ruby/ext/json/generator/generator.h
Jean Boussier cc2e67a138 Elide Generator::State allocation until a to_json method has to be called
Fix: https://github.com/ruby/json/issues/655

For very small documents, the biggest performance gap with alternatives is
that the API impose that we allocate the `State` object. In a real world app
this doesn't make much of a difference, but when running in a micro-benchmark
this doubles the allocations, causing twice the amount of GC runs, making us
look bad.

However, unless we have to call a `to_json` method, the `State` object isn't
visible, so with some refactoring, we can elude that allocation entirely.

Instead we allocate the State internal struct on the stack, and if we need
to call a `to_json` method, we allocate the `State` and spill the struct on
the heap.

As a result, `JSON.generate` is now as fast as re-using a `State` instance,
as long as only primitives are generated.

Before:
```
== Encoding small mixed (34 bytes)
ruby 3.3.4 (2024-07-09 revision be1089c8ec) +YJIT [arm64-darwin23]
Warming up --------------------------------------
        json (reuse)   598.654k i/100ms
                json   400.542k i/100ms
                  oj   533.353k i/100ms
Calculating -------------------------------------
        json (reuse)      6.371M (± 8.6%) i/s  (156.96 ns/i) -     31.729M in   5.059195s
                json      4.120M (± 6.6%) i/s  (242.72 ns/i) -     20.828M in   5.090549s
                  oj      5.622M (± 6.4%) i/s  (177.86 ns/i) -     28.268M in   5.061473s

Comparison:
        json (reuse):  6371126.6 i/s
                  oj:  5622452.0 i/s - same-ish: difference falls within error
                json:  4119991.1 i/s - 1.55x  slower

== Encoding small nested array (121 bytes)
ruby 3.3.4 (2024-07-09 revision be1089c8ec) +YJIT [arm64-darwin23]
Warming up --------------------------------------
        json (reuse)   248.125k i/100ms
                json   215.255k i/100ms
                  oj   217.531k i/100ms
Calculating -------------------------------------
        json (reuse)      2.628M (± 6.1%) i/s  (380.55 ns/i) -     13.151M in   5.030281s
                json      2.185M (± 6.7%) i/s  (457.74 ns/i) -     10.978M in   5.057655s
                  oj      2.217M (± 6.7%) i/s  (451.10 ns/i) -     11.094M in   5.044844s

Comparison:
        json (reuse):  2627799.4 i/s
                  oj:  2216824.8 i/s - 1.19x  slower
                json:  2184669.5 i/s - 1.20x  slower

== Encoding small hash (65 bytes)
ruby 3.3.4 (2024-07-09 revision be1089c8ec) +YJIT [arm64-darwin23]
Warming up --------------------------------------
        json (reuse)   641.334k i/100ms
                json   322.745k i/100ms
                  oj   642.450k i/100ms
Calculating -------------------------------------
        json (reuse)      7.133M (± 6.5%) i/s  (140.19 ns/i) -     35.915M in   5.068201s
                json      4.615M (± 7.0%) i/s  (216.70 ns/i) -     22.915M in   5.003718s
                  oj      6.912M (± 6.4%) i/s  (144.68 ns/i) -     34.692M in   5.047690s

Comparison:
        json (reuse):  7133123.3 i/s
                  oj:  6911977.1 i/s - same-ish: difference falls within error
                json:  4614696.6 i/s - 1.55x  slower
```

After:

```
== Encoding small mixed (34 bytes)
ruby 3.3.4 (2024-07-09 revision be1089c8ec) +YJIT [arm64-darwin23]
Warming up --------------------------------------
        json (reuse)   572.751k i/100ms
                json   457.741k i/100ms
                  oj   512.247k i/100ms
Calculating -------------------------------------
        json (reuse)      6.324M (± 6.9%) i/s  (158.12 ns/i) -     31.501M in   5.023093s
                json      6.263M (± 6.9%) i/s  (159.66 ns/i) -     31.126M in   5.017086s
                  oj      5.569M (± 6.6%) i/s  (179.56 ns/i) -     27.661M in   5.003739s

Comparison:
        json (reuse):  6324183.5 i/s
                json:  6263204.9 i/s - same-ish: difference falls within error
                  oj:  5569049.2 i/s - same-ish: difference falls within error

== Encoding small nested array (121 bytes)
ruby 3.3.4 (2024-07-09 revision be1089c8ec) +YJIT [arm64-darwin23]
Warming up --------------------------------------
        json (reuse)   258.505k i/100ms
                json   242.335k i/100ms
                  oj   220.678k i/100ms
Calculating -------------------------------------
        json (reuse)      2.589M (± 9.6%) i/s  (386.17 ns/i) -     12.925M in   5.071853s
                json      2.594M (± 6.6%) i/s  (385.46 ns/i) -     13.086M in   5.083035s
                  oj      2.250M (± 2.3%) i/s  (444.43 ns/i) -     11.255M in   5.004707s

Comparison:
        json (reuse):  2589499.6 i/s
                json:  2594321.0 i/s - same-ish: difference falls within error
                  oj:  2250064.0 i/s - 1.15x  slower

== Encoding small hash (65 bytes)
ruby 3.3.4 (2024-07-09 revision be1089c8ec) +YJIT [arm64-darwin23]
Warming up --------------------------------------
        json (reuse)   656.373k i/100ms
                json   644.135k i/100ms
                  oj   650.283k i/100ms
Calculating -------------------------------------
        json (reuse)      7.202M (± 7.1%) i/s  (138.84 ns/i) -     36.101M in   5.051438s
                json      7.278M (± 1.7%) i/s  (137.40 ns/i) -     36.716M in   5.046300s
                  oj      7.036M (± 1.7%) i/s  (142.12 ns/i) -     35.766M in   5.084729s

Comparison:
        json (reuse):  7202447.9 i/s
                json:  7277883.0 i/s - same-ish: difference falls within error
                  oj:  7036115.2 i/s - same-ish: difference falls within error

```
2024-11-01 13:04:24 +09:00

91 lines
3.1 KiB
C++

#ifndef _GENERATOR_H_
#define _GENERATOR_H_
#include <math.h>
#include <ctype.h>
#include "ruby.h"
/* This is the fallback definition from Ruby 3.4 */
#ifndef RBIMPL_STDBOOL_H
#if defined(__cplusplus)
# if defined(HAVE_STDBOOL_H) && (__cplusplus >= 201103L)
# include <cstdbool>
# endif
#elif defined(HAVE_STDBOOL_H)
# include <stdbool.h>
#elif !defined(HAVE__BOOL)
typedef unsigned char _Bool;
# define bool _Bool
# define true ((_Bool)+1)
# define false ((_Bool)+0)
# define __bool_true_false_are_defined
#endif
#endif
/* ruby api and some helpers */
typedef struct JSON_Generator_StateStruct {
VALUE indent;
VALUE space;
VALUE space_before;
VALUE object_nl;
VALUE array_nl;
long max_nesting;
long depth;
long buffer_initial_length;
bool allow_nan;
bool ascii_only;
bool script_safe;
bool strict;
} JSON_Generator_State;
static VALUE mHash_to_json(int argc, VALUE *argv, VALUE self);
static VALUE mArray_to_json(int argc, VALUE *argv, VALUE self);
#ifdef RUBY_INTEGER_UNIFICATION
static VALUE mInteger_to_json(int argc, VALUE *argv, VALUE self);
#else
static VALUE mFixnum_to_json(int argc, VALUE *argv, VALUE self);
static VALUE mBignum_to_json(int argc, VALUE *argv, VALUE self);
#endif
static VALUE mFloat_to_json(int argc, VALUE *argv, VALUE self);
static VALUE mString_included_s(VALUE self, VALUE modul);
static VALUE mString_to_json(int argc, VALUE *argv, VALUE self);
static VALUE mString_to_json_raw_object(VALUE self);
static VALUE mString_to_json_raw(int argc, VALUE *argv, VALUE self);
static VALUE mString_Extend_json_create(VALUE self, VALUE o);
static VALUE mTrueClass_to_json(int argc, VALUE *argv, VALUE self);
static VALUE mFalseClass_to_json(int argc, VALUE *argv, VALUE self);
static VALUE mNilClass_to_json(int argc, VALUE *argv, VALUE self);
static VALUE mObject_to_json(int argc, VALUE *argv, VALUE self);
static void State_free(void *state);
static VALUE cState_s_allocate(VALUE klass);
static VALUE cState_generate(VALUE self, VALUE obj);
static VALUE cState_from_state_s(VALUE self, VALUE opts);
static VALUE cState_indent(VALUE self);
static VALUE cState_indent_set(VALUE self, VALUE indent);
static VALUE cState_space(VALUE self);
static VALUE cState_space_set(VALUE self, VALUE space);
static VALUE cState_space_before(VALUE self);
static VALUE cState_space_before_set(VALUE self, VALUE space_before);
static VALUE cState_object_nl(VALUE self);
static VALUE cState_object_nl_set(VALUE self, VALUE object_nl);
static VALUE cState_array_nl(VALUE self);
static VALUE cState_array_nl_set(VALUE self, VALUE array_nl);
static VALUE cState_max_nesting(VALUE self);
static VALUE cState_max_nesting_set(VALUE self, VALUE depth);
static VALUE cState_allow_nan_p(VALUE self);
static VALUE cState_ascii_only_p(VALUE self);
static VALUE cState_depth(VALUE self);
static VALUE cState_depth_set(VALUE self, VALUE depth);
static VALUE cState_script_safe(VALUE self);
static VALUE cState_script_safe_set(VALUE self, VALUE depth);
static VALUE cState_strict(VALUE self);
static VALUE cState_strict_set(VALUE self, VALUE strict);
static const rb_data_type_t JSON_Generator_State_type;
#endif