fae86a701e
While profiling msgpack-ruby I noticed a very substantial amout of time spent in `rb_enc_associate_index`, called by `rb_utf8_str_new`. On that benchmark, `rb_utf8_str_new` is 33% of the total runtime, in big part because it cause GC to trigger often, but even then `5.3%` of the total runtime is spent in `rb_enc_associate_index` called by `rb_utf8_str_new`. After closer inspection, it appears that it's performing a lot of safety check we can assert we don't need, and other extra useless operations, because strings are first created and filled as ASCII-8BIT and then later reassociated to the desired encoding. By directly allocating the string with the right encoding, it allow to skip a lot of duplicated and useless operations. After this change, the time spent in `rb_utf8_str_new` is down to `28.4%` of total runtime, and most of that is GC.
39 lines
1.5 KiB
C
39 lines
1.5 KiB
C
#ifndef INTERNAL_ENCODING_H /*-*-C-*-vi:se ft=c:*/
|
|
#define INTERNAL_ENCODING_H
|
|
/**
|
|
* @author Ruby developers <ruby-core@ruby-lang.org>
|
|
* @copyright This file is a part of the programming language Ruby.
|
|
* Permission is hereby granted, to either redistribute and/or
|
|
* modify this file, provided that the conditions mentioned in the
|
|
* file COPYING are met. Consult the file for details.
|
|
* @brief Internal header for Encoding.
|
|
*/
|
|
#include "ruby/ruby.h" /* for ID */
|
|
#include "ruby/encoding.h" /* for rb_encoding */
|
|
|
|
#define rb_enc_autoload_p(enc) (!rb_enc_mbmaxlen(enc))
|
|
#define rb_is_usascii_enc(enc) ((enc) == rb_usascii_encoding())
|
|
#define rb_is_ascii8bit_enc(enc) ((enc) == rb_ascii8bit_encoding())
|
|
#define rb_is_locale_enc(enc) ((enc) == rb_locale_encoding())
|
|
|
|
/* encoding.c */
|
|
ID rb_id_encoding(void);
|
|
const char * rb_enc_inspect_name(rb_encoding *enc);
|
|
rb_encoding *rb_enc_get_from_index(int index);
|
|
rb_encoding *rb_enc_check_str(VALUE str1, VALUE str2);
|
|
int rb_encdb_replicate(const char *alias, const char *orig);
|
|
int rb_encdb_alias(const char *alias, const char *orig);
|
|
int rb_enc_autoload(rb_encoding *enc);
|
|
int rb_encdb_dummy(const char *name);
|
|
void rb_encdb_declare(const char *name);
|
|
void rb_enc_set_base(const char *name, const char *orig);
|
|
int rb_enc_set_dummy(int index);
|
|
void rb_enc_raw_set(VALUE obj, rb_encoding *enc);
|
|
|
|
PUREFUNC(int rb_data_is_encoding(VALUE obj));
|
|
|
|
/* vm.c */
|
|
void rb_free_global_enc_table(void);
|
|
|
|
#endif /* INTERNAL_ENCODING_H */
|