Add script to build .pkg file for macos

According to
https://cmake.org/cmake/help/latest/command/add_custom_command.html this
more accurately matches the intent

.gitignore

@@ -1,2 +1,3 @@
 .cache
+__pycache__
 build

.pre-commit-config.yaml

@@ -1,11 +1,11 @@
 repos:
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: b111689e7b5cba60be3c62d5db2bd1357f4d36ca
+    rev: 6d365699efc33b1b432eab5b4ae331a19e1857de # frozen: v18.1.2
     hooks:
       - id: clang-format
         exclude: ".*third_party/.*"
   - repo: https://github.com/cheshirekow/cmake-format-precommit
-    rev: e2c2116d86a80e72e7146a06e68b7c228afc6319
+    rev: e2c2116d86a80e72e7146a06e68b7c228afc6319 # frozen: v0.6.13
     hooks:
       - id: cmake-format
   - repo: local
@@ -13,7 +13,7 @@ repos:
       - id: debug verbose check
         name: disallow checking in DEBUG_VERBOSE=1
         description: disallow checking in DEBUG_VERBOSE=1
-        entry: '^#define DEBUG_VERBOSE 1$'
+        entry: "^#define DEBUG_VERBOSE 1$"
         language: pygrep
         types: [c++]
   - repo: local
@@ -21,6 +21,14 @@ repos:
       - id: debug verbose check
         name: disallow checking in SHOW_MEMORY=1
         description: disallow checking in SHOW_MEMORY=1
-        entry: '^#define SHOW_MEMORY 1$'
+        entry: "^#define SHOW_MEMORY 1$"
         language: pygrep
         types: [c++]
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: a23f6b85d0fdd5bb9d564e2579e678033debbdff # frozen: v0.10.0.1
+    hooks:
+      - id: shellcheck
+  - repo: https://github.com/psf/black
+    rev: 552baf822992936134cbd31a38f69c8cfe7c0f05 # frozen: 24.3.0
+    hooks:
+      - id: black

Bench.cpp

@@ -34,7 +34,7 @@ ConflictSet::ReadRange singleton(Arena &arena, std::span<const uint8_t> key) {
       std::span<uint8_t>(new (arena) uint8_t[key.size() + 1], key.size() + 1);
   memcpy(r.data(), key.data(), key.size());
   r[key.size()] = 0;
-  return {key.data(), int(key.size()), r.data(), int(r.size())};
+  return {{key.data(), int(key.size())}, {r.data(), int(r.size())}, 0};
 }
 
 ConflictSet::ReadRange prefixRange(Arena &arena, std::span<const uint8_t> key) {
@@ -52,7 +52,7 @@ ConflictSet::ReadRange prefixRange(Arena &arena, std::span<const uint8_t> key) {
   auto r = std::span<uint8_t>(new (arena) uint8_t[index + 1], index + 1);
   memcpy(r.data(), key.data(), index + 1);
   r[r.size() - 1]++;
-  return {key.data(), int(key.size()), r.data(), int(r.size())};
+  return {{key.data(), int(key.size())}, {r.data(), int(r.size())}, 0};
 }
 
 void benchConflictSet() {

CMakeLists.txt

@@ -1,15 +1,28 @@
 cmake_minimum_required(VERSION 3.18)
 project(
-  conflict_set
+  conflict-set
-  VERSION 0.0.1
+  VERSION 0.0.3
   DESCRIPTION
     "A data structure for optimistic concurrency control on ranges of bitwise-lexicographically-ordered keys."
   HOMEPAGE_URL "https://git.weaselab.dev/weaselab/conflict-set"
   LANGUAGES C CXX)
 set(CMAKE_CXX_STANDARD 20)
 
+file(WRITE ${CMAKE_BINARY_DIR}/version.txt ${PROJECT_VERSION})
+
+include(CMakePushCheckState)
+include(CheckCXXCompilerFlag)
+include(CheckIncludeFileCXX)
+include(CheckCXXSourceCompiles)
+
 set(DEFAULT_BUILD_TYPE "Release")
 
+if(EMSCRIPTEN OR CMAKE_SYSTEM_NAME STREQUAL WASI)
+  set(WASM ON)
+else()
+  set(WASM OFF)
+endif()
+
 if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
   message(
     STATUS
@@ -23,16 +36,32 @@ if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
 endif()
 
 add_compile_options(-fdata-sections -ffunction-sections -Wswitch-enum
-                    -Werror=switch-enum)
+                    -Werror=switch-enum -fPIC)
+
+set(full_relro_flags "-pie;LINKER:-z,relro,-z,now,-z,noexecstack")
+cmake_push_check_state()
+list(APPEND CMAKE_REQUIRED_LINK_OPTIONS ${full_relro_flags})
+check_cxx_source_compiles("int main(){}" HAS_FULL_RELRO FAIL_REGEX "warning:")
+if(HAS_FULL_RELRO)
+  add_link_options(${full_relro_flags})
+endif()
+cmake_pop_check_state()
+
+set(version_script_flags LINKER:--version-script=${CMAKE_SOURCE_DIR}/linker.map)
+cmake_push_check_state()
+list(APPEND CMAKE_REQUIRED_LINK_OPTIONS ${version_script_flags})
+check_cxx_source_compiles("int main(){}" HAS_VERSION_SCRIPT FAIL_REGEX
+                          "warning:")
+cmake_pop_check_state()
+
+option(USE_SIMD_FALLBACK
+       "Use fallback implementations of functions that use SIMD" OFF)
 
 # This is encouraged according to
 # https://valgrind.org/docs/manual/manual-core-adv.html#manual-core-adv.clientreq
 include_directories(SYSTEM ${CMAKE_SOURCE_DIR}/third_party/valgrind)
 
-if(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+add_compile_options($<$<COMPILE_LANGUAGE:CXX>:-Wno-invalid-offsetof>)
-  add_compile_options(-Wno-maybe-uninitialized
-                      $<$<COMPILE_LANGUAGE:CXX>:-Wno-invalid-offsetof>)
-endif()
 
 if(APPLE)
   add_link_options(-Wl,-dead_strip)
@@ -40,32 +69,46 @@ else()
   add_link_options(-Wl,--gc-sections)
 endif()
 
-include(CheckIncludeFileCXX)
+if(EMSCRIPTEN)
-include(CMakePushCheckState)
+  # https://github.com/emscripten-core/emscripten/issues/15377#issuecomment-1285167486
-
+  add_link_options(-lnodefs.js -lnoderawfs.js)
-cmake_push_check_state()
+  add_link_options(-s ALLOW_MEMORY_GROWTH)
-list(APPEND CMAKE_REQUIRED_FLAGS -mavx)
-check_include_file_cxx("immintrin.h" HAS_AVX)
-if(HAS_AVX)
-  add_compile_options(-mavx)
-  add_compile_definitions(HAS_AVX)
 endif()
-cmake_pop_check_state()
 
-check_include_file_cxx("arm_neon.h" HAS_ARM_NEON)
+if(NOT USE_SIMD_FALLBACK)
-if(HAS_ARM_NEON)
+  cmake_push_check_state()
-  add_compile_definitions(HAS_ARM_NEON)
+  list(APPEND CMAKE_REQUIRED_FLAGS -msimd128)
+  check_include_file_cxx("wasm_simd128.h" HAS_WASM_SIMD)
+  if(HAS_WASM_SIMD)
+    add_compile_options(-msimd128)
+    add_compile_definitions(HAS_WASM_SIMD)
+  endif()
+  cmake_pop_check_state()
+
+  cmake_push_check_state()
+  list(APPEND CMAKE_REQUIRED_FLAGS -mavx)
+  check_include_file_cxx("immintrin.h" HAS_AVX)
+  if(HAS_AVX)
+    add_compile_options(-mavx)
+    add_compile_definitions(HAS_AVX)
+  endif()
+  cmake_pop_check_state()
+
+  check_include_file_cxx("arm_neon.h" HAS_ARM_NEON)
+  if(HAS_ARM_NEON)
+    add_compile_definitions(HAS_ARM_NEON)
+  endif()
 endif()
 
 set(CMAKE_CXX_IMPLICIT_LINK_LIBRARIES "")
 
-add_library(${PROJECT_NAME}_object OBJECT ConflictSet.cpp)
+add_library(${PROJECT_NAME}-object OBJECT ConflictSet.cpp)
-target_compile_options(${PROJECT_NAME}_object PRIVATE -fPIC -fno-exceptions
+target_compile_options(${PROJECT_NAME}-object PRIVATE -fno-exceptions
                                                       -fvisibility=hidden)
-target_include_directories(${PROJECT_NAME}_object
+target_include_directories(${PROJECT_NAME}-object
                            PRIVATE ${CMAKE_SOURCE_DIR}/include)
 
-add_library(${PROJECT_NAME} SHARED $<TARGET_OBJECTS:${PROJECT_NAME}_object>)
+add_library(${PROJECT_NAME} SHARED $<TARGET_OBJECTS:${PROJECT_NAME}-object>)
 set_target_properties(
   ${PROJECT_NAME} PROPERTIES LIBRARY_OUTPUT_DIRECTORY
                              "${CMAKE_BINARY_DIR}/radix_tree")
@@ -73,24 +116,32 @@ if(NOT CMAKE_BUILD_TYPE STREQUAL Debug)
   set_target_properties(${PROJECT_NAME} PROPERTIES LINKER_LANGUAGE C)
 endif()
 
-if(NOT APPLE)
+if(HAS_VERSION_SCRIPT)
   target_link_options(${PROJECT_NAME} PRIVATE
                       LINKER:--version-script=${CMAKE_SOURCE_DIR}/linker.map)
 endif()
 
-add_library(${PROJECT_NAME}_static STATIC
+add_library(${PROJECT_NAME}-static STATIC
-            $<TARGET_OBJECTS:${PROJECT_NAME}_object>)
+            $<TARGET_OBJECTS:${PROJECT_NAME}-object>)
 if(NOT CMAKE_BUILD_TYPE STREQUAL Debug)
-  set_target_properties(${PROJECT_NAME}_static PROPERTIES LINKER_LANGUAGE C)
+  set_target_properties(${PROJECT_NAME}-static PROPERTIES LINKER_LANGUAGE C)
 endif()
 
-if(NOT APPLE AND CMAKE_OBJCOPY)
+if(APPLE)
   add_custom_command(
-    TARGET conflict_set_static
+    TARGET ${PROJECT_NAME}-static
+    PRE_LINK
+    COMMAND ${CMAKE_SOURCE_DIR}/privatize_symbols_macos.sh
+            $<TARGET_OBJECTS:${PROJECT_NAME}-object>)
+else()
+  add_custom_command(
+    TARGET ${PROJECT_NAME}-static
     POST_BUILD
     COMMAND
-      ${CMAKE_OBJCOPY} --keep-global-symbols=${CMAKE_SOURCE_DIR}/symbols.txt
+      ${CMAKE_OBJCOPY}
-      $<TARGET_FILE:${PROJECT_NAME}_static>)
+      --keep-global-symbols=${CMAKE_SOURCE_DIR}/symbol-exports.txt
+      $<TARGET_FILE:${PROJECT_NAME}-static> || echo
+      "Proceeding with all symbols global in static library")
 endif()
 
 set(TEST_FLAGS -Wall -Wextra -Wunreachable-code -Wpedantic -UNDEBUG)
@@ -99,30 +150,51 @@ include(CTest)
 
 if(BUILD_TESTING)
 
-  # Shared library version of FoundationDB's skip list implementation
+  # corpus tests, which are tests curated by libfuzzer. The goal is to get broad
-  add_library(skip_list SHARED SkipList.cpp)
+  # coverage with a small number of tests.
-  target_compile_options(skip_list PRIVATE -fPIC -fno-exceptions
-                                           -fvisibility=hidden)
-  target_include_directories(skip_list PUBLIC ${CMAKE_SOURCE_DIR}/include)
-  set_target_properties(skip_list PROPERTIES LIBRARY_OUTPUT_DIRECTORY
-                                             "${CMAKE_BINARY_DIR}/skip_list")
-  set_target_properties(skip_list PROPERTIES OUTPUT_NAME ${PROJECT_NAME})
-  set_target_properties(skip_list PROPERTIES VERSION ${PROJECT_VERSION}
-                                             SOVERSION ${PROJECT_VERSION_MAJOR})
 
-  # Shared library version of a std::unordered_map-based conflict set (point
+  file(GLOB CORPUS_TESTS ${CMAKE_SOURCE_DIR}/corpus/*)
-  # queries only)
-  add_library(hash_table SHARED HashTable.cpp)
-  target_compile_options(hash_table PRIVATE -fPIC -fno-exceptions
-                                            -fvisibility=hidden)
-  target_include_directories(hash_table PUBLIC ${CMAKE_SOURCE_DIR}/include)
-  set_target_properties(hash_table PROPERTIES LIBRARY_OUTPUT_DIRECTORY
-                                              "${CMAKE_BINARY_DIR}/hash_table")
-  set_target_properties(hash_table PROPERTIES OUTPUT_NAME ${PROJECT_NAME})
-  set_target_properties(
-    hash_table PROPERTIES VERSION ${PROJECT_VERSION} SOVERSION
-                                                     ${PROJECT_VERSION_MAJOR})
 
+  # extra testing that relies on shared libraries, which aren't available with
+  # wasm
+  if(NOT WASM)
+    # Shared library version of FoundationDB's skip list implementation
+    add_library(skip_list SHARED SkipList.cpp)
+    target_compile_options(skip_list PRIVATE -fno-exceptions
+                                             -fvisibility=hidden)
+    target_include_directories(skip_list PUBLIC ${CMAKE_SOURCE_DIR}/include)
+    set_target_properties(skip_list PROPERTIES LIBRARY_OUTPUT_DIRECTORY
+                                               "${CMAKE_BINARY_DIR}/skip_list")
+    set_target_properties(skip_list PROPERTIES OUTPUT_NAME ${PROJECT_NAME})
+    set_target_properties(
+      skip_list PROPERTIES VERSION ${PROJECT_VERSION} SOVERSION
+                                                      ${PROJECT_VERSION_MAJOR})
+
+    # Shared library version of a std::unordered_map-based conflict set (point
+    # queries only)
+    add_library(hash_table SHARED HashTable.cpp)
+    target_compile_options(hash_table PRIVATE -fno-exceptions
+                                              -fvisibility=hidden)
+    target_include_directories(hash_table PUBLIC ${CMAKE_SOURCE_DIR}/include)
+    set_target_properties(
+      hash_table PROPERTIES LIBRARY_OUTPUT_DIRECTORY
+                            "${CMAKE_BINARY_DIR}/hash_table")
+    set_target_properties(hash_table PROPERTIES OUTPUT_NAME ${PROJECT_NAME})
+    set_target_properties(
+      hash_table PROPERTIES VERSION ${PROJECT_VERSION} SOVERSION
+                                                       ${PROJECT_VERSION_MAJOR})
+
+    add_executable(driver_skip_list TestDriver.cpp)
+    target_compile_options(driver_skip_list PRIVATE ${TEST_FLAGS})
+    target_link_libraries(driver_skip_list PRIVATE skip_list)
+
+    foreach(TEST ${CORPUS_TESTS})
+      get_filename_component(hash ${TEST} NAME)
+      add_test(NAME skip_list_${hash} COMMAND driver_skip_list ${TEST})
+    endforeach()
+  endif()
+
+  # ad hoc testing
   add_executable(conflict_set_main ConflictSet.cpp)
   target_include_directories(conflict_set_main
                              PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include)
@@ -149,10 +221,7 @@ if(BUILD_TESTING)
     endif()
   endif()
 
-  # corpus tests
+  # whitebox tests
-
-  file(GLOB CORPUS_TESTS ${CMAKE_SOURCE_DIR}/corpus/*)
-
   add_executable(fuzz_driver ConflictSet.cpp FuzzTestDriver.cpp)
   target_compile_options(fuzz_driver PRIVATE ${TEST_FLAGS})
   if(NOT CMAKE_CROSSCOMPILING)
@@ -167,9 +236,8 @@ if(BUILD_TESTING)
     add_test(NAME conflict_set_fuzz_${hash} COMMAND fuzz_driver ${TEST})
   endforeach()
 
-  # tsan
+  # tsan tests
-
+  if(NOT CMAKE_CROSSCOMPILING AND NOT CMAKE_BUILD_TYPE STREQUAL Debug)
-  if(NOT CMAKE_CROSSCOMPILING)
     add_executable(tsan_driver ConflictSet.cpp FuzzTestDriver.cpp)
     target_compile_options(tsan_driver PRIVATE ${TEST_FLAGS} -fsanitize=thread)
     target_link_options(tsan_driver PRIVATE -fsanitize=thread)
@@ -182,24 +250,26 @@ if(BUILD_TESTING)
     endforeach()
   endif()
 
+  # blackbox tests
   add_executable(driver TestDriver.cpp)
   target_compile_options(driver PRIVATE ${TEST_FLAGS})
   target_link_libraries(driver PRIVATE ${PROJECT_NAME})
+  foreach(TEST ${CORPUS_TESTS})
+    get_filename_component(hash ${TEST} NAME)
+    add_test(NAME conflict_set_blackbox_${hash} COMMAND driver ${TEST})
+  endforeach()
 
+  # scripted tests. Written manually to fill in anything libfuzzer couldn't
+  # find.
   add_executable(script_test ScriptTest.cpp)
   target_compile_options(script_test PRIVATE ${TEST_FLAGS})
   target_link_libraries(script_test PRIVATE ${PROJECT_NAME})
-
   file(GLOB SCRIPT_TESTS ${CMAKE_SOURCE_DIR}/script_tests/*)
   foreach(TEST ${SCRIPT_TESTS})
     get_filename_component(name ${TEST} NAME)
     add_test(NAME conflict_set_script_${name} COMMAND script_test ${TEST})
   endforeach()
 
-  add_executable(driver_skip_list TestDriver.cpp)
-  target_compile_options(driver_skip_list PRIVATE ${TEST_FLAGS})
-  target_link_libraries(driver_skip_list PRIVATE skip_list)
-
   find_program(VALGRIND_EXE valgrind)
   if(VALGRIND_EXE AND NOT CMAKE_CROSSCOMPILING)
     add_test(NAME conflict_set_blackbox_valgrind
@@ -207,12 +277,6 @@ if(BUILD_TESTING)
                      $<TARGET_FILE:driver> ${CORPUS_TESTS})
   endif()
 
-  foreach(TEST ${CORPUS_TESTS})
-    get_filename_component(hash ${TEST} NAME)
-    add_test(NAME conflict_set_blackbox_${hash} COMMAND driver ${TEST})
-    add_test(NAME skip_list_${hash} COMMAND driver_skip_list ${TEST})
-  endforeach()
-
   # api smoke tests
 
   # c90
@@ -233,31 +297,45 @@ if(BUILD_TESTING)
                         PROPERTIES CXX_STANDARD_REQUIRED ON)
   add_test(NAME conflict_set_cxx_api_test COMMAND conflict_set_cxx_api_test)
 
-  if(NOT APPLE AND NOT CMAKE_BUILD_TYPE STREQUAL Debug)
+  # symbol visibility tests
+  if(NOT WASM AND NOT CMAKE_BUILD_TYPE STREQUAL Debug)
+    if(APPLE)
+      set(symbol_exports ${CMAKE_SOURCE_DIR}/apple-symbol-exports.txt)
+      set(symbol_imports ${CMAKE_SOURCE_DIR}/apple-symbol-imports.txt)
+    else()
+      set(symbol_exports ${CMAKE_SOURCE_DIR}/symbol-exports.txt)
+      if(CMAKE_SYSTEM_PROCESSOR STREQUAL aarch64)
+        set(symbol_imports ${CMAKE_SOURCE_DIR}/aarch64-symbol-imports.txt)
+      else()
+        set(symbol_imports ${CMAKE_SOURCE_DIR}/symbol-imports.txt)
+      endif()
+    endif()
     add_test(
       NAME conflict_set_shared_symbols
-      COMMAND ${CMAKE_SOURCE_DIR}/test_symbols.sh
+      COMMAND
-              $<TARGET_FILE:${PROJECT_NAME}> ${CMAKE_SOURCE_DIR}/symbols.txt)
+        ${CMAKE_SOURCE_DIR}/test_symbols.sh $<TARGET_FILE:${PROJECT_NAME}>
+        ${symbol_exports} ${symbol_imports})
     add_test(
       NAME conflict_set_static_symbols
       COMMAND
         ${CMAKE_SOURCE_DIR}/test_symbols.sh
-        $<TARGET_FILE:${PROJECT_NAME}_static> ${CMAKE_SOURCE_DIR}/symbols.txt)
+        $<TARGET_FILE:${PROJECT_NAME}-static> ${symbol_exports}
+        ${symbol_imports})
   endif()
 
   # bench
-
   add_executable(conflict_set_bench Bench.cpp)
   target_link_libraries(conflict_set_bench PRIVATE ${PROJECT_NAME})
   set_target_properties(conflict_set_bench PROPERTIES SKIP_BUILD_RPATH ON)
-
   add_executable(real_data_bench RealDataBench.cpp)
   target_link_libraries(real_data_bench PRIVATE ${PROJECT_NAME})
   set_target_properties(real_data_bench PROPERTIES SKIP_BUILD_RPATH ON)
 endif()
+
 # packaging
 
 set(CPACK_PACKAGE_CONTACT andrew@weaselab.dev)
+set(CMAKE_INSTALL_DEFAULT_COMPONENT_NAME all)
 
 set(CPACK_PACKAGE_VENDOR "Weaselab")
 set(CPACK_RESOURCE_FILE_LICENSE "${CMAKE_CURRENT_SOURCE_DIR}/LICENSE")
@@ -267,6 +345,29 @@ set(CPACK_RESOURCE_FILE_README "${CMAKE_CURRENT_SOURCE_DIR}/README.md")
 set(CPACK_RPM_PACKAGE_ARCHITECTURE ${CMAKE_SYSTEM_PROCESSOR})
 set(CPACK_RPM_SPEC_INSTALL_POST "/bin/true") # avoid stripping
 set(CPACK_RPM_PACKAGE_LICENSE "Apache 2.0")
+set(CPACK_RPM_FILE_NAME RPM-DEFAULT)
+
+# deb
+set(CPACK_DEBIAN_FILE_NAME DEB-DEFAULT)
+# see *-imports.txt - dependency versions need to be synced with symbol versions
+if(CMAKE_SYSTEM_PROCESSOR STREQUAL aarch64)
+  set(CPACK_DEBIAN_PACKAGE_DEPENDS "libc6 (>= 2.17)")
+else()
+  set(CPACK_DEBIAN_PACKAGE_DEPENDS "libc6 (>= 2.14)")
+endif()
+
+# macos
+if(APPLE)
+  find_program(PANDOC_EXE pandoc)
+  if(PANDOC_EXE)
+    execute_process(COMMAND ${PANDOC_EXE} ${CMAKE_SOURCE_DIR}/README.md -o
+                            ${CMAKE_BINARY_DIR}/README.txt)
+    set(CPACK_RESOURCE_FILE_README ${CMAKE_BINARY_DIR}/README.txt)
+  endif()
+  configure_file(${CMAKE_SOURCE_DIR}/LICENSE ${CMAKE_BINARY_DIR}/LICENSE.txt
+                 COPYONLY)
+  set(CPACK_RESOURCE_FILE_LICENSE ${CMAKE_BINARY_DIR}/LICENSE.txt)
+endif()
 
 include(CPack)
 
@@ -278,7 +379,7 @@ target_include_directories(
          $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/${PROJECT_NAME}>)
 
 target_include_directories(
-  ${PROJECT_NAME}_static
+  ${PROJECT_NAME}-static
   PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
          $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/${PROJECT_NAME}>)
 
@@ -287,13 +388,16 @@ set_target_properties(
                              SOVERSION ${PROJECT_VERSION_MAJOR})
 
 install(
-  TARGETS ${PROJECT_NAME} ${PROJECT_NAME}_static
+  TARGETS ${PROJECT_NAME} ${PROJECT_NAME}-static
-  EXPORT ConflictSetConfig
+  EXPORT ${PROJECT_NAME}Config
   ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
   LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
   RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+
 install(DIRECTORY include/
         DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/${PROJECT_NAME})
 
-install(EXPORT ConflictSetConfig
+install(EXPORT ${PROJECT_NAME}Config
-        DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/ConflictSet/cmake)
+        DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/${PROJECT_NAME}/cmake)
+
+cpack_add_component(all)

ConflictSet.cpp

@@ -29,6 +29,7 @@ limitations under the License.
 #include <span>
 #include <string>
 #include <string_view>
+#include <type_traits>
 #include <utility>
 
 #ifdef HAS_AVX
@@ -39,6 +40,8 @@ limitations under the License.
 
 #include <memcheck.h>
 
+using namespace weaselab;
+
 // Use assert for checking potentially complex properties during tests.
 // Use assume to hint simple properties to the optimizer.
 
@@ -216,6 +219,7 @@ struct Node {
   /* end section that's copied to the next node */
 
   uint8_t *partialKey();
+  size_t size() const;
 
   Type getType() const { return type; }
   int32_t getCapacity() const { return partialKeyCapacity; }
@@ -249,6 +253,8 @@ struct Node0 : Node {
 
   void copyChildrenAndKeyFrom(const Node0 &other);
   void copyChildrenAndKeyFrom(const struct Node3 &other);
+
+  size_t size() const { return sizeof(Node0) + getCapacity(); }
 };
 
 struct Node3 : Node {
@@ -262,6 +268,8 @@ struct Node3 : Node {
   void copyChildrenAndKeyFrom(const Node0 &other);
   void copyChildrenAndKeyFrom(const Node3 &other);
   void copyChildrenAndKeyFrom(const struct Node16 &other);
+
+  size_t size() const { return sizeof(Node3) + getCapacity(); }
 };
 
 struct Node16 : Node {
@@ -275,6 +283,8 @@ struct Node16 : Node {
   void copyChildrenAndKeyFrom(const Node3 &other);
   void copyChildrenAndKeyFrom(const Node16 &other);
   void copyChildrenAndKeyFrom(const struct Node48 &other);
+
+  size_t size() const { return sizeof(Node16) + getCapacity(); }
 };
 
 struct Node48 : Node {
@@ -290,6 +300,8 @@ struct Node48 : Node {
   void copyChildrenAndKeyFrom(const Node16 &other);
   void copyChildrenAndKeyFrom(const Node48 &other);
   void copyChildrenAndKeyFrom(const struct Node256 &other);
+
+  size_t size() const { return sizeof(Node48) + getCapacity(); }
 };
 
 struct Node256 : Node {
@@ -299,6 +311,8 @@ struct Node256 : Node {
   uint8_t *partialKey() { return (uint8_t *)(this + 1); }
   void copyChildrenAndKeyFrom(const Node48 &other);
   void copyChildrenAndKeyFrom(const Node256 &other);
+
+  size_t size() const { return sizeof(Node256) + getCapacity(); }
 };
 
 inline void Node0::copyChildrenAndKeyFrom(const Node0 &other) {
@@ -535,7 +549,7 @@ template <class T> struct BoundedFreeListAllocator {
       } else {
         // The intent is to filter out too-small nodes in the freelist
         removeNode(n);
-        safe_free(n);
+        safe_free(n, sizeof(T) + n->partialKeyCapacity);
       }
     }
 
@@ -547,10 +561,9 @@ template <class T> struct BoundedFreeListAllocator {
   }
 
   void release(T *p) {
-    static_assert(std::is_trivially_destructible_v<T>);
     if (freeListBytes >= kFreeListMaxMemory) {
       removeNode(p);
-      return safe_free(p);
+      return safe_free(p, sizeof(T) + p->partialKeyCapacity);
     }
     memcpy((void *)p, &freeList, sizeof(freeList));
     freeList = p;
@@ -560,11 +573,11 @@ template <class T> struct BoundedFreeListAllocator {
 
   ~BoundedFreeListAllocator() {
     for (void *iter = freeList; iter != nullptr;) {
-      VALGRIND_MAKE_MEM_DEFINED(iter, sizeof(iter));
+      VALGRIND_MAKE_MEM_DEFINED(iter, sizeof(Node));
-      auto *tmp = iter;
+      auto *tmp = (T *)iter;
       memcpy(&iter, iter, sizeof(void *));
-      removeNode(((T *)tmp));
+      removeNode((tmp));
-      safe_free(tmp);
+      safe_free(tmp, sizeof(T) + tmp->partialKeyCapacity);
     }
   }
 
@@ -590,6 +603,23 @@ uint8_t *Node::partialKey() {
   }
 }
 
+size_t Node::size() const {
+  switch (type) {
+  case Type_Node0:
+    return ((Node0 *)this)->size();
+  case Type_Node3:
+    return ((Node3 *)this)->size();
+  case Type_Node16:
+    return ((Node16 *)this)->size();
+  case Type_Node48:
+    return ((Node48 *)this)->size();
+  case Type_Node256:
+    return ((Node256 *)this)->size();
+  default:                   // GCOVR_EXCL_LINE
+    __builtin_unreachable(); // GCOVR_EXCL_LINE
+  }
+}
+
 struct NodeAllocators {
   BoundedFreeListAllocator<Node0> node0;
   BoundedFreeListAllocator<Node3> node3;
@@ -925,6 +955,42 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
     assert(self->getType() == Type_Node16);
 
     ++self->numChildren;
+#ifdef HAS_AVX
+    __m128i key_vec = _mm_set1_epi8(index);
+    __m128i indices;
+    memcpy(&indices, self16->index, sizeof(self16->index));
+    __m128i results = _mm_cmpeq_epi8(key_vec, _mm_min_epu8(key_vec, indices));
+    int mask = (1 << (self->numChildren - 1)) - 1;
+    uint32_t bitfield = _mm_movemask_epi8(results) & mask;
+    bitfield |= uint32_t(1) << (self->numChildren - 1);
+    int i = std::countr_zero(bitfield);
+    if (i < self->numChildren - 1) {
+      memmove(self16->index + i + 1, self16->index + i,
+              self->numChildren - (i + 1));
+      memmove(self16->children + i + 1, self16->children + i,
+              (self->numChildren - (i + 1)) * sizeof(Child));
+    }
+#elif defined(HAS_ARM_NEON)
+    uint8x16_t indices;
+    memcpy(&indices, self16->index, sizeof(self16->index));
+    // 0xff for each leq
+    auto results = vcleq_u8(vdupq_n_u8(index), indices);
+    uint64_t mask = (uint64_t(1) << ((self->numChildren - 1) * 4)) - 1;
+    // 0xf for each 0xff (within mask)
+    uint64_t bitfield =
+        vget_lane_u64(
+            vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(results), 4)),
+            0) &
+        mask;
+    bitfield |= uint64_t(0xf) << ((self->numChildren - 1) * 4);
+    int i = std::countr_zero(bitfield) / 4;
+    if (i < self->numChildren - 1) {
+      memmove(self16->index + i + 1, self16->index + i,
+              self->numChildren - (i + 1));
+      memmove(self16->children + i + 1, self16->children + i,
+              (self->numChildren - (i + 1)) * sizeof(Child));
+    }
+#else
     int i = 0;
     for (; i < int(self->numChildren) - 1; ++i) {
       if (int(self16->index[i]) > int(index)) {
@@ -935,6 +1001,7 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
         break;
       }
     }
+#endif
     self16->index[i] = index;
     auto &result = self16->children[i].child;
     result = nullptr;
@@ -950,8 +1017,8 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
       self = newSelf;
       goto insert256;
     }
-  insert48:
 
+  insert48:
     auto *self48 = static_cast<Node48 *>(self);
     self48->bitSet.set(index);
     ++self->numChildren;
@@ -963,6 +1030,7 @@ Node *&getOrCreateChild(Node *&self, uint8_t index,
     return result;
   }
   case Type_Node256: {
+
   insert256:
     auto *self256 = static_cast<Node256 *>(self);
     ++self->numChildren;
@@ -1012,7 +1080,7 @@ void freeAndMakeCapacityAtLeast(Node *&self, int capacity,
       allocators->node0.release(self0);
     } else {
       removeNode(self0);
-      safe_free(self0);
+      safe_free(self0, self0->size());
     }
     self = newSelf;
   } break;
@@ -1025,7 +1093,7 @@ void freeAndMakeCapacityAtLeast(Node *&self, int capacity,
       allocators->node3.release(self3);
     } else {
       removeNode(self3);
-      safe_free(self3);
+      safe_free(self3, self3->size());
     }
     self = newSelf;
   } break;
@@ -1038,7 +1106,7 @@ void freeAndMakeCapacityAtLeast(Node *&self, int capacity,
       allocators->node16.release(self16);
     } else {
       removeNode(self16);
-      safe_free(self16);
+      safe_free(self16, self16->size());
     }
     self = newSelf;
   } break;
@@ -1051,7 +1119,7 @@ void freeAndMakeCapacityAtLeast(Node *&self, int capacity,
       allocators->node48.release(self48);
     } else {
       removeNode(self48);
-      safe_free(self48);
+      safe_free(self48, self48->size());
     }
     self = newSelf;
   } break;
@@ -1064,7 +1132,7 @@ void freeAndMakeCapacityAtLeast(Node *&self, int capacity,
       allocators->node256.release(self256);
     } else {
       removeNode(self256);
-      safe_free(self256);
+      safe_free(self256, self256->size());
     }
     self = newSelf;
   } break;
@@ -2178,7 +2246,7 @@ void destroyTree(Node *root) {
       assert(c != nullptr);
       toFree.push_back(c);
     }
-    safe_free(n);
+    safe_free(n, n->size());
   }
 }
 
@@ -2435,10 +2503,10 @@ struct __attribute__((visibility("hidden"))) ConflictSet::Impl {
     }
     if (n == nullptr) {
       removalKey = {};
-      return;
+    } else {
+      removalKeyArena = Arena();
+      removalKey = getSearchPath(removalKeyArena, n);
     }
-    removalKeyArena = Arena();
-    removalKey = getSearchPath(removalKeyArena, n);
   }
 
   explicit Impl(int64_t oldestVersion) : oldestVersion(oldestVersion) {
@@ -2467,6 +2535,7 @@ struct __attribute__((visibility("hidden"))) ConflictSet::Impl {
   Node *root;
   int64_t rootMaxVersion;
   int64_t oldestVersion;
+  int64_t totalBytes = 0;
 };
 
 // Precondition - an entry for index must exist in the node
@@ -2520,20 +2589,39 @@ void ConflictSet::check(const ReadRange *reads, Result *results,
 
 void ConflictSet::addWrites(const WriteRange *writes, int count,
                             int64_t writeVersion) {
-  return impl->addWrites(writes, count, writeVersion);
+  mallocBytesDelta = 0;
+  impl->addWrites(writes, count, writeVersion);
+  impl->totalBytes += mallocBytesDelta;
+#if SHOW_MEMORY
+  if (impl->totalBytes != mallocBytes) {
+    abort();
+  }
+#endif
 }
 
 void ConflictSet::setOldestVersion(int64_t oldestVersion) {
-  return impl->setOldestVersion(oldestVersion);
+  mallocBytesDelta = 0;
+  impl->setOldestVersion(oldestVersion);
+  impl->totalBytes += mallocBytesDelta;
+#if SHOW_MEMORY
+  if (impl->totalBytes != mallocBytes) {
+    abort();
+  }
+#endif
 }
 
+int64_t ConflictSet::getBytes() const { return impl->totalBytes; }
+
 ConflictSet::ConflictSet(int64_t oldestVersion)
-    : impl(new (safe_malloc(sizeof(Impl))) Impl{oldestVersion}) {}
+    : impl((mallocBytesDelta = 0,
+            new(safe_malloc(sizeof(Impl))) Impl{oldestVersion})) {
+  impl->totalBytes += mallocBytesDelta;
+}
 
 ConflictSet::~ConflictSet() {
   if (impl) {
     impl->~Impl();
-    safe_free(impl);
+    safe_free(impl, sizeof(*impl));
   }
 }
 
@@ -2559,24 +2647,44 @@ ConflictSet_check(void *cs, const ConflictSet_ReadRange *reads,
 __attribute__((__visibility__("default"))) void
 ConflictSet_addWrites(void *cs, const ConflictSet_WriteRange *writes, int count,
                       int64_t writeVersion) {
-  ((ConflictSet::Impl *)cs)->addWrites(writes, count, writeVersion);
+  auto *impl = ((ConflictSet::Impl *)cs);
+  mallocBytesDelta = 0;
+  impl->addWrites(writes, count, writeVersion);
+  impl->totalBytes += mallocBytesDelta;
 }
 __attribute__((__visibility__("default"))) void
 ConflictSet_setOldestVersion(void *cs, int64_t oldestVersion) {
-  ((ConflictSet::Impl *)cs)->setOldestVersion(oldestVersion);
+  auto *impl = ((ConflictSet::Impl *)cs);
+  mallocBytesDelta = 0;
+  impl->setOldestVersion(oldestVersion);
+  impl->totalBytes += mallocBytesDelta;
 }
 __attribute__((__visibility__("default"))) void *
 ConflictSet_create(int64_t oldestVersion) {
-  return new (safe_malloc(sizeof(ConflictSet::Impl)))
+  mallocBytesDelta = 0;
+  auto *result = new (safe_malloc(sizeof(ConflictSet::Impl)))
       ConflictSet::Impl{oldestVersion};
+  result->totalBytes += mallocBytesDelta;
+  return result;
 }
 __attribute__((__visibility__("default"))) void ConflictSet_destroy(void *cs) {
   using Impl = ConflictSet::Impl;
   ((Impl *)cs)->~Impl();
-  safe_free(cs);
+  safe_free(cs, sizeof(Impl));
+}
+__attribute__((__visibility__("default"))) int64_t
+ConflictSet_getBytes(void *cs) {
+  using Impl = ConflictSet::Impl;
+  return ((Impl *)cs)->totalBytes;
 }
 }
 
+// Make sure abi is well-defined
+static_assert(std::is_standard_layout_v<ConflictSet::Result>);
+static_assert(std::is_standard_layout_v<ConflictSet::Key>);
+static_assert(std::is_standard_layout_v<ConflictSet::ReadRange>);
+static_assert(std::is_standard_layout_v<ConflictSet::WriteRange>);
+
 namespace {
 
 std::string getSearchPathPrintable(Node *n) {
@@ -2789,8 +2897,8 @@ Iterator firstGeq(Node *n, std::string_view key) {
   }
 }
 
-bool checkCorrectness(Node *node, int64_t oldestVersion,
+[[maybe_unused]] bool checkCorrectness(Node *node, int64_t oldestVersion,
-                      ConflictSet::Impl *impl) {
+                                       ConflictSet::Impl *impl) {
   bool success = true;
 
   checkParentPointers(node, success);

HashTable.cpp

@@ -96,13 +96,15 @@ void ConflictSet::setOldestVersion(int64_t oldestVersion) {
   return impl->setOldestVersion(oldestVersion);
 }
 
+int64_t ConflictSet::getBytes() const { return -1; }
+
 ConflictSet::ConflictSet(int64_t oldestVersion)
-    : impl(new (safe_malloc(sizeof(Impl))) Impl{oldestVersion}) {}
+    : impl(new(safe_malloc(sizeof(Impl))) Impl{oldestVersion}) {}
 
 ConflictSet::~ConflictSet() {
   if (impl) {
     impl->~Impl();
-    safe_free(impl);
+    safe_free(impl, sizeof(Impl));
   }
 }
 
@@ -142,6 +144,11 @@ ConflictSet_create(int64_t oldestVersion) {
 __attribute__((__visibility__("default"))) void ConflictSet_destroy(void *cs) {
   using Impl = ConflictSet::Impl;
   ((Impl *)cs)->~Impl();
-  safe_free(cs);
+  safe_free(cs, sizeof(Impl));
+}
+__attribute__((__visibility__("default"))) int64_t
+ConflictSet_getBytes(void *cs) {
+  using Impl = ConflictSet::Impl;
+  return -1;
 }
 }

Internal.h

@@ -2,6 +2,8 @@
 
 #include "ConflictSet.h"
 
+using namespace weaselab;
+
 #include <bit>
 #include <cassert>
 #include <compare>
@@ -56,43 +58,55 @@ operator<=>(const std::span<const uint8_t> &lhs,
 #if SHOW_MEMORY
 inline int64_t mallocBytes = 0;
 inline int64_t peakMallocBytes = 0;
-constexpr auto kIntMallocHeaderSize = 16;
+#endif
+
+inline thread_local int64_t mallocBytesDelta = 0;
+
+#ifndef NDEBUG
+constexpr auto kMallocHeaderSize = 16;
 #endif
 
 // malloc that aborts on OOM and thus always returns a non-null pointer. Must be
 // paired with `safe_free`.
 __attribute__((always_inline)) inline void *safe_malloc(size_t s) {
+  mallocBytesDelta += s;
 #if SHOW_MEMORY
   mallocBytes += s;
   if (mallocBytes > peakMallocBytes) {
     peakMallocBytes = mallocBytes;
   }
-  void *p = malloc(s + kIntMallocHeaderSize);
-  if (p == nullptr) {
-    abort();
-  }
-  memcpy(p, &s, sizeof(s));
-  return (char *)p + kIntMallocHeaderSize;
-#else
-  void *p = malloc(s);
-  if (p == nullptr) {
-    abort();
-  }
-  return p;
 #endif
+  void *p = malloc(s
+#ifndef NDEBUG
+                   + kMallocHeaderSize
+#endif
+  );
+  if (p == nullptr) {
+    abort();
+  }
+#ifndef NDEBUG
+  memcpy(p, &s, sizeof(s));
+  (char *&)p += kMallocHeaderSize;
+#endif
+  return p;
 }
 
 // Must be paired with `safe_malloc`.
 //
 // There's nothing safer about this than free. Only called safe_free for
 // symmetry with safe_malloc.
-__attribute__((always_inline)) inline void safe_free(void *p) {
+__attribute__((always_inline)) inline void safe_free(void *p, size_t s) {
+  mallocBytesDelta -= s;
 #if SHOW_MEMORY
-  size_t s;
-  memcpy(&s, (char *)p - kIntMallocHeaderSize, sizeof(s));
   mallocBytes -= s;
-  free((char *)p - kIntMallocHeaderSize);
+  free(p);
 #else
+#ifndef NDEBUG
+  (char *&)p -= kMallocHeaderSize;
+  size_t expected;
+  memcpy(&expected, p, sizeof(expected));
+  assert(s == expected);
+#endif
   free(p);
 #endif
 }
@@ -140,6 +154,7 @@ inline void *operator new[](size_t size, std::align_val_t align,
 
 /// align must be a power of two
 template <class T> T *align_up(T *t, size_t align) {
+  assert(std::popcount(align) == 1);
   auto unaligned = uintptr_t(t);
   auto aligned = (unaligned + align - 1) & ~(align - 1);
   return reinterpret_cast<T *>(reinterpret_cast<char *>(t) + aligned -
@@ -148,6 +163,7 @@ template <class T> T *align_up(T *t, size_t align) {
 
 /// align must be a power of two
 constexpr inline int align_up(uint32_t unaligned, uint32_t align) {
+  assert(std::popcount(align) == 1);
   return (unaligned + align - 1) & ~(align - 1);
 }
 
@@ -163,12 +179,10 @@ struct Arena::ArenaImpl {
   uint8_t *begin() { return reinterpret_cast<uint8_t *>(this + 1); }
 };
 
-static_assert(sizeof(Arena::ArenaImpl) == 16);
-static_assert(alignof(Arena::ArenaImpl) == 8);
-
 inline Arena::Arena(int initialSize) : impl(nullptr) {
   if (initialSize > 0) {
-    auto allocationSize = align_up(initialSize + sizeof(ArenaImpl), 16);
+    auto allocationSize =
+        align_up(initialSize + sizeof(ArenaImpl), alignof(ArenaImpl));
     impl = (Arena::ArenaImpl *)safe_malloc(allocationSize);
     impl->prev = nullptr;
     impl->capacity = allocationSize - sizeof(ArenaImpl);
@@ -179,7 +193,7 @@ inline Arena::Arena(int initialSize) : impl(nullptr) {
 inline void onDestroy(Arena::ArenaImpl *impl) {
   while (impl) {
     auto *prev = impl->prev;
-    safe_free(impl);
+    safe_free(impl, sizeof(Arena::ArenaImpl) + impl->capacity);
     impl = prev;
   }
 }
@@ -204,7 +218,7 @@ inline void *operator new(size_t size, std::align_val_t align, Arena &arena) {
                           (arena.impl ? std::max<int>(sizeof(Arena::ArenaImpl),
                                                       arena.impl->capacity * 2)
                                       : 0)),
-        16);
+        alignof(Arena::ArenaImpl));
     auto *impl = (Arena::ArenaImpl *)safe_malloc(allocationSize);
     impl->prev = arena.impl;
     impl->capacity = allocationSize - sizeof(Arena::ArenaImpl);

Jenkinsfile

@@ -48,6 +48,17 @@ pipeline {
                 recordIssues(tools: [clang()])
             }
         }
+        stage('SIMD fallback') {
+            agent {
+                dockerfile {
+                    args '-v /home/jenkins/ccache:/ccache'
+                    reuseNode true
+                }
+            }
+            steps {
+                CleanBuildAndTest("-DUSE_SIMD_FALLBACK=ON")
+            }
+        }
         stage('Release [gcc]') {
             agent {
                 dockerfile {

README.md

@@ -9,76 +9,76 @@ Hardware for all benchmarks is a mac m1 2020.
 ## Skip list
 
 ```
-New conflict set: 1.927 sec
+New conflict set: 1.957 sec
-                  0.649 Mtransactions/sec
+                  0.639 Mtransactions/sec
-                  2.595 Mkeys/sec
+                  2.555 Mkeys/sec
-Detect only:      1.838 sec
+Detect only:      1.845 sec
-                  0.680 Mtransactions/sec
+                  0.678 Mtransactions/sec
-                  2.721 Mkeys/sec
+                  2.710 Mkeys/sec
-Skiplist only:    1.256 sec
+Skiplist only:    1.263 sec
-                  0.995 Mtransactions/sec
+                  0.990 Mtransactions/sec
-                  3.981 Mkeys/sec
+                  3.960 Mkeys/sec
 Performance counters:
-               Build: 0.0381
+               Build: 0.0546
-                 Add: 0.0499
+                 Add: 0.0563
               Detect: 1.84
-              D.Sort: 0.411
+              D.Sort: 0.412
            D.Combine: 0.0141
-         D.CheckRead: 0.667
+         D.CheckRead: 0.671
-   D.CheckIntraBatch: 0.00673
+   D.CheckIntraBatch: 0.0068
-        D.MergeWrite: 0.589
+        D.MergeWrite: 0.592
       D.RemoveBefore: 0.146
 ```
 
 ## Radix tree (this implementation)
 
 ```
-New conflict set: 1.318 sec
+New conflict set: 1.366 sec
-                  0.949 Mtransactions/sec
+                  0.915 Mtransactions/sec
-                  3.795 Mkeys/sec
+                  3.660 Mkeys/sec
-Detect only:      1.202 sec
+Detect only:      1.248 sec
-                  1.040 Mtransactions/sec
+                  1.002 Mtransactions/sec
-                  4.160 Mkeys/sec
+                  4.007 Mkeys/sec
-Skiplist only:    0.542 sec
+Skiplist only:    0.573 sec
-                  2.307 Mtransactions/sec
+                  2.182 Mtransactions/sec
-                  9.227 Mkeys/sec
+                  8.730 Mkeys/sec
 Performance counters:
-               Build: 0.0566
+               Build: 0.0594
-                 Add: 0.058
+                 Add: 0.0572
-              Detect: 1.2
+              Detect: 1.25
-              D.Sort: 0.411
+              D.Sort: 0.418
-           D.Combine: 0.0136
+           D.Combine: 0.0149
-         D.CheckRead: 0.22
+         D.CheckRead: 0.232
-   D.CheckIntraBatch: 0.00659
+   D.CheckIntraBatch: 0.0067
-        D.MergeWrite: 0.322
+        D.MergeWrite: 0.341
-      D.RemoveBefore: 0.226
+      D.RemoveBefore: 0.232
 ```
 
 # Our benchmark
 
 ## Skip list
 
-|               ns/op |                op/s |    err% |     total | benchmark
+|  ns/op |         op/s | err% | total | benchmark                           |
-|--------------------:|--------------------:|--------:|----------:|:----------
+| -----: | -----------: | ---: | ----: | :---------------------------------- |
-|              257.12 |        3,889,241.18 |    0.2% |      0.01 | `point reads`
+| 246.99 | 4,048,700.59 | 0.2% |  0.01 | `point reads`                       |
-|              276.38 |        3,618,145.21 |    0.3% |      0.01 | `prefix reads`
+| 260.16 | 3,843,784.65 | 0.1% |  0.01 | `prefix reads`                      |
-|              494.19 |        2,023,531.84 |    0.2% |      0.01 | `range reads`
+| 493.35 | 2,026,953.19 | 0.1% |  0.01 | `range reads`                       |
-|              451.22 |        2,216,229.54 |    1.3% |      0.01 | `point writes`
+| 462.05 | 2,164,289.23 | 0.6% |  0.01 | `point writes`                      |
-|              435.80 |        2,294,622.46 |    0.3% |      0.01 | `prefix writes`
+| 448.19 | 2,231,205.25 | 0.9% |  0.01 | `prefix writes`                     |
-|              246.67 |        4,053,999.27 |    4.2% |      0.02 | `range writes`
+| 255.83 | 3,908,845.72 | 1.5% |  0.02 | `range writes`                      |
-|              555.46 |        1,800,304.91 |    0.9% |      0.01 | `monotonic increasing point writes`
+| 582.63 | 1,716,349.02 | 1.3% |  0.01 | `monotonic increasing point writes` |
 
 ## Radix tree (this implementation)
 
-|               ns/op |                op/s |    err% |     total | benchmark
+|  ns/op |          op/s | err% | total | benchmark                           |
-|--------------------:|--------------------:|--------:|----------:|:----------
+| -----: | ------------: | ---: | ----: | :---------------------------------- |
-|               19.40 |       51,554,711.61 |    0.2% |      0.01 | `point reads`
+|  19.42 | 51,483,206.67 | 0.3% |  0.01 | `point reads`                       |
-|               57.10 |       17,514,573.13 |    0.4% |      0.01 | `prefix reads`
+|  58.43 | 17,115,612.57 | 0.1% |  0.01 | `prefix reads`                      |
-|              215.65 |        4,637,096.77 |    0.4% |      0.01 | `range reads`
+| 216.09 |  4,627,766.60 | 0.2% |  0.01 | `range reads`                       |
-|               27.52 |       36,340,784.38 |    0.2% |      0.01 | `point writes`
+|  28.35 | 35,267,567.72 | 0.2% |  0.01 | `point writes`                      |
-|               42.16 |       23,720,515.40 |    0.7% |      0.01 | `prefix writes`
+|  43.43 | 23,026,226.17 | 0.2% |  0.01 | `prefix writes`                     |
-|               48.33 |       20,691,082.14 |    2.7% |      0.01 | `range writes`
+|  50.00 | 20,000,000.00 | 0.0% |  0.01 | `range writes`                      |
-|               87.93 |       11,372,164.55 |    2.5% |      0.01 | `monotonic increasing point writes`
+|  92.38 | 10,824,863.69 | 4.1% |  0.01 | `monotonic increasing point writes` |
 
 # "Real data" test
 
@@ -87,13 +87,13 @@ Point queries only, best of three runs. Gc ratio is the ratio of time spent doin
 ## skip list
 
 ```
-Check: 11.3839 seconds, 328.404 MB/s, Add: 5.32878 seconds, 131.745 MB/s, Gc ratio: 45.5903%
+Check: 11.3385 seconds, 329.718 MB/s, Add: 5.35612 seconds, 131.072 MB/s, Gc ratio: 45.7173%
 ```
 
 ## radix tree
 
 ```
-Check: 2.55069 seconds, 1465.69 MB/s, Add: 2.08443 seconds, 336.801 MB/s, Gc ratio: 41.748%
+Check: 2.48583 seconds, 1503.93 MB/s, Add: 2.12768 seconds, 329.954 MB/s, Gc ratio: 41.7943%
 ```
 
 ## hash table
@@ -101,5 +101,5 @@ Check: 2.55069 seconds, 1465.69 MB/s, Add: 2.08443 seconds, 336.801 MB/s, Gc rat
 (The hash table implementation doesn't work on range queries, and its purpose is to provide an idea of how fast point queries can be)
 
 ```
-Check: 1.84205 seconds, 2029.54 MB/s, Add: 0.60281 seconds, 1164.61 MB/s, Gc ratio: 48.8159%
+Check: 1.83386 seconds, 2038.6 MB/s, Add: 0.601411 seconds, 1167.32 MB/s, Gc ratio: 48.9776%
 ```

RealDataBench.cpp

@@ -1,13 +1,18 @@
 #include <ConflictSet.h>
 
+#include <cerrno>
 #include <chrono>
+#include <cstdio>
 #include <cstring>
 #include <fcntl.h>
+#include <string_view>
 #include <sys/mman.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <vector>
 
+using namespace weaselab;
+
 double now() {
   return std::chrono::duration_cast<std::chrono::nanoseconds>(
              std::chrono::steady_clock::now().time_since_epoch())
@@ -28,7 +33,7 @@ constexpr inline size_t rightAlign(size_t offset, size_t alignment) {
 
 int main(int argc, const char **argv) {
   // Use with this dataset https://snap.stanford.edu/data/memetracker9.html
-  // Preprocess the files with `sed -i '' '/^Q/d'`
+  // Preprocess the files with `sed -i'' '/^Q/d'`
 
   double checkTime = 0;
   double addTime = 0;
@@ -40,6 +45,8 @@ int main(int argc, const char **argv) {
   int64_t version = 0;
   double timer = 0;
 
+  int64_t peakMemory = 0;
+
   for (int i = 1; i < argc; ++i) {
     int fd = open(argv[i], O_RDONLY);
     struct stat st;
@@ -109,6 +116,10 @@ int main(int argc, const char **argv) {
         write = {};
         reads.clear();
 
+        if (cs.getBytes() > peakMemory) {
+          peakMemory = cs.getBytes();
+        }
+
         timer = now();
         cs.setOldestVersion(version - 10000);
         gcTime += now() - timer;
@@ -118,8 +129,9 @@ int main(int argc, const char **argv) {
     close(fd);
   }
 
-  printf(
+  printf("Check: %g seconds, %g MB/s, Add: %g seconds, %g MB/s, Gc ratio: "
-      "Check: %g seconds, %g MB/s, Add: %g seconds, %g MB/s, Gc ratio: %g%%\n",
+         "%g%%, Peak idle memory: %g\n",
-      checkTime, checkBytes / checkTime * 1e-6, addTime,
+         checkTime, checkBytes / checkTime * 1e-6, addTime,
-      addBytes / addTime * 1e-6, gcTime / (gcTime + addTime) * 1e2);
+         addBytes / addTime * 1e-6, gcTime / (gcTime + addTime) * 1e2,
+         double(peakMemory));
 }

SkipList.cpp

@@ -149,7 +149,7 @@ private:
       setMaxVersion(level, v);
     }
 
-    void destroy() { safe_free(this); }
+    void destroy() { safe_free(this, getNodeSize()); }
 
   private:
     int getNodeSize() const {
@@ -627,6 +627,8 @@ struct __attribute__((visibility("hidden"))) ConflictSet::Impl {
         removalArena, {finger.getValue().data(), finger.getValue().size()});
   }
 
+  int64_t totalBytes = 0;
+
 private:
   int64_t keyUpdates = 10;
   Arena removalArena;
@@ -637,25 +639,44 @@ private:
 
 void ConflictSet::check(const ReadRange *reads, Result *results,
                         int count) const {
-  return impl->check(reads, results, count);
+  impl->check(reads, results, count);
 }
 
 void ConflictSet::addWrites(const WriteRange *writes, int count,
                             int64_t writeVersion) {
-  return impl->addWrites(writes, count, writeVersion);
+  mallocBytesDelta = 0;
+  impl->addWrites(writes, count, writeVersion);
+  impl->totalBytes += mallocBytesDelta;
+#if SHOW_MEMORY
+  if (impl->totalBytes != mallocBytes) {
+    abort();
+  }
+#endif
 }
 
 void ConflictSet::setOldestVersion(int64_t oldestVersion) {
-  return impl->setOldestVersion(oldestVersion);
+  mallocBytesDelta = 0;
+  impl->setOldestVersion(oldestVersion);
+  impl->totalBytes += mallocBytesDelta;
+#if SHOW_MEMORY
+  if (impl->totalBytes != mallocBytes) {
+    abort();
+  }
+#endif
 }
 
+int64_t ConflictSet::getBytes() const { return impl->totalBytes; }
+
 ConflictSet::ConflictSet(int64_t oldestVersion)
-    : impl(new (safe_malloc(sizeof(Impl))) Impl{oldestVersion}) {}
+    : impl((mallocBytesDelta = 0,
+            new(safe_malloc(sizeof(Impl))) Impl{oldestVersion})) {
+  impl->totalBytes += mallocBytesDelta;
+}
 
 ConflictSet::~ConflictSet() {
   if (impl) {
     impl->~Impl();
-    safe_free(impl);
+    safe_free(impl, sizeof(Impl));
   }
 }
 
@@ -695,7 +716,12 @@ ConflictSet_create(int64_t oldestVersion) {
 __attribute__((__visibility__("default"))) void ConflictSet_destroy(void *cs) {
   using Impl = ConflictSet::Impl;
   ((Impl *)cs)->~Impl();
-  safe_free(cs);
+  safe_free(cs, sizeof(Impl));
+}
+__attribute__((__visibility__("default"))) int64_t
+ConflictSet_getBytes(void *cs) {
+  using Impl = ConflictSet::Impl;
+  return ((Impl *)cs)->totalBytes;
 }
 }
 

aarch64-symbol-imports.txt

@@ -0,0 +1,8 @@
+__stack_chk_fail@GLIBC_2.17
+__stack_chk_guard@GLIBC_2.17
+abort@GLIBC_2.17
+free@GLIBC_2.17
+malloc@GLIBC_2.17
+memcpy@GLIBC_2.17
+memmove@GLIBC_2.17
+memset@GLIBC_2.17

apple-symbol-exports.txt

@@ -0,0 +1,17 @@
+_ConflictSet_addWrites
+_ConflictSet_check
+_ConflictSet_create
+_ConflictSet_destroy
+_ConflictSet_getBytes
+_ConflictSet_setOldestVersion
+__ZN8weaselab11ConflictSet16setOldestVersionEx
+__ZN8weaselab11ConflictSet9addWritesEPKNS0_10WriteRangeEix
+__ZN8weaselab11ConflictSetC1EOS0_
+__ZN8weaselab11ConflictSetC1Ex
+__ZN8weaselab11ConflictSetC2EOS0_
+__ZN8weaselab11ConflictSetC2Ex
+__ZN8weaselab11ConflictSetD1Ev
+__ZN8weaselab11ConflictSetD2Ev
+__ZN8weaselab11ConflictSetaSEOS0_
+__ZNK8weaselab11ConflictSet5checkEPKNS0_9ReadRangeEPNS0_6ResultEi
+__ZNK8weaselab11ConflictSet8getBytesEv

apple-symbol-imports.txt

@@ -0,0 +1,7 @@
+__tlv_bootstrap
+_abort
+_bzero
+_free
+_malloc
+_memcpy
+_memmove

conflict_set.py

@@ -0,0 +1,120 @@
+import ctypes
+import enum
+import os
+
+from typing import Optional
+
+_lib = None
+for f in (
+    os.path.dirname(__file__) + "/build/radix_tree/libconflict-set.so.0",
+    os.path.dirname(__file__) + "/build/radix_tree/libconflict-set.0.dylib",
+):
+    try:
+        _lib = ctypes.cdll.LoadLibrary(f)
+    except:
+        pass
+
+if _lib is None:
+    import sys
+
+    print("Could not find libconflict-set", file=sys.stderr)
+    sys.exit(1)
+
+
+class _Key(ctypes.Structure):
+    _fields_ = [("p", ctypes.POINTER(ctypes.c_ubyte)), ("len", ctypes.c_int)]
+
+
+class ReadRange(ctypes.Structure):
+    _fields_ = [
+        ("begin", _Key),
+        ("end", _Key),
+        ("readVersion", ctypes.c_int64),
+    ]
+
+
+class WriteRange(ctypes.Structure):
+    _fields_ = [("begin", _Key), ("end", _Key)]
+
+
+_lib.ConflictSet_create.argtypes = (ctypes.c_int64,)
+_lib.ConflictSet_create.restype = ctypes.c_void_p
+
+_lib.ConflictSet_check.argtypes = (
+    ctypes.c_void_p,
+    ctypes.POINTER(ReadRange),
+    ctypes.POINTER(ctypes.c_int),
+    ctypes.c_int,
+)
+
+_lib.ConflictSet_addWrites.argtypes = (
+    ctypes.c_void_p,
+    ctypes.POINTER(WriteRange),
+    ctypes.c_int,
+    ctypes.c_int64,
+)
+
+_lib.ConflictSet_setOldestVersion.argtypes = (ctypes.c_void_p, ctypes.c_int64)
+
+_lib.ConflictSet_destroy.argtypes = (ctypes.c_void_p,)
+
+
+class Result(enum.Enum):
+    COMMIT = 0
+    CONFLICT = 1
+    TOO_OLD = 2
+
+
+def write(begin: bytes, end: Optional[bytes] = None) -> WriteRange:
+    b = (ctypes.c_ubyte * len(begin))()
+    b.value = begin
+    if end is None:
+        e = (ctypes.c_ubyte * 0)()
+        e.value = b""
+    else:
+        e = (ctypes.c_ubyte * len(end))()
+        e.value = end
+    return WriteRange(_Key(b, len(b)), _Key(e, len(e)))
+
+
+def read(version: int, begin: bytes, end: Optional[bytes] = None) -> ReadRange:
+    b = (ctypes.c_ubyte * len(begin))()
+    b.value = begin
+    if end is None:
+        e = (ctypes.c_ubyte * 0)()
+        e.value = b""
+    else:
+        e = (ctypes.c_ubyte * len(end))()
+        e.value = end
+    return ReadRange(_Key(b, len(b)), _Key(e, len(e)), version)
+
+
+class ConflictSet:
+    def __init__(self, version: int = 0) -> None:
+        self.p = _lib.ConflictSet_create(version)
+
+    def addWrites(self, version: int, *writes: WriteRange):
+        _lib.ConflictSet_addWrites(
+            self.p, (WriteRange * len(writes))(*writes), len(writes), version
+        )
+
+    def check(self, *reads: ReadRange) -> list[Result]:
+        r = (ctypes.c_int * len(reads))()
+        _lib.ConflictSet_check(self.p, *reads, r, 1)
+        return [Result(x) for x in r]
+
+    def setOldestVersion(self, version: int) -> None:
+        _lib.ConflictSet_setOldestVersion(self.p, version)
+
+    def __enter__(self):
+        return self
+
+    def close(self) -> None:
+        if self.p is not None:
+            _lib.ConflictSet_destroy(self.p)
+            self.p = None
+
+    def __exit__(self, exception_type, exception_value, exception_traceback):
+        if self.p is not None:
+            _lib.ConflictSet_destroy(self.p)
+            self.p = None

conflict_set_c_api_test.c

@@ -7,6 +7,7 @@ int main(void) {
   ConflictSet_WriteRange w;
   ConflictSet_Result result;
   ConflictSet_ReadRange r;
+  int64_t bytes;
   w.begin.p = (const uint8_t *)"0000";
   w.begin.len = 4;
   w.end.len = 0;
@@ -17,6 +18,8 @@ int main(void) {
   r.readVersion = 0;
   ConflictSet_check(cs, &r, &result, 1);
   assert(result == ConflictSet_Conflict);
+  bytes = ConflictSet_getBytes(cs);
+  assert(bytes > 0);
   ConflictSet_destroy(cs);
   return 0;
 }

conflict_set_cxx_api_test.cpp

@@ -2,6 +2,8 @@
 
 #include <cassert>
 
+using namespace weaselab;
+
 int main(void) {
   ConflictSet cs(0);
   ConflictSet::WriteRange w;
@@ -17,4 +19,6 @@ int main(void) {
   r.readVersion = 0;
   cs.check(&r, &result, 1);
   assert(result == ConflictSet::Conflict);
+  int64_t bytes = cs.getBytes();
+  assert(bytes > 0);
 }

fdb-patch.txt

@@ -1,32 +1,19 @@
-giff --git a/fdbserver/CMakeLists.txt b/fdbserver/CMakeLists.txt
+diff --git a/fdbserver/CMakeLists.txt b/fdbserver/CMakeLists.txt
-index 3f353c2ef..cd0834761 100644
+index 3f353c2ef..074a18628 100644
 --- a/fdbserver/CMakeLists.txt
 +++ b/fdbserver/CMakeLists.txt
 @@ -22,6 +22,9 @@ file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/workloads)
  
  add_flow_target(EXECUTABLE NAME fdbserver SRCS ${FDBSERVER_SRCS})
  
-+find_package(ConflictSet)
++find_package(conflict-set)
-+target_link_libraries(fdbserver PRIVATE conflict_set_static)
++target_link_libraries(fdbserver PRIVATE conflict-set-static)
 +
  if (WITH_SWIFT)
    # Setup the Swift sources in FDBServer.
    include(FindSwiftLibs)
-diff --git a/fdbserver/Resolver.actor.cpp b/fdbserver/Resolver.actor.cpp
-index bf4118f5f..d3b4eaad8 100644
---- a/fdbserver/Resolver.actor.cpp
-+++ b/fdbserver/Resolver.actor.cpp
-@@ -132,7 +132,7 @@ struct Resolver : ReferenceCounted<Resolver> {
- 	AsyncVar<int64_t> totalStateBytes;
- 	AsyncTrigger checkNeededVersion;
- 	std::map<NetworkAddress, ProxyRequestsInfo> proxyInfoMap;
--	ConflictSet* conflictSet;
-+	ConflictSet2* conflictSet;
- 	TransientStorageMetricSample iopsSample;
- 
- 	// Use LogSystem as backend for txnStateStore. However, the real commit
 diff --git a/fdbserver/SkipList.cpp b/fdbserver/SkipList.cpp
-index b48d32c6b..da106b5d2 100644
+index b48d32c6b..da99e03aa 100644
 --- a/fdbserver/SkipList.cpp
 +++ b/fdbserver/SkipList.cpp
 @@ -25,6 +25,7 @@
@@ -46,50 +33,35 @@ index b48d32c6b..da106b5d2 100644
  static std::vector<PerfDoubleCounter*> skc;
  
  static thread_local uint32_t g_seed = 0;
-@@ -782,26 +785,34 @@ private:
+@@ -783,10 +786,14 @@ private:
- 	}
  };
  
--struct ConflictSet {
+ struct ConflictSet {
 -	ConflictSet() : removalKey(makeString(0)), oldestVersion(0) {}
--	~ConflictSet() {}
++	ConflictSet() : versionHistory(0), removalKey(makeString(0)), oldestVersion(0) {}
-+struct ConflictSet2 {
+ 	~ConflictSet() {}
-+	ConflictSet2() : versionHistory(0), removalKey(makeString(0)), oldestVersion(0) {}
-+	~ConflictSet2() {}
  
 +#if USE_RADIX_TREE
-+	ConflictSet versionHistory;
++	weaselab::ConflictSet versionHistory;
 +#else
  	SkipList versionHistory;
 +#endif
  	Key removalKey;
  	Version oldestVersion;
  };
- 
+@@ -795,7 +802,11 @@ ConflictSet* newConflictSet() {
--ConflictSet* newConflictSet() {
+ 	return new ConflictSet;
--	return new ConflictSet;
-+ConflictSet2* newConflictSet() {
-+	return new ConflictSet2;
  }
--void clearConflictSet(ConflictSet* cs, Version v) {
+ void clearConflictSet(ConflictSet* cs, Version v) {
 -	SkipList(v).swap(cs->versionHistory);
-+void clearConflictSet(ConflictSet2* cs, Version v) {
 +#if USE_RADIX_TREE
-+	cs->versionHistory = ConflictSet{ 0 };
++	cs->versionHistory = weaselab::ConflictSet{ 0 };
 +#else
 +	SkipList().swap(cs->versionHistory);
 +#endif
  }
--void destroyConflictSet(ConflictSet* cs) {
+ void destroyConflictSet(ConflictSet* cs) {
-+void destroyConflictSet(ConflictSet2* cs) {
  	delete cs;
- }
- 
--ConflictBatch::ConflictBatch(ConflictSet* cs,
-+ConflictBatch::ConflictBatch(ConflictSet2* cs,
-                              std::map<int, VectorRef<int>>* conflictingKeyRangeMap,
-                              Arena* resolveBatchReplyArena)
-   : cs(cs), transactionCount(0), conflictingKeyRangeMap(conflictingKeyRangeMap),
 @@ -971,11 +982,15 @@ void ConflictBatch::detectConflicts(Version now,
  	t = timer();
  	if (newOldestVersion > cs->oldestVersion) {
@@ -112,7 +84,7 @@ index b48d32c6b..da106b5d2 100644
  
 +#if USE_RADIX_TREE
 +	Arena arena;
-+	auto* reads = new (arena) ConflictSet::ReadRange[combinedReadConflictRanges.size()];
++	auto* reads = new (arena) weaselab::ConflictSet::ReadRange[combinedReadConflictRanges.size()];
 +
 +	for (int i = 0; i < combinedReadConflictRanges.size(); ++i) {
 +		auto& read = reads[i];
@@ -122,11 +94,11 @@ index b48d32c6b..da106b5d2 100644
 +		read.end.p = combinedReadConflictRanges[i].end.begin();
 +		read.end.len = combinedReadConflictRanges[i].end.size();
 +	}
-+	auto* results = new (arena) ConflictSet::Result[combinedReadConflictRanges.size()];
++	auto* results = new (arena) weaselab::ConflictSet::Result[combinedReadConflictRanges.size()];
 +	cs->versionHistory.check(reads, results, combinedReadConflictRanges.size());
 +
 +	for (int i = 0; i < combinedReadConflictRanges.size(); ++i) {
-+		if (results[i] == ConflictSet::Conflict) {
++		if (results[i] == weaselab::ConflictSet::Conflict) {
 +			transactionConflictStatus[combinedReadConflictRanges[i].transaction] = true;
 +			if (combinedReadConflictRanges[i].conflictingKeyRange != nullptr) {
 +				combinedReadConflictRanges[i].conflictingKeyRange->push_back(*combinedReadConflictRanges[i].cKRArena,
@@ -147,7 +119,7 @@ index b48d32c6b..da106b5d2 100644
  
 +#if USE_RADIX_TREE
 +	Arena arena;
-+	auto* writes = new (arena) ConflictSet::WriteRange[combinedWriteConflictRanges.size()];
++	auto* writes = new (arena) weaselab::ConflictSet::WriteRange[combinedWriteConflictRanges.size()];
 +
 +	for (int i = 0; i < combinedWriteConflictRanges.size(); ++i) {
 +		auto& write = writes[i];
@@ -164,15 +136,6 @@ index b48d32c6b..da106b5d2 100644
  }
  
  void ConflictBatch::combineWriteConflictRanges() {
-@@ -1115,7 +1171,7 @@ void skipListTest() {
- 
- 	double start;
- 
--	ConflictSet* cs = newConflictSet();
-+	ConflictSet2* cs = newConflictSet();
- 
- 	Arena testDataArena;
- 	VectorRef<VectorRef<KeyRangeRef>> testData;
 @@ -1197,6 +1253,4 @@ void skipListTest() {
  	for (const auto& counter : skc) {
  		printf("%20s: %s\n", counter->getMetric().name().c_str(), counter->getMetric().formatted().c_str());
@@ -180,35 +143,3 @@ index b48d32c6b..da106b5d2 100644
 -
 -	printf("%d entries in version history\n", cs->versionHistory.count());
  }
-diff --git a/fdbserver/include/fdbserver/ConflictSet.h b/fdbserver/include/fdbserver/ConflictSet.h
-index 90ed2c406..b7e31217c 100644
---- a/fdbserver/include/fdbserver/ConflictSet.h
-+++ b/fdbserver/include/fdbserver/ConflictSet.h
-@@ -28,13 +28,13 @@
- #include "fdbclient/CommitTransaction.h"
- #include "fdbserver/ResolverBug.h"
- 
--struct ConflictSet;
--ConflictSet* newConflictSet();
--void clearConflictSet(ConflictSet*, Version);
--void destroyConflictSet(ConflictSet*);
-+struct ConflictSet2;
-+ConflictSet2* newConflictSet();
-+void clearConflictSet(ConflictSet2*, Version);
-+void destroyConflictSet(ConflictSet2*);
- 
- struct ConflictBatch {
--	explicit ConflictBatch(ConflictSet*,
-+	explicit ConflictBatch(ConflictSet2*,
- 	                       std::map<int, VectorRef<int>>* conflictingKeyRangeMap = nullptr,
- 	                       Arena* resolveBatchReplyArena = nullptr);
- 	~ConflictBatch();
-@@ -54,7 +54,7 @@ struct ConflictBatch {
- 	void GetTooOldTransactions(std::vector<int>& tooOldTransactions);
- 
- private:
--	ConflictSet* cs;
-+	ConflictSet2* cs;
- 	Standalone<VectorRef<struct TransactionInfo*>> transactionInfo;
- 	std::vector<struct KeyInfo> points;
- 	int transactionCount;

include/ConflictSet.h

@@ -19,6 +19,7 @@ limitations under the License.
 #include <stdint.h>
 
 #ifdef __cplusplus
+namespace weaselab {
 /** A data structure for optimistic concurrency control on ranges of
  * bitwise-lexicographically-ordered keys.
  *
@@ -26,7 +27,7 @@ limitations under the License.
  *   - It's safe to operate on two different ConflictSets in two different
  * threads concurrently
  *   - It's safe to have multiple threads operating on the same ConflictSet
- * concurrently if and only if all threads only call `check`.
+ * concurrently if and only if all threads only call const methods
  */
 struct __attribute__((__visibility__("default"))) ConflictSet {
   enum Result {
@@ -84,6 +85,9 @@ struct __attribute__((__visibility__("default"))) ConflictSet {
 
   ~ConflictSet();
 
+  /** Returns the total bytes in use by this ConflictSet */
+  int64_t getBytes() const;
+
 #if __cplusplus > 199711L
   ConflictSet(ConflictSet &&) noexcept;
   ConflictSet &operator=(ConflictSet &&) noexcept;
@@ -97,6 +101,7 @@ struct __attribute__((__visibility__("default"))) ConflictSet {
 private:
   Impl *impl;
 };
+} /* namespace weaselab */
 
 #else
 
@@ -107,7 +112,8 @@ private:
  *   - It's safe to operate on two different ConflictSets in two different
  * threads concurrently
  *   - It's safe to have multiple threads operating on the same ConflictSet
- * concurrently if and only if all threads only call `check`.
+ * concurrently if and only if all threads only call functions that accept a
+ * const ConflictSet pointer
  */
 typedef struct ConflictSet ConflictSet;
 
@@ -147,7 +153,8 @@ typedef struct {
 } ConflictSet_WriteRange;
 
 /** The result of checking reads[i] is written in results[i] */
-void ConflictSet_check(ConflictSet *cs, const ConflictSet_ReadRange *reads,
+void ConflictSet_check(const ConflictSet *cs,
+                       const ConflictSet_ReadRange *reads,
                        ConflictSet_Result *results, int count);
 
 /** `writes` must be sorted ascending, and must not have adjacent or
@@ -169,4 +176,7 @@ ConflictSet *ConflictSet_create(int64_t oldestVersion);
 
 void ConflictSet_destroy(ConflictSet *cs);
 
+/** Returns the total bytes in use by this ConflictSet */
+int64_t ConflictSet_getBytes(const ConflictSet *cs);
+
 #endif

package_macos.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+set -euxo pipefail
+
+umask 022
+
+SRC_DIR="${0%/*}"
+BUILD_ARM="$(mktemp -d -t conflict-set-arm)"
+BUILD_X86="$(mktemp -d -t conflict-set-x86)"
+
+cmake_args=(-DCMAKE_CXX_FLAGS=-DNVALGRIND -DCPACK_PACKAGING_INSTALL_PREFIX=/usr/local)
+
+cmake -S"$SRC_DIR" -B"$BUILD_ARM" -DCMAKE_OSX_ARCHITECTURES=arm64 "${cmake_args[@]}"
+cmake --build "$BUILD_ARM" --target conflict-set --target conflict-set-static
+
+cmake -S"$SRC_DIR" -B"$BUILD_X86" -DCMAKE_OSX_ARCHITECTURES=x86_64 "${cmake_args[@]}"
+cmake --build "$BUILD_X86" --target conflict-set --target conflict-set-static
+
+VERSION="$(cat "$BUILD_ARM/version.txt")"
+
+lipo -create "$BUILD_ARM/radix_tree/libconflict-set.$VERSION.dylib" "$BUILD_X86/radix_tree/libconflict-set.$VERSION.dylib" -output "libconflict-set.$VERSION.dylib.tmp"
+lipo -create "$BUILD_ARM"/libconflict-set-static.a "$BUILD_X86"/libconflict-set-static.a -output libconflict-set-static.a.tmp
+
+mv "libconflict-set.$VERSION.dylib.tmp" "$BUILD_ARM/radix_tree/libconflict-set.$VERSION.dylib"
+mv libconflict-set-static.a.tmp "$BUILD_ARM/libconflict-set-static.a"
+
+pushd "$BUILD_ARM"
+cpack -G productbuild
+popd
+
+mv "$BUILD_ARM/conflict-set-$VERSION-Darwin.pkg" .
+
+rm -rf  "$BUILD_ARM" "$BUILD_X86"

privatize_symbols_macos.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+# This has the effect of making visibility=hidden symbols private in object files
+for obj in "$@" ; do
+  ld -r "$obj" -o "$obj.tmp"
+  touch -r "$obj" "$obj.tmp"
+  mv "$obj.tmp" "$obj"
+done

symbol-exports.txt

@@ -0,0 +1,17 @@
+ConflictSet_addWrites
+ConflictSet_check
+ConflictSet_create
+ConflictSet_destroy
+ConflictSet_getBytes
+ConflictSet_setOldestVersion
+_ZN8weaselab11ConflictSet16setOldestVersionEl
+_ZN8weaselab11ConflictSet9addWritesEPKNS0_10WriteRangeEil
+_ZN8weaselab11ConflictSetaSEOS0_
+_ZN8weaselab11ConflictSetC1El
+_ZN8weaselab11ConflictSetC1EOS0_
+_ZN8weaselab11ConflictSetC2El
+_ZN8weaselab11ConflictSetC2EOS0_
+_ZN8weaselab11ConflictSetD1Ev
+_ZN8weaselab11ConflictSetD2Ev
+_ZNK8weaselab11ConflictSet5checkEPKNS0_9ReadRangeEPNS0_6ResultEi
+_ZNK8weaselab11ConflictSet8getBytesEv

symbol-imports.txt

@@ -0,0 +1,9 @@
+_GLOBAL_OFFSET_TABLE_
+__stack_chk_fail@GLIBC_2.4
+__tls_get_addr@GLIBC_2.3
+abort@GLIBC_2.2.5
+free@GLIBC_2.2.5
+malloc@GLIBC_2.2.5
+memcpy@GLIBC_2.14
+memmove@GLIBC_2.2.5
+memset@GLIBC_2.2.5

symbols.txt

@@ -1,15 +0,0 @@
-ConflictSet_addWrites
-ConflictSet_check
-ConflictSet_create
-ConflictSet_destroy
-ConflictSet_setOldestVersion
-_ZN11ConflictSet16setOldestVersionEl
-_ZN11ConflictSet9addWritesEPKNS_10WriteRangeEil
-_ZN11ConflictSetaSEOS_
-_ZN11ConflictSetC1El
-_ZN11ConflictSetC1EOS_
-_ZN11ConflictSetC2El
-_ZN11ConflictSetC2EOS_
-_ZN11ConflictSetD1Ev
-_ZN11ConflictSetD2Ev
-_ZNK11ConflictSet5checkEPKNS_9ReadRangeEPNS_6ResultEi

test_conflict_set.py

@@ -0,0 +1,9 @@
+from conflict_set import *
+
+
+def test_conflict_set():
+    with ConflictSet() as cs:
+        cs.addWrites(1, write(b""))
+        assert cs.check(read(0, b"")) == [Result.CONFLICT]
+        cs.setOldestVersion(1)
+        assert cs.check(read(0, b"")) == [Result.TOO_OLD]

test_symbols.sh

@@ -2,5 +2,15 @@
 
 set -euo pipefail
 
+# ./test_symbols.sh <library> <expected exported symbols file> <allowed imported symbols file>
+
 diff -u <(sort < "$2") <(nm "$1" | grep " T " | cut -f3 -d " " | sort)
-nm "$1" | grep " U " | (! grep -Pv 'abort|free|malloc|mem[a-z]*|__ashlti3|__stack_chk_[a-z]*')
+ec=0
+for symbol in $(nm "$1" | grep " U " | sed 's/ U //') ; do
+    if ! grep --fixed-strings "$symbol" "$3" > /dev/null ; then
+        echo "Imported symbol $symbol not present in $3"
+        ec=1
+    fi
+done
+
+exit $ec