Improve / refactor anonymous mmap capabilities (facebook#10810)

Summary:
The motivation for this change is a planned feature (related to HyperClockCache) that will depend on a large array that can essentially grow automatically, up to some bound, without the pointer address changing and with guaranteed zero-initialization of the data. Anonymous mmaps provide such functionality, and this change provides an internal API for that.

The other existing use of anonymous mmap in RocksDB is for allocating in huge pages. That code and other related Arena code used some awkward non-RAII and pre-C++11 idioms, so I cleaned up much of that as well, with RAII, move semantics, constexpr, etc.

More specifcs:
* Minimize conditional compilation
* Add Windows support for anonymous mmaps
* Use std::deque instead of std::vector for more efficient bag

Pull Request resolved: facebook#10810

Test Plan: unit test added for new functionality

Reviewed By: riversand963

Differential Revision: D40347204

Pulled By: pdillinger

fbshipit-source-id: ca83fcc47e50fabf7595069380edd2954f4f879c

.circleci/config.yml

@@ -584,7 +584,7 @@ jobs:
           name: "Test RocksDB"
           shell: powershell.exe
           command: |
-            build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test,db_test2,db_merge_operand_test,bloom_test,c_test,coding_test,crc32c_test,dynamic_bloom_test,env_basic_test,env_test,hash_test,random_test -Concurrency 16
+            build_tools\run_ci_db_test.ps1 -SuiteRun arena_test,db_basic_test,db_test,db_test2,db_merge_operand_test,bloom_test,c_test,coding_test,crc32c_test,dynamic_bloom_test,env_basic_test,env_test,hash_test,random_test -Concurrency 16
 
   build-linux-java:
     executor: linux-docker

CMakeLists.txt

@@ -796,6 +796,7 @@ set(SOURCES
         options/options.cc
         options/options_helper.cc
         options/options_parser.cc
+        port/mmap.cc
         port/stack_trace.cc
         table/adaptive/adaptive_table_factory.cc
         table/block_based/binary_search_index_reader.cc

TARGETS

@@ -163,6 +163,7 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "options/options.cc",
         "options/options_helper.cc",
         "options/options_parser.cc",
+        "port/mmap.cc",
         "port/port_posix.cc",
         "port/stack_trace.cc",
         "port/win/env_default.cc",
@@ -502,6 +503,7 @@ cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[
         "options/options.cc",
         "options/options_helper.cc",
         "options/options_parser.cc",
+        "port/mmap.cc",
         "port/port_posix.cc",
         "port/stack_trace.cc",
         "port/win/env_default.cc",

db/db_test_util.h

@@ -49,6 +49,9 @@
 #include "util/string_util.h"
 #include "utilities/merge_operators.h"
 
+// In case defined by Windows headers
+#undef small
+
 namespace ROCKSDB_NAMESPACE {
 class MockEnv;
 

db/memtable.cc

@@ -76,7 +76,7 @@ MemTable::MemTable(const InternalKeyComparator& cmp,
     : comparator_(cmp),
       moptions_(ioptions, mutable_cf_options),
       refs_(0),
-      kArenaBlockSize(OptimizeBlockSize(moptions_.arena_block_size)),
+      kArenaBlockSize(Arena::OptimizeBlockSize(moptions_.arena_block_size)),
       mem_tracker_(write_buffer_manager),
       arena_(moptions_.arena_block_size,
              (write_buffer_manager != nullptr &&

memory/arena.cc

@@ -8,9 +8,7 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
 #include "memory/arena.h"
-#ifndef OS_WIN
-#include <sys/mman.h>
-#endif
+
 #include <algorithm>
 
 #include "logging/logging.h"
@@ -22,16 +20,7 @@
 
 namespace ROCKSDB_NAMESPACE {
 
-// MSVC complains that it is already defined since it is static in the header.
-#ifndef _MSC_VER
-const size_t Arena::kInlineSize;
-#endif
-
-const size_t Arena::kMinBlockSize = 4096;
-const size_t Arena::kMaxBlockSize = 2u << 30;
-static const int kAlignUnit = alignof(max_align_t);
-
-size_t OptimizeBlockSize(size_t block_size) {
+size_t Arena::OptimizeBlockSize(size_t block_size) {
   // Make sure block_size is in optimal range
   block_size = std::max(Arena::kMinBlockSize, block_size);
   block_size = std::min(Arena::kMaxBlockSize, block_size);
@@ -53,14 +42,12 @@ Arena::Arena(size_t block_size, AllocTracker* tracker, size_t huge_page_size)
   blocks_memory_ += alloc_bytes_remaining_;
   aligned_alloc_ptr_ = inline_block_;
   unaligned_alloc_ptr_ = inline_block_ + alloc_bytes_remaining_;
-#ifdef MAP_HUGETLB
-  hugetlb_size_ = huge_page_size;
-  if (hugetlb_size_ && kBlockSize > hugetlb_size_) {
-    hugetlb_size_ = ((kBlockSize - 1U) / hugetlb_size_ + 1U) * hugetlb_size_;
+  if (MemMapping::kHugePageSupported) {
+    hugetlb_size_ = huge_page_size;
+    if (hugetlb_size_ && kBlockSize > hugetlb_size_) {
+      hugetlb_size_ = ((kBlockSize - 1U) / hugetlb_size_ + 1U) * hugetlb_size_;
+    }
   }
-#else
-  (void)huge_page_size;
-#endif
   if (tracker_ != nullptr) {
     tracker_->Allocate(kInlineSize);
   }
@@ -71,21 +58,6 @@ Arena::~Arena() {
     assert(tracker_->is_freed());
     tracker_->FreeMem();
   }
-  for (const auto& block : blocks_) {
-    delete[] block;
-  }
-
-#ifdef MAP_HUGETLB
-  for (const auto& mmap_info : huge_blocks_) {
-    if (mmap_info.addr_ == nullptr) {
-      continue;
-    }
-    auto ret = munmap(mmap_info.addr_, mmap_info.length_);
-    if (ret != 0) {
-      // TODO(sdong): Better handling
-    }
-  }
-#endif
 }
 
 char* Arena::AllocateFallback(size_t bytes, bool aligned) {
@@ -99,12 +71,10 @@ char* Arena::AllocateFallback(size_t bytes, bool aligned) {
   // We waste the remaining space in the current block.
   size_t size = 0;
   char* block_head = nullptr;
-#ifdef MAP_HUGETLB
-  if (hugetlb_size_) {
+  if (MemMapping::kHugePageSupported && hugetlb_size_ > 0) {
     size = hugetlb_size_;
     block_head = AllocateFromHugePage(size);
   }
-#endif
   if (!block_head) {
     size = kBlockSize;
     block_head = AllocateNewBlock(size);
@@ -123,45 +93,22 @@ char* Arena::AllocateFallback(size_t bytes, bool aligned) {
 }
 
 char* Arena::AllocateFromHugePage(size_t bytes) {
-#ifdef MAP_HUGETLB
-  if (hugetlb_size_ == 0) {
-    return nullptr;
-  }
-  // Reserve space in `huge_blocks_` before calling `mmap`.
-  // Use `emplace_back()` instead of `reserve()` to let std::vector manage its
-  // own memory and do fewer reallocations.
-  //
-  // - If `emplace_back` throws, no memory leaks because we haven't called
-  //   `mmap` yet.
-  // - If `mmap` throws, no memory leaks because the vector will be cleaned up
-  //   via RAII.
-  huge_blocks_.emplace_back(nullptr /* addr */, 0 /* length */);
-
-  void* addr = mmap(nullptr, bytes, (PROT_READ | PROT_WRITE),
-                    (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB), -1, 0);
-
-  if (addr == MAP_FAILED) {
-    return nullptr;
-  }
-  huge_blocks_.back() = MmapInfo(addr, bytes);
-  blocks_memory_ += bytes;
-  if (tracker_ != nullptr) {
-    tracker_->Allocate(bytes);
+  MemMapping mm = MemMapping::AllocateHuge(bytes);
+  auto addr = static_cast<char*>(mm.Get());
+  if (addr) {
+    huge_blocks_.push_back(std::move(mm));
+    blocks_memory_ += bytes;
+    if (tracker_ != nullptr) {
+      tracker_->Allocate(bytes);
+    }
   }
-  return reinterpret_cast<char*>(addr);
-#else
-  (void)bytes;
-  return nullptr;
-#endif
+  return addr;
 }
 
 char* Arena::AllocateAligned(size_t bytes, size_t huge_page_size,
                              Logger* logger) {
-  assert((kAlignUnit & (kAlignUnit - 1)) ==
-         0);  // Pointer size should be a power of 2
-
-#ifdef MAP_HUGETLB
-  if (huge_page_size > 0 && bytes > 0) {
+  if (MemMapping::kHugePageSupported && hugetlb_size_ > 0 &&
+      huge_page_size > 0 && bytes > 0) {
     // Allocate from a huge page TLB table.
     size_t reserved_size =
         ((bytes - 1U) / huge_page_size + 1U) * huge_page_size;
@@ -177,10 +124,6 @@ char* Arena::AllocateAligned(size_t bytes, size_t huge_page_size,
       return addr;
     }
   }
-#else
-  (void)huge_page_size;
-  (void)logger;
-#endif
 
   size_t current_mod =
       reinterpret_cast<uintptr_t>(aligned_alloc_ptr_) & (kAlignUnit - 1);
@@ -200,17 +143,10 @@ char* Arena::AllocateAligned(size_t bytes, size_t huge_page_size,
 }
 
 char* Arena::AllocateNewBlock(size_t block_bytes) {
-  // Reserve space in `blocks_` before allocating memory via new.
-  // Use `emplace_back()` instead of `reserve()` to let std::vector manage its
-  // own memory and do fewer reallocations.
-  //
-  // - If `emplace_back` throws, no memory leaks because we haven't called `new`
-  //   yet.
-  // - If `new` throws, no memory leaks because the vector will be cleaned up
-  //   via RAII.
-  blocks_.emplace_back(nullptr);
-
-  char* block = new char[block_bytes];
+  auto uniq = std::make_unique<char[]>(block_bytes);
+  char* block = uniq.get();
+  blocks_.push_back(std::move(uniq));
+
   size_t allocated_size;
 #ifdef ROCKSDB_MALLOC_USABLE_SIZE
   allocated_size = malloc_usable_size(block);
@@ -227,7 +163,6 @@ char* Arena::AllocateNewBlock(size_t block_bytes) {
   if (tracker_ != nullptr) {
     tracker_->Allocate(allocated_size);
   }
-  blocks_.back() = block;
   return block;
 }
 

memory/arena.h

@@ -12,16 +12,13 @@
 // size, it uses malloc to directly get the requested size.
 
 #pragma once
-#ifndef OS_WIN
-#include <sys/mman.h>
-#endif
-#include <assert.h>
-#include <stdint.h>
-#include <cerrno>
+
 #include <cstddef>
-#include <vector>
+#include <deque>
+
 #include "memory/allocator.h"
-#include "util/mutexlock.h"
+#include "port/mmap.h"
+#include "rocksdb/env.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -31,9 +28,13 @@ class Arena : public Allocator {
   Arena(const Arena&) = delete;
   void operator=(const Arena&) = delete;
 
-  static const size_t kInlineSize = 2048;
-  static const size_t kMinBlockSize;
-  static const size_t kMaxBlockSize;
+  static constexpr size_t kInlineSize = 2048;
+  static constexpr size_t kMinBlockSize = 4096;
+  static constexpr size_t kMaxBlockSize = 2u << 30;
+
+  static constexpr unsigned kAlignUnit = alignof(std::max_align_t);
+  static_assert((kAlignUnit & (kAlignUnit - 1)) == 0,
+                "Pointer size should be power of 2");
 
   // huge_page_size: if 0, don't use huge page TLB. If > 0 (should set to the
   // supported hugepage size of the system), block allocation will try huge
@@ -63,7 +64,7 @@ class Arena : public Allocator {
   // by the arena (exclude the space allocated but not yet used for future
   // allocations).
   size_t ApproximateMemoryUsage() const {
-    return blocks_memory_ + blocks_.capacity() * sizeof(char*) -
+    return blocks_memory_ + blocks_.size() * sizeof(char*) -
            alloc_bytes_remaining_;
   }
 
@@ -81,21 +82,19 @@ class Arena : public Allocator {
     return blocks_.empty() && huge_blocks_.empty();
   }
 
+  // check and adjust the block_size so that the return value is
+  //  1. in the range of [kMinBlockSize, kMaxBlockSize].
+  //  2. the multiple of align unit.
+  static size_t OptimizeBlockSize(size_t block_size);
+
  private:
-  char inline_block_[kInlineSize] __attribute__((__aligned__(alignof(max_align_t))));
+  alignas(std::max_align_t) char inline_block_[kInlineSize];
   // Number of bytes allocated in one block
   const size_t kBlockSize;
-  // Array of new[] allocated memory blocks
-  using Blocks = std::vector<char*>;
-  Blocks blocks_;
-
-  struct MmapInfo {
-    void* addr_;
-    size_t length_;
-
-    MmapInfo(void* addr, size_t length) : addr_(addr), length_(length) {}
-  };
-  std::vector<MmapInfo> huge_blocks_;
+  // Allocated memory blocks
+  std::deque<std::unique_ptr<char[]>> blocks_;
+  // Huge page allocations
+  std::deque<MemMapping> huge_blocks_;
   size_t irregular_block_num = 0;
 
   // Stats for current active block.
@@ -108,15 +107,15 @@ class Arena : public Allocator {
   // How many bytes left in currently active block?
   size_t alloc_bytes_remaining_ = 0;
 
-#ifdef MAP_HUGETLB
   size_t hugetlb_size_ = 0;
-#endif  // MAP_HUGETLB
+
   char* AllocateFromHugePage(size_t bytes);
   char* AllocateFallback(size_t bytes, bool aligned);
   char* AllocateNewBlock(size_t block_bytes);
 
   // Bytes of memory in blocks allocated so far
   size_t blocks_memory_ = 0;
+  // Non-owned
   AllocTracker* tracker_;
 };
 
@@ -133,9 +132,4 @@ inline char* Arena::Allocate(size_t bytes) {
   return AllocateFallback(bytes, false /* unaligned */);
 }
 
-// check and adjust the block_size so that the return value is
-//  1. in the range of [kMinBlockSize, kMaxBlockSize].
-//  2. the multiple of align unit.
-extern size_t OptimizeBlockSize(size_t block_size);
-
 }  // namespace ROCKSDB_NAMESPACE