archive/ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2025-08-15 05:29:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Implement gen_fields_tbl cache

Browse source 
There is a high likelyhood that `rb_obj_fields` is called
consecutively for the same object.

If we keep a cache of the last IMEMO/fields we interacted with,
we can save having to lookup the `gen_fields_tbl`, synchronize
the VM lock, etc.

On yjit-bench's, I instrumented the hit rate of this cache at:

  - `shipit`: 38%, with 111k hits.
  - `lobsters`: 59%, with 367k hits.
  - `rubocop`: 100% with only 300 hits.

I also ran a micro-benchmark which shows that ivar access is:

  - 1.25x faster when the cache is hit in single ractor mode.
  - 2x faster when the cache is hit in multi ractor mode.
  - 1.06x slower when the cache miss in single ractor mode.
  - 1.01x slower when the cache miss in multi ractor mode.

```yml
prelude: |
  class GenIvar < Array
    def initialize(...)
      super
      @iv = 1
    end

    attr_reader :iv
  end

  a = GenIvar.new
  b = GenIvar.new
benchmark:
  hit: a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv; a.iv;
  miss: a.iv; b.iv; a.iv; b.iv; a.iv; b.iv; a.iv; b.iv; a.iv; b.iv; a.iv; b.iv; a.iv; b.iv; a.iv; b.iv; a.iv; b.iv; a.iv; b.iv;
```

Single ractor:
```
compare-ruby: ruby 3.5.0dev (2025-08-12T02:14:57Z master 428937a536) +YJIT +PRISM [arm64-darwin24]
built-ruby: ruby 3.5.0dev (2025-08-12T09:25:35Z gen-fields-cache 9456c35893) +YJIT +PRISM [arm64-darwin24]
warming up..

|      |compare-ruby|built-ruby|
|:-----|-----------:|---------:|
|hit   |      4.090M|    5.121M|
|      |           -|     1.25x|
|miss  |      3.756M|    3.534M|
|      |       1.06x|         -|
```

Multi-ractor:
```
compare-ruby: ruby 3.5.0dev (2025-08-12T02:14:57Z master 428937a536) +YJIT +PRISM [arm64-darwin24]
built-ruby: ruby 3.5.0dev (2025-08-12T09:25:35Z gen-fields-cache 9456c35893) +YJIT +PRISM [arm64-darwin24]
warming up..

|      |compare-ruby|built-ruby|
|:-----|-----------:|---------:|
|hit   |      2.205M|    4.460M|
|      |           -|     2.02x|
|miss  |      2.117M|    2.094M|
|      |       1.01x|         -|
```
This commit is contained in:
Jean Boussier 2025-08-06 17:39:24 +02:00
parent 10aa4134d4
commit 2083fa89fc
3 changed files with 44 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

41
variable.c
View file

@ -1245,9 +1245,19 @@ rb_obj_fields(VALUE obj, ID field_name)
goto generic_fields;
default:
generic_fields:
RB_VM_LOCKING() {
if (!st_lookup(generic_fields_tbl_, (st_data_t)obj, (st_data_t *)&fields_obj)) {
rb_bug("Object is missing entry in generic_fields_tbl");
{
rb_execution_context_t *ec = GET_EC();
if (ec->gen_fields_cache.obj == obj) {
fields_obj = ec->gen_fields_cache.fields_obj;
}
else {
RB_VM_LOCKING() {
if (!st_lookup(generic_fields_tbl_, (st_data_t)obj, (st_data_t *)&fields_obj)) {
rb_bug("Object is missing entry in generic_fields_tbl");
}
}
ec->gen_fields_cache.fields_obj = fields_obj;
ec->gen_fields_cache.obj = obj;
}
}
}
@ -1275,8 +1285,15 @@ rb_free_generic_ivar(VALUE obj)
goto generic_fields;
default:
generic_fields:
RB_VM_LOCKING() {
st_delete(generic_fields_tbl_no_ractor_check(), &key, &value);
{
rb_execution_context_t *ec = GET_EC();
if (ec->gen_fields_cache.obj == obj) {
ec->gen_fields_cache.obj = Qundef;
ec->gen_fields_cache.fields_obj = Qundef;
}
RB_VM_LOCKING() {
st_delete(generic_fields_tbl_no_ractor_check(), &key, &value);
}
}
}
RBASIC_SET_SHAPE_ID(obj, ROOT_SHAPE_ID);
@ -1307,10 +1324,18 @@ rb_obj_set_fields(VALUE obj, VALUE fields_obj, ID field_name, VALUE original_fie
goto generic_fields;
default:
generic_fields:
RB_VM_LOCKING() {
st_insert(generic_fields_tbl_, (st_data_t)obj, (st_data_t)fields_obj);
{
RB_VM_LOCKING() {
st_insert(generic_fields_tbl_, (st_data_t)obj, (st_data_t)fields_obj);
}
RB_OBJ_WRITTEN(obj, original_fields_obj, fields_obj);
rb_execution_context_t *ec = GET_EC();
if (ec->gen_fields_cache.fields_obj != fields_obj) {
ec->gen_fields_cache.obj = obj;
ec->gen_fields_cache.fields_obj = fields_obj;
}
}
RB_OBJ_WRITTEN(obj, original_fields_obj, fields_obj);
}
if (original_fields_obj) {

6
vm.c
View file

@ -3441,6 +3441,9 @@ rb_execution_context_update(rb_execution_context_t *ec)
}
ec->storage = rb_gc_location(ec->storage);
ec->gen_fields_cache.obj = rb_gc_location(ec->gen_fields_cache.obj);
ec->gen_fields_cache.fields_obj = rb_gc_location(ec->gen_fields_cache.fields_obj);
}
static enum rb_id_table_iterator_result
@ -3505,6 +3508,9 @@ rb_execution_context_mark(const rb_execution_context_t *ec)
rb_gc_mark(ec->private_const_reference);
rb_gc_mark_movable(ec->storage);
rb_gc_mark_weak((VALUE *)&ec->gen_fields_cache.obj);
rb_gc_mark_weak((VALUE *)&ec->gen_fields_cache.fields_obj);
}
void rb_fiber_mark_self(rb_fiber_t *fib);

5
vm_core.h
View file

@ -1070,6 +1070,11 @@ struct rb_execution_context_struct {
VALUE private_const_reference;
struct {
VALUE obj;
VALUE fields_obj;
} gen_fields_cache;
/* for GC */
struct {
VALUE *stack_start;