From 9f36c7e704ea7a604a7962452b15dc8646659744 Mon Sep 17 00:00:00 2001
From: Haojian Wu <hokein@google.com>
Date: Wed, 11 Apr 2018 08:13:07 +0000
Subject: [PATCH] [Tooling] Optimize memory usage in InMemoryToolResults.

Avoid storing duplicated "std::string"s.

clangd's global-symbol-builder takes 20+GB memory running across LLVM
repository. With this patch, the used memory is ~10GB (running on 48
threads, most of meory are AST-related).

Subscribers: klimek, cfe-commits

Differential Revision: https://reviews.llvm.org/D45479

llvm-svn: 329784
---
 clang/include/clang/Tooling/Execution.h | 17 ++++++++++++++---
 clang/lib/Tooling/AllTUsExecution.cpp   |  3 ++-
 clang/lib/Tooling/Execution.cpp         | 13 +++++++++++--
 3 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/clang/include/clang/Tooling/Execution.h b/clang/include/clang/Tooling/Execution.h
index 1a44c478..a3036bd 100644
--- a/clang/include/clang/Tooling/Execution.h
+++ b/clang/include/clang/Tooling/Execution.h
@@ -32,6 +32,7 @@
 #include "clang/Tooling/Tooling.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/Registry.h"
+#include "llvm/Support/StringSaver.h"
 
 namespace clang {
 namespace tooling {
@@ -45,20 +46,30 @@ class ToolResults {
 public:
   virtual ~ToolResults() = default;
   virtual void addResult(StringRef Key, StringRef Value) = 0;
-  virtual std::vector<std::pair<std::string, std::string>> AllKVResults() = 0;
+  virtual std::vector<std::pair<llvm::StringRef, llvm::StringRef>>
+  AllKVResults() = 0;
   virtual void forEachResult(
       llvm::function_ref<void(StringRef Key, StringRef Value)> Callback) = 0;
 };
 
+/// \brief Stores the key-value results in memory. It maintains the lifetime of
+/// the result. Clang tools using this class are expected to generate a small
+/// set of different results, or a large set of duplicated results.
 class InMemoryToolResults : public ToolResults {
 public:
+  InMemoryToolResults() : StringsPool(Arena) {}
   void addResult(StringRef Key, StringRef Value) override;
-  std::vector<std::pair<std::string, std::string>> AllKVResults() override;
+  std::vector<std::pair<llvm::StringRef, llvm::StringRef>>
+  AllKVResults() override;
   void forEachResult(llvm::function_ref<void(StringRef Key, StringRef Value)>
                          Callback) override;
 
 private:
-  std::vector<std::pair<std::string, std::string>> KVResults;
+  llvm::BumpPtrAllocator Arena;
+  llvm::StringSaver StringsPool;
+  llvm::DenseSet<llvm::StringRef> Strings;
+
+  std::vector<std::pair<llvm::StringRef, llvm::StringRef>> KVResults;
 };
 
 /// \brief The context of an execution, including the information about
diff --git a/clang/lib/Tooling/AllTUsExecution.cpp b/clang/lib/Tooling/AllTUsExecution.cpp
index 0c0854d..b761556 100644
--- a/clang/lib/Tooling/AllTUsExecution.cpp
+++ b/clang/lib/Tooling/AllTUsExecution.cpp
@@ -36,7 +36,8 @@ public:
     Results.addResult(Key, Value);
   }
 
-  std::vector<std::pair<std::string, std::string>> AllKVResults() override {
+  std::vector<std::pair<llvm::StringRef, llvm::StringRef>>
+  AllKVResults() override {
     return Results.AllKVResults();
   }
 
diff --git a/clang/lib/Tooling/Execution.cpp b/clang/lib/Tooling/Execution.cpp
index ff68f85..5d6559f 100644
--- a/clang/lib/Tooling/Execution.cpp
+++ b/clang/lib/Tooling/Execution.cpp
@@ -21,10 +21,19 @@ static llvm::cl::opt<std::string>
                  llvm::cl::init("standalone"));
 
 void InMemoryToolResults::addResult(StringRef Key, StringRef Value) {
-  KVResults.push_back({Key.str(), Value.str()});
+  auto Intern = [&](StringRef &V) {
+    auto R = Strings.insert(V);
+    if (R.second) { // A new entry, create a new string copy.
+      *R.first = StringsPool.save(V);
+    }
+    V = *R.first;
+  };
+  Intern(Key);
+  Intern(Value);
+  KVResults.push_back({Key, Value});
 }
 
-std::vector<std::pair<std::string, std::string>>
+std::vector<std::pair<llvm::StringRef, llvm::StringRef>>
 InMemoryToolResults::AllKVResults() {
   return KVResults;
 }
-- 
2.7.4