From 6ad0f89d5aa2466cdfcd1a056ce9b28b39245033 Mon Sep 17 00:00:00 2001
From: Benoit Daloze <eregontp@gmail.com>
Date: Fri, 1 Mar 2024 21:30:31 +0100
Subject: [PATCH] [ruby/prism] Use a more efficient StringIO on TruffleRuby

* The stdlib StringIO is synchronized and this occurs a high overhead.
* This is about twice as fast on TruffleRuby but surprisingly it is slower on JRuby.
  I am not sure why but probably @ivar access and integer arithmetic
  is much slower than Java field access/arithmetic on JRuby.
* On CRuby interpreter it is slower, which is expected as the GVL already protects StringIO.
* So we enable this only on TruffleRuby to not slow down other Rubies.
* PRISM_FFI_BACKEND=true ruby -v -Ilib -rprism -rbenchmark -e '300.times { p Benchmark.realtime { Dir.glob("lib/**/*.rb") { |f| Prism.parse_file(f) } } }'
  ruby 3.3.0:         0.215 => 0.251 (cext: 0.062)
  ruby 3.3.0 YJIT:    0.118 => 0.113 (cext: 0.053)
  truffleruby JVM:    0.101 => 0.054
  jruby 9.4.6.0:      0.162 => 0.219
  jruby 9.4.6.0 indy: 0.078 => 0.086
* For the record here are the numbers for using the String directly, without a StringIO-like object:
  ruby 3.3.0:         0.215 => 0.234 (cext: 0.062)
  ruby 3.3.0 YJIT:    0.118 => 0.111 (cext: 0.053)
  truffleruby native: 0.101 => 0.053
  jruby 9.4.6.0:      0.162 => 0.195
  jruby 9.4.6.0 indy: 0.078 => 0.082
  As we can see, that extra object adds a non-trivial overhead on CRuby interpreter and JRuby.
  But we need to make it possible to use StringIO and SimpleStringIO interchangeably.

https://github.com/ruby/prism/commit/938677cbd2
---
 prism/templates/lib/prism/serialize.rb.erb | 51 +++++++++++++++++-----
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/prism/templates/lib/prism/serialize.rb.erb b/prism/templates/lib/prism/serialize.rb.erb
index 4370363773..4f4efe7c10 100644
--- a/prism/templates/lib/prism/serialize.rb.erb
+++ b/prism/templates/lib/prism/serialize.rb.erb
@@ -44,6 +44,37 @@ module Prism
     end
 
     class Loader # :nodoc:
+      if RUBY_ENGINE == "truffleruby"
+        # StringIO is synchronized and that adds a high overhead on TruffleRuby.
+        class FastStringIO # :nodoc:
+          attr_accessor :pos
+
+          def initialize(string)
+            @string = string
+            @pos = 0
+          end
+
+          def getbyte
+            byte = @string.getbyte(@pos)
+            @pos += 1
+            byte
+          end
+
+          def read(n)
+            slice = @string.byteslice(@pos, n)
+            @pos += n
+            slice
+          end
+
+          def eof?
+            @pos >= @string.bytesize
+          end
+        end
+      else
+        FastStringIO = ::StringIO
+      end
+      private_constant :FastStringIO
+
       attr_reader :encoding, :input, :serialized, :io
       attr_reader :constant_pool_offset, :constant_pool, :source
       attr_reader :start_line
@@ -52,9 +83,9 @@ module Prism
         @encoding = Encoding::UTF_8
 
         @input = source.source.dup
+        raise unless serialized.encoding == Encoding::BINARY
         @serialized = serialized
-        @io = StringIO.new(serialized)
-        @io.set_encoding(Encoding::BINARY)
+        @io = FastStringIO.new(serialized)
 
         @constant_pool_offset = nil
         @constant_pool = nil
@@ -66,7 +97,7 @@ module Prism
       def load_header
         raise "Invalid serialization" if io.read(5) != "PRISM"
         raise "Invalid serialization" if io.read(3).unpack("C3") != [MAJOR_VERSION, MINOR_VERSION, PATCH_VERSION]
-        only_semantic_fields = io.read(1).unpack1("C")
+        only_semantic_fields = io.getbyte
         unless only_semantic_fields == 0
           raise "Invalid serialization (location fields must be included but are not)"
         end
@@ -137,7 +168,7 @@ module Prism
 
         comments, magic_comments, data_loc, errors, warnings = load_metadata
 
-        @constant_pool_offset = io.read(4).unpack1("L")
+        @constant_pool_offset = load_uint32
         @constant_pool = Array.new(load_varuint, nil)
 
         [load_node, comments, magic_comments, data_loc, errors, warnings]
@@ -186,7 +217,7 @@ module Prism
         io.read(8).unpack1("D")
       end
 
-      def load_serialized_length
+      def load_uint32
         io.read(4).unpack1("L")
       end
 
@@ -234,14 +265,14 @@ module Prism
 
         unless constant
           offset = constant_pool_offset + index * 8
-          start = serialized.unpack1("L", offset: offset)
-          length = serialized.unpack1("L", offset: offset + 4)
+          start = @serialized.unpack1("L", offset: offset)
+          length = @serialized.unpack1("L", offset: offset + 4)
 
           constant =
             if start.nobits?(1 << 31)
               input.byteslice(start, length).force_encoding(@encoding).to_sym
             else
-              serialized.byteslice(start & ((1 << 31) - 1), length).force_encoding(@encoding).to_sym
+              @serialized.byteslice(start & ((1 << 31) - 1), length).force_encoding(@encoding).to_sym
             end
 
           constant_pool[index] = constant
@@ -294,7 +325,7 @@ module Prism
           <%- nodes.each_with_index do |node, index| -%>
           when <%= index + 1 %> then
             <%- if node.needs_serialized_length? -%>
-            load_serialized_length
+            load_uint32
             <%- end -%>
             <%= node.name %>.new(
               source, <%= (node.fields.map { |field|
@@ -331,7 +362,7 @@ module Prism
             -> {
               location = load_location
               <%- if node.needs_serialized_length? -%>
-              load_serialized_length
+              load_uint32
               <%- end -%>
               <%= node.name %>.new(
                 source, <%= (node.fields.map { |field|