Add std::unordered_map implementation

As a rough upper bound for point query throughput

CMakeLists.txt

@@ -109,6 +109,19 @@ if(BUILD_TESTING)
   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 -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})
+
   add_executable(conflict_set_main ConflictSet.cpp)
   target_include_directories(conflict_set_main
                              PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include)

HashTable.cpp

@@ -0,0 +1,141 @@
+#include "ConflictSet.h"
+#include "Internal.h"
+#include <functional>
+#include <string>
+#include <unordered_map>
+
+// This implementation isn't correct for range queries :). It's just intended as
+// a reference for performance comparison with point queries.
+
+// struct is from "https://www.cppstories.com/2021/heterogeneous-access-cpp20/"
+struct string_hash {
+  using is_transparent = void;
+  [[nodiscard]] size_t operator()(std::string_view txt) const {
+    return std::hash<std::string_view>{}(txt);
+  }
+  [[nodiscard]] size_t operator()(const std::string &txt) const {
+    return std::hash<std::string>{}(txt);
+  }
+};
+
+struct __attribute__((visibility("hidden"))) ConflictSet::Impl {
+  Impl(int64_t oldestVersion) : oldestVersion(oldestVersion) {}
+  void check(const ConflictSet::ReadRange *reads, ConflictSet::Result *results,
+             int count) const {
+    for (int i = 0; i < count; ++i) {
+      auto key =
+          std::string_view((const char *)reads[i].begin.p, reads[i].begin.len);
+      auto version = reads[i].readVersion;
+      if (version < oldestVersion) {
+        results[i] = TooOld;
+        continue;
+      }
+      auto iter = map.find(key);
+      results[i] =
+          iter == map.end() || iter->second <= version ? Commit : Conflict;
+    }
+  }
+
+  void addWrites(const ConflictSet::WriteRange *writes, int count) {
+    for (int i = 0; i < count; ++i) {
+      auto &max = map[std::string((const char *)writes[i].begin.p,
+                                  writes[i].begin.len)];
+      max = std::max(max, writes[i].writeVersion);
+      keyUpdates += 2;
+    }
+  }
+
+  void setOldestVersion(int64_t oldestVersion) {
+    if (oldestVersion <= this->oldestVersion) {
+      return;
+    }
+    this->oldestVersion = oldestVersion;
+    if (keyUpdates < 100) {
+      return;
+    }
+
+    for (; keyUpdates > 0 && removalIter != map.end(); --keyUpdates) {
+      if (removalIter->second <= oldestVersion) {
+        removalIter = map.erase(removalIter);
+      } else {
+        ++removalIter;
+      }
+    }
+
+    if (removalIter == map.end()) {
+      removalIter = map.begin();
+    }
+  }
+
+private:
+  int64_t keyUpdates = 0;
+  int64_t oldestVersion;
+  std::unordered_map<std::string, int64_t, string_hash, std::equal_to<>> map;
+
+  // This iterator outliving the call to setOldestVersion is only safe because
+  // we only erase from within setOldestVersion
+  decltype(map.begin()) removalIter;
+};
+
+void ConflictSet::check(const ReadRange *reads, Result *results,
+                        int count) const {
+  return impl->check(reads, results, count);
+}
+
+void ConflictSet::addWrites(const WriteRange *writes, int count) {
+  return impl->addWrites(writes, count);
+}
+
+void ConflictSet::setOldestVersion(int64_t oldestVersion) {
+  return impl->setOldestVersion(oldestVersion);
+}
+
+ConflictSet::ConflictSet(int64_t oldestVersion)
+    : impl(new (safe_malloc(sizeof(Impl))) Impl{oldestVersion}) {}
+
+ConflictSet::~ConflictSet() {
+  if (impl) {
+    impl->~Impl();
+    free(impl);
+  }
+}
+
+ConflictSet::ConflictSet(ConflictSet &&other) noexcept
+    : impl(std::exchange(other.impl, nullptr)) {}
+
+ConflictSet &ConflictSet::operator=(ConflictSet &&other) noexcept {
+  impl = std::exchange(other.impl, nullptr);
+  return *this;
+}
+
+using ConflictSet_Result = ConflictSet::Result;
+using ConflictSet_Key = ConflictSet::Key;
+using ConflictSet_ReadRange = ConflictSet::ReadRange;
+using ConflictSet_WriteRange = ConflictSet::WriteRange;
+
+extern "C" {
+__attribute__((__visibility__("default"))) void
+ConflictSet_check(void *cs, const ConflictSet_ReadRange *reads,
+                  ConflictSet_Result *results, int count) {
+  ((ConflictSet::Impl *)cs)->check(reads, results, count);
+}
+__attribute__((__visibility__("default"))) void
+ConflictSet_addWrites(void *cs, const ConflictSet_WriteRange *writes,
+                      int count) {
+  ((ConflictSet::Impl *)cs)->addWrites(writes, count);
+}
+__attribute__((__visibility__("default"))) void
+ConflictSet_setOldestVersion(void *cs, int64_t oldestVersion) {
+  ((ConflictSet::Impl *)cs)->setOldestVersion(oldestVersion);
+}
+__attribute__((__visibility__("default"))) void *
+ConflictSet_create(int64_t oldestVersion) {
+  return new (safe_malloc(sizeof(ConflictSet::Impl)))
+      ConflictSet::Impl{oldestVersion};
+}
+__attribute__((__visibility__("default"))) void ConflictSet_destroy(void *cs) {
+  using Impl = ConflictSet::Impl;
+  ((Impl *)cs)->~Impl();
+  free(cs);
+}
+}

RealDataBench.cpp

@@ -3,7 +3,6 @@
 #include <chrono>
 #include <cstring>
 #include <fcntl.h>
-#include <fstream>
 #include <sys/mman.h>
 #include <sys/stat.h>
 #include <unistd.h>