perf(core) Reduce script name and script code copies (#18298)

Reduce the number of copies and allocations of script code by carrying
around ownership/reference information from creation time.

As an advantage, this allows us to maintain the identity of `&'static
str`-based scripts and use v8's external 1-byte strings (to avoid
incorrectly passing non-ASCII strings, debug `assert!`s gate all string
reference paths).

Benchmark results:

Perf improvements -- ~0.1 - 0.2ms faster, but should reduce garbage
w/external strings and reduces data copies overall. May also unlock some
more interesting optimizations in the future.

This requires adding some generics to functions, but manual
monomorphization has been applied (outer/inner function) to avoid code
bloat.

1 files changed, 59 insertions, 40 deletions

diff --git a/core/runtime.rs b/core/runtime.rs
index 7b6dfba92..f9f2e5523 100644
--- a/core/runtime.rs
+++ b/core/runtime.rs
@@ -9,6 +9,7 @@ use crate::extensions::OpEventLoopFn;
 use crate::inspector::JsRuntimeInspector;
 use crate::module_specifier::ModuleSpecifier;
 use crate::modules::ExtModuleLoaderCb;
+use crate::modules::ModuleCode;
 use crate::modules::ModuleError;
 use crate::modules::ModuleId;
 use crate::modules::ModuleLoadId;
@@ -50,6 +51,8 @@ use std::sync::Mutex;
 use std::sync::Once;
 use std::task::Context;
 use std::task::Poll;
+use v8::HandleScope;
+use v8::Local;
 use v8::OwnedIsolate;
 
 type PendingOpFuture = OpCall<(RealmIdx, PromiseId, OpId, OpResult)>;
@@ -748,7 +751,7 @@ impl JsRuntime {
             realm.execute_script(
               self.v8_isolate(),
               file_source.specifier,
-              &file_source.code.load()?,
+              file_source.code.load()?,
             )?;
           }
         }
@@ -902,7 +905,7 @@ impl JsRuntime {
   /// The execution takes place on the current global context, so it is possible
   /// to maintain local JS state and invoke this method multiple times.
   ///
-  /// `name` can be a filepath or any other string, eg.
+  /// `name` can be a filepath or any other string, but it is required to be 7-bit ASCII, eg.
   ///
   ///   - "/some/file/path.js"
   ///   - "<anon>"
@@ -911,10 +914,10 @@ impl JsRuntime {
   /// The same `name` value can be used for multiple executions.
   ///
   /// `Error` can usually be downcast to `JsError`.
-  pub fn execute_script(
+  pub fn execute_script<S: Into<ModuleCode>>(
     &mut self,
-    name: &str,
-    source_code: &str,
+    name: &'static str,
+    source_code: S,
   ) -> Result<v8::Global<v8::Value>, Error> {
     self
       .global_realm()
@@ -2056,21 +2059,15 @@ impl JsRuntime {
   pub async fn load_main_module(
     &mut self,
     specifier: &ModuleSpecifier,
-    code: Option<String>,
+    code: Option<ModuleCode>,
   ) -> Result<ModuleId, Error> {
     let module_map_rc = Self::module_map(self.v8_isolate());
     if let Some(code) = code {
       let scope = &mut self.handle_scope();
+      // true for main module
       module_map_rc
         .borrow_mut()
-        .new_es_module(
-          scope,
-          // main module
-          true,
-          specifier.as_str(),
-          code.as_bytes(),
-          false,
-        )
+        .new_es_module(scope, true, specifier, &code, false)
         .map_err(|e| match e {
           ModuleError::Exception(exception) => {
             let exception = v8::Local::new(scope, exception);
@@ -2116,21 +2113,15 @@ impl JsRuntime {
   pub async fn load_side_module(
     &mut self,
     specifier: &ModuleSpecifier,
-    code: Option<String>,
+    code: Option<ModuleCode>,
   ) -> Result<ModuleId, Error> {
     let module_map_rc = Self::module_map(self.v8_isolate());
     if let Some(code) = code {
       let scope = &mut self.handle_scope();
+      // false for side module (not main module)
       module_map_rc
         .borrow_mut()
-        .new_es_module(
-          scope,
-          // not main module
-          false,
-          specifier.as_str(),
-          code.as_bytes(),
-          false,
-        )
+        .new_es_module(scope, false, specifier, &code, false)
         .map_err(|e| match e {
           ModuleError::Exception(exception) => {
             let exception = v8::Local::new(scope, exception);
@@ -2476,6 +2467,21 @@ impl JsRealm {
     self.0.open(scope).global(scope)
   }
 
+  fn string_from_code<'a>(
+    scope: &mut HandleScope<'a>,
+    code: &ModuleCode,
+  ) -> Option<Local<'a, v8::String>> {
+    if let Some(code) = code.try_static_ascii() {
+      v8::String::new_external_onebyte_static(scope, code)
+    } else {
+      v8::String::new_from_utf8(
+        scope,
+        code.as_bytes(),
+        v8::NewStringType::Normal,
+      )
+    }
+  }
+
   /// Executes traditional JavaScript code (traditional = not ES modules) in the
   /// realm's context.
   ///
@@ -2488,16 +2494,28 @@ impl JsRealm {
   /// The same `name` value can be used for multiple executions.
   ///
   /// `Error` can usually be downcast to `JsError`.
-  pub fn execute_script(
+  pub fn execute_script<S: Into<ModuleCode>>(
     &self,
     isolate: &mut v8::Isolate,
-    name: &str,
-    source_code: &str,
+    name: &'static str,
+    source_code: S,
+  ) -> Result<v8::Global<v8::Value>, Error> {
+    // Manual monomorphization (TODO: replace w/momo)
+    self.execute_script_inner(isolate, name, source_code.into())
+  }
+
+  fn execute_script_inner(
+    &self,
+    isolate: &mut v8::Isolate,
+    name: &'static str,
+    source_code: ModuleCode,
   ) -> Result<v8::Global<v8::Value>, Error> {
     let scope = &mut self.handle_scope(isolate);
 
-    let source = v8::String::new(scope, source_code).unwrap();
-    let name = v8::String::new(scope, name).unwrap();
+    let source = Self::string_from_code(scope, &source_code).unwrap();
+    assert!(name.is_ascii());
+    let name =
+      v8::String::new_external_onebyte_static(scope, name.as_bytes()).unwrap();
     let origin = bindings::script_origin(scope, name);
 
     let tc_scope = &mut v8::TryCatch::new(scope);
@@ -3104,7 +3122,8 @@ pub mod tests {
       runtime
         .execute_script(
           "encode_decode_test.js",
-          include_str!("encode_decode_test.js"),
+          // Note: We make this to_owned because it contains non-ASCII chars
+          include_str!("encode_decode_test.js").to_owned(),
         )
         .unwrap();
       if let Poll::Ready(Err(_)) = runtime.poll_event_loop(cx, false) {
@@ -3320,7 +3339,7 @@ pub mod tests {
       export const a = "b";
       export default 1 + 2;
       "#
-    .to_string();
+    .into();
 
     let module_id = futures::executor::block_on(
       runtime.load_main_module(&specifier, Some(source_code)),
@@ -3490,7 +3509,8 @@ pub mod tests {
         import {{ f{prev} }} from "file:///{prev}.js";
         export function f{i}() {{ return f{prev}() }}
         "#
-      );
+      )
+      .into();
 
       let id = if main {
         futures::executor::block_on(
@@ -3559,8 +3579,7 @@ pub mod tests {
     });
 
     let specifier = crate::resolve_url("file:///0.js").unwrap();
-    let source_code =
-      r#"export function f0() { return "hello world" }"#.to_string();
+    let source_code = r#"export function f0() { return "hello world" }"#.into();
     let id = futures::executor::block_on(
       runtime.load_side_module(&specifier, Some(source_code)),
     )
@@ -3620,7 +3639,7 @@ pub mod tests {
       return mod.f400() + " " + Deno.core.ops.op_test();
     })();"#
       .to_string();
-    let val = runtime3.execute_script(".", &source_code).unwrap();
+    let val = runtime3.execute_script(".", source_code).unwrap();
     let val = futures::executor::block_on(runtime3.resolve_value(val)).unwrap();
     {
       let scope = &mut runtime3.handle_scope();
@@ -4163,7 +4182,7 @@ Deno.core.opAsync("op_async_serialize_object_with_numbers_as_keys", {
       ) -> Pin<Box<ModuleSourceFuture>> {
         async move {
           Ok(ModuleSource {
-            code: b"console.log('hello world');".to_vec().into_boxed_slice(),
+            code: b"console.log('hello world');".into(),
             module_url_specified: "file:///main.js".to_string(),
             module_url_found: "file:///main.js".to_string(),
             module_type: ModuleType::JavaScript,
@@ -4180,7 +4199,7 @@ Deno.core.opAsync("op_async_serialize_object_with_numbers_as_keys", {
     });
 
     let specifier = crate::resolve_url("file:///main.js").unwrap();
-    let source_code = "Deno.core.print('hello\\n')".to_string();
+    let source_code = "Deno.core.print('hello\\n')".into();
 
     let module_id = futures::executor::block_on(
       runtime.load_main_module(&specifier, Some(source_code)),
@@ -4273,7 +4292,7 @@ Deno.core.opAsync("op_async_serialize_object_with_numbers_as_keys", {
         .execute_script(
           runtime.v8_isolate(),
           "",
-          &format!(
+          format!(
             r#"
               
               globalThis.rejectValue = undefined;
@@ -4282,7 +4301,7 @@ Deno.core.opAsync("op_async_serialize_object_with_numbers_as_keys", {
               }});
               Deno.core.opAsync("op_void_async").then(() => Promise.reject({number}));
             "#
-          ),
+          )
         )
         .unwrap();
     }
@@ -4344,7 +4363,7 @@ Deno.core.opAsync("op_async_serialize_object_with_numbers_as_keys", {
 
         async move {
           Ok(ModuleSource {
-            code: source.as_bytes().to_vec().into_boxed_slice(),
+            code: source.into(),
             module_url_specified: "file:///main.js".to_string(),
             module_url_found: "file:///main.js".to_string(),
             module_type: ModuleType::JavaScript,
@@ -4858,7 +4877,7 @@ Deno.core.opAsync("op_async_serialize_object_with_numbers_as_keys", {
 
         async move {
           Ok(ModuleSource {
-            code: source.as_bytes().to_vec().into_boxed_slice(),
+            code: source.into(),
             module_url_specified: "file:///main.js".to_string(),
             module_url_found: "file:///main.js".to_string(),
             module_type: ModuleType::JavaScript,