src,tools: speed up startup by 2.5%

Use zero-copy external string resources for storing the built-in JS
source code.  Saves a few hundred kilobyte of memory and consistently
speeds up `benchmark/misc/startup.js` by 2.5%.

Everything old is new again!  Commit 74954ce ("Add string class that
uses ExternalAsciiStringResource.") from 2011 did the same thing but
I removed that in 2013 in commit 34b0a36 ("src: don't use NewExternal()
with unaligned strings") because of a limitation in the V8 API.

V8 no longer requires that strings are aligned if they are one-byte
strings so it should be safe to re-enable external strings again.

PR-URL: #5458
Reviewed-By: James M Snell <jasnell@gmail.com>
Reviewed-By: Robert Jefe Lindstaedt <robert.lindstaedt@gmail.com>

Author: bnoordhuis

src/node_javascript.cc

@@ -6,33 +6,46 @@
 
 namespace node {
 
-using v8::HandleScope;
 using v8::Local;
 using v8::NewStringType;
 using v8::Object;
 using v8::String;
 
+// id##_data is defined in node_natives.h.
+#define V(id)                                                                 \
+  static struct : public String::ExternalOneByteStringResource {              \
+    const char* data() const override {                                       \
+      return reinterpret_cast<const char*>(id##_data);                        \
+    }                                                                         \
+    size_t length() const override { return sizeof(id##_data); }              \
+    void Dispose() override { /* Default calls `delete this`. */ }            \
+  } id##_external_data;
+NODE_NATIVES_MAP(V)
+#undef V
+
 Local<String> MainSource(Environment* env) {
-  return String::NewFromUtf8(
-      env->isolate(),
-      reinterpret_cast<const char*>(internal_bootstrap_node_native),
-      NewStringType::kNormal,
-      sizeof(internal_bootstrap_node_native)).ToLocalChecked();
+  auto maybe_string =
+      String::NewExternalOneByte(
+          env->isolate(),
+          &internal_bootstrap_node_external_data);
+  return maybe_string.ToLocalChecked();
 }
 
 void DefineJavaScript(Environment* env, Local<Object> target) {
-  HandleScope scope(env->isolate());
-
-  for (auto native : natives) {
-    if (native.source != internal_bootstrap_node_native) {
-      Local<String> name = String::NewFromUtf8(env->isolate(), native.name);
-      Local<String> source =
-          String::NewFromUtf8(
-              env->isolate(), reinterpret_cast<const char*>(native.source),
-              NewStringType::kNormal, native.source_len).ToLocalChecked();
-      target->Set(name, source);
-    }
-  }
+  auto context = env->context();
+#define V(id)                                                                 \
+  do {                                                                        \
+    auto key =                                                                \
+        String::NewFromOneByte(                                               \
+            env->isolate(), id##_name, NewStringType::kNormal,                \
+            sizeof(id##_name)).ToLocalChecked();                              \
+    auto value =                                                              \
+        String::NewExternalOneByte(                                           \
+            env->isolate(), &id##_external_data).ToLocalChecked();            \
+    CHECK(target->Set(context, key, value).FromJust());                       \
+  } while (0);
+  NODE_NATIVES_MAP(V)
+#undef V
 }
 
 }  // namespace node

tools/js2c.py

@@ -37,8 +37,11 @@
 import string
 
 
-def ToCArray(filename, lines):
-  return ','.join(str(ord(c)) for c in lines)
+def ToCString(contents):
+  step = 20
+  slices = (contents[i:i+step] for i in xrange(0, len(contents), step))
+  slices = map(lambda s: ','.join(str(ord(c)) for c in s), slices)
+  return ',\n'.join(slices)
 
 
 def ReadFile(filename):
@@ -61,21 +64,6 @@ def ReadLines(filename):
   return result
 
 
-def LoadConfigFrom(name):
-  import ConfigParser
-  config = ConfigParser.ConfigParser()
-  config.read(name)
-  return config
-
-
-def ParseValue(string):
-  string = string.strip()
-  if string.startswith('[') and string.endswith(']'):
-    return string.lstrip('[').rstrip(']').split()
-  else:
-    return string
-
-
 def ExpandConstants(lines, constants):
   for key, value in constants.items():
     lines = lines.replace(key, str(value))
@@ -174,53 +162,37 @@ def ReadMacros(lines):
 
 
 HEADER_TEMPLATE = """\
-#ifndef node_natives_h
-#define node_natives_h
-namespace node {
-
-%(source_lines)s\
+#ifndef NODE_NATIVES_H_
+#define NODE_NATIVES_H_
 
-struct _native {
-  const char* name;
-  const unsigned char* source;
-  size_t source_len;
-};
+#include <stdint.h>
 
-static const struct _native natives[] = { %(native_lines)s };
+#define NODE_NATIVES_MAP(V) \\
+{node_natives_map}
 
-}
-#endif
-"""
-
-
-NATIVE_DECLARATION = """\
-  { "%(id)s", %(escaped_id)s_native, sizeof(%(escaped_id)s_native) },
-"""
+namespace node {{
+{sources}
+}}  // namespace node
 
-SOURCE_DECLARATION = """\
-  const unsigned char %(escaped_id)s_native[] = { %(data)s };
+#endif  // NODE_NATIVES_H_
 """
 
 
-GET_DELAY_INDEX_CASE = """\
-    if (strcmp(name, "%(id)s") == 0) return %(i)i;
+NODE_NATIVES_MAP = """\
+  V({escaped_id}) \\
 """
 
 
-GET_DELAY_SCRIPT_SOURCE_CASE = """\
-    if (index == %(i)i) return Vector<const char>(%(id)s, %(length)i);
+SOURCES = """\
+static const uint8_t {escaped_id}_name[] = {{
+{name}}};
+static const uint8_t {escaped_id}_data[] = {{
+{data}}};
 """
 
 
-GET_DELAY_SCRIPT_NAME_CASE = """\
-    if (index == %(i)i) return Vector<const char>("%(name)s", %(length)i);
-"""
-
 def JS2C(source, target):
-  ids = []
-  delay_ids = []
   modules = []
-  # Locate the macros file name.
   consts = {}
   macros = {}
   macro_lines = []
@@ -235,18 +207,14 @@ def JS2C(source, target):
   (consts, macros) = ReadMacros(macro_lines)
 
   # Build source code lines
-  source_lines = [ ]
-  source_lines_empty = []
-
-  native_lines = []
+  node_natives_map = []
+  sources = []
 
   for s in modules:
-    delay = str(s).endswith('-delay.js')
     lines = ReadFile(str(s))
-
     lines = ExpandConstants(lines, consts)
     lines = ExpandMacros(lines, macros)
-    data = ToCArray(s, lines)
+    data = ToCString(lines)
 
     # On Windows, "./foo.bar" in the .gyp file is passed as "foo.bar"
     # so don't assume there is always a slash in the file path.
@@ -258,89 +226,19 @@ def JS2C(source, target):
     if '.' in id:
       id = id.split('.', 1)[0]
 
-    if delay: id = id[:-6]
-    if delay:
-      delay_ids.append((id, len(lines)))
-    else:
-      ids.append((id, len(lines)))
-
+    name = ToCString(id)
     escaped_id = id.replace('-', '_').replace('/', '_')
-    source_lines.append(SOURCE_DECLARATION % {
-      'id': id,
-      'escaped_id': escaped_id,
-      'data': data
-    })
-    source_lines_empty.append(SOURCE_DECLARATION % {
-      'id': id,
-      'escaped_id': escaped_id,
-      'data': 0
-    })
-    native_lines.append(NATIVE_DECLARATION % {
-      'id': id,
-      'escaped_id': escaped_id
-    })
-
-  # Build delay support functions
-  get_index_cases = [ ]
-  get_script_source_cases = [ ]
-  get_script_name_cases = [ ]
-
-  i = 0
-  for (id, length) in delay_ids:
-    native_name = "native %s.js" % id
-    get_index_cases.append(GET_DELAY_INDEX_CASE % { 'id': id, 'i': i })
-    get_script_source_cases.append(GET_DELAY_SCRIPT_SOURCE_CASE % {
-      'id': id,
-      'length': length,
-      'i': i
-    })
-    get_script_name_cases.append(GET_DELAY_SCRIPT_NAME_CASE % {
-      'name': native_name,
-      'length': len(native_name),
-      'i': i
-    });
-    i = i + 1
-
-  for (id, length) in ids:
-    native_name = "native %s.js" % id
-    get_index_cases.append(GET_DELAY_INDEX_CASE % { 'id': id, 'i': i })
-    get_script_source_cases.append(GET_DELAY_SCRIPT_SOURCE_CASE % {
-      'id': id,
-      'length': length,
-      'i': i
-    })
-    get_script_name_cases.append(GET_DELAY_SCRIPT_NAME_CASE % {
-      'name': native_name,
-      'length': len(native_name),
-      'i': i
-    });
-    i = i + 1
+    node_natives_map.append(NODE_NATIVES_MAP.format(**locals()))
+    sources.append(SOURCES.format(**locals()))
+
+  node_natives_map = ''.join(node_natives_map)
+  sources = ''.join(sources)
 
   # Emit result
   output = open(str(target[0]), "w")
-  output.write(HEADER_TEMPLATE % {
-    'builtin_count': len(ids) + len(delay_ids),
-    'delay_count': len(delay_ids),
-    'source_lines': "\n".join(source_lines),
-    'native_lines': "\n".join(native_lines),
-    'get_index_cases': "".join(get_index_cases),
-    'get_script_source_cases': "".join(get_script_source_cases),
-    'get_script_name_cases': "".join(get_script_name_cases)
-  })
+  output.write(HEADER_TEMPLATE.format(**locals()))
   output.close()
 
-  if len(target) > 1:
-    output = open(str(target[1]), "w")
-    output.write(HEADER_TEMPLATE % {
-      'builtin_count': len(ids) + len(delay_ids),
-      'delay_count': len(delay_ids),
-      'source_lines': "\n".join(source_lines_empty),
-      'get_index_cases': "".join(get_index_cases),
-      'get_script_source_cases': "".join(get_script_source_cases),
-      'get_script_name_cases': "".join(get_script_name_cases)
-    })
-    output.close()
-
 def main():
   natives = sys.argv[1]
   source_files = sys.argv[2:]