@nxtedition/rocksdb 8.2.8 → 9.0.0

package/deps/rocksdb/rocksdb/CMakeLists.txt

@@ -547,7 +547,7 @@ if(HAVE_SCHED_GETCPU)
   add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
 endif()
 
-check_cxx_symbol_exists(getauxval auvx.h HAVE_AUXV_GETAUXVAL)
+check_cxx_symbol_exists(getauxval "sys/auxv.h" HAVE_AUXV_GETAUXVAL)
 if(HAVE_AUXV_GETAUXVAL)
   add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
 endif()
@@ -865,6 +865,8 @@ set(SOURCES
         util/string_util.cc
         util/thread_local.cc
         util/threadpool_imp.cc
+        util/udt_util.cc
+        util/write_batch_util.cc
         util/xxhash.cc
         utilities/agg_merge/agg_merge.cc
         utilities/backup/backup_engine.cc
@@ -1421,6 +1423,7 @@ if(WITH_TESTS)
         util/timer_test.cc
         util/thread_list_test.cc
         util/thread_local_test.cc
+        util/udt_util_test.cc
         util/work_queue_test.cc
         utilities/agg_merge/agg_merge_test.cc
         utilities/backup/backup_engine_test.cc
@@ -1589,3 +1592,6 @@ option(WITH_BENCHMARK "build benchmark tests" OFF)
 if(WITH_BENCHMARK)
   add_subdirectory(${PROJECT_SOURCE_DIR}/microbench/)
 endif()
+
+target_include_directories(${PROJECT_NAME} PUBLIC
+  $<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>)

package/deps/rocksdb/rocksdb/Makefile

@@ -88,6 +88,25 @@ endif
 
 $(info $$DEBUG_LEVEL is $(DEBUG_LEVEL), $$LIB_MODE is $(LIB_MODE))
 
+# Detect what platform we're building on.
+# Export some common variables that might have been passed as Make variables
+# instead of environment variables.
+dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; \
+                  export CXXFLAGS="$(EXTRA_CXXFLAGS)"; \
+                  export LDFLAGS="$(EXTRA_LDFLAGS)"; \
+                  export COMPILE_WITH_ASAN="$(COMPILE_WITH_ASAN)"; \
+                  export COMPILE_WITH_TSAN="$(COMPILE_WITH_TSAN)"; \
+                  export COMPILE_WITH_UBSAN="$(COMPILE_WITH_UBSAN)"; \
+                  export PORTABLE="$(PORTABLE)"; \
+                  export ROCKSDB_NO_FBCODE="$(ROCKSDB_NO_FBCODE)"; \
+                  export USE_CLANG="$(USE_CLANG)"; \
+                  export LIB_MODE="$(LIB_MODE)"; \
+		  export ROCKSDB_CXX_STANDARD="$(ROCKSDB_CXX_STANDARD)"; \
+		  export USE_FOLLY="$(USE_FOLLY)"; \
+                  "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
+# this file is generated by the previous line to set build flags and sources
+include make_config.mk
+
 # Figure out optimize level.
 ifneq ($(DEBUG_LEVEL), 2)
 	OPTIMIZE_LEVEL ?= -O2
@@ -223,25 +242,6 @@ am__v_AR_1 =
 AM_LINK = $(AM_V_CCLD)$(CXX) -L. $(patsubst lib%.a, -l%, $(patsubst lib%.$(PLATFORM_SHARED_EXT), -l%, $^)) $(EXEC_LDFLAGS) -o $@ $(LDFLAGS) $(COVERAGEFLAGS)
 AM_SHARE = $(AM_V_CCLD) $(CXX) $(PLATFORM_SHARED_LDFLAGS)$@ -L. $(patsubst lib%.$(PLATFORM_SHARED_EXT), -l%, $^) $(EXEC_LDFLAGS) $(LDFLAGS) -o $@
 
-# Detect what platform we're building on.
-# Export some common variables that might have been passed as Make variables
-# instead of environment variables.
-dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; \
-                  export CXXFLAGS="$(EXTRA_CXXFLAGS)"; \
-                  export LDFLAGS="$(EXTRA_LDFLAGS)"; \
-                  export COMPILE_WITH_ASAN="$(COMPILE_WITH_ASAN)"; \
-                  export COMPILE_WITH_TSAN="$(COMPILE_WITH_TSAN)"; \
-                  export COMPILE_WITH_UBSAN="$(COMPILE_WITH_UBSAN)"; \
-                  export PORTABLE="$(PORTABLE)"; \
-                  export ROCKSDB_NO_FBCODE="$(ROCKSDB_NO_FBCODE)"; \
-                  export USE_CLANG="$(USE_CLANG)"; \
-                  export LIB_MODE="$(LIB_MODE)"; \
-		  export ROCKSDB_CXX_STANDARD="$(ROCKSDB_CXX_STANDARD)"; \
-		  export USE_FOLLY="$(USE_FOLLY)"; \
-                  "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
-# this file is generated by the previous line to set build flags and sources
-include make_config.mk
-
 ROCKSDB_PLUGIN_MKS = $(foreach plugin, $(ROCKSDB_PLUGINS), plugin/$(plugin)/*.mk)
 include $(ROCKSDB_PLUGIN_MKS)
 ROCKSDB_PLUGIN_PROTO =ROCKSDB_NAMESPACE::ObjectLibrary\&, const std::string\&
@@ -1417,6 +1417,9 @@ thread_local_test: $(OBJ_DIR)/util/thread_local_test.o $(TEST_LIBRARY) $(LIBRARY
 work_queue_test: $(OBJ_DIR)/util/work_queue_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
+udt_util_test: $(OBJ_DIR)/util/udt_util_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 corruption_test: $(OBJ_DIR)/db/corruption_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 

package/deps/rocksdb/rocksdb/TARGETS

@@ -264,6 +264,8 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "util/string_util.cc",
         "util/thread_local.cc",
         "util/threadpool_imp.cc",
+        "util/udt_util.cc",
+        "util/write_batch_util.cc",
         "util/xxhash.cc",
         "utilities/agg_merge/agg_merge.cc",
         "utilities/backup/backup_engine.cc",
@@ -5508,6 +5510,12 @@ cpp_unittest_wrapper(name="ttl_test",
             extra_compiler_flags=[])
 
 
+cpp_unittest_wrapper(name="udt_util_test",
+            srcs=["util/udt_util_test.cc"],
+            deps=[":rocksdb_test_lib"],
+            extra_compiler_flags=[])
+
+
 cpp_unittest_wrapper(name="util_merge_operators_test",
             srcs=["utilities/util_merge_operators_test.cc"],
             deps=[":rocksdb_test_lib"],

package/deps/rocksdb/rocksdb/cache/cache_bench_tool.cc

@@ -31,6 +31,7 @@
 #include "util/hash.h"
 #include "util/mutexlock.h"
 #include "util/random.h"
+#include "util/stderr_logger.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
 
@@ -49,8 +50,11 @@ DEFINE_double(resident_ratio, 0.25,
               "Ratio of keys fitting in cache to keyspace.");
 DEFINE_uint64(ops_per_thread, 2000000U, "Number of operations per thread.");
 DEFINE_uint32(value_bytes, 8 * KiB, "Size of each value added.");
+DEFINE_uint32(value_bytes_estimate, 0,
+              "If > 0, overrides estimated_entry_charge or "
+              "min_avg_entry_charge depending on cache_type.");
 
-DEFINE_uint32(skew, 5, "Degree of skew in key selection");
+DEFINE_uint32(skew, 5, "Degree of skew in key selection. 0 = no skew");
 DEFINE_bool(populate_cache, true, "Populate cache before operations");
 
 DEFINE_uint32(lookup_insert_percent, 87,
@@ -71,12 +75,22 @@ DEFINE_uint32(
 
 DEFINE_uint32(gather_stats_entries_per_lock, 256,
               "For Cache::ApplyToAllEntries");
-DEFINE_bool(skewed, false, "If true, skew the key access distribution");
 
 DEFINE_bool(lean, false,
             "If true, no additional computation is performed besides cache "
             "operations.");
 
+DEFINE_bool(early_exit, false,
+            "Exit before deallocating most memory. Good for malloc stats, e.g."
+            "MALLOC_CONF=\"stats_print:true\"");
+
+DEFINE_bool(histograms, true,
+            "Whether to track and print histogram statistics.");
+
+DEFINE_bool(report_problems, true, "Whether to ReportProblems() at the end.");
+
+DEFINE_uint32(seed, 0, "Hashing/random seed to use. 0 = choose at random");
+
 DEFINE_string(secondary_cache_uri, "",
               "Full URI for creating a custom secondary cache object");
 static class std::shared_ptr<ROCKSDB_NAMESPACE::SecondaryCache> secondary_cache;
@@ -145,9 +159,6 @@ class SharedState {
  public:
   explicit SharedState(CacheBench* cache_bench)
       : cv_(&mu_),
-        num_initialized_(0),
-        start_(false),
-        num_done_(0),
         cache_bench_(cache_bench) {}
 
   ~SharedState() {}
@@ -170,15 +181,27 @@ class SharedState {
 
   bool Started() const { return start_; }
 
+  void AddLookupStats(uint64_t hits, uint64_t misses) {
+    MutexLock l(&mu_);
+    lookup_count_ += hits + misses;
+    lookup_hits_ += hits;
+  }
+
+  double GetLookupHitRatio() const {
+    return 1.0 * lookup_hits_ / lookup_count_;
+  }
+
  private:
   port::Mutex mu_;
   port::CondVar cv_;
 
-  uint64_t num_initialized_;
-  bool start_;
-  uint64_t num_done_;
-
   CacheBench* cache_bench_;
+
+  uint64_t num_initialized_ = 0;
+  bool start_ = false;
+  uint64_t num_done_ = 0;
+  uint64_t lookup_count_ = 0;
+  uint64_t lookup_hits_ = 0;
 };
 
 // Per-thread state for concurrent executions of the same benchmark.
@@ -190,27 +213,19 @@ struct ThreadState {
   uint64_t duration_us = 0;
 
   ThreadState(uint32_t index, SharedState* _shared)
-      : tid(index), rnd(1000 + index), shared(_shared) {}
+      : tid(index), rnd(FLAGS_seed + 1 + index), shared(_shared) {}
 };
 
 struct KeyGen {
   char key_data[27];
 
-  Slice GetRand(Random64& rnd, uint64_t max_key, int max_log) {
-    uint64_t key = 0;
-    if (!FLAGS_skewed) {
-      uint64_t raw = rnd.Next();
-      // Skew according to setting
-      for (uint32_t i = 0; i < FLAGS_skew; ++i) {
-        raw = std::min(raw, rnd.Next());
-      }
-      key = FastRange64(raw, max_key);
-    } else {
-      key = rnd.Skewed(max_log);
-      if (key > max_key) {
-        key -= max_key;
-      }
+  Slice GetRand(Random64& rnd, uint64_t max_key, uint32_t skew) {
+    uint64_t raw = rnd.Next();
+    // Skew according to setting
+    for (uint32_t i = 0; i < skew; ++i) {
+      raw = std::min(raw, rnd.Next());
     }
+    uint64_t key = FastRange64(raw, max_key);
     // Variable size and alignment
     size_t off = key % 8;
     key_data[0] = char{42};
@@ -281,31 +296,38 @@ class CacheBench {
         lookup_threshold_(insert_threshold_ +
                           kHundredthUint64 * FLAGS_lookup_percent),
         erase_threshold_(lookup_threshold_ +
-                         kHundredthUint64 * FLAGS_erase_percent),
-        skewed_(FLAGS_skewed) {
+                         kHundredthUint64 * FLAGS_erase_percent) {
     if (erase_threshold_ != 100U * kHundredthUint64) {
       fprintf(stderr, "Percentages must add to 100.\n");
       exit(1);
     }
 
-    max_log_ = 0;
-    if (skewed_) {
-      uint64_t max_key = max_key_;
-      while (max_key >>= 1) max_log_++;
-      if (max_key > (static_cast<uint64_t>(1) << max_log_)) max_log_++;
-    }
-
     if (FLAGS_cache_type == "clock_cache") {
       fprintf(stderr, "Old clock cache implementation has been removed.\n");
       exit(1);
-    } else if (FLAGS_cache_type == "hyper_clock_cache") {
-      cache_ = HyperClockCacheOptions(FLAGS_cache_size, FLAGS_value_bytes,
-                                      FLAGS_num_shard_bits)
-                   .MakeSharedCache();
+    } else if (EndsWith(FLAGS_cache_type, "hyper_clock_cache")) {
+      HyperClockCacheOptions opts(
+          FLAGS_cache_size, /*estimated_entry_charge=*/0, FLAGS_num_shard_bits);
+      opts.hash_seed = BitwiseAnd(FLAGS_seed, INT32_MAX);
+      if (FLAGS_cache_type == "fixed_hyper_clock_cache" ||
+          FLAGS_cache_type == "hyper_clock_cache") {
+        opts.estimated_entry_charge = FLAGS_value_bytes_estimate > 0
+                                          ? FLAGS_value_bytes_estimate
+                                          : FLAGS_value_bytes;
+      } else if (FLAGS_cache_type == "auto_hyper_clock_cache") {
+        if (FLAGS_value_bytes_estimate > 0) {
+          opts.min_avg_entry_charge = FLAGS_value_bytes_estimate;
+        }
+      } else {
+        fprintf(stderr, "Cache type not supported.");
+        exit(1);
+      }
+      cache_ = opts.MakeSharedCache();
     } else if (FLAGS_cache_type == "lru_cache") {
       LRUCacheOptions opts(FLAGS_cache_size, FLAGS_num_shard_bits,
                            false /* strict_capacity_limit */,
                            0.5 /* high_pri_pool_ratio */);
+      opts.hash_seed = BitwiseAnd(FLAGS_seed, INT32_MAX);
       if (!FLAGS_secondary_cache_uri.empty()) {
         Status s = SecondaryCache::CreateFromString(
             ConfigOptions(), FLAGS_secondary_cache_uri, &secondary_cache);
@@ -329,13 +351,50 @@ class CacheBench {
   ~CacheBench() {}
 
   void PopulateCache() {
-    Random64 rnd(1);
+    Random64 rnd(FLAGS_seed);
     KeyGen keygen;
-    for (uint64_t i = 0; i < 2 * FLAGS_cache_size; i += FLAGS_value_bytes) {
-      Status s = cache_->Insert(keygen.GetRand(rnd, max_key_, max_log_),
-                                createValue(rnd), &helper1, FLAGS_value_bytes);
+    size_t max_occ = 0;
+    size_t inserts_since_max_occ_increase = 0;
+    size_t keys_since_last_not_found = 0;
+
+    // Avoid redundant insertions by checking Lookup before Insert.
+    // Loop until insertions consistently fail to increase max occupancy or
+    // it becomes difficult to find keys not already inserted.
+    while (inserts_since_max_occ_increase < 100 &&
+           keys_since_last_not_found < 100) {
+      Slice key = keygen.GetRand(rnd, max_key_, FLAGS_skew);
+
+      Cache::Handle* handle = cache_->Lookup(key);
+      if (handle != nullptr) {
+        cache_->Release(handle);
+        ++keys_since_last_not_found;
+        continue;
+      }
+      keys_since_last_not_found = 0;
+
+      Status s =
+          cache_->Insert(key, createValue(rnd), &helper1, FLAGS_value_bytes);
       assert(s.ok());
+
+      handle = cache_->Lookup(key);
+      if (!handle) {
+        fprintf(stderr, "Failed to lookup key just inserted.\n");
+        assert(false);
+        exit(42);
+      } else {
+        cache_->Release(handle);
+      }
+
+      size_t occ = cache_->GetOccupancyCount();
+      if (occ > max_occ) {
+        max_occ = occ;
+        inserts_since_max_occ_increase = 0;
+      } else {
+        ++inserts_since_max_occ_increase;
+      }
     }
+    printf("Population complete (%zu entries, %g average charge)\n", max_occ,
+           1.0 * FLAGS_cache_size / max_occ);
   }
 
   bool Run() {
@@ -394,19 +453,33 @@ class CacheBench {
                                         FLAGS_ops_per_thread / elapsed_secs);
     printf("Thread ops/sec = %u\n", ops_per_sec);
 
-    printf("\nOperation latency (ns):\n");
-    HistogramImpl combined;
-    for (uint32_t i = 0; i < FLAGS_threads; i++) {
-      combined.Merge(threads[i]->latency_ns_hist);
-    }
-    printf("%s", combined.ToString().c_str());
+    printf("Lookup hit ratio: %g\n", shared.GetLookupHitRatio());
 
-    if (FLAGS_gather_stats) {
-      printf("\nGather stats latency (us):\n");
-      printf("%s", stats_hist.ToString().c_str());
+    size_t occ = cache_->GetOccupancyCount();
+    size_t slot = cache_->GetTableAddressCount();
+    printf("Final load factor: %g (%zu / %zu)\n", 1.0 * occ / slot, occ, slot);
+
+    if (FLAGS_histograms) {
+      printf("\nOperation latency (ns):\n");
+      HistogramImpl combined;
+      for (uint32_t i = 0; i < FLAGS_threads; i++) {
+        combined.Merge(threads[i]->latency_ns_hist);
+      }
+      printf("%s", combined.ToString().c_str());
+
+      if (FLAGS_gather_stats) {
+        printf("\nGather stats latency (us):\n");
+        printf("%s", stats_hist.ToString().c_str());
+      }
     }
 
-    printf("\n%s", stats_report.c_str());
+    if (FLAGS_report_problems) {
+      printf("\n");
+      std::shared_ptr<Logger> logger =
+          std::make_shared<StderrLogger>(InfoLogLevel::DEBUG_LEVEL);
+      cache_->ReportProblems(logger);
+    }
+    printf("%s", stats_report.c_str());
 
     return true;
   }
@@ -419,8 +492,6 @@ class CacheBench {
   const uint64_t insert_threshold_;
   const uint64_t lookup_threshold_;
   const uint64_t erase_threshold_;
-  const bool skewed_;
-  int max_log_;
 
   // A benchmark version of gathering stats on an active block cache by
   // iterating over it. The primary purpose is to measure the impact of
@@ -453,7 +524,7 @@ class CacheBench {
         for (;;) {
           if (shared->AllDone()) {
             std::ostringstream ostr;
-            ostr << "Most recent cache entry stats:\n"
+            ostr << "\nMost recent cache entry stats:\n"
                  << "Number of entries: " << total_entry_count << "\n"
                  << "Table occupancy: " << table_occupancy << " / "
                  << table_size << " = "
@@ -490,13 +561,17 @@ class CacheBench {
         // Something slightly more expensive as in stats by category
         helpers.insert(helper);
       };
-      timer.Start();
+      if (FLAGS_histograms) {
+        timer.Start();
+      }
       Cache::ApplyToAllEntriesOptions opts;
       opts.average_entries_per_lock = FLAGS_gather_stats_entries_per_lock;
       shared->GetCacheBench()->cache_->ApplyToAllEntries(fn, opts);
       table_occupancy = shared->GetCacheBench()->cache_->GetOccupancyCount();
       table_size = shared->GetCacheBench()->cache_->GetTableAddressCount();
-      stats_hist->Add(timer.ElapsedNanos() / 1000);
+      if (FLAGS_histograms) {
+        stats_hist->Add(timer.ElapsedNanos() / 1000);
+      }
     }
   }
 
@@ -527,6 +602,8 @@ class CacheBench {
   void OperateCache(ThreadState* thread) {
     // To use looked-up values
     uint64_t result = 0;
+    uint64_t lookup_misses = 0;
+    uint64_t lookup_hits = 0;
     // To hold handles for a non-trivial amount of time
     Cache::Handle* handle = nullptr;
     KeyGen gen;
@@ -535,10 +612,12 @@ class CacheBench {
     StopWatchNano timer(clock);
 
     for (uint64_t i = 0; i < FLAGS_ops_per_thread; i++) {
-      Slice key = gen.GetRand(thread->rnd, max_key_, max_log_);
+      Slice key = gen.GetRand(thread->rnd, max_key_, FLAGS_skew);
       uint64_t random_op = thread->rnd.Next();
 
-      timer.Start();
+      if (FLAGS_histograms) {
+        timer.Start();
+      }
 
       if (random_op < lookup_insert_threshold_) {
         if (handle) {
@@ -549,12 +628,14 @@ class CacheBench {
         handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
                                 Cache::Priority::LOW);
         if (handle) {
+          ++lookup_hits;
           if (!FLAGS_lean) {
             // do something with the data
             result += NPHash64(static_cast<char*>(cache_->Value(handle)),
                                FLAGS_value_bytes);
           }
         } else {
+          ++lookup_misses;
           // do insert
           Status s = cache_->Insert(key, createValue(thread->rnd), &helper2,
                                     FLAGS_value_bytes, &handle);
@@ -578,11 +659,14 @@ class CacheBench {
         handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
                                 Cache::Priority::LOW);
         if (handle) {
+          ++lookup_hits;
           if (!FLAGS_lean) {
             // do something with the data
             result += NPHash64(static_cast<char*>(cache_->Value(handle)),
                                FLAGS_value_bytes);
           }
+        } else {
+          ++lookup_misses;
         }
       } else if (random_op < erase_threshold_) {
         // do erase
@@ -591,7 +675,14 @@ class CacheBench {
         // Should be extremely unlikely (noop)
         assert(random_op >= kHundredthUint64 * 100U);
       }
-      thread->latency_ns_hist.Add(timer.ElapsedNanos());
+      if (FLAGS_histograms) {
+        thread->latency_ns_hist.Add(timer.ElapsedNanos());
+      }
+      thread->shared->AddLookupStats(lookup_hits, lookup_misses);
+    }
+    if (FLAGS_early_exit) {
+      MutexLock l(thread->shared->GetMutex());
+      exit(0);
     }
     if (handle) {
       cache_->Release(handle);
@@ -613,7 +704,9 @@ class CacheBench {
 #ifndef NDEBUG
     printf("WARNING: Assertions are enabled; benchmarks unnecessarily slow\n");
 #endif
+    printf("----------------------------\n");
     printf("RocksDB version     : %d.%d\n", kMajorVersion, kMinorVersion);
+    printf("Cache impl name     : %s\n", cache_->Name());
     printf("DMutex impl name    : %s\n", DMutex::kName());
     printf("Number of threads   : %u\n", FLAGS_threads);
     printf("Ops per thread      : %" PRIu64 "\n", FLAGS_ops_per_thread);
@@ -952,11 +1045,14 @@ int cache_bench_tool(int argc, char** argv) {
     exit(1);
   }
 
+  if (FLAGS_seed == 0) {
+    FLAGS_seed = static_cast<uint32_t>(port::GetProcessID());
+    printf("Using seed = %" PRIu32 "\n", FLAGS_seed);
+  }
+
   ROCKSDB_NAMESPACE::CacheBench bench;
   if (FLAGS_populate_cache) {
     bench.PopulateCache();
-    printf("Population complete\n");
-    printf("----------------------------\n");
   }
   if (bench.Run()) {
     return 0;