Make dwarf parsing multi-threaded

Tamas Berghammer · Tamas Berghammer · commit f84916d40fb2 · 2015-10-20T12:42:10.000Z
Loading the debug info from a large application is the slowest task LLDB do. This CL makes most of the dwarf parsing code multi-threaded. As a result the speed of "attach; backtrace; exit;" when the inferior is an LLDB with full debug info increased by a factor of 2 (on my machine). Differential revision: http://reviews.llvm.org/D13662 llvm-svn: 250821
diff --git a/lldb/source/Plugins/SymbolFile/DWARF/NameToDIE.cpp b/lldb/source/Plugins/SymbolFile/DWARF/NameToDIE.cpp
@@ -83,3 +83,14 @@ NameToDIE::ForEach (std::function <bool(const char *name, const DIERef& die_ref)
             break;
     }
 }
+
+void
+NameToDIE::Append (const NameToDIE& other)
+{
+    const uint32_t size = other.m_map.GetSize();
+    for (uint32_t i = 0; i < size; ++i)
+    {
+        m_map.Append(other.m_map.GetCStringAtIndexUnchecked (i),
+                     other.m_map.GetValueAtIndexUnchecked (i));
+    }
+}
diff --git a/lldb/source/Plugins/SymbolFile/DWARF/NameToDIE.h b/lldb/source/Plugins/SymbolFile/DWARF/NameToDIE.h
@@ -37,6 +37,9 @@ class NameToDIE
     void
     Insert (const lldb_private::ConstString& name, const DIERef& die_ref);
 
+    void
+    Append (const NameToDIE& other);
+
     void
     Finalize();
 
diff --git a/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp b/lldb/source/Plugins/SymbolFile/DWARF/SymbolFileDWARF.cpp
@@ -50,6 +50,8 @@
 
 #include "lldb/Target/Language.h"
 
+#include "lldb/Utility/TaskPool.h"
+
 #include "DWARFASTParser.h"
 #include "DWARFCompileUnit.h"
 #include "DWARFDebugAbbrev.h"
@@ -2035,40 +2037,72 @@ SymbolFileDWARF::Index ()
                         "SymbolFileDWARF::Index (%s)",
                         GetObjectFile()->GetFileSpec().GetFilename().AsCString("<Unknown>"));
 
+    
+
     DWARFDebugInfo* debug_info = DebugInfo();
     if (debug_info)
     {
-        uint32_t cu_idx = 0;
         const uint32_t num_compile_units = GetNumCompileUnits();
-        for (cu_idx = 0; cu_idx < num_compile_units; ++cu_idx)
+        std::vector<NameToDIE> function_basename_index(num_compile_units);
+        std::vector<NameToDIE> function_fullname_index(num_compile_units);
+        std::vector<NameToDIE> function_method_index(num_compile_units);
+        std::vector<NameToDIE> function_selector_index(num_compile_units);
+        std::vector<NameToDIE> objc_class_selectors_index(num_compile_units);
+        std::vector<NameToDIE> global_index(num_compile_units);
+        std::vector<NameToDIE> type_index(num_compile_units);
+        std::vector<NameToDIE> namespace_index(num_compile_units);
+        
+        auto parser_fn = [this,
+                          debug_info,
+                          &function_basename_index,
+                          &function_fullname_index,
+                          &function_method_index,
+                          &function_selector_index,
+                          &objc_class_selectors_index,
+                          &global_index,
+                          &type_index,
+                          &namespace_index](uint32_t cu_idx)
         {
             DWARFCompileUnit* dwarf_cu = debug_info->GetCompileUnitAtIndex(cu_idx);
+            bool clear_dies = dwarf_cu->ExtractDIEsIfNeeded(false) > 1;
 
-            bool clear_dies = dwarf_cu->ExtractDIEsIfNeeded (false) > 1;
+            dwarf_cu->Index(function_basename_index[cu_idx],
+                            function_fullname_index[cu_idx],
+                            function_method_index[cu_idx],
+                            function_selector_index[cu_idx],
+                            objc_class_selectors_index[cu_idx],
+                            global_index[cu_idx],
+                            type_index[cu_idx],
+                            namespace_index[cu_idx]);
 
-            dwarf_cu->Index (m_function_basename_index,
-                             m_function_fullname_index,
-                             m_function_method_index,
-                             m_function_selector_index,
-                             m_objc_class_selectors_index,
-                             m_global_index, 
-                             m_type_index,
-                             m_namespace_index);
-            
             // Keep memory down by clearing DIEs if this generate function
             // caused them to be parsed
             if (clear_dies)
-                dwarf_cu->ClearDIEs (true);
-        }
-        
-        m_function_basename_index.Finalize();
-        m_function_fullname_index.Finalize();
-        m_function_method_index.Finalize();
-        m_function_selector_index.Finalize();
-        m_objc_class_selectors_index.Finalize();
-        m_global_index.Finalize(); 
-        m_type_index.Finalize();
-        m_namespace_index.Finalize();
+                dwarf_cu->ClearDIEs(true);
+        };
+
+        std::vector<std::future<void>> results;
+        for (uint32_t cu_idx = 0; cu_idx < num_compile_units; ++cu_idx)
+            results.emplace_back(TaskPool::AddTask(parser_fn, cu_idx));
+        for (auto& f : results)
+            f.wait();
+
+        auto merge_fn = [](NameToDIE& target, const std::vector<NameToDIE>& sources)
+        {
+            for (const auto& src : sources)
+                target.Append(src);
+            target.Finalize();
+        };
+
+        TaskPool::RunTasks(
+            [&]() { merge_fn(m_function_basename_index, function_basename_index); },
+            [&]() { merge_fn(m_function_fullname_index, function_fullname_index); },
+            [&]() { merge_fn(m_function_method_index, function_method_index); },
+            [&]() { merge_fn(m_function_selector_index, function_selector_index); },
+            [&]() { merge_fn(m_objc_class_selectors_index, objc_class_selectors_index); },
+            [&]() { merge_fn(m_global_index, global_index); },
+            [&]() { merge_fn(m_type_index, type_index); },
+            [&]() { merge_fn(m_namespace_index, namespace_index); });
 
 #if defined (ENABLE_DEBUG_PRINTF)
         StreamFile s(stdout, false);
