Peter Zhu a41fbc2c95 Increase SIZE_POOL_COUNT to 5 ... Having more size pools will allow us to allocate larger objects through Variable Width Allocation. I have attached some benchmark results below. Discourse: On Discourse, we don't see much change in response times. We do see a small reduction in RSS. Branch RSS: 377.8 MB Master RSS: 396.3 MB railsbench: On railsbench, we don't see a big change in RPS or p99 performance. We see a small increase in RSS. Branch RPS: 815.38 Master RPS: 811.73 Branch p99: 1.69 ms Master p99: 1.68 ms Branch RSS: 90.6 MB Master RSS: 89.4 MB liquid: We don't see a significant change in liquid performance. Branch parse & render: 29.041 I/s Master parse & render: 29.211 I/s		2022-05-09 08:45:24 -04:00
..
arithmetic
attr
compiler_is
core	Increase SIZE_POOL_COUNT to 5	2022-05-09 08:45:24 -04:00
encoding	[DOC] Fix reference in rb_enc_associate() description	2022-03-01 10:11:59 +09:00
has	Define HAVE___BUILTIN_UNREACHABLE instead of UNREACHABLE	2022-02-19 23:32:52 +09:00
intern	Expose rb_hash_new_capa(long)	2022-04-26 16:12:47 +02:00
abi.h	[Feature #18634] Implement Arrays on Variable Width Allocation	2022-03-22 09:42:39 -04:00
anyargs.h
arithmetic.h
assume.h	Check if __assume is supported	2022-02-19 23:32:52 +09:00
cast.h
compiler_is.h
compiler_since.h
config.h	Enable Variable Width Allocation by default	2022-01-12 12:00:55 -05:00
constant_p.h
core.h
ctype.h
dllexport.h
dosish.h
error.h
eval.h
event.h
fl_type.h	Remove tainted and trusted features	2021-12-26 23:28:54 +09:00
gc.h
glob.h
globals.h
interpreter.h
iterator.h
memory.h	Revert zero-check for alloca	2021-12-10 18:39:48 +09:00
method.h
module.h
newobj.h
rgengc.h
scan_args.h
special_consts.h
static_assert.h
stdalign.h
stdbool.h	Honor if _Bool is available	2022-03-16 17:50:13 +09:00
symbol.h
value.h
value_type.h
variable.h	[DOC] Fix function name in example	2022-03-01 09:59:12 +09:00
warning_push.h
xmalloc.h