@nxtedition/rocksdb 5.2.1 → 5.2.2

package/deps/rocksdb/rocksdb/port/jemalloc_helper.h

@@ -0,0 +1,106 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#if defined(__clang__)
+// glibc's `posix_memalign()` declaration specifies `throw()` while clang's
+// declaration does not. There is a hack in clang to make its re-declaration
+// compatible with glibc's if they are declared consecutively. That hack breaks
+// if yet another `posix_memalign()` declaration comes between glibc's and
+// clang's declarations. Include "mm_malloc.h" here ensures glibc's and clang's
+// declarations both come before "jemalloc.h"'s `posix_memalign()` declaration.
+//
+// This problem could also be avoided if "jemalloc.h"'s `posix_memalign()`
+// declaration did not specify `throw()` when built with clang.
+#include <mm_malloc.h>
+#endif
+
+#ifdef ROCKSDB_JEMALLOC
+#ifdef __FreeBSD__
+#include <malloc_np.h>
+#else
+#define JEMALLOC_MANGLE
+#include <jemalloc/jemalloc.h>
+#endif
+
+#ifndef JEMALLOC_CXX_THROW
+#define JEMALLOC_CXX_THROW
+#endif
+
+#if defined(OS_WIN) && defined(_MSC_VER)
+
+// MSVC does not have weak symbol support. As long as ROCKSDB_JEMALLOC is
+// defined, Jemalloc memory allocator is used.
+static inline bool HasJemalloc() { return true; }
+
+#else
+
+// definitions for compatibility with older versions of jemalloc
+#if !defined(JEMALLOC_ALLOCATOR)
+#define JEMALLOC_ALLOCATOR
+#endif
+#if !defined(JEMALLOC_RESTRICT_RETURN)
+#define JEMALLOC_RESTRICT_RETURN
+#endif
+#if !defined(JEMALLOC_NOTHROW)
+#define JEMALLOC_NOTHROW JEMALLOC_ATTR(nothrow)
+#endif
+#if !defined(JEMALLOC_ALLOC_SIZE)
+#ifdef JEMALLOC_HAVE_ATTR_ALLOC_SIZE
+#define JEMALLOC_ALLOC_SIZE(s) JEMALLOC_ATTR(alloc_size(s))
+#else
+#define JEMALLOC_ALLOC_SIZE(s)
+#endif
+#endif
+
+// Declare non-standard jemalloc APIs as weak symbols. We can null-check these
+// symbols to detect whether jemalloc is linked with the binary.
+extern "C" JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW *
+mallocx(size_t, int) JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1)
+    __attribute__((__weak__));
+extern "C" JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN void JEMALLOC_NOTHROW *
+rallocx(void *, size_t, int) JEMALLOC_ALLOC_SIZE(2) __attribute__((__weak__));
+extern "C" size_t JEMALLOC_NOTHROW xallocx(void *, size_t, size_t, int)
+    __attribute__((__weak__));
+extern "C" size_t JEMALLOC_NOTHROW sallocx(const void *, int)
+    JEMALLOC_ATTR(pure) __attribute__((__weak__));
+extern "C" void JEMALLOC_NOTHROW dallocx(void *, int) __attribute__((__weak__));
+extern "C" void JEMALLOC_NOTHROW sdallocx(void *, size_t, int)
+    __attribute__((__weak__));
+extern "C" size_t JEMALLOC_NOTHROW nallocx(size_t, int) JEMALLOC_ATTR(pure)
+    __attribute__((__weak__));
+extern "C" int JEMALLOC_NOTHROW mallctl(const char *, void *, size_t *, void *,
+                                        size_t) __attribute__((__weak__));
+extern "C" int JEMALLOC_NOTHROW mallctlnametomib(const char *, size_t *,
+                                                 size_t *)
+    __attribute__((__weak__));
+extern "C" int JEMALLOC_NOTHROW mallctlbymib(const size_t *, size_t, void *,
+                                             size_t *, void *, size_t)
+    __attribute__((__weak__));
+extern "C" void JEMALLOC_NOTHROW
+malloc_stats_print(void (*)(void *, const char *), void *, const char *)
+    __attribute__((__weak__));
+extern "C" size_t JEMALLOC_NOTHROW
+malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *) JEMALLOC_CXX_THROW
+    __attribute__((__weak__));
+
+// Check if Jemalloc is linked with the binary. Note the main program might be
+// using a different memory allocator even this method return true.
+// It is loosely based on folly::usingJEMalloc(), minus the check that actually
+// allocate memory and see if it is through jemalloc, to handle the dlopen()
+// case:
+// https://github.com/facebook/folly/blob/76cf8b5841fb33137cfbf8b224f0226437c855bc/folly/memory/Malloc.h#L147
+static inline bool HasJemalloc() {
+  return mallocx != nullptr && rallocx != nullptr && xallocx != nullptr &&
+         sallocx != nullptr && dallocx != nullptr && sdallocx != nullptr &&
+         nallocx != nullptr && mallctl != nullptr &&
+         mallctlnametomib != nullptr && mallctlbymib != nullptr &&
+         malloc_stats_print != nullptr && malloc_usable_size != nullptr;
+}
+
+#endif
+
+#endif  // ROCKSDB_JEMALLOC

package/deps/rocksdb/rocksdb/port/lang.h

@@ -0,0 +1,16 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#ifndef FALLTHROUGH_INTENDED
+#if defined(__clang__)
+#define FALLTHROUGH_INTENDED [[clang::fallthrough]]
+#elif defined(__GNUC__) && __GNUC__ >= 7
+#define FALLTHROUGH_INTENDED [[gnu::fallthrough]]
+#else
+#define FALLTHROUGH_INTENDED do {} while (0)
+#endif
+#endif

package/deps/rocksdb/rocksdb/port/likely.h

@@ -0,0 +1,18 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// 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.
+
+#pragma once
+
+#if defined(__GNUC__) && __GNUC__ >= 4
+#define LIKELY(x)   (__builtin_expect((x), 1))
+#define UNLIKELY(x) (__builtin_expect((x), 0))
+#else
+#define LIKELY(x)   (x)
+#define UNLIKELY(x) (x)
+#endif

package/deps/rocksdb/rocksdb/port/malloc.h

@@ -0,0 +1,17 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// 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.
+#pragma once
+
+#ifdef ROCKSDB_MALLOC_USABLE_SIZE
+#ifdef OS_FREEBSD
+#include <malloc_np.h>
+#else
+#include <malloc.h>
+#endif  // OS_FREEBSD
+#endif  // ROCKSDB_MALLOC_USABLE_SIZE

package/deps/rocksdb/rocksdb/port/port.h

@@ -0,0 +1,21 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// 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.
+
+#pragma once
+
+#include <string>
+
+// Include the appropriate platform specific file below.  If you are
+// porting to a new platform, see "port_example.h" for documentation
+// of what the new port_<platform>.h file must provide.
+#if defined(ROCKSDB_PLATFORM_POSIX)
+#include "port/port_posix.h"
+#elif defined(OS_WIN)
+#include "port/win/port_win.h"
+#endif

package/deps/rocksdb/rocksdb/port/port_dirent.h

@@ -0,0 +1,44 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// 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.
+//
+// See port_example.h for documentation for the following types/functions.
+
+#pragma once
+
+#ifdef ROCKSDB_PLATFORM_POSIX
+#include <dirent.h>
+#include <sys/types.h>
+#elif defined(OS_WIN)
+
+namespace ROCKSDB_NAMESPACE {
+namespace port {
+
+struct dirent {
+  char d_name[_MAX_PATH]; /* filename */
+};
+
+struct DIR;
+
+DIR* opendir(const char* name);
+
+dirent* readdir(DIR* dirp);
+
+int closedir(DIR* dirp);
+
+}  // namespace port
+
+using port::dirent;
+using port::DIR;
+using port::opendir;
+using port::readdir;
+using port::closedir;
+
+}  // namespace ROCKSDB_NAMESPACE
+
+#endif  // OS_WIN

package/deps/rocksdb/rocksdb/port/port_example.h

@@ -0,0 +1,101 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// 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.
+//
+// This file contains the specification, but not the implementations,
+// of the types/operations/etc. that should be defined by a platform
+// specific port_<platform>.h file.  Use this file as a reference for
+// how to port this package to a new platform.
+
+#pragma once
+
+namespace ROCKSDB_NAMESPACE {
+namespace port {
+
+// TODO(jorlow): Many of these belong more in the environment class rather than
+//               here. We should try moving them and see if it affects perf.
+
+// The following boolean constant must be true on a little-endian machine
+// and false otherwise.
+static const bool kLittleEndian = true /* or some other expression */;
+
+// ------------------ Threading -------------------
+
+// A Mutex represents an exclusive lock.
+class Mutex {
+ public:
+  Mutex();
+  ~Mutex();
+
+  // Lock the mutex.  Waits until other lockers have exited.
+  // Will deadlock if the mutex is already locked by this thread.
+  void Lock();
+
+  // Unlock the mutex.
+  // REQUIRES: This mutex was locked by this thread.
+  void Unlock();
+
+  // Optionally crash if this thread does not hold this mutex.
+  // The implementation must be fast, especially if NDEBUG is
+  // defined.  The implementation is allowed to skip all checks.
+  void AssertHeld();
+};
+
+class CondVar {
+ public:
+  explicit CondVar(Mutex* mu);
+  ~CondVar();
+
+  // Atomically release *mu and block on this condition variable until
+  // either a call to SignalAll(), or a call to Signal() that picks
+  // this thread to wakeup.
+  // REQUIRES: this thread holds *mu
+  void Wait();
+
+  // If there are some threads waiting, wake up at least one of them.
+  void Signal();
+
+  // Wake up all waiting threads.
+  void SignallAll();
+};
+
+// Thread-safe initialization.
+// Used as follows:
+//      static port::OnceType init_control = LEVELDB_ONCE_INIT;
+//      static void Initializer() { ... do something ...; }
+//      ...
+//      port::InitOnce(&init_control, &Initializer);
+typedef intptr_t OnceType;
+#define LEVELDB_ONCE_INIT 0
+extern void InitOnce(port::OnceType*, void (*initializer)());
+
+// ------------------ Compression -------------------
+
+// Store the snappy compression of "input[0,input_length-1]" in *output.
+// Returns false if snappy is not supported by this port.
+extern bool Snappy_Compress(const char* input, size_t input_length,
+                            std::string* output);
+
+// If input[0,input_length-1] looks like a valid snappy compressed
+// buffer, store the size of the uncompressed data in *result and
+// return true.  Else return false.
+extern bool Snappy_GetUncompressedLength(const char* input, size_t length,
+                                         size_t* result);
+
+// Attempt to snappy uncompress input[0,input_length-1] into *output.
+// Returns true if successful, false if the input is invalid lightweight
+// compressed data.
+//
+// REQUIRES: at least the first "n" bytes of output[] must be writable
+// where "n" is the result of a successful call to
+// Snappy_GetUncompressedLength.
+extern bool Snappy_Uncompress(const char* input_data, size_t input_length,
+                              char* output);
+
+}  // namespace port
+}  // namespace ROCKSDB_NAMESPACE

package/deps/rocksdb/rocksdb/port/port_posix.cc

@@ -0,0 +1,266 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// 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.
+
+#if !defined(OS_WIN)
+
+#include "port/port_posix.h"
+
+#include <assert.h>
+#if defined(__i386__) || defined(__x86_64__)
+#include <cpuid.h>
+#endif
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <cstdlib>
+
+namespace ROCKSDB_NAMESPACE {
+
+// We want to give users opportunity to default all the mutexes to adaptive if
+// not specified otherwise. This enables a quick way to conduct various
+// performance related experiements.
+//
+// NB! Support for adaptive mutexes is turned on by definining
+// ROCKSDB_PTHREAD_ADAPTIVE_MUTEX during the compilation. If you use RocksDB
+// build environment then this happens automatically; otherwise it's up to the
+// consumer to define the identifier.
+#ifdef ROCKSDB_DEFAULT_TO_ADAPTIVE_MUTEX
+extern const bool kDefaultToAdaptiveMutex = true;
+#else
+extern const bool kDefaultToAdaptiveMutex = false;
+#endif
+
+namespace port {
+
+static int PthreadCall(const char* label, int result) {
+  if (result != 0 && result != ETIMEDOUT) {
+    fprintf(stderr, "pthread %s: %s\n", label, strerror(result));
+    abort();
+  }
+  return result;
+}
+
+Mutex::Mutex(bool adaptive) {
+  (void) adaptive;
+#ifdef ROCKSDB_PTHREAD_ADAPTIVE_MUTEX
+  if (!adaptive) {
+    PthreadCall("init mutex", pthread_mutex_init(&mu_, nullptr));
+  } else {
+    pthread_mutexattr_t mutex_attr;
+    PthreadCall("init mutex attr", pthread_mutexattr_init(&mutex_attr));
+    PthreadCall("set mutex attr",
+                pthread_mutexattr_settype(&mutex_attr,
+                                          PTHREAD_MUTEX_ADAPTIVE_NP));
+    PthreadCall("init mutex", pthread_mutex_init(&mu_, &mutex_attr));
+    PthreadCall("destroy mutex attr",
+                pthread_mutexattr_destroy(&mutex_attr));
+  }
+#else
+  PthreadCall("init mutex", pthread_mutex_init(&mu_, nullptr));
+#endif // ROCKSDB_PTHREAD_ADAPTIVE_MUTEX
+}
+
+Mutex::~Mutex() { PthreadCall("destroy mutex", pthread_mutex_destroy(&mu_)); }
+
+void Mutex::Lock() {
+  PthreadCall("lock", pthread_mutex_lock(&mu_));
+#ifndef NDEBUG
+  locked_ = true;
+#endif
+}
+
+void Mutex::Unlock() {
+#ifndef NDEBUG
+  locked_ = false;
+#endif
+  PthreadCall("unlock", pthread_mutex_unlock(&mu_));
+}
+
+void Mutex::AssertHeld() {
+#ifndef NDEBUG
+  assert(locked_);
+#endif
+}
+
+CondVar::CondVar(Mutex* mu)
+    : mu_(mu) {
+    PthreadCall("init cv", pthread_cond_init(&cv_, nullptr));
+}
+
+CondVar::~CondVar() { PthreadCall("destroy cv", pthread_cond_destroy(&cv_)); }
+
+void CondVar::Wait() {
+#ifndef NDEBUG
+  mu_->locked_ = false;
+#endif
+  PthreadCall("wait", pthread_cond_wait(&cv_, &mu_->mu_));
+#ifndef NDEBUG
+  mu_->locked_ = true;
+#endif
+}
+
+bool CondVar::TimedWait(uint64_t abs_time_us) {
+  struct timespec ts;
+  ts.tv_sec = static_cast<time_t>(abs_time_us / 1000000);
+  ts.tv_nsec = static_cast<suseconds_t>((abs_time_us % 1000000) * 1000);
+
+#ifndef NDEBUG
+  mu_->locked_ = false;
+#endif
+  int err = pthread_cond_timedwait(&cv_, &mu_->mu_, &ts);
+#ifndef NDEBUG
+  mu_->locked_ = true;
+#endif
+  if (err == ETIMEDOUT) {
+    return true;
+  }
+  if (err != 0) {
+    PthreadCall("timedwait", err);
+  }
+  return false;
+}
+
+void CondVar::Signal() {
+  PthreadCall("signal", pthread_cond_signal(&cv_));
+}
+
+void CondVar::SignalAll() {
+  PthreadCall("broadcast", pthread_cond_broadcast(&cv_));
+}
+
+RWMutex::RWMutex() {
+  PthreadCall("init mutex", pthread_rwlock_init(&mu_, nullptr));
+}
+
+RWMutex::~RWMutex() { PthreadCall("destroy mutex", pthread_rwlock_destroy(&mu_)); }
+
+void RWMutex::ReadLock() { PthreadCall("read lock", pthread_rwlock_rdlock(&mu_)); }
+
+void RWMutex::WriteLock() { PthreadCall("write lock", pthread_rwlock_wrlock(&mu_)); }
+
+void RWMutex::ReadUnlock() { PthreadCall("read unlock", pthread_rwlock_unlock(&mu_)); }
+
+void RWMutex::WriteUnlock() { PthreadCall("write unlock", pthread_rwlock_unlock(&mu_)); }
+
+int PhysicalCoreID() {
+#if defined(ROCKSDB_SCHED_GETCPU_PRESENT) && defined(__x86_64__) && \
+    (__GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 22))
+  // sched_getcpu uses VDSO getcpu() syscall since 2.22. I believe Linux offers VDSO
+  // support only on x86_64. This is the fastest/preferred method if available.
+  int cpuno = sched_getcpu();
+  if (cpuno < 0) {
+    return -1;
+  }
+  return cpuno;
+#elif defined(__x86_64__) || defined(__i386__)
+  // clang/gcc both provide cpuid.h, which defines __get_cpuid(), for x86_64 and i386.
+  unsigned eax, ebx = 0, ecx, edx;
+  if (!__get_cpuid(1, &eax, &ebx, &ecx, &edx)) {
+    return -1;
+  }
+  return ebx >> 24;
+#else
+  // give up, the caller can generate a random number or something.
+  return -1;
+#endif
+}
+
+void InitOnce(OnceType* once, void (*initializer)()) {
+  PthreadCall("once", pthread_once(once, initializer));
+}
+
+void Crash(const std::string& srcfile, int srcline) {
+  fprintf(stdout, "Crashing at %s:%d\n", srcfile.c_str(), srcline);
+  fflush(stdout);
+  kill(getpid(), SIGTERM);
+}
+
+int GetMaxOpenFiles() {
+#if defined(RLIMIT_NOFILE)
+  struct rlimit no_files_limit;
+  if (getrlimit(RLIMIT_NOFILE, &no_files_limit) != 0) {
+    return -1;
+  }
+  // protect against overflow
+  if (static_cast<uintmax_t>(no_files_limit.rlim_cur) >=
+      static_cast<uintmax_t>(std::numeric_limits<int>::max())) {
+    return std::numeric_limits<int>::max();
+  }
+  return static_cast<int>(no_files_limit.rlim_cur);
+#endif
+  return -1;
+}
+
+void *cacheline_aligned_alloc(size_t size) {
+#if __GNUC__ < 5 && defined(__SANITIZE_ADDRESS__)
+  return malloc(size);
+#elif ( _POSIX_C_SOURCE >= 200112L || _XOPEN_SOURCE >= 600 || defined(__APPLE__))
+  void *m;
+  errno = posix_memalign(&m, CACHE_LINE_SIZE, size);
+  return errno ? nullptr : m;
+#else
+  return malloc(size);
+#endif
+}
+
+void cacheline_aligned_free(void *memblock) {
+  free(memblock);
+}
+
+static size_t GetPageSize() {
+#if defined(OS_LINUX) || defined(_SC_PAGESIZE)
+  long v = sysconf(_SC_PAGESIZE);
+  if (v >= 1024) {
+    return static_cast<size_t>(v);
+  }
+#endif
+  // Default assume 4KB
+  return 4U * 1024U;
+}
+
+const size_t kPageSize = GetPageSize();
+
+void SetCpuPriority(ThreadId id, CpuPriority priority) {
+#ifdef OS_LINUX
+  sched_param param;
+  param.sched_priority = 0;
+  switch (priority) {
+    case CpuPriority::kHigh:
+      sched_setscheduler(id, SCHED_OTHER, &param);
+      setpriority(PRIO_PROCESS, id, -20);
+      break;
+    case CpuPriority::kNormal:
+      sched_setscheduler(id, SCHED_OTHER, &param);
+      setpriority(PRIO_PROCESS, id, 0);
+      break;
+    case CpuPriority::kLow:
+      sched_setscheduler(id, SCHED_OTHER, &param);
+      setpriority(PRIO_PROCESS, id, 19);
+      break;
+    case CpuPriority::kIdle:
+      sched_setscheduler(id, SCHED_IDLE, &param);
+      break;
+    default:
+      assert(false);
+  }
+#else
+  (void)id;
+  (void)priority;
+#endif
+}
+
+}  // namespace port
+}  // namespace ROCKSDB_NAMESPACE
+
+#endif