Breakpad Linux/Mac symbol dumper: Share duplicate strings that arise in DWARF data.

This patch avoids allocating many copies of identical strings appearing in
debugging information. Without this patch, running dump_syms on Mozilla's
libxul.so (with 173MiB of debugging information) has a peak resident set of
around 450MiB. With this patch, the peak is around 365MiB.

a=jimblandy, r=mark


git-svn-id: http://google-breakpad.googlecode.com/svn/trunk@626 4c0a9323-5329-0410-9bdc-e9ce6186880e

3 files changed, 62 insertions, 7 deletions

diff --git a/src/common/dwarf_cfi_to_module.cc b/src/common/dwarf_cfi_to_module.cc
index 611cecd5..ed0b406d 100644
--- a/src/common/dwarf_cfi_to_module.cc
+++ b/src/common/dwarf_cfi_to_module.cc
@@ -117,7 +117,7 @@ bool DwarfCFIToModule::Entry(size_t offset, uint64 address, uint64 length,
   // address on entry to the function. So establish an initial .ra
   // rule citing the return address register.
   if (return_address_ < register_names_.size())
-    entry_->initial_rules[".ra"] = register_names_[return_address_];
+    entry_->initial_rules[ra_name_] = register_names_[return_address_];
 
   return true;
 }
@@ -126,11 +126,11 @@ string DwarfCFIToModule::RegisterName(int i) {
   assert(entry_);
   if (i < 0) {
     assert(i == kCFARegister);
-    return ".cfa";
+    return cfa_name_;
   }
   unsigned reg = i;
   if (reg == return_address_)
-    return ".ra";
+    return ra_name_;
 
   if (0 <= reg && reg < register_names_.size())
     return register_names_[reg];
@@ -144,12 +144,21 @@ string DwarfCFIToModule::RegisterName(int i) {
 void DwarfCFIToModule::Record(Module::Address address, int reg,
                               const string &rule) {
   assert(entry_);
+
+  // Place the name in our global set of strings, and then use the string
+  // from the set. Even though the assignment looks like a copy, all the
+  // major std::string implementations use reference counting internally,
+  // so the effect is to have all our data structures share copies of rules
+  // whenever possible. Since register names are drawn from a
+  // vector<string>, register names are already shared.
+  string shared_rule = *common_strings_.insert(rule).first;
+
   // Is this one of this entry's initial rules?
   if (address == entry_->address)
-    entry_->initial_rules[RegisterName(reg)] = rule;
+    entry_->initial_rules[RegisterName(reg)] = shared_rule;
   // File it under the appropriate address.
   else
-    entry_->rule_changes[address][RegisterName(reg)] = rule;
+    entry_->rule_changes[address][RegisterName(reg)] = shared_rule;
 }
 
 bool DwarfCFIToModule::UndefinedRule(uint64 address, int reg) {
diff --git a/src/common/dwarf_cfi_to_module.h b/src/common/dwarf_cfi_to_module.h
index dc11ec53..d29a796c 100644
--- a/src/common/dwarf_cfi_to_module.h
+++ b/src/common/dwarf_cfi_to_module.h
@@ -40,7 +40,9 @@
 #define COMMON_LINUX_DWARF_CFI_TO_MODULE_H
 
 #include <assert.h>
+#include <stdio.h>
 
+#include <set>
 #include <string>
 #include <vector>
 
@@ -51,6 +53,7 @@ namespace google_breakpad {
 
 using dwarf2reader::CallFrameInfo;
 using google_breakpad::Module;
+using std::set;
 using std::string;
 using std::vector;
 
@@ -124,7 +127,8 @@ class DwarfCFIToModule: public CallFrameInfo::Handler {
   DwarfCFIToModule(Module *module, const vector<string> &register_names,
                    Reporter *reporter)
       : module_(module), register_names_(register_names), reporter_(reporter),
-        entry_(NULL), return_address_(-1) { }
+        entry_(NULL), return_address_(-1), cfa_name_(".cfa"), ra_name_(".ra") {
+  }
   virtual ~DwarfCFIToModule() { delete entry_; }
 
   virtual bool Entry(size_t offset, uint64 address, uint64 length,
@@ -168,6 +172,23 @@ class DwarfCFIToModule: public CallFrameInfo::Handler {
 
   // The return address column for that entry.
   unsigned return_address_;
+
+  // The names of the return address and canonical frame address. Putting
+  // these here instead of using string literals allows us to share their
+  // texts in reference-counted std::string implementations (all the
+  // popular ones). Many, many rules cite these strings.
+  string cfa_name_, ra_name_;
+
+  // A set of strings used by this CFI. Before storing a string in one of
+  // our data structures, insert it into this set, and then use the string
+  // from the set.
+  // 
+  // Because std::string uses reference counting internally, simply using
+  // strings from this set, even if passed by value, assigned, or held
+  // directly in structures and containers (map<string, ...>, for example),
+  // causes those strings to share a single instance of each distinct piece
+  // of text.
+  set<string> common_strings_;
 };
 
 } // namespace google_breakpad
diff --git a/src/common/dwarf_cu_to_module.cc b/src/common/dwarf_cu_to_module.cc
index 85d1d8c4..9b538283 100644
--- a/src/common/dwarf_cu_to_module.cc
+++ b/src/common/dwarf_cu_to_module.cc
@@ -36,12 +36,16 @@
 #include <assert.h>
 
 #include <algorithm>
+#include <set>
+#include <utility>
 
 #include "common/dwarf_line_to_module.h"
 
 namespace google_breakpad {
 
 using std::map;
+using std::pair;
+using std::set;
 using std::vector;
 
 // Data provided by a DWARF specification DIE.
@@ -83,6 +87,17 @@ typedef map<uint64, AbstractOrigin> AbstractOriginByOffset;
 // Data global to the DWARF-bearing file that is private to the
 // DWARF-to-Module process.
 struct DwarfCUToModule::FilePrivate {
+  // A set of strings used in this CU. Before storing a string in one of
+  // our data structures, insert it into this set, and then use the string
+  // from the set.
+  // 
+  // Because std::string uses reference counting internally, simply using
+  // strings from this set, even if passed by value, assigned, or held
+  // directly in structures and containers (map<string, ...>, for example),
+  // causes those strings to share a single instance of each distinct piece
+  // of text.
+  set<string> common_strings;
+
   // A map from offsets of DIEs within the .debug_info section to
   // Specifications describing those DIEs. Specification references can
   // cross compilation unit boundaries.
@@ -256,7 +271,17 @@ void DwarfCUToModule::GenericDIEHandler::ProcessAttributeString(
     enum DwarfForm form,
     const string &data) {
   switch (attr) {
-    case dwarf2reader::DW_AT_name: name_attribute_ = data; break;
+    case dwarf2reader::DW_AT_name: {
+      // Place the name in our global set of strings, and then use the
+      // string from the set. Even though the assignment looks like a copy,
+      // all the major std::string implementations use reference counting
+      // internally, so the effect is to have all our data structures share
+      // copies of strings whenever possible.
+      pair<set<string>::iterator, bool> result =
+          cu_context_->file_context->file_private->common_strings.insert(data);
+      name_attribute_ = *result.first; 
+      break;
+    }
     default: break;
   }
 }