[clangd] [C++20] [Modules] Add scanning cache

ChuanqiXu9 · ChuanqiXu9 · commit b452efa55d58 · 2025-02-06T11:17:04.000+08:00
Previously, everytime we want to get a source file declaring a specific
module, we need to scan the whole projects again and again. The
performance is not wanted. This patch tries to improve this by
introducing a simple cache.
diff --git a/clang-tools-extra/clangd/CMakeLists.txt b/clang-tools-extra/clangd/CMakeLists.txt
@@ -99,6 +99,7 @@ add_clang_library(clangDaemon STATIC
   ModulesBuilder.cpp
   PathMapping.cpp
   Protocol.cpp
+  ProjectModulesCache.cpp
   Quality.cpp
   ParsedAST.cpp
   Preamble.cpp
diff --git a/clang-tools-extra/clangd/ModulesBuilder.cpp b/clang-tools-extra/clangd/ModulesBuilder.cpp
@@ -361,15 +361,16 @@ void ModuleFileCache::remove(StringRef ModuleName) {
 /// ModuleName in topological order. The \param ModuleName is guaranteed to
 /// be the last element in \param ModuleNames.
 llvm::SmallVector<StringRef> getAllRequiredModules(ProjectModules &MDB,
-                                                   StringRef ModuleName) {
+                                                   StringRef ModuleName,
+                                                   ProjectModulesCache &Cache) {
   llvm::SmallVector<llvm::StringRef> ModuleNames;
   llvm::StringSet<> ModuleNamesSet;
 
   auto VisitDeps = [&](StringRef ModuleName, auto Visitor) -> void {
     ModuleNamesSet.insert(ModuleName);
 
     for (StringRef RequiredModuleName :
-         MDB.getRequiredModules(MDB.getSourceForModuleName(ModuleName)))
+         MDB.getRequiredModules(MDB.getSourceForModuleName(Cache, ModuleName)))
       if (ModuleNamesSet.insert(RequiredModuleName).second)
         Visitor(RequiredModuleName, Visitor);
 
@@ -384,7 +385,9 @@ llvm::SmallVector<StringRef> getAllRequiredModules(ProjectModules &MDB,
 
 class ModulesBuilder::ModulesBuilderImpl {
 public:
-  ModulesBuilderImpl(const GlobalCompilationDatabase &CDB) : Cache(CDB) {}
+  ModulesBuilderImpl(const GlobalCompilationDatabase &CDB) : Cache(CDB) {
+    MDBCache = createProjectModulesCache();
+  }
 
   const GlobalCompilationDatabase &getCDB() const { return Cache.getCDB(); }
 
@@ -395,6 +398,7 @@ class ModulesBuilder::ModulesBuilderImpl {
 
 private:
   ModuleFileCache Cache;
+  std::unique_ptr<ProjectModulesCache> MDBCache;
 };
 
 llvm::Error ModulesBuilder::ModulesBuilderImpl::getOrBuildModuleFile(
@@ -403,7 +407,8 @@ llvm::Error ModulesBuilder::ModulesBuilderImpl::getOrBuildModuleFile(
   if (BuiltModuleFiles.isModuleUnitBuilt(ModuleName))
     return llvm::Error::success();
 
-  PathRef ModuleUnitFileName = MDB.getSourceForModuleName(ModuleName);
+  PathRef ModuleUnitFileName =
+      MDB.getSourceForModuleName(*MDBCache, ModuleName);
   /// It is possible that we're meeting third party modules (modules whose
   /// source are not in the project. e.g, the std module may be a third-party
   /// module for most project) or something wrong with the implementation of
@@ -416,7 +421,7 @@ llvm::Error ModulesBuilder::ModulesBuilderImpl::getOrBuildModuleFile(
         llvm::formatv("Don't get the module unit for module {0}", ModuleName));
 
   // Get Required modules in topological order.
-  auto ReqModuleNames = getAllRequiredModules(MDB, ModuleName);
+  auto ReqModuleNames = getAllRequiredModules(MDB, ModuleName, *MDBCache);
   for (llvm::StringRef ReqModuleName : ReqModuleNames) {
     if (BuiltModuleFiles.isModuleUnitBuilt(ModuleName))
       continue;
diff --git a/clang-tools-extra/clangd/ProjectModules.h b/clang-tools-extra/clangd/ProjectModules.h
@@ -9,6 +9,7 @@
 #ifndef LLVM_CLANG_TOOLS_EXTRA_CLANGD_PROJECTMODULES_H
 #define LLVM_CLANG_TOOLS_EXTRA_CLANGD_PROJECTMODULES_H
 
+#include "ProjectModulesCache.h"
 #include "support/Function.h"
 #include "support/Path.h"
 #include "support/ThreadsafeFS.h"
@@ -43,7 +44,7 @@ class ProjectModules {
 
   virtual std::vector<std::string> getRequiredModules(PathRef File) = 0;
   virtual PathRef
-  getSourceForModuleName(llvm::StringRef ModuleName,
+  getSourceForModuleName(ProjectModulesCache &Cache, llvm::StringRef ModuleName,
                          PathRef RequiredSrcFile = PathRef()) = 0;
 
   virtual void setCommandMangler(CommandMangler Mangler) {}
diff --git a/clang-tools-extra/clangd/ProjectModulesCache.cpp b/clang-tools-extra/clangd/ProjectModulesCache.cpp
@@ -0,0 +1,56 @@
+//===------------------ ProjectModulesCache.cpp ------------------*- C++-*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "ProjectModulesCache.h"
+#include "llvm/ADT/StringMap.h"
+#include <mutex>
+
+namespace clang::clangd {
+namespace {
+class SharedProjectModulesCache : public ProjectModulesCache {
+public:
+  std::optional<std::string>
+  getSourceForModuleName(llvm::StringRef ModuleName,
+                         PathRef RequiredSrcFile = PathRef()) override {
+    std::lock_guard<std::mutex> Lock(Mutex);
+
+    auto Iter = ModuleNameToSource.find(ModuleName);
+    if (Iter == ModuleNameToSource.end())
+      return std::nullopt;
+
+    return Iter->second;
+  }
+
+  void clearEntry(llvm::StringRef ModuleName,
+                  PathRef RequiredSrcFile = PathRef()) override {
+    std::lock_guard<std::mutex> Lock(Mutex);
+
+    auto Iter = ModuleNameToSource.find(ModuleName);
+    if (Iter == ModuleNameToSource.end())
+      return;
+
+    ModuleNameToSource.erase(Iter);
+  }
+
+  void setEntry(PathRef FilePath, llvm::StringRef ModuleName) override {
+    std::lock_guard<std::mutex> Lock(Mutex);
+
+    ModuleNameToSource[ModuleName] = FilePath;
+  }
+
+private:
+  std::mutex Mutex;
+  llvm::StringMap<std::string> ModuleNameToSource;
+};
+} // namespace
+
+std::unique_ptr<ProjectModulesCache> createProjectModulesCache() {
+  return std::make_unique<SharedProjectModulesCache>();
+}
+
+} // namespace clang::clangd
diff --git a/clang-tools-extra/clangd/ProjectModulesCache.h b/clang-tools-extra/clangd/ProjectModulesCache.h
@@ -0,0 +1,46 @@
+//===------------------ ProjectModulesCache.h --------------------*- C++-*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANGD_PROJECTMODULESCACHE_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANGD_PROJECTMODULESCACHE_H
+
+#include "support/Path.h"
+#include <memory>
+
+namespace clang {
+namespace clangd {
+
+/// A cache for the module name to file name map in the project.
+/// The rationale is:
+///   (1) It is fast to get the module name to a file.
+///   (2) It may be slow to get a file with a specified module name.
+///   (3) The module name of files may not change drastically and frequently.
+///
+/// The cache itself is not responsible for the validness of cached result.
+/// Users of the cache should check it after getting the result and updating
+/// the cache if the result is invalid.
+class ProjectModulesCache {
+public:
+  virtual ~ProjectModulesCache() = default;
+
+  virtual std::optional<std::string>
+  getSourceForModuleName(llvm::StringRef ModuleName,
+                         PathRef RequiredSrcFile = PathRef()) = 0;
+
+  virtual void clearEntry(llvm::StringRef ModuleName,
+                          PathRef RequiredSrcFile = PathRef()) = 0;
+
+  virtual void setEntry(PathRef FilePath, llvm::StringRef ModuleName) = 0;
+};
+
+std::unique_ptr<ProjectModulesCache> createProjectModulesCache();
+
+} // namespace clangd
+} // namespace clang
+
+#endif
diff --git a/clang-tools-extra/clangd/ScanningProjectModules.cpp b/clang-tools-extra/clangd/ScanningProjectModules.cpp
@@ -49,7 +49,8 @@ class ModuleDependencyScanner {
 
   /// Scanning the single file specified by \param FilePath.
   std::optional<ModuleDependencyInfo>
-  scan(PathRef FilePath, const ProjectModules::CommandMangler &Mangler);
+  scan(PathRef FilePath, const ProjectModules::CommandMangler &Mangler,
+       ProjectModulesCache *Cache);
 
   /// Scanning every source file in the current project to get the
   /// <module-name> to <module-unit-source> map.
@@ -58,7 +59,8 @@ class ModuleDependencyScanner {
   /// a global module dependency scanner to monitor every file. Or we
   /// can simply require the build systems (or even the end users)
   /// to provide the map.
-  void globalScan(const ProjectModules::CommandMangler &Mangler);
+  void globalScan(const ProjectModules::CommandMangler &Mangler,
+                  ProjectModulesCache &Cache);
 
   /// Get the source file from the module name. Note that the language
   /// guarantees all the module names are unique in a valid program.
@@ -68,6 +70,12 @@ class ModuleDependencyScanner {
   /// declaring the same module.
   PathRef getSourceForModuleName(llvm::StringRef ModuleName) const;
 
+  /// Validate if source file \c Source declare a module with \c ModuleName.
+  /// If yes, return the source file path. Otherwise, return std::nullopt.
+  std::optional<PathRef>
+  validateSourceForModuleName(PathRef Source, llvm::StringRef ModuleName,
+                              const ProjectModules::CommandMangler &Mangler);
+
   /// Return the direct required modules. Indirect required modules are not
   /// included.
   std::vector<std::string>
@@ -83,15 +91,14 @@ class ModuleDependencyScanner {
 
   clang::tooling::dependencies::DependencyScanningService Service;
 
-  // TODO: Add a scanning cache.
-
   // Map module name to source file path.
   llvm::StringMap<std::string> ModuleNameToSource;
 };
 
 std::optional<ModuleDependencyScanner::ModuleDependencyInfo>
 ModuleDependencyScanner::scan(PathRef FilePath,
-                              const ProjectModules::CommandMangler &Mangler) {
+                              const ProjectModules::CommandMangler &Mangler,
+                              ProjectModulesCache *Cache) {
   auto Candidates = CDB->getCompileCommands(FilePath);
   if (Candidates.empty())
     return std::nullopt;
@@ -124,6 +131,9 @@ ModuleDependencyScanner::scan(PathRef FilePath,
   if (ScanningResult->Provides) {
     ModuleNameToSource[ScanningResult->Provides->ModuleName] = FilePath;
     Result.ModuleName = ScanningResult->Provides->ModuleName;
+
+    if (Cache)
+      Cache->setEntry(FilePath, ScanningResult->Provides->ModuleName);
   }
 
   for (auto &Required : ScanningResult->Requires)
@@ -133,9 +143,9 @@ ModuleDependencyScanner::scan(PathRef FilePath,
 }
 
 void ModuleDependencyScanner::globalScan(
-    const ProjectModules::CommandMangler &Mangler) {
+    const ProjectModules::CommandMangler &Mangler, ProjectModulesCache &Cache) {
   for (auto &File : CDB->getAllFiles())
-    scan(File, Mangler);
+    scan(File, Mangler, &Cache);
 
   GlobalScanned = true;
 }
@@ -155,12 +165,28 @@ PathRef ModuleDependencyScanner::getSourceForModuleName(
 
 std::vector<std::string> ModuleDependencyScanner::getRequiredModules(
     PathRef File, const ProjectModules::CommandMangler &Mangler) {
-  auto ScanningResult = scan(File, Mangler);
+  auto ScanningResult = scan(File, Mangler, /*Cache=*/nullptr);
   if (!ScanningResult)
     return {};
 
   return ScanningResult->RequiredModules;
 }
+
+std::optional<PathRef> ModuleDependencyScanner::validateSourceForModuleName(
+    PathRef Source, llvm::StringRef ModuleName,
+    const ProjectModules::CommandMangler &Mangler) {
+  auto ScanningResult = scan(Source, Mangler, /*Cache=*/nullptr);
+  if (!ScanningResult)
+    return std::nullopt;
+
+  // If the name matches, return the source file path from ModuleNameToSource
+  // cache instead of the input. Since the lifetime of the input may not be long
+  // enough.
+  if (ScanningResult->ModuleName == ModuleName)
+    return ModuleNameToSource[ModuleName];
+
+  return std::nullopt;
+}
 } // namespace
 
 /// TODO: The existing `ScanningAllProjectModules` is not efficient. See the
@@ -190,9 +216,18 @@ class ScanningAllProjectModules : public ProjectModules {
   /// RequiredSourceFile is not used intentionally. See the comments of
   /// ModuleDependencyScanner for detail.
   PathRef
-  getSourceForModuleName(llvm::StringRef ModuleName,
+  getSourceForModuleName(ProjectModulesCache &Cache, llvm::StringRef ModuleName,
                          PathRef RequiredSourceFile = PathRef()) override {
-    Scanner.globalScan(Mangler);
+    if (auto Source =
+            Cache.getSourceForModuleName(ModuleName, RequiredSourceFile)) {
+      if (std::optional<PathRef> Path =
+              Scanner.validateSourceForModuleName(*Source, ModuleName, Mangler))
+        return *Path;
+
+      Cache.clearEntry(ModuleName, RequiredSourceFile);
+    }
+
+    Scanner.globalScan(Mangler, Cache);
     return Scanner.getSourceForModuleName(ModuleName);
   }
 
