[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

1 files changed, 11 insertions, 2 deletions

diff --git a/clang/lib/Tooling/Execution.cpp b/clang/lib/Tooling/Execution.cpp
index ff68f85adb2..5d6559fb2b4 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;
 }