_FOUND
+    uint64_t next_found_count_;
+    // Map to Tickers::NUMBER_DB_PREV
+    uint64_t prev_count_;
+    // Map to Tickers::NUMBER_DB_PREV_FOUND
+    uint64_t prev_found_count_;
+    // Map to Tickers::ITER_BYTES_READ
+    uint64_t bytes_read_;
+  };
+
  DBIter(Env* env, const ImmutableCFOptions& ioptions, const Comparator* cmp,
         InternalIterator* iter, SequenceNumber s, bool arena_mode,
-         uint64_t max_sequential_skip_in_iterations,
+         uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
         const Slice* iterate_upper_bound = nullptr,
         bool prefix_same_as_start = false)
      : arena_mode_(arena_mode),
@@ -75,6 +114,7 @@ class DBIter: public Iterator {
        valid_(false),
        current_entry_is_merged_(false),
        statistics_(ioptions.statistics),
+        version_number_(version_number),
        iterate_upper_bound_(iterate_upper_bound),
        prefix_same_as_start_(prefix_same_as_start),
        iter_pinned_(false) {
@@ -84,6 +124,7 @@ class DBIter: public Iterator {
  }
  virtual ~DBIter() {
    RecordTick(statistics_, NO_ITERATORS, -1);
+    local_stats_.BumpGlobalStatistics(statistics_);
    if (!arena_mode_) {
      delete iter_;
    } else {
@@ -136,9 +177,27 @@ class DBIter: public Iterator {
    }
    return s;
  }
-  virtual bool IsKeyPinned() const override {
-    assert(valid_);
-    return iter_pinned_ && saved_key_.IsKeyPinned();
+
+  virtual Status GetProperty(std::string prop_name,
+                             std::string* prop) override {
+    if (prop == nullptr) {
+      return Status::InvalidArgument("prop is nullptr");
+    }
+    if (prop_name == "rocksdb.iterator.super-version-number") {
+      // First try to pass the value returned from inner iterator.
+      if (!iter_->GetProperty(prop_name, prop).ok()) {
+        *prop = ToString(version_number_);
+      }
+      return Status::OK();
+    } else if (prop_name == "rocksdb.iterator.is-key-pinned") {
+      if (valid_) {
+        *prop = (iter_pinned_ && saved_key_.IsKeyPinned()) ? "1" : "0";
+      } else {
+        *prop = "Iterator is not valid.";
+      }
+      return Status::OK();
+    }
+    return Status::InvalidArgument("Undentified property.");
  }

  virtual void Next() override;
@@ -186,12 +245,14 @@ class DBIter: public Iterator {
  bool current_entry_is_merged_;
  Statistics* statistics_;
  uint64_t max_skip_;
+  uint64_t version_number_;
  const Slice* iterate_upper_bound_;
  IterKey prefix_start_;
  bool prefix_same_as_start_;
  bool iter_pinned_;
  // List of operands for merge operator.
  std::deque<std::string> merge_operands_;
+  LocalStatistics local_stats_;

  // No copying allowed
  DBIter(const DBIter&);
@@ -229,6 +290,9 @@ void DBIter::Next() {
    PERF_COUNTER_ADD(internal_key_skipped_count, 1);
  }

+  if (statistics_ != nullptr) {
+    local_stats_.next_count_++;
+  }
  // Now we point to the next internal position, for both of merge and
  // not merge cases.
  if (!iter_->Valid()) {
@@ -236,18 +300,15 @@ void DBIter::Next() {
    return;
  }
  FindNextUserEntry(true /* skipping the current user key */);
-  if (statistics_ != nullptr) {
-    RecordTick(statistics_, NUMBER_DB_NEXT);
-    if (valid_) {
-      RecordTick(statistics_, NUMBER_DB_NEXT_FOUND);
-      RecordTick(statistics_, ITER_BYTES_READ, key().size() + value().size());
-    }
-  }
  if (valid_ && prefix_extractor_ && prefix_same_as_start_ &&
      prefix_extractor_->Transform(saved_key_.GetKey())
              .compare(prefix_start_.GetKey()) != 0) {
    valid_ = false;
  }
+  if (statistics_ != nullptr && valid_) {
+    local_stats_.next_found_count_++;
+    local_stats_.bytes_read_ += (key().size() + value().size());
+  }
 }

 // PRE: saved_key_ has the current user key if skipping
@@ -275,7 +336,7 @@ void DBIter::FindNextUserEntryInternal(bool skipping) {

    if (ParseKey(&ikey)) {
      if (iterate_upper_bound_ != nullptr &&
-          ikey.user_key.compare(*iterate_upper_bound_) >= 0) {
+          user_comparator_->Compare(ikey.user_key, *iterate_upper_bound_) >= 0) {
        break;
      }

@@ -415,10 +476,10 @@ void DBIter::Prev() {
  }
  PrevInternal();
  if (statistics_ != nullptr) {
-    RecordTick(statistics_, NUMBER_DB_PREV);
+    local_stats_.prev_count_++;
    if (valid_) {
-      RecordTick(statistics_, NUMBER_DB_PREV_FOUND);
-      RecordTick(statistics_, ITER_BYTES_READ, key().size() + value().size());
+      local_stats_.prev_found_count_++;
+      local_stats_.bytes_read_ += (key().size() + value().size());
    }
  }
  if (valid_ && prefix_extractor_ && prefix_same_as_start_ &&
@@ -818,12 +879,13 @@ Iterator* NewDBIterator(Env* env, const ImmutableCFOptions& ioptions,
                        InternalIterator* internal_iter,
                        const SequenceNumber& sequence,
                        uint64_t max_sequential_skip_in_iterations,
+                        uint64_t version_number,
                        const Slice* iterate_upper_bound,
                        bool prefix_same_as_start, bool pin_data) {
  DBIter* db_iter =
      new DBIter(env, ioptions, user_key_comparator, internal_iter, sequence,
-                 false, max_sequential_skip_in_iterations, iterate_upper_bound,
-                 prefix_same_as_start);
+                 false, max_sequential_skip_in_iterations, version_number,
+                 iterate_upper_bound, prefix_same_as_start);
  if (pin_data) {
    db_iter->PinData();
  }
@@ -850,12 +912,13 @@ inline Slice ArenaWrappedDBIter::key() const { return db_iter_->key(); }
 inline Slice ArenaWrappedDBIter::value() const { return db_iter_->value(); }
 inline Status ArenaWrappedDBIter::status() const { return db_iter_->status(); }
 inline Status ArenaWrappedDBIter::PinData() { return db_iter_->PinData(); }
+inline Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
+                                              std::string* prop) {
+  return db_iter_->GetProperty(prop_name, prop);
+}
 inline Status ArenaWrappedDBIter::ReleasePinnedData() {
  return db_iter_->ReleasePinnedData();
 }
-inline bool ArenaWrappedDBIter::IsKeyPinned() const {
-  return db_iter_->IsKeyPinned();
-}
 void ArenaWrappedDBIter::RegisterCleanup(CleanupFunction function, void* arg1,
                                         void* arg2) {
  db_iter_->RegisterCleanup(function, arg1, arg2);
@@ -864,7 +927,7 @@ void ArenaWrappedDBIter::RegisterCleanup(CleanupFunction function, void* arg1,
 ArenaWrappedDBIter* NewArenaWrappedDbIterator(
    Env* env, const ImmutableCFOptions& ioptions,
    const Comparator* user_key_comparator, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations,
+    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
    const Slice* iterate_upper_bound, bool prefix_same_as_start,
    bool pin_data) {
  ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
@@ -872,7 +935,7 @@ ArenaWrappedDBIter* NewArenaWrappedDbIterator(
  auto mem = arena->AllocateAligned(sizeof(DBIter));
  DBIter* db_iter =
      new (mem) DBIter(env, ioptions, user_key_comparator, nullptr, sequence,
-                       true, max_sequential_skip_in_iterations,
+                       true, max_sequential_skip_in_iterations, version_number,
                       iterate_upper_bound, prefix_same_as_start);

  iter->SetDBIter(db_iter);
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -9,6 +9,7 @@

 #pragma once
 #include <stdint.h>
+#include <string>
 #include "rocksdb/db.h"
 #include "rocksdb/iterator.h"
 #include "db/dbformat.h"
@@ -24,14 +25,12 @@ class InternalIterator;
 // Return a new iterator that converts internal keys (yielded by
 // "*internal_iter") that were live at the specified "sequence" number
 // into appropriate user keys.
-extern Iterator* NewDBIterator(Env* env, const ImmutableCFOptions& options,
-                               const Comparator* user_key_comparator,
-                               InternalIterator* internal_iter,
-                               const SequenceNumber& sequence,
-                               uint64_t max_sequential_skip_in_iterations,
-                               const Slice* iterate_upper_bound = nullptr,
-                               bool prefix_same_as_start = false,
-                               bool pin_data = false);
+extern Iterator* NewDBIterator(
+    Env* env, const ImmutableCFOptions& options,
+    const Comparator* user_key_comparator, InternalIterator* internal_iter,
+    const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
+    uint64_t version_number, const Slice* iterate_upper_bound = nullptr,
+    bool prefix_same_as_start = false, bool pin_data = false);

 // A wrapper iterator which wraps DB Iterator and the arena, with which the DB
 // iterator is supposed be allocated. This class is used as an entry point of
@@ -66,7 +65,7 @@ class ArenaWrappedDBIter : public Iterator {
  void RegisterCleanup(CleanupFunction function, void* arg1, void* arg2);
  virtual Status PinData();
  virtual Status ReleasePinnedData();
-  virtual bool IsKeyPinned() const override;
+  virtual Status GetProperty(std::string prop_name, std::string* prop) override;

 private:
  DBIter* db_iter_;
@@ -77,7 +76,7 @@ class ArenaWrappedDBIter : public Iterator {
 extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
    Env* env, const ImmutableCFOptions& options,
    const Comparator* user_key_comparator, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations,
+    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
    const Slice* iterate_upper_bound = nullptr,
    bool prefix_same_as_start = false, bool pin_data = false);

@@ -1,4 +1,4 @@
-//  Copyright (c) 2014, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -181,10 +181,9 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
    internal_iter->AddPut("b", "val_b");
    internal_iter->Finish();

-    std::unique_ptr<Iterator> db_iter(
-        NewDBIterator(env_, ImmutableCFOptions(options),
-                      BytewiseComparator(), internal_iter, 10,
-                      options.max_sequential_skip_in_iterations));
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, 0));

    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
@@ -215,7 +214,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations));
+        10, options.max_sequential_skip_in_iterations, 0));

    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
@@ -241,7 +240,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
@@ -273,7 +273,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
@@ -308,7 +309,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    db_iter->SeekToLast();
    ASSERT_TRUE(!db_iter->Valid());
@@ -337,7 +339,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        7, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        7, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    SetPerfLevel(kEnableCount);
    ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -374,7 +377,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        4, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
@@ -399,7 +403,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    db_iter->SeekToLast();
    ASSERT_TRUE(!db_iter->Valid());
@@ -421,7 +426,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
@@ -456,7 +462,8 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        7, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
+        7, options.max_sequential_skip_in_iterations, 0,
+        ro.iterate_upper_bound));

    SetPerfLevel(kEnableCount);
    ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -482,10 +489,9 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
    internal_iter->AddPut("b", "val_b");
    internal_iter->Finish();

-    std::unique_ptr<Iterator> db_iter(
-        NewDBIterator(env_, ImmutableCFOptions(options),
-                      BytewiseComparator(), internal_iter, 10,
-                      options.max_sequential_skip_in_iterations));
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, 0));

    db_iter->SeekToFirst();
    ASSERT_TRUE(db_iter->Valid());
@@ -524,10 +530,9 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
    internal_iter->AddPut("b", "val_b");
    internal_iter->Finish();

-    std::unique_ptr<Iterator> db_iter(
-        NewDBIterator(env_, ImmutableCFOptions(options),
-                      BytewiseComparator(), internal_iter, 2,
-                      options.max_sequential_skip_in_iterations));
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        2, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -555,10 +560,9 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
    internal_iter->AddPut("c", "val_c");
    internal_iter->Finish();

-    std::unique_ptr<Iterator> db_iter(
-        NewDBIterator(env_, ImmutableCFOptions(options),
-                      BytewiseComparator(), internal_iter, 10,
-                      options.max_sequential_skip_in_iterations));
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        10, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -583,10 +587,9 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
    internal_iter->Finish();

-    std::unique_ptr<Iterator> db_iter(
-        NewDBIterator(env_, ImmutableCFOptions(options),
-                      BytewiseComparator(), internal_iter, 0,
-                      options.max_sequential_skip_in_iterations));
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        0, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(!db_iter->Valid());
  }
@@ -595,10 +598,9 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
    internal_iter->Finish();

-    std::unique_ptr<Iterator> db_iter(
-        NewDBIterator(env_, ImmutableCFOptions(options),
-                      BytewiseComparator(), internal_iter, 0,
-                      options.max_sequential_skip_in_iterations));
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        0, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToFirst();
    ASSERT_TRUE(!db_iter->Valid());
  }
@@ -617,10 +619,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkipCountSkips) {
  }
  internal_iter->Finish();

-  std::unique_ptr<Iterator> db_iter(
-      NewDBIterator(env_, ImmutableCFOptions(options),
-                    BytewiseComparator(), internal_iter, 2,
-                    options.max_sequential_skip_in_iterations));
+  std::unique_ptr<Iterator> db_iter(NewDBIterator(
+      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 2,
+      options.max_sequential_skip_in_iterations, 0));
  db_iter->SeekToLast();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -659,9 +660,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {

      options.statistics = rocksdb::CreateDBStatistics();
      std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options),
-          BytewiseComparator(), internal_iter, i + 2,
-          options.max_sequential_skip_in_iterations));
+          env_, ImmutableCFOptions(options), BytewiseComparator(),
+          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
      db_iter->SeekToLast();
      ASSERT_TRUE(db_iter->Valid());

@@ -695,9 +695,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
      internal_iter->Finish();

      std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options),
-          BytewiseComparator(), internal_iter, i + 2,
-          options.max_sequential_skip_in_iterations));
+          env_, ImmutableCFOptions(options), BytewiseComparator(),
+          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
      db_iter->SeekToLast();
      ASSERT_TRUE(db_iter->Valid());

@@ -724,9 +723,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
      internal_iter->Finish();

      std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options),
-          BytewiseComparator(), internal_iter, 202,
-          options.max_sequential_skip_in_iterations));
+          env_, ImmutableCFOptions(options), BytewiseComparator(),
+          internal_iter, 202, options.max_sequential_skip_in_iterations, 0));
      db_iter->SeekToLast();
      ASSERT_TRUE(db_iter->Valid());

@@ -756,10 +754,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
      }
      internal_iter->AddPut("c", "200");
      internal_iter->Finish();
-      std::unique_ptr<Iterator> db_iter(
-          NewDBIterator(env_, ImmutableCFOptions(options),
-                        BytewiseComparator(), internal_iter, i,
-                        options.max_sequential_skip_in_iterations));
+      std::unique_ptr<Iterator> db_iter(NewDBIterator(
+          env_, ImmutableCFOptions(options), BytewiseComparator(),
+          internal_iter, i, options.max_sequential_skip_in_iterations, 0));
      db_iter->SeekToLast();
      ASSERT_TRUE(!db_iter->Valid());

@@ -773,10 +770,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
    }
    internal_iter->AddPut("c", "200");
    internal_iter->Finish();
-    std::unique_ptr<Iterator> db_iter(
-        NewDBIterator(env_, ImmutableCFOptions(options),
-                      BytewiseComparator(), internal_iter, 200,
-                      options.max_sequential_skip_in_iterations));
+    std::unique_ptr<Iterator> db_iter(NewDBIterator(
+        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+        200, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -809,9 +805,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
      internal_iter->Finish();

      std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options),
-          BytewiseComparator(), internal_iter, i + 2,
-          options.max_sequential_skip_in_iterations));
+          env_, ImmutableCFOptions(options), BytewiseComparator(),
+          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
      db_iter->SeekToLast();
      ASSERT_TRUE(db_iter->Valid());

@@ -844,9 +839,8 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
      internal_iter->Finish();

      std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options),
-          BytewiseComparator(), internal_iter, i + 2,
-          options.max_sequential_skip_in_iterations));
+          env_, ImmutableCFOptions(options), BytewiseComparator(),
+          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
      db_iter->SeekToLast();
      ASSERT_TRUE(db_iter->Valid());

@@ -887,7 +881,7 @@ TEST_F(DBIteratorTest, DBIterator1) {

  std::unique_ptr<Iterator> db_iter(NewDBIterator(
      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 1,
-      options.max_sequential_skip_in_iterations));
+      options.max_sequential_skip_in_iterations, 0));
  db_iter->SeekToFirst();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -913,7 +907,7 @@ TEST_F(DBIteratorTest, DBIterator2) {

  std::unique_ptr<Iterator> db_iter(NewDBIterator(
      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 0,
-      options.max_sequential_skip_in_iterations));
+      options.max_sequential_skip_in_iterations, 0));
  db_iter->SeekToFirst();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -936,7 +930,7 @@ TEST_F(DBIteratorTest, DBIterator3) {

  std::unique_ptr<Iterator> db_iter(NewDBIterator(
      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 2,
-      options.max_sequential_skip_in_iterations));
+      options.max_sequential_skip_in_iterations, 0));
  db_iter->SeekToFirst();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -958,7 +952,7 @@ TEST_F(DBIteratorTest, DBIterator4) {

  std::unique_ptr<Iterator> db_iter(NewDBIterator(
      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 4,
-      options.max_sequential_skip_in_iterations));
+      options.max_sequential_skip_in_iterations, 0));
  db_iter->SeekToFirst();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -987,7 +981,7 @@ TEST_F(DBIteratorTest, DBIterator5) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations));
+        0, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1009,7 +1003,7 @@ TEST_F(DBIteratorTest, DBIterator5) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        1, options.max_sequential_skip_in_iterations));
+        1, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1031,7 +1025,7 @@ TEST_F(DBIteratorTest, DBIterator5) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        2, options.max_sequential_skip_in_iterations));
+        2, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1053,7 +1047,7 @@ TEST_F(DBIteratorTest, DBIterator5) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        3, options.max_sequential_skip_in_iterations));
+        3, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1075,7 +1069,7 @@ TEST_F(DBIteratorTest, DBIterator5) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations));
+        4, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1097,7 +1091,7 @@ TEST_F(DBIteratorTest, DBIterator5) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        5, options.max_sequential_skip_in_iterations));
+        5, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1119,7 +1113,7 @@ TEST_F(DBIteratorTest, DBIterator5) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        6, options.max_sequential_skip_in_iterations));
+        6, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1145,7 +1139,7 @@ TEST_F(DBIteratorTest, DBIterator6) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations));
+        0, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1167,7 +1161,7 @@ TEST_F(DBIteratorTest, DBIterator6) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        1, options.max_sequential_skip_in_iterations));
+        1, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1189,7 +1183,7 @@ TEST_F(DBIteratorTest, DBIterator6) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        2, options.max_sequential_skip_in_iterations));
+        2, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1211,7 +1205,7 @@ TEST_F(DBIteratorTest, DBIterator6) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        3, options.max_sequential_skip_in_iterations));
+        3, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(!db_iter->Valid());
  }
@@ -1229,7 +1223,7 @@ TEST_F(DBIteratorTest, DBIterator6) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations));
+        4, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1251,7 +1245,7 @@ TEST_F(DBIteratorTest, DBIterator6) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        5, options.max_sequential_skip_in_iterations));
+        5, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1273,7 +1267,7 @@ TEST_F(DBIteratorTest, DBIterator6) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        6, options.max_sequential_skip_in_iterations));
+        6, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1311,7 +1305,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations));
+        0, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
    ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1345,7 +1339,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        2, options.max_sequential_skip_in_iterations));
+        2, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1385,7 +1379,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations));
+        4, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1425,7 +1419,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        5, options.max_sequential_skip_in_iterations));
+        5, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1470,7 +1464,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        6, options.max_sequential_skip_in_iterations));
+        6, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1516,7 +1510,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        7, options.max_sequential_skip_in_iterations));
+        7, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1556,7 +1550,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        9, options.max_sequential_skip_in_iterations));
+        9, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1602,7 +1596,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        13, options.max_sequential_skip_in_iterations));
+        13, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1649,7 +1643,7 @@ TEST_F(DBIteratorTest, DBIterator7) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        14, options.max_sequential_skip_in_iterations));
+        14, options.max_sequential_skip_in_iterations, 0));
    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());

@@ -1678,7 +1672,7 @@ TEST_F(DBIteratorTest, DBIterator8) {

  std::unique_ptr<Iterator> db_iter(NewDBIterator(
      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-      10, options.max_sequential_skip_in_iterations));
+      10, options.max_sequential_skip_in_iterations, 0));
  db_iter->SeekToLast();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -1707,7 +1701,7 @@ TEST_F(DBIteratorTest, DBIterator9) {

    std::unique_ptr<Iterator> db_iter(NewDBIterator(
        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations));
+        10, options.max_sequential_skip_in_iterations, 0));

    db_iter->SeekToLast();
    ASSERT_TRUE(db_iter->Valid());
@@ -1754,7 +1748,7 @@ TEST_F(DBIteratorTest, DBIterator10) {

  std::unique_ptr<Iterator> db_iter(NewDBIterator(
      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-      10, options.max_sequential_skip_in_iterations));
+      10, options.max_sequential_skip_in_iterations, 0));

  db_iter->Seek("c");
  ASSERT_TRUE(db_iter->Valid());
@@ -1778,9 +1772,9 @@ TEST_F(DBIteratorTest, SeekToLastOccurrenceSeq0) {
  internal_iter->AddPut("b", "2");
  internal_iter->Finish();

-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-      10, 0 /* force seek */));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ImmutableCFOptions(options), BytewiseComparator(),
+                    internal_iter, 10, 0 /* force seek */, 0));
  db_iter->SeekToFirst();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1807,7 +1801,7 @@ TEST_F(DBIteratorTest, DBIterator11) {

  std::unique_ptr<Iterator> db_iter(NewDBIterator(
      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 1,
-      options.max_sequential_skip_in_iterations));
+      options.max_sequential_skip_in_iterations, 0));
  db_iter->SeekToFirst();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1832,7 +1826,7 @@ TEST_F(DBIteratorTest, DBIterator12) {

  std::unique_ptr<Iterator> db_iter(
      NewDBIterator(env_, ImmutableCFOptions(options), BytewiseComparator(),
-                    internal_iter, 10, 0));
+                    internal_iter, 10, 0, 0));
  db_iter->SeekToLast();
  ASSERT_TRUE(db_iter->Valid());
  ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -1874,7 +1868,7 @@ class DBIterWithMergeIterTest : public testing::Test {
    db_iter_.reset(NewDBIterator(env_, ImmutableCFOptions(options_),
                                 BytewiseComparator(), merge_iter,
                                 8 /* read data earlier than seqId 8 */,
-                                 3 /* max iterators before reseek */));
+                                 3 /* max iterators before reseek */, 0));
  }

  Env* env_;
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-// Copyright (c) 2016, Facebook, Inc.  All rights reserved.
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 // This source code is licensed under the BSD-style license found in the
 // LICENSE file in the root directory of this source tree. An additional grant
 // of patent rights can be found in the PATENTS file in the same directory.
@@ -90,6 +90,21 @@ TEST_F(DBPropertiesTest, Empty) {
  } while (ChangeOptions());
 }

+TEST_F(DBPropertiesTest, CurrentVersionNumber) {
+  uint64_t v1, v2, v3;
+  ASSERT_TRUE(
+      dbfull()->GetIntProperty("rocksdb.current-super-version-number", &v1));
+  Put("12345678", "");
+  ASSERT_TRUE(
+      dbfull()->GetIntProperty("rocksdb.current-super-version-number", &v2));
+  Flush();
+  ASSERT_TRUE(
+      dbfull()->GetIntProperty("rocksdb.current-super-version-number", &v3));
+
+  ASSERT_EQ(v1, v2);
+  ASSERT_GT(v3, v2);
+}
+
 TEST_F(DBPropertiesTest, GetAggregatedIntPropertyTest) {
  const int kKeySize = 100;
  const int kValueSize = 500;
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -654,6 +654,51 @@ TEST_F(DBTestTailingIterator, ManagedTailingIteratorSeekToSame) {
  ASSERT_EQ(found, iter->key().ToString());
 }

+TEST_F(DBTestTailingIterator, ForwardIteratorVersionProperty) {
+  Options options = CurrentOptions();
+  options.write_buffer_size = 1000;
+
+  ReadOptions read_options;
+  read_options.tailing = true;
+
+  Put("foo", "bar");
+
+  uint64_t v1, v2, v3, v4;
+  {
+    std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+    iter->Seek("foo");
+    std::string prop_value;
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.super-version-number",
+                                &prop_value));
+    v1 = static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+
+    Put("foo1", "bar1");
+    Flush();
+
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.super-version-number",
+                                &prop_value));
+    v2 = static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+
+    iter->Seek("f");
+
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.super-version-number",
+                                &prop_value));
+    v3 = static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+
+    ASSERT_EQ(v1, v2);
+    ASSERT_GT(v3, v2);
+  }
+
+  {
+    std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
+    iter->Seek("foo");
+    std::string prop_value;
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.super-version-number",
+                                &prop_value));
+    v4 = static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+  }
+  ASSERT_EQ(v3, v4);
+}
 }  // namespace rocksdb

 #endif  // !defined(ROCKSDB_LITE)
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -235,13 +235,11 @@ TEST_F(DBTest, WriteEmptyBatch) {
  CreateAndReopenWithCF({"pikachu"}, options);

  ASSERT_OK(Put(1, "foo", "bar"));
-  env_->sync_counter_.store(0);
  WriteOptions wo;
  wo.sync = true;
  wo.disableWAL = false;
  WriteBatch empty_batch;
  ASSERT_OK(dbfull()->Write(wo, &empty_batch));
-  ASSERT_GE(env_->sync_counter_.load(), 1);

  // make sure we can re-open it.
  ASSERT_OK(TryReopenWithColumnFamilies({"default", "pikachu"}, options));
@@ -521,6 +519,156 @@ TEST_F(DBTest, PutSingleDeleteGet) {
                         kSkipUniversalCompaction | kSkipMergePut));
 }

+TEST_F(DBTest, ReadFromPersistedTier) {
+  do {
+    Random rnd(301);
+    Options options = CurrentOptions();
+    for (int disableWAL = 0; disableWAL <= 1; ++disableWAL) {
+      CreateAndReopenWithCF({"pikachu"}, options);
+      WriteOptions wopt;
+      wopt.disableWAL = (disableWAL == 1);
+      // 1st round: put but not flush
+      ASSERT_OK(db_->Put(wopt, handles_[1], "foo", "first"));
+      ASSERT_OK(db_->Put(wopt, handles_[1], "bar", "one"));
+      ASSERT_EQ("first", Get(1, "foo"));
+      ASSERT_EQ("one", Get(1, "bar"));
+
+      // Read directly from persited data.
+      ReadOptions ropt;
+      ropt.read_tier = kPersistedTier;
+      std::string value;
+      if (wopt.disableWAL) {
+        // as data has not yet being flushed, we expect not found.
+        ASSERT_TRUE(db_->Get(ropt, handles_[1], "foo", &value).IsNotFound());
+        ASSERT_TRUE(db_->Get(ropt, handles_[1], "bar", &value).IsNotFound());
+      } else {
+        ASSERT_OK(db_->Get(ropt, handles_[1], "foo", &value));
+        ASSERT_OK(db_->Get(ropt, handles_[1], "bar", &value));
+      }
+
+      // Multiget
+      std::vector<ColumnFamilyHandle*> multiget_cfs;
+      multiget_cfs.push_back(handles_[1]);
+      multiget_cfs.push_back(handles_[1]);
+      std::vector<Slice> multiget_keys;
+      multiget_keys.push_back("foo");
+      multiget_keys.push_back("bar");
+      std::vector<std::string> multiget_values;
+      auto statuses =
+          db_->MultiGet(ropt, multiget_cfs, multiget_keys, &multiget_values);
+      if (wopt.disableWAL) {
+        ASSERT_TRUE(statuses[0].IsNotFound());
+        ASSERT_TRUE(statuses[1].IsNotFound());
+      } else {
+        ASSERT_OK(statuses[0]);
+        ASSERT_OK(statuses[1]);
+      }
+
+      // 2nd round: flush and put a new value in memtable.
+      ASSERT_OK(Flush(1));
+      ASSERT_OK(db_->Put(wopt, handles_[1], "rocksdb", "hello"));
+
+      // once the data has been flushed, we are able to get the
+      // data when kPersistedTier is used.
+      ASSERT_TRUE(db_->Get(ropt, handles_[1], "foo", &value).ok());
+      ASSERT_EQ(value, "first");
+      ASSERT_TRUE(db_->Get(ropt, handles_[1], "bar", &value).ok());
+      ASSERT_EQ(value, "one");
+      if (wopt.disableWAL) {
+        ASSERT_TRUE(
+            db_->Get(ropt, handles_[1], "rocksdb", &value).IsNotFound());
+      } else {
+        ASSERT_OK(db_->Get(ropt, handles_[1], "rocksdb", &value));
+        ASSERT_EQ(value, "hello");
+      }
+
+      // Expect same result in multiget
+      multiget_cfs.push_back(handles_[1]);
+      multiget_keys.push_back("rocksdb");
+      statuses =
+          db_->MultiGet(ropt, multiget_cfs, multiget_keys, &multiget_values);
+      ASSERT_TRUE(statuses[0].ok());
+      ASSERT_EQ("first", multiget_values[0]);
+      ASSERT_TRUE(statuses[1].ok());
+      ASSERT_EQ("one", multiget_values[1]);
+      if (wopt.disableWAL) {
+        ASSERT_TRUE(statuses[2].IsNotFound());
+      } else {
+        ASSERT_OK(statuses[2]);
+      }
+
+      // 3rd round: delete and flush
+      ASSERT_OK(db_->Delete(wopt, handles_[1], "foo"));
+      Flush(1);
+      ASSERT_OK(db_->Delete(wopt, handles_[1], "bar"));
+
+      ASSERT_TRUE(db_->Get(ropt, handles_[1], "foo", &value).IsNotFound());
+      if (wopt.disableWAL) {
+        // Still expect finding the value as its delete has not yet being
+        // flushed.
+        ASSERT_TRUE(db_->Get(ropt, handles_[1], "bar", &value).ok());
+        ASSERT_EQ(value, "one");
+      } else {
+        ASSERT_TRUE(db_->Get(ropt, handles_[1], "bar", &value).IsNotFound());
+      }
+      ASSERT_TRUE(db_->Get(ropt, handles_[1], "rocksdb", &value).ok());
+      ASSERT_EQ(value, "hello");
+
+      statuses =
+          db_->MultiGet(ropt, multiget_cfs, multiget_keys, &multiget_values);
+      ASSERT_TRUE(statuses[0].IsNotFound());
+      if (wopt.disableWAL) {
+        ASSERT_TRUE(statuses[1].ok());
+        ASSERT_EQ("one", multiget_values[1]);
+      } else {
+        ASSERT_TRUE(statuses[1].IsNotFound());
+      }
+      ASSERT_TRUE(statuses[2].ok());
+      ASSERT_EQ("hello", multiget_values[2]);
+      if (wopt.disableWAL == 0) {
+        DestroyAndReopen(options);
+      }
+    }
+  } while (ChangeOptions(kSkipHashCuckoo));
+}
+
+TEST_F(DBTest, IteratorProperty) {
+  // The test needs to be changed if kPersistedTier is supported in iterator.
+  Options options = CurrentOptions();
+  CreateAndReopenWithCF({"pikachu"}, options);
+  Put(1, "1", "2");
+  ReadOptions ropt;
+  ropt.pin_data = false;
+  {
+    unique_ptr<Iterator> iter(db_->NewIterator(ropt, handles_[1]));
+    iter->SeekToFirst();
+    std::string prop_value;
+    ASSERT_NOK(iter->GetProperty("non_existing.value", &prop_value));
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+    ASSERT_EQ("0", prop_value);
+    iter->Next();
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+    ASSERT_EQ("Iterator is not valid.", prop_value);
+  }
+  Close();
+}
+
+TEST_F(DBTest, PersistedTierOnIterator) {
+  // The test needs to be changed if kPersistedTier is supported in iterator.
+  Options options = CurrentOptions();
+  CreateAndReopenWithCF({"pikachu"}, options);
+  ReadOptions ropt;
+  ropt.read_tier = kPersistedTier;
+
+  auto* iter = db_->NewIterator(ropt, handles_[1]);
+  ASSERT_TRUE(iter->status().IsNotSupported());
+  delete iter;
+
+  std::vector<Iterator*> iters;
+  ASSERT_TRUE(db_->NewIterators(ropt, {handles_[1]}, &iters).IsNotSupported());
+  Close();
+}
+
 TEST_F(DBTest, SingleDeleteFlush) {
  // Test to check whether flushing preserves a single delete hidden
  // behind a put.
@@ -5272,6 +5420,7 @@ class DBTestRandomized : public DBTest,
        option_configs.push_back(option_config);
      }
    }
+    option_configs.push_back(kBlockBasedTableWithIndexRestartInterval);
    return option_configs;
  }
 };
@@ -5737,6 +5886,28 @@ TEST_F(DBTest, TableOptionsSanitizeTest) {
  options.prefix_extractor.reset(NewFixedPrefixTransform(1));
  ASSERT_OK(TryReopen(options));
 }
+
+TEST_F(DBTest, ConcurrentMemtableNotSupported) {
+  Options options = CurrentOptions();
+  options.allow_concurrent_memtable_write = true;
+  options.soft_pending_compaction_bytes_limit = 0;
+  options.hard_pending_compaction_bytes_limit = 100;
+  options.create_if_missing = true;
+
+  DestroyDB(dbname_, options);
+  options.memtable_factory.reset(NewHashLinkListRepFactory(4, 0, 3, true, 4));
+  ASSERT_NOK(TryReopen(options));
+
+  options.memtable_factory.reset(new SkipListFactory);
+  ASSERT_OK(TryReopen(options));
+
+  ColumnFamilyOptions cf_options(options);
+  cf_options.memtable_factory.reset(
+      NewHashLinkListRepFactory(4, 0, 3, true, 4));
+  ColumnFamilyHandle* handle;
+  ASSERT_NOK(db_->CreateColumnFamily(cf_options, "name", &handle));
+}
+
 #endif  // ROCKSDB_LITE

 TEST_F(DBTest, SanitizeNumThreads) {
@@ -8486,7 +8657,6 @@ TEST_F(DBTest, DeletingOldWalAfterDrop) {
  EXPECT_GT(lognum2, lognum1);
 }

-#ifndef ROCKSDB_LITE
 TEST_F(DBTest, DBWithSstFileManager) {
  std::shared_ptr<SstFileManager> sst_file_manager(NewSstFileManager(env_));
  auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
@@ -8551,6 +8721,7 @@ TEST_F(DBTest, DBWithSstFileManager) {
  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }

+#ifndef ROCKSDB_LITE
 TEST_F(DBTest, RateLimitedDelete) {
  rocksdb::SyncPoint::GetInstance()->LoadDependency({
      {"DBTest::RateLimitedDelete:1", "DeleteScheduler::BackgroundEmptyTrash"},
@@ -8723,6 +8894,102 @@ TEST_F(DBTest, DestroyDBWithRateLimitedDelete) {
 }
 #endif  // ROCKSDB_LITE

+TEST_F(DBTest, DBWithMaxSpaceAllowed) {
+  std::shared_ptr<SstFileManager> sst_file_manager(NewSstFileManager(env_));
+  auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
+
+  Options options = CurrentOptions();
+  options.sst_file_manager = sst_file_manager;
+  options.disable_auto_compactions = true;
+  DestroyAndReopen(options);
+
+  Random rnd(301);
+
+  // Generate a file containing 100 keys.
+  for (int i = 0; i < 100; i++) {
+    ASSERT_OK(Put(Key(i), RandomString(&rnd, 50)));
+  }
+  ASSERT_OK(Flush());
+
+  uint64_t first_file_size = 0;
+  auto files_in_db = GetAllSSTFiles(&first_file_size);
+  ASSERT_EQ(sfm->GetTotalSize(), first_file_size);
+
+  // Set the maximum allowed space usage to the current total size
+  sfm->SetMaxAllowedSpaceUsage(first_file_size + 1);
+
+  ASSERT_OK(Put("key1", "val1"));
+  // This flush will cause bg_error_ and will fail
+  ASSERT_NOK(Flush());
+}
+
+TEST_F(DBTest, DBWithMaxSpaceAllowedRandomized) {
+  // This test will set a maximum allowed space for the DB, then it will
+  // keep filling the DB until the limit is reached and bg_error_ is set.
+  // When bg_error_ is set we will verify that the DB size is greater
+  // than the limit.
+
+  std::vector<int> max_space_limits_mbs = {1, 2, 4, 8, 10};
+
+  bool bg_error_set = false;
+  uint64_t total_sst_files_size = 0;
+
+  int reached_max_space_on_flush = 0;
+  int reached_max_space_on_compaction = 0;
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::FlushMemTableToOutputFile:MaxAllowedSpaceReached",
+      [&](void* arg) {
+        bg_error_set = true;
+        GetAllSSTFiles(&total_sst_files_size);
+        reached_max_space_on_flush++;
+      });
+
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "CompactionJob::FinishCompactionOutputFile:MaxAllowedSpaceReached",
+      [&](void* arg) {
+        bg_error_set = true;
+        GetAllSSTFiles(&total_sst_files_size);
+        reached_max_space_on_compaction++;
+      });
+
+  for (auto limit_mb : max_space_limits_mbs) {
+    bg_error_set = false;
+    total_sst_files_size = 0;
+    rocksdb::SyncPoint::GetInstance()->ClearTrace();
+    rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+    std::shared_ptr<SstFileManager> sst_file_manager(NewSstFileManager(env_));
+    auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
+
+    Options options = CurrentOptions();
+    options.sst_file_manager = sst_file_manager;
+    options.write_buffer_size = 1024 * 512;  // 512 Kb
+    DestroyAndReopen(options);
+    Random rnd(301);
+
+    sfm->SetMaxAllowedSpaceUsage(limit_mb * 1024 * 1024);
+
+    int keys_written = 0;
+    uint64_t estimated_db_size = 0;
+    while (true) {
+      auto s = Put(RandomString(&rnd, 10), RandomString(&rnd, 50));
+      if (!s.ok()) {
+        break;
+      }
+      keys_written++;
+      // Check the estimated db size vs the db limit just to make sure we
+      // dont run into an infinite loop
+      estimated_db_size = keys_written * 60;  // ~60 bytes per key
+      ASSERT_LT(estimated_db_size, limit_mb * 1024 * 1024 * 2);
+    }
+    ASSERT_TRUE(bg_error_set);
+    ASSERT_GE(total_sst_files_size, limit_mb * 1024 * 1024);
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  }
+
+  ASSERT_GT(reached_max_space_on_flush, 0);
+  ASSERT_GT(reached_max_space_on_compaction, 0);
+}
+
 TEST_F(DBTest, UnsupportedManualSync) {
  DestroyAndReopen(CurrentOptions());
  env_->is_wal_sync_thread_safe_.store(false);
@@ -9142,6 +9409,58 @@ TEST_F(DBTest, AddExternalSstFile) {
                         kSkipFIFOCompaction));
 }

+// This test reporduce a bug that can happen in some cases if the DB started
+// purging obsolete files when we are adding an external sst file.
+// This situation may result in deleting the file while it's being added.
+TEST_F(DBTest, AddExternalSstFilePurgeObsoleteFilesBug) {
+  std::string sst_files_folder = test::TmpDir(env_) + "/sst_files/";
+  env_->CreateDir(sst_files_folder);
+  Options options = CurrentOptions();
+  options.env = env_;
+  const ImmutableCFOptions ioptions(options);
+
+  SstFileWriter sst_file_writer(EnvOptions(), ioptions, options.comparator);
+
+  // file1.sst (0 => 500)
+  std::string sst_file_path = sst_files_folder + "file1.sst";
+  Status s = sst_file_writer.Open(sst_file_path);
+  ASSERT_OK(s);
+  for (int i = 0; i < 500; i++) {
+    std::string k = Key(i);
+    s = sst_file_writer.Add(k, k + "_val");
+    ASSERT_OK(s);
+  }
+
+  ExternalSstFileInfo sst_file_info;
+  s = sst_file_writer.Finish(&sst_file_info);
+  ASSERT_OK(s);
+
+  options.delete_obsolete_files_period_micros = 0;
+  options.disable_auto_compactions = true;
+  DestroyAndReopen(options);
+
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::AddFile:FileCopied", [&](void* arg) {
+        ASSERT_OK(Put("aaa", "bbb"));
+        ASSERT_OK(Flush());
+        ASSERT_OK(Put("aaa", "xxx"));
+        ASSERT_OK(Flush());
+        db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  s = db_->AddFile(sst_file_path);
+  ASSERT_OK(s);
+
+  for (int i = 0; i < 500; i++) {
+    std::string k = Key(i);
+    std::string v = k + "_val";
+    ASSERT_EQ(Get(k), v);
+  }
+
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+}
+
 TEST_F(DBTest, AddExternalSstFileNoCopy) {
  std::string sst_files_folder = test::TmpDir(env_) + "/sst_files/";
  env_->CreateDir(sst_files_folder);
@@ -9543,7 +9862,10 @@ TEST_F(DBTest, PinnedDataIteratorRandomized) {
          ASSERT_EQ(true_data.lower_bound(k), true_data.end());
          continue;
        }
-        ASSERT_TRUE(iter->IsKeyPinned());
+        std::string prop_value;
+        ASSERT_OK(
+            iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+        ASSERT_EQ("1", prop_value);
        keys_slices.push_back(iter->key());
        true_keys.push_back(true_data.lower_bound(k)->first);
      }
@@ -9558,7 +9880,10 @@ TEST_F(DBTest, PinnedDataIteratorRandomized) {
      printf("Testing iterating forward on all keys\n");
      std::vector<Slice> all_keys;
      for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-        ASSERT_TRUE(iter->IsKeyPinned());
+        std::string prop_value;
+        ASSERT_OK(
+            iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+        ASSERT_EQ("1", prop_value);
        all_keys.push_back(iter->key());
      }
      ASSERT_EQ(all_keys.size(), true_data.size());
@@ -9576,7 +9901,10 @@ TEST_F(DBTest, PinnedDataIteratorRandomized) {
      printf("Testing iterating backward on all keys\n");
      std::vector<Slice> all_keys;
      for (iter->SeekToLast(); iter->Valid(); iter->Prev()) {
-        ASSERT_TRUE(iter->IsKeyPinned());
+        std::string prop_value;
+        ASSERT_OK(
+            iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+        ASSERT_EQ("1", prop_value);
        all_keys.push_back(iter->key());
      }
      ASSERT_EQ(all_keys.size(), true_data.size());
@@ -9647,7 +9975,9 @@ TEST_F(DBTest, PinnedDataIteratorMultipleFiles) {

  std::vector<std::pair<Slice, std::string>> results;
  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-    ASSERT_TRUE(iter->IsKeyPinned());
+    std::string prop_value;
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+    ASSERT_EQ("1", prop_value);
    results.emplace_back(iter->key(), iter->value().ToString());
  }

@@ -9700,7 +10030,9 @@ TEST_F(DBTest, PinnedDataIteratorMergeOperator) {

  std::vector<std::pair<Slice, std::string>> results;
  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-    ASSERT_TRUE(iter->IsKeyPinned());
+    std::string prop_value;
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+    ASSERT_EQ("1", prop_value);
    results.emplace_back(iter->key(), iter->value().ToString());
  }

@@ -9755,7 +10087,9 @@ TEST_F(DBTest, PinnedDataIteratorReadAfterUpdate) {

  std::vector<std::pair<Slice, std::string>> results;
  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-    ASSERT_TRUE(iter->IsKeyPinned());
+    std::string prop_value;
+    ASSERT_OK(iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+    ASSERT_EQ("1", prop_value);
    results.emplace_back(iter->key(), iter->value().ToString());
  }

@@ -10277,6 +10611,88 @@ TEST_F(DBTest, PrefixExtractorBlockFilter) {
  delete iter;
 }

+TEST_F(DBTest, IteratorWithLocalStatistics) {
+  Options options = CurrentOptions();
+  options.statistics = rocksdb::CreateDBStatistics();
+  DestroyAndReopen(options);
+
+  Random rnd(301);
+  for (int i = 0; i < 1000; i++) {
+    // Key 10 bytes / Value 10 bytes
+    ASSERT_OK(Put(RandomString(&rnd, 10), RandomString(&rnd, 10)));
+  }
+
+  std::atomic<uint64_t> total_next(0);
+  std::atomic<uint64_t> total_next_found(0);
+  std::atomic<uint64_t> total_prev(0);
+  std::atomic<uint64_t> total_prev_found(0);
+  std::atomic<uint64_t> total_bytes(0);
+
+  std::vector<std::thread> threads;
+  std::function<void()> reader_func_next = [&]() {
+    Iterator* iter = db_->NewIterator(ReadOptions());
+
+    iter->SeekToFirst();
+    // Seek will bump ITER_BYTES_READ
+    total_bytes += iter->key().size();
+    total_bytes += iter->value().size();
+    while (true) {
+      iter->Next();
+      total_next++;
+
+      if (!iter->Valid()) {
+        break;
+      }
+      total_next_found++;
+      total_bytes += iter->key().size();
+      total_bytes += iter->value().size();
+    }
+
+    delete iter;
+  };
+
+  std::function<void()> reader_func_prev = [&]() {
+    Iterator* iter = db_->NewIterator(ReadOptions());
+
+    iter->SeekToLast();
+    // Seek will bump ITER_BYTES_READ
+    total_bytes += iter->key().size();
+    total_bytes += iter->value().size();
+    while (true) {
+      iter->Prev();
+      total_prev++;
+
+      if (!iter->Valid()) {
+        break;
+      }
+      total_prev_found++;
+      total_bytes += iter->key().size();
+      total_bytes += iter->value().size();
+    }
+
+    delete iter;
+  };
+
+  for (int i = 0; i < 10; i++) {
+    threads.emplace_back(reader_func_next);
+  }
+  for (int i = 0; i < 15; i++) {
+    threads.emplace_back(reader_func_prev);
+  }
+
+  for (auto& t : threads) {
+    t.join();
+  }
+
+  ASSERT_EQ(TestGetTickerCount(options, NUMBER_DB_NEXT), total_next);
+  ASSERT_EQ(TestGetTickerCount(options, NUMBER_DB_NEXT_FOUND),
+            total_next_found);
+  ASSERT_EQ(TestGetTickerCount(options, NUMBER_DB_PREV), total_prev);
+  ASSERT_EQ(TestGetTickerCount(options, NUMBER_DB_PREV_FOUND),
+            total_prev_found);
+  ASSERT_EQ(TestGetTickerCount(options, ITER_BYTES_READ), total_bytes);
+}
+
 #ifndef ROCKSDB_LITE
 class BloomStatsTestWithParam
    : public DBTest,
@@ -0,0 +1,67 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+#include <cstdlib>
+#include "db/db_test_util.h"
+#include "port/stack_trace.h"
+
+namespace rocksdb {
+
+class DBTest2 : public DBTestBase {
+ public:
+  DBTest2() : DBTestBase("/db_test2") {}
+};
+
+TEST_F(DBTest2, IteratorPropertyVersionNumber) {
+  Put("", "");
+  Iterator* iter1 = db_->NewIterator(ReadOptions());
+  std::string prop_value;
+  ASSERT_OK(
+      iter1->GetProperty("rocksdb.iterator.super-version-number", &prop_value));
+  uint64_t version_number1 =
+      static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+
+  Put("", "");
+  Flush();
+
+  Iterator* iter2 = db_->NewIterator(ReadOptions());
+  ASSERT_OK(
+      iter2->GetProperty("rocksdb.iterator.super-version-number", &prop_value));
+  uint64_t version_number2 =
+      static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+
+  ASSERT_GT(version_number2, version_number1);
+
+  Put("", "");
+
+  Iterator* iter3 = db_->NewIterator(ReadOptions());
+  ASSERT_OK(
+      iter3->GetProperty("rocksdb.iterator.super-version-number", &prop_value));
+  uint64_t version_number3 =
+      static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+
+  ASSERT_EQ(version_number2, version_number3);
+
+  iter1->SeekToFirst();
+  ASSERT_OK(
+      iter1->GetProperty("rocksdb.iterator.super-version-number", &prop_value));
+  uint64_t version_number1_new =
+      static_cast<uint64_t>(std::atoi(prop_value.c_str()));
+  ASSERT_EQ(version_number1, version_number1_new);
+
+  delete iter1;
+  delete iter2;
+  delete iter3;
+}
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
@@ -1,4 +1,4 @@
-// Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 // This source code is licensed under the BSD-style license found in the
 // LICENSE file in the root directory of this source tree. An additional grant
 // of patent rights can be found in the PATENTS file in the same directory.
@@ -339,6 +339,10 @@ Options DBTestBase::CurrentOptions(
      options.prefix_extractor.reset(NewNoopTransform());
      break;
    }
+    case kBlockBasedTableWithIndexRestartInterval: {
+      table_options.index_block_restart_interval = 8;
+      break;
+    }
    case kOptimizeFiltersForHits: {
      options.optimize_filters_for_hits = true;
      set_block_based_table_factory = true;
@@ -1011,9 +1015,13 @@ void DBTestBase::CopyFile(const std::string& source,
  ASSERT_OK(destfile->Close());
 }

-std::unordered_map<std::string, uint64_t> DBTestBase::GetAllSSTFiles() {
+std::unordered_map<std::string, uint64_t> DBTestBase::GetAllSSTFiles(
+    uint64_t* total_size) {
  std::unordered_map<std::string, uint64_t> res;

+  if (total_size) {
+    *total_size = 0;
+  }
  std::vector<std::string> files;
  env_->GetChildren(dbname_, &files);
  for (auto& file_name : files) {
@@ -1024,6 +1032,9 @@ std::unordered_map<std::string, uint64_t> DBTestBase::GetAllSSTFiles() {
      uint64_t file_size = 0;
      env_->GetFileSize(file_path, &file_size);
      res[file_path] = file_size;
+      if (total_size) {
+        *total_size += file_size;
+      }
    }
  }
  return res;
@@ -1,4 +1,4 @@
-// Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 // This source code is licensed under the BSD-style license found in the
 // LICENSE file in the root directory of this source tree. An additional grant
 // of patent rights can be found in the PATENTS file in the same directory.
@@ -529,6 +529,7 @@ class DBTestBase : public testing::Test {
    kEnd = 31,
    kLevelSubcompactions = 31,
    kUniversalSubcompactions = 32,
+    kBlockBasedTableWithIndexRestartInterval = 33,
  };
  int option_config_;

@@ -753,7 +754,8 @@ class DBTestBase : public testing::Test {
  void CopyFile(const std::string& source, const std::string& destination,
                uint64_t size = 0);

-  std::unordered_map<std::string, uint64_t> GetAllSSTFiles();
+  std::unordered_map<std::string, uint64_t> GetAllSSTFiles(
+      uint64_t* total_size = nullptr);
 };

 }  // namespace rocksdb
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1103,16 +1103,11 @@ TEST_P(DBTestUniversalCompaction, IncreaseUniversalCompactionNumLevels) {
  for (int i = 0; i <= max_key1; i++) {
    // each value is 10K
    ASSERT_OK(Put(1, Key(i), RandomString(&rnd, 10000)));
+    dbfull()->TEST_WaitForFlushMemTable(handles_[1]);
  }
  ASSERT_OK(Flush(1));
  dbfull()->TEST_WaitForCompact();

-  int non_level0_num_files = 0;
-  for (int i = 1; i < options.num_levels; i++) {
-    non_level0_num_files += NumTableFilesAtLevel(i, 1);
-  }
-  ASSERT_EQ(non_level0_num_files, 0);
-
  // Stage 2: reopen with universal compaction, num_levels=4
  options.compaction_style = kCompactionStyleUniversal;
  options.num_levels = 4;
@@ -1125,6 +1120,7 @@ TEST_P(DBTestUniversalCompaction, IncreaseUniversalCompactionNumLevels) {
  for (int i = max_key1 + 1; i <= max_key2; i++) {
    // each value is 10K
    ASSERT_OK(Put(1, Key(i), RandomString(&rnd, 10000)));
+    dbfull()->TEST_WaitForFlushMemTable(handles_[1]);
  }
  ASSERT_OK(Flush(1));
  dbfull()->TEST_WaitForCompact();
@@ -1155,6 +1151,7 @@ TEST_P(DBTestUniversalCompaction, IncreaseUniversalCompactionNumLevels) {
  for (int i = max_key2 + 1; i <= max_key3; i++) {
    // each value is 10K
    ASSERT_OK(Put(1, Key(i), RandomString(&rnd, 10000)));
+    dbfull()->TEST_WaitForFlushMemTable(handles_[1]);
  }
  ASSERT_OK(Flush(1));
  dbfull()->TEST_WaitForCompact();
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -37,6 +37,7 @@ class DeleteFileTest : public testing::Test {
  DeleteFileTest() {
    db_ = nullptr;
    env_ = Env::Default();
+    options_.delete_obsolete_files_period_micros = 0;  // always do full purge
    options_.enable_thread_tracking = true;
    options_.write_buffer_size = 1024*1024*1000;
    options_.target_file_size_base = 1024*1024*1000;
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2014, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2015, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -10,15 +10,16 @@
 #include <string>
 #include <utility>

-#include "db/job_context.h"
+#include "db/column_family.h"
 #include "db/db_impl.h"
 #include "db/db_iter.h"
-#include "db/column_family.h"
+#include "db/dbformat.h"
+#include "db/job_context.h"
 #include "rocksdb/env.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/slice_transform.h"
 #include "table/merger.h"
-#include "db/dbformat.h"
+#include "util/string_util.h"
 #include "util/sync_point.h"

 namespace rocksdb {
@@ -471,6 +472,15 @@ Status ForwardIterator::status() const {
  return immutable_status_;
 }

+Status ForwardIterator::GetProperty(std::string prop_name, std::string* prop) {
+  assert(prop != nullptr);
+  if (prop_name == "rocksdb.iterator.super-version-number") {
+    *prop = ToString(sv_->version_number);
+    return Status::OK();
+  }
+  return Status::InvalidArgument();
+}
+
 void ForwardIterator::RebuildIterators(bool refresh_sv) {
  // Clean up
  Cleanup(refresh_sv);
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -71,6 +71,8 @@ class ForwardIterator : public InternalIterator {
  virtual Slice key() const override;
  virtual Slice value() const override;
  virtual Status status() const override;
+  virtual Status GetProperty(std::string prop_name, std::string* prop) override;
+
  bool TEST_CheckDeletedIters(int* deleted_iters, int* num_iters);

 private:
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional
 //  grant of patent rights can be found in the PATENTS file in the same
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -132,6 +132,8 @@ static const std::string is_file_deletions_enabled =
 static const std::string num_snapshots = "num-snapshots";
 static const std::string oldest_snapshot_time = "oldest-snapshot-time";
 static const std::string num_live_versions = "num-live-versions";
+static const std::string current_version_number =
+    "current-super-version-number";
 static const std::string estimate_live_data_size = "estimate-live-data-size";
 static const std::string base_level = "base-level";
 static const std::string total_sst_files_size = "total-sst-files-size";
@@ -191,6 +193,8 @@ const std::string DB::Properties::kOldestSnapshotTime =
                      rocksdb_prefix + oldest_snapshot_time;
 const std::string DB::Properties::kNumLiveVersions =
                      rocksdb_prefix + num_live_versions;
+const std::string DB::Properties::kCurrentSuperVersionNumber =
+    rocksdb_prefix + current_version_number;
 const std::string DB::Properties::kEstimateLiveDataSize =
                      rocksdb_prefix + estimate_live_data_size;
 const std::string DB::Properties::kTotalSstFilesSize =
@@ -254,6 +258,8 @@ const std::unordered_map<std::string,
     {false, nullptr, &InternalStats::HandleOldestSnapshotTime}},
    {DB::Properties::kNumLiveVersions,
     {false, nullptr, &InternalStats::HandleNumLiveVersions}},
+    {DB::Properties::kCurrentSuperVersionNumber,
+     {false, nullptr, &InternalStats::HandleCurrentSuperVersionNumber}},
    {DB::Properties::kEstimateLiveDataSize,
     {true, nullptr, &InternalStats::HandleEstimateLiveDataSize}},
    {DB::Properties::kBaseLevel,
@@ -519,6 +525,12 @@ bool InternalStats::HandleNumLiveVersions(uint64_t* value, DBImpl* db,
  return true;
 }

+bool InternalStats::HandleCurrentSuperVersionNumber(uint64_t* value, DBImpl* db,
+                                                    Version* version) {
+  *value = cfd_->GetSuperVersionNumber();
+  return true;
+}
+
 bool InternalStats::HandleIsFileDeletionsEnabled(uint64_t* value, DBImpl* db,
                                                 Version* version) {
  *value = db->IsFileDeletionsEnabled();
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -328,6 +328,8 @@ class InternalStats {
  bool HandleNumSnapshots(uint64_t* value, DBImpl* db, Version* version);
  bool HandleOldestSnapshotTime(uint64_t* value, DBImpl* db, Version* version);
  bool HandleNumLiveVersions(uint64_t* value, DBImpl* db, Version* version);
+  bool HandleCurrentSuperVersionNumber(uint64_t* value, DBImpl* db,
+                                       Version* version);
  bool HandleIsFileDeletionsEnabled(uint64_t* value, DBImpl* db,
                                    Version* version);
  bool HandleBaseLevel(uint64_t* value, DBImpl* db, Version* version);
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -22,9 +22,9 @@ class MemTable;
 struct JobContext {
  inline bool HaveSomethingToDelete() const {
    return full_scan_candidate_files.size() || sst_delete_files.size() ||
-           log_delete_files.size() || new_superversion != nullptr ||
-           superversions_to_free.size() > 0 || memtables_to_free.size() > 0 ||
-           logs_to_free.size() > 0;
+           log_delete_files.size() || manifest_delete_files.size() ||
+           new_superversion != nullptr || superversions_to_free.size() > 0 ||
+           memtables_to_free.size() > 0 || logs_to_free.size() > 0;
  }

  // Structure to store information for candidate files to delete.
@@ -56,6 +56,9 @@ struct JobContext {
  // a list of log files that we need to delete
  std::vector<uint64_t> log_delete_files;

+  // a list of manifest files that we need to delete
+  std::vector<std::string> manifest_delete_files;
+
  // a list of memtables to be free
  autovector<MemTable*> memtables_to_free;

@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -1,4 +1,4 @@
-//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.