mirror of
https://github.com/ruby/ruby.git
synced 2025-09-20 11:03:58 +02:00

When an inline cache misses, it is very likely that the stale shape_id
and the current instance shape_id have a close common ancestor.
For example if the instance variable is sometimes frozen sometimes
not, one of the two shape will be the direct parent of the other.
Another pattern that commonly cause IC misses is "memoization",
in such case the object will have a "base common shape" and then
a number of close descendants.
In addition, when we find a common ancestor, we store it in the
inline cache instead of the current shape. This help prevent the
cache from flip-flopping, ensuring the next lookup will be marginally
faster and more generally avoid writing in memory too much.
However, now that shapes have an ancestors index, we only check
for a few ancestors before falling back to use the index.
So overall this change speeds up what is assumed to be the more common
case, but makes what is assumed to be the less common case a bit slower.
```
compare-ruby: ruby 3.3.0dev (2023-10-26T05:30:17Z master 701ca070b4
) [arm64-darwin22]
built-ruby: ruby 3.3.0dev (2023-10-26T09:25:09Z shapes_double_sear.. a723a85235) [arm64-darwin22]
warming up......
| |compare-ruby|built-ruby|
|:------------------------------------|-----------:|---------:|
|vm_ivar_stable_shape | 11.672M| 11.679M|
| | -| 1.00x|
|vm_ivar_memoize_unstable_shape | 7.551M| 10.506M|
| | -| 1.39x|
|vm_ivar_memoize_unstable_shape_miss | 11.591M| 11.624M|
| | -| 1.00x|
|vm_ivar_unstable_undef | 9.037M| 7.981M|
| | 1.13x| -|
|vm_ivar_divergent_shape | 8.034M| 6.657M|
| | 1.21x| -|
|vm_ivar_divergent_shape_imbalanced | 10.471M| 9.231M|
| | 1.13x| -|
```
Co-Authored-By: John Hawthorn <john@hawthorn.email>
243 lines
6.6 KiB
C
243 lines
6.6 KiB
C
#ifndef RUBY_SHAPE_H
|
|
#define RUBY_SHAPE_H
|
|
|
|
#include "internal/gc.h"
|
|
|
|
#if (SIZEOF_UINT64_T <= SIZEOF_VALUE)
|
|
|
|
#define SIZEOF_SHAPE_T 4
|
|
#define SHAPE_IN_BASIC_FLAGS 1
|
|
typedef uint32_t attr_index_t;
|
|
typedef uint32_t shape_id_t;
|
|
typedef uint32_t redblack_id_t;
|
|
# define SHAPE_ID_NUM_BITS 32
|
|
|
|
#else
|
|
|
|
#define SIZEOF_SHAPE_T 2
|
|
#define SHAPE_IN_BASIC_FLAGS 0
|
|
typedef uint16_t attr_index_t;
|
|
typedef uint16_t shape_id_t;
|
|
typedef uint16_t redblack_id_t;
|
|
# define SHAPE_ID_NUM_BITS 16
|
|
|
|
#endif
|
|
|
|
#define MAX_IVARS (attr_index_t)(-1)
|
|
|
|
# define SHAPE_MASK (((uintptr_t)1 << SHAPE_ID_NUM_BITS) - 1)
|
|
# define SHAPE_FLAG_MASK (((VALUE)-1) >> SHAPE_ID_NUM_BITS)
|
|
|
|
# define SHAPE_FLAG_SHIFT ((SIZEOF_VALUE * 8) - SHAPE_ID_NUM_BITS)
|
|
|
|
# define SHAPE_MAX_VARIATIONS 8
|
|
|
|
# define INVALID_SHAPE_ID SHAPE_MASK
|
|
# define ROOT_SHAPE_ID 0x0
|
|
|
|
# define SPECIAL_CONST_SHAPE_ID (SIZE_POOL_COUNT * 2)
|
|
# define OBJ_TOO_COMPLEX_SHAPE_ID (SPECIAL_CONST_SHAPE_ID + 1)
|
|
|
|
typedef struct redblack_node redblack_node_t;
|
|
|
|
struct rb_shape {
|
|
struct rb_id_table * edges; // id_table from ID (ivar) to next shape
|
|
ID edge_name; // ID (ivar) for transition from parent to rb_shape
|
|
attr_index_t next_iv_index;
|
|
uint32_t capacity; // Total capacity of the object with this shape
|
|
uint8_t type;
|
|
uint8_t size_pool_index;
|
|
shape_id_t parent_id;
|
|
redblack_node_t * ancestor_index;
|
|
};
|
|
|
|
typedef struct rb_shape rb_shape_t;
|
|
|
|
struct redblack_node {
|
|
ID key;
|
|
rb_shape_t * value;
|
|
redblack_id_t l;
|
|
redblack_id_t r;
|
|
};
|
|
|
|
enum shape_type {
|
|
SHAPE_ROOT,
|
|
SHAPE_IVAR,
|
|
SHAPE_FROZEN,
|
|
SHAPE_CAPACITY_CHANGE,
|
|
SHAPE_T_OBJECT,
|
|
SHAPE_OBJ_TOO_COMPLEX,
|
|
};
|
|
|
|
typedef struct {
|
|
/* object shapes */
|
|
rb_shape_t *shape_list;
|
|
rb_shape_t *root_shape;
|
|
shape_id_t next_shape_id;
|
|
|
|
redblack_node_t *shape_cache;
|
|
unsigned int cache_size;
|
|
} rb_shape_tree_t;
|
|
RUBY_EXTERN rb_shape_tree_t *rb_shape_tree_ptr;
|
|
|
|
static inline rb_shape_tree_t *
|
|
rb_current_shape_tree(void)
|
|
{
|
|
return rb_shape_tree_ptr;
|
|
}
|
|
#define GET_SHAPE_TREE() rb_current_shape_tree()
|
|
|
|
static inline shape_id_t
|
|
get_shape_id_from_flags(VALUE obj)
|
|
{
|
|
RUBY_ASSERT(!RB_SPECIAL_CONST_P(obj));
|
|
return (shape_id_t)(SHAPE_MASK & ((RBASIC(obj)->flags) >> SHAPE_FLAG_SHIFT));
|
|
}
|
|
|
|
static inline void
|
|
set_shape_id_in_flags(VALUE obj, shape_id_t shape_id)
|
|
{
|
|
// Ractors are occupying the upper 32 bits of flags, but only in debug mode
|
|
// Object shapes are occupying top bits
|
|
RBASIC(obj)->flags &= SHAPE_FLAG_MASK;
|
|
RBASIC(obj)->flags |= ((VALUE)(shape_id) << SHAPE_FLAG_SHIFT);
|
|
}
|
|
|
|
|
|
#if SHAPE_IN_BASIC_FLAGS
|
|
static inline shape_id_t
|
|
RBASIC_SHAPE_ID(VALUE obj)
|
|
{
|
|
return get_shape_id_from_flags(obj);
|
|
}
|
|
|
|
static inline void
|
|
RBASIC_SET_SHAPE_ID(VALUE obj, shape_id_t shape_id)
|
|
{
|
|
set_shape_id_in_flags(obj, shape_id);
|
|
}
|
|
#endif
|
|
|
|
static inline shape_id_t
|
|
ROBJECT_SHAPE_ID(VALUE obj)
|
|
{
|
|
RBIMPL_ASSERT_TYPE(obj, RUBY_T_OBJECT);
|
|
return get_shape_id_from_flags(obj);
|
|
}
|
|
|
|
static inline void
|
|
ROBJECT_SET_SHAPE_ID(VALUE obj, shape_id_t shape_id)
|
|
{
|
|
RBIMPL_ASSERT_TYPE(obj, RUBY_T_OBJECT);
|
|
set_shape_id_in_flags(obj, shape_id);
|
|
}
|
|
|
|
static inline shape_id_t
|
|
RCLASS_SHAPE_ID(VALUE obj)
|
|
{
|
|
RUBY_ASSERT(RB_TYPE_P(obj, T_CLASS) || RB_TYPE_P(obj, T_MODULE));
|
|
return get_shape_id_from_flags(obj);
|
|
}
|
|
|
|
static inline void
|
|
RCLASS_SET_SHAPE_ID(VALUE obj, shape_id_t shape_id)
|
|
{
|
|
RUBY_ASSERT(RB_TYPE_P(obj, T_CLASS) || RB_TYPE_P(obj, T_MODULE));
|
|
set_shape_id_in_flags(obj, shape_id);
|
|
}
|
|
|
|
rb_shape_t * rb_shape_get_root_shape(void);
|
|
int32_t rb_shape_id_offset(void);
|
|
|
|
rb_shape_t * rb_shape_get_parent(rb_shape_t * shape);
|
|
|
|
rb_shape_t* rb_shape_get_shape_by_id(shape_id_t shape_id);
|
|
shape_id_t rb_shape_get_shape_id(VALUE obj);
|
|
rb_shape_t * rb_shape_get_next_iv_shape(rb_shape_t * shape, ID id);
|
|
bool rb_shape_get_iv_index(rb_shape_t * shape, ID id, attr_index_t * value);
|
|
bool rb_shape_get_iv_index_with_hint(shape_id_t shape_id, ID id, attr_index_t * value, shape_id_t *shape_id_hint);
|
|
bool rb_shape_obj_too_complex(VALUE obj);
|
|
|
|
void rb_shape_set_shape(VALUE obj, rb_shape_t* shape);
|
|
rb_shape_t* rb_shape_get_shape(VALUE obj);
|
|
int rb_shape_frozen_shape_p(rb_shape_t* shape);
|
|
rb_shape_t* rb_shape_transition_shape_frozen(VALUE obj);
|
|
bool rb_shape_transition_shape_remove_ivar(VALUE obj, ID id, rb_shape_t *shape, VALUE * removed);
|
|
rb_shape_t * rb_shape_transition_shape_capa(rb_shape_t * shape);
|
|
rb_shape_t* rb_shape_get_next(rb_shape_t* shape, VALUE obj, ID id);
|
|
|
|
rb_shape_t * rb_shape_rebuild_shape(rb_shape_t * initial_shape, rb_shape_t * dest_shape);
|
|
|
|
static inline uint32_t
|
|
ROBJECT_IV_CAPACITY(VALUE obj)
|
|
{
|
|
RBIMPL_ASSERT_TYPE(obj, RUBY_T_OBJECT);
|
|
// Asking for capacity doesn't make sense when the object is using
|
|
// a hash table for storing instance variables
|
|
RUBY_ASSERT(!rb_shape_obj_too_complex(obj));
|
|
return rb_shape_get_shape_by_id(ROBJECT_SHAPE_ID(obj))->capacity;
|
|
}
|
|
|
|
static inline st_table *
|
|
ROBJECT_IV_HASH(VALUE obj)
|
|
{
|
|
RBIMPL_ASSERT_TYPE(obj, RUBY_T_OBJECT);
|
|
RUBY_ASSERT(rb_shape_obj_too_complex(obj));
|
|
return (st_table *)ROBJECT(obj)->as.heap.ivptr;
|
|
}
|
|
|
|
static inline void
|
|
ROBJECT_SET_IV_HASH(VALUE obj, const st_table *tbl)
|
|
{
|
|
RBIMPL_ASSERT_TYPE(obj, RUBY_T_OBJECT);
|
|
RUBY_ASSERT(rb_shape_obj_too_complex(obj));
|
|
ROBJECT(obj)->as.heap.ivptr = (VALUE *)tbl;
|
|
}
|
|
|
|
size_t rb_id_table_size(const struct rb_id_table *tbl);
|
|
|
|
static inline uint32_t
|
|
ROBJECT_IV_COUNT(VALUE obj)
|
|
{
|
|
if (rb_shape_obj_too_complex(obj)) {
|
|
return (uint32_t)rb_st_table_size(ROBJECT_IV_HASH(obj));
|
|
}
|
|
else {
|
|
RBIMPL_ASSERT_TYPE(obj, RUBY_T_OBJECT);
|
|
RUBY_ASSERT(!rb_shape_obj_too_complex(obj));
|
|
return rb_shape_get_shape_by_id(ROBJECT_SHAPE_ID(obj))->next_iv_index;
|
|
}
|
|
}
|
|
|
|
static inline uint32_t
|
|
RBASIC_IV_COUNT(VALUE obj)
|
|
{
|
|
return rb_shape_get_shape_by_id(rb_shape_get_shape_id(obj))->next_iv_index;
|
|
}
|
|
|
|
static inline uint32_t
|
|
RCLASS_IV_COUNT(VALUE obj)
|
|
{
|
|
RUBY_ASSERT(RB_TYPE_P(obj, RUBY_T_CLASS) || RB_TYPE_P(obj, RUBY_T_MODULE));
|
|
uint32_t ivc = rb_shape_get_shape_by_id(RCLASS_SHAPE_ID(obj))->next_iv_index;
|
|
return ivc;
|
|
}
|
|
|
|
rb_shape_t *rb_shape_traverse_from_new_root(rb_shape_t *initial_shape, rb_shape_t *orig_shape);
|
|
|
|
bool rb_shape_set_shape_id(VALUE obj, shape_id_t shape_id);
|
|
|
|
VALUE rb_obj_debug_shape(VALUE self, VALUE obj);
|
|
void rb_shape_set_too_complex(VALUE obj);
|
|
|
|
// For ext/objspace
|
|
RUBY_SYMBOL_EXPORT_BEGIN
|
|
typedef void each_shape_callback(rb_shape_t * shape, void *data);
|
|
void rb_shape_each_shape(each_shape_callback callback, void *data);
|
|
size_t rb_shape_memsize(rb_shape_t *shape);
|
|
size_t rb_shape_edges_count(rb_shape_t *shape);
|
|
size_t rb_shape_depth(rb_shape_t *shape);
|
|
shape_id_t rb_shape_id(rb_shape_t * shape);
|
|
RUBY_SYMBOL_EXPORT_END
|
|
|
|
#endif
|