1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
ruby/debug_counter.h

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

428 lines
15 KiB
C
Raw Normal View History

add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
/**********************************************************************
debug_counter.h -
created at: Tue Feb 21 16:51:18 2017
Copyright (C) 2017 Koichi Sasada
**********************************************************************/
#ifndef USE_DEBUG_COUNTER
#define USE_DEBUG_COUNTER 0
#endif
debug_counter.c: debug_counter_names [ci skip] * debug_counter.c (debug_counter_names): stringize debug counter names by preprocessor. * debug_counter.h (RB_DEBUG_COUNTER): define counter names outside the include guard, to expand multiple times. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57826 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-03-10 07:18:03 +00:00
#ifdef RB_DEBUG_COUNTER
add debug counters for local variable (lavr) access. * debug_counter.h: add the following counters: * lvar_get: counter for lvar get. * lvar_get_dynamic: counter for lvar get from upper frames. * lvar_set: coutner for lvar set. * lvar_set_dynamic: coutner for lvar set from upper frames. * lvar_set_slowpath: counter for lavr set using slowpath. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58977 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-31 06:46:57 +00:00
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
// method cache (IMC: inline method cache)
RB_DEBUG_COUNTER(mc_inline_hit) // IMC hit
RB_DEBUG_COUNTER(mc_inline_miss_klass) // IMC miss by different class
RB_DEBUG_COUNTER(mc_inline_miss_invalidated) // IMC miss by invalidated ME
add debug counters to survey the IMC miss
2020-12-14 17:56:34 +09:00
RB_DEBUG_COUNTER(mc_inline_miss_empty) // IMC miss because prev is empty slot
RB_DEBUG_COUNTER(mc_inline_miss_same_cc) // IMC miss, but same CC
RB_DEBUG_COUNTER(mc_inline_miss_same_cme) // IMC miss, but same CME
fix condition and add another debug counter mc_inline_miss_same_def is added to check same method or not. Also the mc_inline_miss_same_cc calculation was fixed.
2020-12-14 18:37:22 +09:00
RB_DEBUG_COUNTER(mc_inline_miss_same_def) // IMC miss, but same definition
add debug counters to survey the IMC miss
2020-12-14 17:56:34 +09:00
RB_DEBUG_COUNTER(mc_inline_miss_diff) // IMC miss, different methods
Add a cache for class variables Redo of 34a2acdac788602c14bf05fb616215187badd504 and 931138b00696419945dc03e10f033b1f53cd50f3 which were reverted. GitHub PR #4340. This change implements a cache for class variables. Previously there was no cache for cvars. Cvar access is slow due to needing to travel all the way up th ancestor tree before returning the cvar value. The deeper the ancestor tree the slower cvar access will be. The benefits of the cache are more visible with a higher number of included modules due to the way Ruby looks up class variables. The benchmark here includes 26 modules and shows with the cache, this branch is 6.5x faster when accessing class variables. ``` compare-ruby: ruby 3.1.0dev (2021-03-15T06:22:34Z master 9e5105c) [x86_64-darwin19] built-ruby: ruby 3.1.0dev (2021-03-15T12:12:44Z add-cache-for-clas.. c6be009) [x86_64-darwin19] | |compare-ruby|built-ruby| |:--------|-----------:|---------:| |vm_cvar | 5.681M| 36.980M| | | -| 6.51x| ``` Benchmark.ips calling `ActiveRecord::Base.logger` from within a Rails application. ActiveRecord::Base.logger has 71 ancestors. The more ancestors a tree has, the more clear the speed increase. IE if Base had only one ancestor we'd see no improvement. This benchmark is run on a vanilla Rails application. Benchmark code: ```ruby require "benchmark/ips" require_relative "config/environment" Benchmark.ips do |x| x.report "logger" do ActiveRecord::Base.logger end end ``` Ruby 3.0 master / Rails 6.1: ``` Warming up -------------------------------------- logger 155.251k i/100ms Calculating ------------------------------------- ``` Ruby 3.0 with cvar cache / Rails 6.1: ``` Warming up -------------------------------------- logger 1.546M i/100ms Calculating ------------------------------------- logger 14.857M (± 4.8%) i/s - 74.198M in 5.006202s ``` Lastly we ran a benchmark to demonstate the difference between master and our cache when the number of modules increases. This benchmark measures 1 ancestor, 30 ancestors, and 100 ancestors. Ruby 3.0 master: ``` Warming up -------------------------------------- 1 module 1.231M i/100ms 30 modules 432.020k i/100ms 100 modules 145.399k i/100ms Calculating ------------------------------------- 1 module 12.210M (± 2.1%) i/s - 61.553M in 5.043400s 30 modules 4.354M (± 2.7%) i/s - 22.033M in 5.063839s 100 modules 1.434M (± 2.9%) i/s - 7.270M in 5.072531s Comparison: 1 module: 12209958.3 i/s 30 modules: 4354217.8 i/s - 2.80x (± 0.00) slower 100 modules: 1434447.3 i/s - 8.51x (± 0.00) slower ``` Ruby 3.0 with cvar cache: ``` Warming up -------------------------------------- 1 module 1.641M i/100ms 30 modules 1.655M i/100ms 100 modules 1.620M i/100ms Calculating ------------------------------------- 1 module 16.279M (± 3.8%) i/s - 82.038M in 5.046923s 30 modules 15.891M (± 3.9%) i/s - 79.459M in 5.007958s 100 modules 16.087M (± 3.6%) i/s - 81.005M in 5.041931s Comparison: 1 module: 16279458.0 i/s 100 modules: 16087484.6 i/s - same-ish: difference falls within error 30 modules: 15891406.2 i/s - same-ish: difference falls within error ``` Co-authored-by: Aaron Patterson <tenderlove@ruby-lang.org>
2021-06-01 13:34:06 -04:00
RB_DEBUG_COUNTER(cvar_write_inline_hit) // cvar cache hit on write
RB_DEBUG_COUNTER(cvar_read_inline_hit) // cvar cache hit on read
RB_DEBUG_COUNTER(cvar_inline_miss) // miss inline cache
RB_DEBUG_COUNTER(cvar_class_invalidate) // invalidate cvar cache when define a cvar that's defined on a subclass
RB_DEBUG_COUNTER(cvar_include_invalidate) // invalidate cvar cache on module include or prepend
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(mc_cme_complement) // number of acquiring complement CME
Fix typos [ci skip]
2020-03-16 23:21:08 +09:00
RB_DEBUG_COUNTER(mc_cme_complement_hit) // number of cache hit for complemented CME
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(mc_search) // count for method lookup in class tree
RB_DEBUG_COUNTER(mc_search_notfound) // method lookup, but not found
RB_DEBUG_COUNTER(mc_search_super) // total traversed classes
Add debug counters. * debug_counter.h: add the following counters to measure object types. obj_free: freed count obj_str_ptr: freed count of Strings they have extra buff. obj_str_embed: freed count of Strings they don't have extra buff. obj_str_shared: freed count of Strings they have shared extra buff. obj_str_nofree: freed count of Strings they are marked as nofree. obj_str_fstr: freed count of Strings they are marked as fstr. obj_ary_ptr: freed count of Arrays they have extra buff. obj_ary_embed: freed count of Arrays they don't have extra buff. obj_obj_ptr: freed count of Objects (T_OBJECT) they have extra buff. obj_obj_embed: freed count of Objects they don't have extra buff. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58865 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-24 06:46:44 +00:00
VALUE size packed callinfo (ci). Now, rb_call_info contains how to call the method with tuple of (mid, orig_argc, flags, kwarg). Most of cases, kwarg == NULL and mid+argc+flags only requires 64bits. So this patch packed rb_call_info to VALUE (1 word) on such cases. If we can not represent it in VALUE, then use imemo_callinfo which contains conventional callinfo (rb_callinfo, renamed from rb_call_info). iseq->body->ci_kw_size is removed because all of callinfo is VALUE size (packed ci or a pointer to imemo_callinfo). To access ci information, we need to use these functions: vm_ci_mid(ci), _flag(ci), _argc(ci), _kwarg(ci). struct rb_call_info_kw_arg is renamed to rb_callinfo_kwarg. rb_funcallv_with_cc() and rb_method_basic_definition_p_with_cc() is temporary removed because cd->ci should be marked.
2020-01-08 08:20:36 +09:00
// callinfo
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(ci_packed) // number of packed CI
RB_DEBUG_COUNTER(ci_kw) // non-packed CI w/ keywords
RB_DEBUG_COUNTER(ci_nokw) // non-packed CI w/o keywords
RB_DEBUG_COUNTER(ci_runtime) // creating temporary CI
// callcache
RB_DEBUG_COUNTER(cc_new) // number of CC
RB_DEBUG_COUNTER(cc_temp) // dummy CC (stack-allocated)
add several debug counters add cc_found_in_ccs (renamed from cc_found_ccs), cc_not_found_in_ccs, call0_public, call0_other debug counters to measure more details. also it contains several modification.
2020-12-15 12:10:35 +09:00
RB_DEBUG_COUNTER(cc_found_in_ccs) // count for CC lookup success in CCS
RB_DEBUG_COUNTER(cc_not_found_in_ccs) // count for CC lookup success in CCS
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(cc_ent_invalidate) // count for invalidating cc (cc->klass = 0)
Fix typos [ci skip]
2020-03-16 23:21:08 +09:00
RB_DEBUG_COUNTER(cc_cme_invalidate) // count for invalidating CME
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
Fix some typos by spell checker
2021-04-26 00:10:39 +09:00
RB_DEBUG_COUNTER(cc_invalidate_leaf) // count for invalidating klass if klass has no-subclasses
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(cc_invalidate_leaf_ccs) // corresponding CCS
RB_DEBUG_COUNTER(cc_invalidate_leaf_callable) // complimented cache (no-subclasses)
Fix some typos by spell checker
2021-04-26 00:10:39 +09:00
RB_DEBUG_COUNTER(cc_invalidate_tree) // count for invalidating klass if klass has subclasses
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(cc_invalidate_tree_cme) // cme if cme is found in this class or superclasses
RB_DEBUG_COUNTER(cc_invalidate_tree_callable) // complimented cache (subclasses)
add cc_invalidate_negative debug counter counts for invalidating negative cache.
2020-12-14 10:49:07 +09:00
RB_DEBUG_COUNTER(cc_invalidate_negative) // count for invalidating negative cache
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(ccs_free) // count for free'ing ccs
RB_DEBUG_COUNTER(ccs_maxlen) // maximum length of ccs
add ccs_not_found debug counter ccs_not_found to count not found in ccs table.
2020-12-14 18:17:35 +09:00
RB_DEBUG_COUNTER(ccs_found) // count for finding corresponding ccs on method lookup
RB_DEBUG_COUNTER(ccs_not_found) // count for not found corresponding ccs on method lookup
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
add several debug counters add cc_found_in_ccs (renamed from cc_found_ccs), cc_not_found_in_ccs, call0_public, call0_other debug counters to measure more details. also it contains several modification.
2020-12-15 12:10:35 +09:00
// vm_eval.c
RB_DEBUG_COUNTER(call0_public)
RB_DEBUG_COUNTER(call0_other)
global call-cache cache table for rb_funcall* rb_funcall* (rb_funcall(), rb_funcallv(), ...) functions invokes Ruby's method with given receiver. Ruby 2.7 introduced inline method cache with static memory area. However, Ruby 3.0 reimplemented the method cache data structures and the inline cache was removed. Without inline cache, rb_funcall* searched methods everytime. Most of cases per-Class Method Cache (pCMC) will be helped but pCMC requires VM-wide locking and it hurts performance on multi-Ractor execution, especially all Ractors calls methods with rb_funcall*. This patch introduced Global Call-Cache Cache Table (gccct) for rb_funcall*. Call-Cache was introduced from Ruby 3.0 to manage method cache entry atomically and gccct enables method-caching without VM-wide locking. This table solves the performance issue on multi-ractor execution. [Bug #17497] Ruby-level method invocation does not use gccct because it has inline-method-cache and the table size is limited. Basically rb_funcall* is not used frequently, so 1023 entries can be enough. We will revisit the table size if it is not enough.
2021-01-21 03:33:59 +09:00
RB_DEBUG_COUNTER(gccct_hit)
RB_DEBUG_COUNTER(gccct_miss)
RB_DEBUG_COUNTER(gccct_null)
add several debug counters add cc_found_in_ccs (renamed from cc_found_ccs), cc_not_found_in_ccs, call0_public, call0_other debug counters to measure more details. also it contains several modification.
2020-12-15 12:10:35 +09:00
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
// iseq
RB_DEBUG_COUNTER(iseq_num) // number of total created iseq
RB_DEBUG_COUNTER(iseq_cd_num) // number of total created cd (call_data)
VALUE size packed callinfo (ci). Now, rb_call_info contains how to call the method with tuple of (mid, orig_argc, flags, kwarg). Most of cases, kwarg == NULL and mid+argc+flags only requires 64bits. So this patch packed rb_call_info to VALUE (1 word) on such cases. If we can not represent it in VALUE, then use imemo_callinfo which contains conventional callinfo (rb_callinfo, renamed from rb_call_info). iseq->body->ci_kw_size is removed because all of callinfo is VALUE size (packed ci or a pointer to imemo_callinfo). To access ci information, we need to use these functions: vm_ci_mid(ci), _flag(ci), _argc(ci), _kwarg(ci). struct rb_call_info_kw_arg is renamed to rb_callinfo_kwarg. rb_funcallv_with_cc() and rb_method_basic_definition_p_with_cc() is temporary removed because cd->ci should be marked.
2020-01-08 08:20:36 +09:00
add debug counters to count call cache fastpath. Add counters to count ccf (call cache fastpath) usage. These counters will help which kind of method dispatch is important to optimize. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67336 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-22 07:57:26 +00:00
/*
* call cache fastpath usage
*/
RB_DEBUG_COUNTER(ccf_general)
RB_DEBUG_COUNTER(ccf_iseq_setup)
RB_DEBUG_COUNTER(ccf_iseq_setup_0start)
RB_DEBUG_COUNTER(ccf_iseq_setup_tailcall_0start)
RB_DEBUG_COUNTER(ccf_iseq_fix) /* several functions created with tool/mk_call_iseq_optimized.rb */
Elaborate more on some debug counters [ci skip] git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67374 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-29 12:31:08 +00:00
RB_DEBUG_COUNTER(ccf_iseq_opt) /* has_opt == TRUE (has optional parameters), but other flags are FALSE */
Fix a typo [ci skip] git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67377 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-29 13:06:48 +00:00
RB_DEBUG_COUNTER(ccf_iseq_kw1) /* vm_call_iseq_setup_kwparm_kwarg() */
Elaborate more on some debug counters [ci skip] git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67374 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-29 12:31:08 +00:00
RB_DEBUG_COUNTER(ccf_iseq_kw2) /* vm_call_iseq_setup_kwparm_nokwarg() */
add debug counters to count call cache fastpath. Add counters to count ccf (call cache fastpath) usage. These counters will help which kind of method dispatch is important to optimize. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67336 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-22 07:57:26 +00:00
RB_DEBUG_COUNTER(ccf_cfunc)
Make vm_call_cfunc_with_frame a fastpath (#3027) when there's no need to call CALLER_SETUP_ARG and CALLER_REMOVE_EMPTY_KW_SPLAT (i.e. !rb_splat_or_kwargs_p(ci) && !calling->kw_splat). Micro benchmark: ``` $ benchmark-driver -v --rbenv 'before;after' benchmark/vm_send_cfunc.yml --repeat-count=4 before: ruby 2.8.0dev (2020-04-13T23:45:05Z master b9d3ceee8f) [x86_64-linux] after: ruby 2.8.0dev (2020-04-14T00:48:52Z no-splat-fastpath 418d363722) [x86_64-linux] Calculating ------------------------------------- before after vm_send_cfunc 69.585M 88.724M i/s - 100.000M times in 1.437097s 1.127096s Comparison: vm_send_cfunc after: 88723605.2 i/s before: 69584737.1 i/s - 1.28x slower ``` Optcarrot: ``` $ benchmark-driver -v --rbenv 'before;after' benchmark.yml --repeat-count=12 --output=all before: ruby 2.8.0dev (2020-04-13T23:45:05Z master b9d3ceee8f) [x86_64-linux] after: ruby 2.8.0dev (2020-04-14T00:48:52Z no-splat-fastpath 418d363722) [x86_64-linux] Calculating ------------------------------------- before after Optcarrot Lan_Master.nes 50.76119601545175 42.73858236484051 fps 50.76388649761503 51.04211379912850 50.80930672252514 51.39455790755538 50.90236000778749 51.75656936556145 51.01744746340430 51.86875277356489 51.06495279015112 51.88692482485558 51.07785337168974 51.93429603190578 51.20163525187862 51.95768145071314 51.34671771913112 52.45577266040274 51.35918340835583 52.53163888762858 51.46641337418146 52.62172484121034 51.50835463462257 52.85064021113239 ```
2020-04-13 20:32:59 -07:00
RB_DEBUG_COUNTER(ccf_cfunc_with_frame)
Elaborate more on some debug counters [ci skip] git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67374 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-29 12:31:08 +00:00
RB_DEBUG_COUNTER(ccf_ivar) /* attr_reader */
RB_DEBUG_COUNTER(ccf_attrset) /* attr_writer */
add debug counters to count call cache fastpath. Add counters to count ccf (call cache fastpath) usage. These counters will help which kind of method dispatch is important to optimize. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67336 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-22 07:57:26 +00:00
RB_DEBUG_COUNTER(ccf_method_missing)
RB_DEBUG_COUNTER(ccf_zsuper)
RB_DEBUG_COUNTER(ccf_bmethod)
RB_DEBUG_COUNTER(ccf_opt_send)
RB_DEBUG_COUNTER(ccf_opt_call)
RB_DEBUG_COUNTER(ccf_opt_block_call)
optimize `Struct` getter/setter Introduce new optimized method type `OPTIMIZED_METHOD_TYPE_STRUCT_AREF/ASET` with index information.
2021-11-18 11:01:31 +09:00
RB_DEBUG_COUNTER(ccf_opt_struct_aref)
RB_DEBUG_COUNTER(ccf_opt_struct_aset)
add debug counters to count call cache fastpath. Add counters to count ccf (call cache fastpath) usage. These counters will help which kind of method dispatch is important to optimize. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67336 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-22 07:57:26 +00:00
RB_DEBUG_COUNTER(ccf_super_method)
Add Missing Counters to `rb_debug_counter_type` enum (#8297) Add missing counters to rb_debug_counter_type enum On master we have calls to the RB_DEBUG_COUNTER_INC macro for counters that are not getting defined in the rb_debug_counter_type enum. This commit adds those that are missing in order for compilation to pass with -DUSE_RUBY_DEBUG_LOG.
2023-08-25 18:27:56 -04:00
RB_DEBUG_COUNTER(ccf_cfunc_other)
RB_DEBUG_COUNTER(ccf_cfunc_only_splat)
RB_DEBUG_COUNTER(ccf_cfunc_only_splat_kw)
RB_DEBUG_COUNTER(ccf_iseq_bmethod)
RB_DEBUG_COUNTER(ccf_noniseq_bmethod)
RB_DEBUG_COUNTER(ccf_opt_send_complex)
RB_DEBUG_COUNTER(ccf_opt_send_simple)
add debug counters to count call cache fastpath. Add counters to count ccf (call cache fastpath) usage. These counters will help which kind of method dispatch is important to optimize. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67336 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-03-22 07:57:26 +00:00
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
/*
* control frame push counts.
*
* * frame_push: frame push counts.
add debug counters more. * debug_counter.h: add debug counters to count frame state transitions: * frame_R2R: Ruby frame to Ruby frame * frame_R2C: Ruby frame to C frame * frame_C2C: C frame to C frame * frame_C2R: C frame to Ruby frame * vm_insnhelper.c (vm_push_frame): ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64871 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 03:35:15 +00:00
* * frame_push_*: frame push counts per each type.
* * frame_R2R: Ruby frame to Ruby frame
* * frame_R2C: Ruby frame to C frame
* * frame_C2C: C frame to C frame
* * frame_C2R: C frame to Ruby frame
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
*/
RB_DEBUG_COUNTER(frame_push)
RB_DEBUG_COUNTER(frame_push_method)
RB_DEBUG_COUNTER(frame_push_block)
RB_DEBUG_COUNTER(frame_push_class)
RB_DEBUG_COUNTER(frame_push_top)
RB_DEBUG_COUNTER(frame_push_cfunc)
RB_DEBUG_COUNTER(frame_push_ifunc)
RB_DEBUG_COUNTER(frame_push_eval)
RB_DEBUG_COUNTER(frame_push_rescue)
RB_DEBUG_COUNTER(frame_push_dummy)
add debug counters more. * debug_counter.h: add debug counters to count frame state transitions: * frame_R2R: Ruby frame to Ruby frame * frame_R2C: Ruby frame to C frame * frame_C2C: C frame to C frame * frame_C2R: C frame to Ruby frame * vm_insnhelper.c (vm_push_frame): ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64871 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 03:35:15 +00:00
RB_DEBUG_COUNTER(frame_R2R)
RB_DEBUG_COUNTER(frame_R2C)
RB_DEBUG_COUNTER(frame_C2C)
RB_DEBUG_COUNTER(frame_C2R)
Refactor / document instance variable debug counters This commit is refactoring and documenting the debug counters related to instance variables.
2023-02-14 14:41:23 -08:00
/* instance variable counts */
RB_DEBUG_COUNTER(ivar_get_obj_hit) // Only T_OBJECT hits
RB_DEBUG_COUNTER(ivar_get_obj_miss) // Only T_OBJECT misses
RB_DEBUG_COUNTER(ivar_get_ic_hit) // All hits
RB_DEBUG_COUNTER(ivar_get_ic_miss) // All misses
RB_DEBUG_COUNTER(ivar_set_ic_hit) // All hits
RB_DEBUG_COUNTER(ivar_set_obj_hit) // Only T_OBJECT hits
RB_DEBUG_COUNTER(ivar_set_obj_miss) // Only T_OBJECT misses
RB_DEBUG_COUNTER(ivar_set_ic_miss) // All misses
RB_DEBUG_COUNTER(ivar_set_ic_miss_noobject) // Miss because non T_OBJECT
RB_DEBUG_COUNTER(ivar_get_base) // Calls to `rb_ivar_get` (very slow path)
RB_DEBUG_COUNTER(ivar_set_base) // Calls to `ivar_set` (very slow path)
RB_DEBUG_COUNTER(ivar_get_ic_miss_set) // Misses on IV reads where the cache was wrong
RB_DEBUG_COUNTER(ivar_get_cc_miss_set) // Misses on attr_reader where the cache was wrong
RB_DEBUG_COUNTER(ivar_get_ic_miss_unset) // Misses on IV read where the cache wasn't set
RB_DEBUG_COUNTER(ivar_get_cc_miss_unset) // Misses on attr_reader where the cache wasn't set
Add debug counters. * debug_counter.h: add the following counters to measure object types. obj_free: freed count obj_str_ptr: freed count of Strings they have extra buff. obj_str_embed: freed count of Strings they don't have extra buff. obj_str_shared: freed count of Strings they have shared extra buff. obj_str_nofree: freed count of Strings they are marked as nofree. obj_str_fstr: freed count of Strings they are marked as fstr. obj_ary_ptr: freed count of Arrays they have extra buff. obj_ary_embed: freed count of Arrays they don't have extra buff. obj_obj_ptr: freed count of Objects (T_OBJECT) they have extra buff. obj_obj_embed: freed count of Objects they don't have extra buff. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58865 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-24 06:46:44 +00:00
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
/* local variable counts
*
* * lvar_get: total lvar get counts (VM insn)
* * lvar_get_dynamic: lvar get counts if accessing upper env (VM insn)
* * lvar_set*: same as "get"
* * lvar_set_slowpath: counts using vm_env_write_slowpath()
*/
add debug counters for local variable (lavr) access. * debug_counter.h: add the following counters: * lvar_get: counter for lvar get. * lvar_get_dynamic: counter for lvar get from upper frames. * lvar_set: coutner for lvar set. * lvar_set_dynamic: coutner for lvar set from upper frames. * lvar_set_slowpath: counter for lavr set using slowpath. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58977 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-31 06:46:57 +00:00
RB_DEBUG_COUNTER(lvar_get)
RB_DEBUG_COUNTER(lvar_get_dynamic)
RB_DEBUG_COUNTER(lvar_set)
RB_DEBUG_COUNTER(lvar_set_dynamic)
RB_DEBUG_COUNTER(lvar_set_slowpath)
add new debug_counters for GC. * debug_counter.h: add new debug counters to count GC. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65359 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-24 22:17:03 +00:00
/* GC counts:
*
* * count: simple count
* * _minor: minor gc
* * _major: major gc
* * other suffix is corresponding to last_gc_info or
* gc_profile_record_flag in gc.c.
*/
RB_DEBUG_COUNTER(gc_count)
RB_DEBUG_COUNTER(gc_minor_newobj)
RB_DEBUG_COUNTER(gc_minor_malloc)
RB_DEBUG_COUNTER(gc_minor_method)
RB_DEBUG_COUNTER(gc_minor_capi)
RB_DEBUG_COUNTER(gc_minor_stress)
RB_DEBUG_COUNTER(gc_major_nofree)
RB_DEBUG_COUNTER(gc_major_oldgen)
RB_DEBUG_COUNTER(gc_major_shady)
RB_DEBUG_COUNTER(gc_major_force)
add new counter about GC. * debug_counter.h: add `gc_major_oldmalloc`. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65362 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-25 02:23:58 +00:00
RB_DEBUG_COUNTER(gc_major_oldmalloc)
add new debug_counters for GC. * debug_counter.h: add new debug counters to count GC. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65359 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-24 22:17:03 +00:00
add debug counters for gc start events
2020-12-17 17:03:05 +09:00
RB_DEBUG_COUNTER(gc_enter_start)
Refactor to separate marking and sweeping phases This commit separates the marking and sweeping phases so that marking functions do not directly call sweeping functions.
2023-02-14 15:50:45 -05:00
RB_DEBUG_COUNTER(gc_enter_continue)
add debug counters for gc start events
2020-12-17 17:03:05 +09:00
RB_DEBUG_COUNTER(gc_enter_rest)
RB_DEBUG_COUNTER(gc_enter_finalizer)
add new debug_counters about is_pointer_to_heap(). is_pointer_to_heap() is used for conservative marking. To analyze this function's behavior, introduce some debug_counters.
2019-05-07 14:06:25 +09:00
RB_DEBUG_COUNTER(gc_isptr_trial)
RB_DEBUG_COUNTER(gc_isptr_range)
RB_DEBUG_COUNTER(gc_isptr_align)
RB_DEBUG_COUNTER(gc_isptr_maybe)
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
/* object allocation counts:
*
* * obj_newobj: newobj counts
* * obj_newobj_slowpath: newobj with slowpath counts
Fix typos [ci skip]
2020-03-16 23:21:08 +09:00
* * obj_newobj_wb_unprotected: newobj for wb_unprotected.
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
* * obj_free: obj_free() counts
add some debug counters. * debug_counter.h: new debug counters obj_promote, obj_wb_unprotect and obj_struct_(ptr|embed) are added. * gc.c: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64853 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-26 07:28:04 +00:00
* * obj_promote: promoted counts (oldgen)
* * obj_wb_unprotect: wb unprotect counts
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
*
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
* * obj_[type]_[attr]: *free'ed counts* for each type.
* Note that it is not a allocated counts.
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
* * [type]
* * _obj: T_OBJECT
* * _str: T_STRING
* * _ary: T_ARRAY
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
* * _xxx: T_XXX (hash, struct, ...)
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
*
* * [attr]
* * _ptr: R?? is not embed.
* * _embed: R?? is embed.
* * type specific attr.
* * str_shared: str is shared.
* * str_nofree: nofree
* * str_fstr: fstr
* * hash_empty: hash is empty
fix debug counter for Hash counts. Change debug_counters for Hash object counts: * obj_hash_under4 (1-3) -> obj_hash_1_4 (1-4) * obj_hash_ge4 (4-7) -> obj_hash_5_8 (5-8) * obj_hash_ge8 (>=8) -> obj_hash_g8 (> 8) For example on rdoc benchmark: [RUBY_DEBUG_COUNTER] obj_hash_empty 554,900 [RUBY_DEBUG_COUNTER] obj_hash_under4 572,998 [RUBY_DEBUG_COUNTER] obj_hash_ge4 1,825 [RUBY_DEBUG_COUNTER] obj_hash_ge8 2,344 [RUBY_DEBUG_COUNTER] obj_hash_empty 553,097 [RUBY_DEBUG_COUNTER] obj_hash_1_4 571,880 [RUBY_DEBUG_COUNTER] obj_hash_5_8 982 [RUBY_DEBUG_COUNTER] obj_hash_g8 2,189
2019-07-19 16:24:14 +09:00
* * hash_1_4: has 1 to 4 entries
* * hash_5_8: has 5 to 8 entries
* * hash_g8: has n entries (n>8)
Reduce ONIG_NREGION from 10 to 4: power of 2 and testing revealed most pattern matches are less than or equal to 4 results Closes: https://github.com/ruby/ruby/pull/2135
2019-04-20 00:44:51 +01:00
* * match_under4: has under 4 oniguruma regions allocated
* * match_ge4: has n regions allocated (4<=n<8)
* * match_ge8: has n regions allocated (8<=n)
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
* * data_empty: T_DATA but no memory free.
* * data_xfree: free'ed by xfree().
* * data_imm_free: free'ed immediately.
* * data_zombie: free'ed with zombie.
* * imemo_*: T_IMEMO with each type.
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
*/
RB_DEBUG_COUNTER(obj_newobj)
RB_DEBUG_COUNTER(obj_newobj_slowpath)
RB_DEBUG_COUNTER(obj_newobj_wb_unprotected)
Add debug counters. * debug_counter.h: add the following counters to measure object types. obj_free: freed count obj_str_ptr: freed count of Strings they have extra buff. obj_str_embed: freed count of Strings they don't have extra buff. obj_str_shared: freed count of Strings they have shared extra buff. obj_str_nofree: freed count of Strings they are marked as nofree. obj_str_fstr: freed count of Strings they are marked as fstr. obj_ary_ptr: freed count of Arrays they have extra buff. obj_ary_embed: freed count of Arrays they don't have extra buff. obj_obj_ptr: freed count of Objects (T_OBJECT) they have extra buff. obj_obj_embed: freed count of Objects they don't have extra buff. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58865 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-24 06:46:44 +00:00
RB_DEBUG_COUNTER(obj_free)
add some debug counters. * debug_counter.h: new debug counters obj_promote, obj_wb_unprotect and obj_struct_(ptr|embed) are added. * gc.c: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64853 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-26 07:28:04 +00:00
RB_DEBUG_COUNTER(obj_promote)
RB_DEBUG_COUNTER(obj_wb_unprotect)
Add debug counters. * debug_counter.h: add the following counters to measure object types. obj_free: freed count obj_str_ptr: freed count of Strings they have extra buff. obj_str_embed: freed count of Strings they don't have extra buff. obj_str_shared: freed count of Strings they have shared extra buff. obj_str_nofree: freed count of Strings they are marked as nofree. obj_str_fstr: freed count of Strings they are marked as fstr. obj_ary_ptr: freed count of Arrays they have extra buff. obj_ary_embed: freed count of Arrays they don't have extra buff. obj_obj_ptr: freed count of Objects (T_OBJECT) they have extra buff. obj_obj_embed: freed count of Objects they don't have extra buff. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58865 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-24 06:46:44 +00:00
revert r65444 and r65446 because of commit miss git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65447 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-30 21:01:55 +00:00
RB_DEBUG_COUNTER(obj_obj_embed)
support theap for T_OBJECT. * variable.c: now instance variable space has theap supports. obj_ivar_heap_alloc() tries to acquire memory from theap. * debug_counter.h: add some counters for theap. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65451 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-30 22:01:17 +00:00
RB_DEBUG_COUNTER(obj_obj_ptr)
Transition complex objects to "too complex" shape When an object becomes "too complex" (in other words it has too many variations in the shape tree), we transition it to use a "too complex" shape and use a hash for storing instance variables. Without this patch, there were rare cases where shape tree growth could "explode" and cause performance degradation on what would otherwise have been cached fast paths. This patch puts a limit on shape tree growth, and gracefully degrades in the rare case where there could be a factorial growth in the shape tree. For example: ```ruby class NG; end HUGE_NUMBER.times do NG.new.instance_variable_set(:"@unique_ivar_#{_1}", 1) end ``` We consider objects to be "too complex" when the object's class has more than SHAPE_MAX_VARIATIONS (currently 8) leaf nodes in the shape tree and the object introduces a new variation (a new leaf node) associated with that class. For example, new variations on instances of the following class would be considered "too complex" because those instances create more than 8 leaves in the shape tree: ```ruby class Foo; end 9.times { Foo.new.instance_variable_set(":@uniq_#{_1}", 1) } ``` However, the following class is *not* too complex because it only has one leaf in the shape tree: ```ruby class Foo def initialize @a = @b = @c = @d = @e = @f = @g = @h = @i = nil end end 9.times { Foo.new } `` This case is rare, so we don't expect this change to impact performance of most applications, but it needs to be handled. Co-Authored-By: Aaron Patterson <tenderlove@ruby-lang.org>
2022-12-08 17:16:52 -05:00
RB_DEBUG_COUNTER(obj_obj_too_complex)
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
Add debug counters. * debug_counter.h: add the following counters to measure object types. obj_free: freed count obj_str_ptr: freed count of Strings they have extra buff. obj_str_embed: freed count of Strings they don't have extra buff. obj_str_shared: freed count of Strings they have shared extra buff. obj_str_nofree: freed count of Strings they are marked as nofree. obj_str_fstr: freed count of Strings they are marked as fstr. obj_ary_ptr: freed count of Arrays they have extra buff. obj_ary_embed: freed count of Arrays they don't have extra buff. obj_obj_ptr: freed count of Objects (T_OBJECT) they have extra buff. obj_obj_embed: freed count of Objects they don't have extra buff. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58865 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-24 06:46:44 +00:00
RB_DEBUG_COUNTER(obj_str_ptr)
RB_DEBUG_COUNTER(obj_str_embed)
RB_DEBUG_COUNTER(obj_str_shared)
RB_DEBUG_COUNTER(obj_str_nofree)
RB_DEBUG_COUNTER(obj_str_fstr)
revert r65444 and r65446 because of commit miss git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65447 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-30 21:01:55 +00:00
RB_DEBUG_COUNTER(obj_ary_embed)
support theap for T_OBJECT. * variable.c: now instance variable space has theap supports. obj_ivar_heap_alloc() tries to acquire memory from theap. * debug_counter.h: add some counters for theap. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65451 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-30 22:01:17 +00:00
RB_DEBUG_COUNTER(obj_ary_ptr)
introduce `obj_ary_extracapa`. Introduce a new debug counter `obj_ary_extracapa` which counts arrays which are `len < capa`.
2019-09-25 16:55:54 +09:00
RB_DEBUG_COUNTER(obj_ary_extracapa)
fix shared array terminology. Shared arrays created by Array#dup and so on points a shared_root object to manage lifetime of Array buffer. However, sometimes shared_root is called only shared so it is confusing. So I fixed these wording "shared" to "shared_root". * RArray::heap::aux::shared -> RArray::heap::aux::shared_root * ARY_SHARED() -> ARY_SHARED_ROOT() * ARY_SHARED_NUM() -> ARY_SHARED_ROOT_REFCNT() Also, add some debug_counters to count shared array objects. * ary_shared_create: shared ary by Array#dup and so on. * ary_shared: finished in shard. * ary_shared_root_occupied: shared_root but has only 1 refcnt. The number (ary_shared - ary_shared_root_occupied) is meaningful.
2019-07-19 13:02:38 +09:00
/*
ary_shared_create: shared ary by Array#dup and so on.
ary_shared: finished in shard.
ary_shared_root_occupied: shared_root but has only 1 refcnt.
The number (ary_shared - ary_shared_root_occupied) is meaningful.
*/
RB_DEBUG_COUNTER(obj_ary_shared_create)
RB_DEBUG_COUNTER(obj_ary_shared)
RB_DEBUG_COUNTER(obj_ary_shared_root_occupied)
Add debug counters. * debug_counter.h: add the following counters to measure object types. obj_free: freed count obj_str_ptr: freed count of Strings they have extra buff. obj_str_embed: freed count of Strings they don't have extra buff. obj_str_shared: freed count of Strings they have shared extra buff. obj_str_nofree: freed count of Strings they are marked as nofree. obj_str_fstr: freed count of Strings they are marked as fstr. obj_ary_ptr: freed count of Arrays they have extra buff. obj_ary_embed: freed count of Arrays they don't have extra buff. obj_obj_ptr: freed count of Objects (T_OBJECT) they have extra buff. obj_obj_embed: freed count of Objects they don't have extra buff. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58865 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-05-24 06:46:44 +00:00
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
RB_DEBUG_COUNTER(obj_hash_empty)
add debug_counters to check details. add debug_counters to check the Hash object statistics.
2019-08-02 14:59:29 +09:00
RB_DEBUG_COUNTER(obj_hash_1)
RB_DEBUG_COUNTER(obj_hash_2)
RB_DEBUG_COUNTER(obj_hash_3)
RB_DEBUG_COUNTER(obj_hash_4)
fix debug counter for Hash counts. Change debug_counters for Hash object counts: * obj_hash_under4 (1-3) -> obj_hash_1_4 (1-4) * obj_hash_ge4 (4-7) -> obj_hash_5_8 (5-8) * obj_hash_ge8 (>=8) -> obj_hash_g8 (> 8) For example on rdoc benchmark: [RUBY_DEBUG_COUNTER] obj_hash_empty 554,900 [RUBY_DEBUG_COUNTER] obj_hash_under4 572,998 [RUBY_DEBUG_COUNTER] obj_hash_ge4 1,825 [RUBY_DEBUG_COUNTER] obj_hash_ge8 2,344 [RUBY_DEBUG_COUNTER] obj_hash_empty 553,097 [RUBY_DEBUG_COUNTER] obj_hash_1_4 571,880 [RUBY_DEBUG_COUNTER] obj_hash_5_8 982 [RUBY_DEBUG_COUNTER] obj_hash_g8 2,189
2019-07-19 16:24:14 +09:00
RB_DEBUG_COUNTER(obj_hash_5_8)
RB_DEBUG_COUNTER(obj_hash_g8)
add debug_counters to check details. add debug_counters to check the Hash object statistics.
2019-08-02 14:59:29 +09:00
RB_DEBUG_COUNTER(obj_hash_null)
rename li_table->ar_table (and related names). * internal.h: rename the following names: * li_table -> ar_table. "li" means linear (from linear search), but we use the word "array" (from data layout). * RHASH_ARRAY -> RHASH_AR_TABLE. AR_TABLE is more clear. * rb_hash_array_* -> rb_hash_ar_table_*. * RHASH_TABLE_P() -> RHASH_ST_TABLE_P(). more clear. * RHASH_CLEAR() -> RHASH_ST_CLEAR(). * hash.c: rename "linear_" prefix functions to "ar_" prefix. * hash.c (linear_init_table): rename to ar_alloc_table. * debug_counter.h: rename obj_hash_array to obj_hash_ar. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66390 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-12-14 01:10:15 +00:00
RB_DEBUG_COUNTER(obj_hash_ar)
support theap for T_HASH. [Feature #14989] * hash.c, internal.h: support theap for small Hash. Introduce RHASH_ARRAY (li_table) besides st_table and small Hash (<=8 entries) are managed by an array data structure. This array data can be managed by theap. If st_table is needed, then converting array data to st_table data. For st_table using code, we prepare "stlike" APIs which accepts hash value and are very similar to st_ APIs. This work is based on the GSoC achievement by tacinight <tacingiht@gmail.com> and refined by ko1. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65454 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-30 22:11:51 +00:00
RB_DEBUG_COUNTER(obj_hash_st)
RB_DEBUG_COUNTER(obj_hash_force_convert)
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
add some debug counters. * debug_counter.h: new debug counters obj_promote, obj_wb_unprotect and obj_struct_(ptr|embed) are added. * gc.c: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64853 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-26 07:28:04 +00:00
RB_DEBUG_COUNTER(obj_struct_embed)
support theap for T_STRUCT. * struct.c: members memory can use theap. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65452 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-10-30 22:03:42 +00:00
RB_DEBUG_COUNTER(obj_struct_ptr)
add some debug counters. * debug_counter.h: new debug counters obj_promote, obj_wb_unprotect and obj_struct_(ptr|embed) are added. * gc.c: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64853 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-26 07:28:04 +00:00
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
RB_DEBUG_COUNTER(obj_data_empty)
RB_DEBUG_COUNTER(obj_data_xfree)
RB_DEBUG_COUNTER(obj_data_imm_free)
RB_DEBUG_COUNTER(obj_data_zombie)
Reduce ONIG_NREGION from 10 to 4: power of 2 and testing revealed most pattern matches are less than or equal to 4 results Closes: https://github.com/ruby/ruby/pull/2135
2019-04-20 00:44:51 +01:00
RB_DEBUG_COUNTER(obj_match_under4)
RB_DEBUG_COUNTER(obj_match_ge4)
RB_DEBUG_COUNTER(obj_match_ge8)
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
RB_DEBUG_COUNTER(obj_match_ptr)
add more debug counters to count numeric objects.
2019-12-23 16:30:45 +09:00
RB_DEBUG_COUNTER(obj_iclass_ptr)
RB_DEBUG_COUNTER(obj_class_ptr)
RB_DEBUG_COUNTER(obj_module_ptr)
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
RB_DEBUG_COUNTER(obj_bignum_ptr)
add more debug counters to count numeric objects.
2019-12-23 16:30:45 +09:00
RB_DEBUG_COUNTER(obj_bignum_embed)
RB_DEBUG_COUNTER(obj_float)
RB_DEBUG_COUNTER(obj_complex)
RB_DEBUG_COUNTER(obj_rational)
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
add more debug counters to count numeric objects.
2019-12-23 16:30:45 +09:00
RB_DEBUG_COUNTER(obj_regexp_ptr)
RB_DEBUG_COUNTER(obj_file_ptr)
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
RB_DEBUG_COUNTER(obj_symbol)
RB_DEBUG_COUNTER(obj_imemo_ment)
RB_DEBUG_COUNTER(obj_imemo_iseq)
RB_DEBUG_COUNTER(obj_imemo_env)
RB_DEBUG_COUNTER(obj_imemo_tmpbuf)
RB_DEBUG_COUNTER(obj_imemo_ast)
RB_DEBUG_COUNTER(obj_imemo_cref)
RB_DEBUG_COUNTER(obj_imemo_svar)
RB_DEBUG_COUNTER(obj_imemo_throw_data)
RB_DEBUG_COUNTER(obj_imemo_ifunc)
RB_DEBUG_COUNTER(obj_imemo_memo)
RB_DEBUG_COUNTER(obj_imemo_parser_strterm)
VALUE size packed callinfo (ci). Now, rb_call_info contains how to call the method with tuple of (mid, orig_argc, flags, kwarg). Most of cases, kwarg == NULL and mid+argc+flags only requires 64bits. So this patch packed rb_call_info to VALUE (1 word) on such cases. If we can not represent it in VALUE, then use imemo_callinfo which contains conventional callinfo (rb_callinfo, renamed from rb_call_info). iseq->body->ci_kw_size is removed because all of callinfo is VALUE size (packed ci or a pointer to imemo_callinfo). To access ci information, we need to use these functions: vm_ci_mid(ci), _flag(ci), _argc(ci), _kwarg(ci). struct rb_call_info_kw_arg is renamed to rb_callinfo_kwarg. rb_funcallv_with_cc() and rb_method_basic_definition_p_with_cc() is temporary removed because cd->ci should be marked.
2020-01-08 08:20:36 +09:00
RB_DEBUG_COUNTER(obj_imemo_callinfo)
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
RB_DEBUG_COUNTER(obj_imemo_callcache)
enable constant cache on ractors constant cache `IC` is accessed by non-atomic manner and there are thread-safety issues, so Ruby 3.0 disables to use const cache on non-main ractors. This patch enables it by introducing `imemo_constcache` and allocates it by every re-fill of const cache like `imemo_callcache`. [Bug #17510] Now `IC` only has one entry `IC::entry` and it points to `iseq_inline_constant_cache_entry`, managed by T_IMEMO object. `IC` is atomic data structure so `rb_mjit_before_vm_ic_update()` and `rb_mjit_after_vm_ic_update()` is not needed.
2021-01-04 18:08:25 +09:00
RB_DEBUG_COUNTER(obj_imemo_constcache)
Turn `rb_classext_t.fields` into a T_IMEMO/class_fields This behave almost exactly as a T_OBJECT, the layout is entirely compatible. This aims to solve two problems. First, it solves the problem of namspaced classes having a single `shape_id`. Now each namespaced classext has an object that can hold the namespace specific shape. Second, it open the door to later make class instance variable writes atomics, hence be able to read class variables without locking the VM. In the future, in multi-ractor mode, we can do the write on a copy of the `fields_obj` and then atomically swap it. Considerations: - Right now the `RClass` shape_id is always synchronized, but with namespace we should likely mark classes that have multiple namespace with a specific shape flag.
2025-05-22 14:01:46 +02:00
RB_DEBUG_COUNTER(obj_imemo_class_fields)
add debug counters more. * debug_counter.h: add the following counters. * frame_push: control frame counts (total counts). * frame_push_*: control frame counts per every frame type. * obj_*: add free'ed counts for each type. * gc.c: ditto. * vm_insnhelper.c (vm_push_frame): ditto. * debug_counter.c (rb_debug_counter_show_results): widen counts field to show >10G numbers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64867 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-28 01:10:43 +00:00
Inline Class#new. This commit inlines instructions for Class#new. To make this work, we added a new YARV instructions, `opt_new`. `opt_new` checks whether or not the `new` method is the default allocator method. If it is, it allocates the object, and pushes the instance on the stack. If not, the instruction jumps to the "slow path" method call instructions. Old instructions: ``` > ruby --dump=insns -e'Object.new' == disasm: #<ISeq:<main>@-e:1 (1,0)-(1,10)> 0000 opt_getconstant_path <ic:0 Object> ( 1)[Li] 0002 opt_send_without_block <calldata!mid:new, argc:0, ARGS_SIMPLE> 0004 leave ``` New instructions: ``` > ./miniruby --dump=insns -e'Object.new' == disasm: #<ISeq:<main>@-e:1 (1,0)-(1,10)> 0000 opt_getconstant_path <ic:0 Object> ( 1)[Li] 0002 putnil 0003 swap 0004 opt_new <calldata!mid:new, argc:0, ARGS_SIMPLE>, 11 0007 opt_send_without_block <calldata!mid:initialize, argc:0, FCALL|ARGS_SIMPLE> 0009 jump 14 0011 opt_send_without_block <calldata!mid:new, argc:0, ARGS_SIMPLE> 0013 swap 0014 pop 0015 leave ``` This commit speeds up basic object allocation (`Foo.new`) by 60%, but classes that take keyword parameters see an even bigger benefit because no hash is allocated when instantiating the object (3x to 6x faster). Here is an example that uses `Hash.new(capacity: 0)`: ``` > hyperfine "ruby --disable-gems -e'i = 0; while i < 10_000_000; Hash.new(capacity: 0); i += 1; end'" "./ruby --disable-gems -e'i = 0; while i < 10_000_000; Hash.new(capacity: 0); i += 1; end'" Benchmark 1: ruby --disable-gems -e'i = 0; while i < 10_000_000; Hash.new(capacity: 0); i += 1; end' Time (mean ± σ): 1.082 s ± 0.004 s [User: 1.074 s, System: 0.008 s] Range (min … max): 1.076 s … 1.088 s 10 runs Benchmark 2: ./ruby --disable-gems -e'i = 0; while i < 10_000_000; Hash.new(capacity: 0); i += 1; end' Time (mean ± σ): 627.9 ms ± 3.5 ms [User: 622.7 ms, System: 4.8 ms] Range (min … max): 622.7 ms … 633.2 ms 10 runs Summary ./ruby --disable-gems -e'i = 0; while i < 10_000_000; Hash.new(capacity: 0); i += 1; end' ran 1.72 ± 0.01 times faster than ruby --disable-gems -e'i = 0; while i < 10_000_000; Hash.new(capacity: 0); i += 1; end' ``` This commit changes the backtrace for `initialize`: ``` aaron@tc ~/g/ruby (inline-new)> cat test.rb class Foo def initialize puts caller end end def hello Foo.new end hello aaron@tc ~/g/ruby (inline-new)> ruby -v test.rb ruby 3.4.2 (2025-02-15 revision d2930f8e7a) +PRISM [arm64-darwin24] test.rb:8:in 'Class#new' test.rb:8:in 'Object#hello' test.rb:11:in '<main>' aaron@tc ~/g/ruby (inline-new)> ./miniruby -v test.rb ruby 3.5.0dev (2025-03-28T23:59:40Z inline-new c4157884e4) +PRISM [arm64-darwin24] test.rb:8:in 'Object#hello' test.rb:11:in '<main>' ``` It also increases memory usage for calls to `new` by 122 bytes: ``` aaron@tc ~/g/ruby (inline-new)> cat test.rb require "objspace" class Foo def initialize puts caller end end def hello Foo.new end puts ObjectSpace.memsize_of(RubyVM::InstructionSequence.of(method(:hello))) aaron@tc ~/g/ruby (inline-new)> make runruby RUBY_ON_BUG='gdb -x ./.gdbinit -p' ./miniruby -I./lib -I. -I.ext/common ./tool/runruby.rb --extout=.ext -- --disable-gems ./test.rb 656 aaron@tc ~/g/ruby (inline-new)> ruby -v test.rb ruby 3.4.2 (2025-02-15 revision d2930f8e7a) +PRISM [arm64-darwin24] 544 ``` Thanks to @ko1 for coming up with this idea! Co-Authored-By: John Hawthorn <john@hawthorn.email>
2025-03-17 16:59:19 -07:00
RB_DEBUG_COUNTER(opt_new_hit)
RB_DEBUG_COUNTER(opt_new_miss)
Use 1 byte hint for ar_table [Feature #15602] On ar_table, Do not keep a full-length hash value (FLHV, 8 bytes) but keep a 1 byte hint from a FLHV (lowest byte of FLHV). An ar_table only contains at least 8 entries, so hints consumes 8 bytes at most. We can store hints in RHash::ar_hint. On 32bit CPU, we use 4 entries ar_table. The advantages: * We don't need to keep FLHV so ar_table only consumes 16 bytes (VALUEs of key and value) * 8 entries = 128 bytes. * We don't need to scan ar_table, but only need to check hints in many cases. Especially we don't need to access ar_table if there is no match entries (in many cases). It will increase memory cache locality. The disadvantages: * This technique can increase `#eql?` time because hints can conflicts (in theory, it conflicts once in 256 times). It can introduce incompatibility if there is a object x where x.eql? returns true even if hash values are different. I believe we don't need to care such irregular case. * We need to re-calculate FLHV if we need to switch from ar_table to st_table (e.g. exceeds 8 entries). It also can introduce incompatibility, on mutating key objects. I believe we don't need to care such irregular case too. Add new debug counters to measure the performance: * artable_hint_hit - hint is matched and eql?#=>true * artable_hint_miss - hint is not matched but eql?#=>false * artable_hint_notfound - lookup counts
2019-01-17 16:53:10 +00:00
/* ar_table */
RB_DEBUG_COUNTER(artable_hint_hit)
RB_DEBUG_COUNTER(artable_hint_miss)
RB_DEBUG_COUNTER(artable_hint_notfound)
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
/* heap function counts
*
* * heap_xmalloc/realloc/xfree: call counts
*/
RB_DEBUG_COUNTER(heap_xmalloc)
RB_DEBUG_COUNTER(heap_xrealloc)
RB_DEBUG_COUNTER(heap_xfree)
add vm_sync debug counters * vm_sync_lock * vm_sync_lock_enter * vm_sync_lock_enter_nb * vm_sync_lock_enter_cr * vm_sync_barrier
2020-12-16 10:10:05 +09:00
// VM sync
RB_DEBUG_COUNTER(vm_sync_lock)
RB_DEBUG_COUNTER(vm_sync_lock_enter)
RB_DEBUG_COUNTER(vm_sync_lock_enter_nb)
RB_DEBUG_COUNTER(vm_sync_lock_enter_cr)
RB_DEBUG_COUNTER(vm_sync_barrier)
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
/* load (not implemented yet) */
/*
rename absolute_path to realpath internally and introduce pathobj. * vm_core.h: rename absolute_path to realpath because it is expected name. external APIs (#absolute_path methods) are remained. * vm_core.h: remove rb_iseq_location_struct::path and rb_iseq_location_struct::absolute_path and introduce pathobj. if given path equals to given absolute_path (and most of case it is true), pathobj is simply given path String. If it is not same, pathobj is Array and pathobj[0] is path and pathobj[1] is realpath. This size optimization reduce 8 bytes and sizeof(struct rb_iseq_constant_body) is 200 bytes -> 192 bytes on 64bit CPU. To support this change, the following functions are introduced: * pathobj_path() (defined in vm_core.h) * pathobj_realpath() (ditto) * rb_iseq_path() (decl. in vm_core.h) * rb_iseq_realpath() (ditto) * rb_iseq_pathobj_new() (ditto) * rb_iseq_pathobj_set() (ditto) * vm_core.h (rb_binding_t): use pathobj instead of path. If binding is given at eval methods, realpath (absolute_path) was caller's realpath. However, they should use binding's realpath. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58979 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-06-01 00:05:33 +00:00
RB_DEBUG_COUNTER(load_files)
RB_DEBUG_COUNTER(load_path_is_not_realpath)
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
*/
debug_counter.c: debug_counter_names [ci skip] * debug_counter.c (debug_counter_names): stringize debug counter names by preprocessor. * debug_counter.h (RB_DEBUG_COUNTER): define counter names outside the include guard, to expand multiple times. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57826 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-03-10 07:18:03 +00:00
#endif
#ifndef RUBY_DEBUG_COUNTER_H
#define RUBY_DEBUG_COUNTER_H 1
sed -i 's|ruby/impl|ruby/internal|' To fix build failures.
2020-05-08 18:31:09 +09:00
#include "ruby/internal/config.h"
debug_counter.h must be self-contained Include what is necessary.
2019-12-25 14:19:48 +09:00
#include <stddef.h> /* for size_t */
#include "ruby/ruby.h" /* for VALUE */
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
#if !defined(__GNUC__) && USE_DEBUG_COUNTER
#error "USE_DEBUG_COUNTER is not supported by other than __GNUC__"
#endif
enum rb_debug_counter_type {
debug_counter.c: debug_counter_names [ci skip] * debug_counter.c (debug_counter_names): stringize debug counter names by preprocessor. * debug_counter.h (RB_DEBUG_COUNTER): define counter names outside the include guard, to expand multiple times. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57826 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-03-10 07:18:03 +00:00
#define RB_DEBUG_COUNTER(name) RB_DEBUG_COUNTER_##name,
Use real filename instead of `__FILE__`
2024-06-02 21:22:39 +09:00
#include "debug_counter.h"
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
RB_DEBUG_COUNTER_MAX
debug_counter.c: debug_counter_names [ci skip] * debug_counter.c (debug_counter_names): stringize debug counter names by preprocessor. * debug_counter.h (RB_DEBUG_COUNTER): define counter names outside the include guard, to expand multiple times. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57826 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-03-10 07:18:03 +00:00
#undef RB_DEBUG_COUNTER
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
};
#if USE_DEBUG_COUNTER
debug_counter.c: debug_counter_names [ci skip] * debug_counter.c (debug_counter_names): stringize debug counter names by preprocessor. * debug_counter.h (RB_DEBUG_COUNTER): define counter names outside the include guard, to expand multiple times. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57826 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-03-10 07:18:03 +00:00
extern size_t rb_debug_counter[];
make RB_DEBUG_COUNTER_INC()_thread-safe
2020-12-17 01:29:15 +09:00
RUBY_EXTERN struct rb_ractor_struct *ruby_single_main_ractor;
RUBY_EXTERN void rb_debug_counter_add_atomic(enum rb_debug_counter_type type, int add);
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
inline static int
rb_debug_counter_add(enum rb_debug_counter_type type, int add, int cond)
{
if (cond) {
make RB_DEBUG_COUNTER_INC()_thread-safe
2020-12-17 01:29:15 +09:00
if (ruby_single_main_ractor != NULL) {
rb_debug_counter[(int)type] += add;
}
else {
rb_debug_counter_add_atomic(type, add);
}
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
}
return cond;
}
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
inline static int
rb_debug_counter_max(enum rb_debug_counter_type type, unsigned int num)
{
make RB_DEBUG_COUNTER_INC()_thread-safe
2020-12-17 01:29:15 +09:00
// TODO: sync
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
if (rb_debug_counter[(int)type] < num) {
rb_debug_counter[(int)type] = num;
return 1;
}
else {
return 0;
}
}
Fix rb_define_singleton_method warning for debug counters ``` ../include/ruby/intern.h:1175:137: warning: passing argument 3 of 'rb_define_singleton_method0' from incompatible pointer type [-Wincompatible-pointer-types] #define rb_define_singleton_method(klass, mid, func, arity) rb_define_singleton_method_choose_prototypem3((arity),(func))((klass),(mid),(func),(arity)); ^ ../vm.c:2958:5: note: in expansion of macro 'rb_define_singleton_method' rb_define_singleton_method(rb_cRubyVM, "show_debug_counters", rb_debug_counter_show, 0); ^~~~~~~~~~~~~~~~~~~~~~~~~~ ../include/ruby/intern.h:1139:99: note: expected 'VALUE (*)(VALUE) {aka long unsigned int (*)(long unsigned int)}' but argument is of type 'VALUE (*)(void) {aka long unsigned int (*)(void)}' __attribute__((__unused__,__weakref__("rb_define_singleton_method"),__nonnull__(2,3)))static void rb_define_singleton_method0 (VALUE,const char*,VALUE(*)(VALUE),int); ```
2019-09-20 17:44:16 +09:00
VALUE rb_debug_counter_reset(VALUE klass);
VALUE rb_debug_counter_show(VALUE klass);
Add RubyVM.reset_debug_counters when RB_DEBUG_COUNTER is defined. It's 0 by default and so it dissappears on actual build. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67544 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2019-04-14 06:57:21 +00:00
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
#define RB_DEBUG_COUNTER_INC(type) rb_debug_counter_add(RB_DEBUG_COUNTER_##type, 1, 1)
#define RB_DEBUG_COUNTER_INC_UNLESS(type, cond) (!rb_debug_counter_add(RB_DEBUG_COUNTER_##type, 1, !(cond)))
Explicit conversion to boolean to suppress shorten-64-to-32 warnings
2020-07-10 13:02:31 +09:00
#define RB_DEBUG_COUNTER_INC_IF(type, cond) rb_debug_counter_add(RB_DEBUG_COUNTER_##type, 1, !!(cond))
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
#define RB_DEBUG_COUNTER_ADD(type, num) rb_debug_counter_add(RB_DEBUG_COUNTER_##type, (num), 1)
#define RB_DEBUG_COUNTER_SETMAX(type, num) rb_debug_counter_max(RB_DEBUG_COUNTER_##type, (unsigned int)(num))
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
#else
#define RB_DEBUG_COUNTER_INC(type) ((void)0)
Explicit conversion to boolean to suppress shorten-64-to-32 warnings
2020-07-10 13:02:31 +09:00
#define RB_DEBUG_COUNTER_INC_UNLESS(type, cond) (!!(cond))
#define RB_DEBUG_COUNTER_INC_IF(type, cond) (!!(cond))
Introduce disposable call-cache. This patch contains several ideas: (1) Disposable inline method cache (IMC) for race-free inline method cache * Making call-cache (CC) as a RVALUE (GC target object) and allocate new CC on cache miss. * This technique allows race-free access from parallel processing elements like RCU. (2) Introduce per-Class method cache (pCMC) * Instead of fixed-size global method cache (GMC), pCMC allows flexible cache size. * Caching CCs reduces CC allocation and allow sharing CC's fast-path between same call-info (CI) call-sites. (3) Invalidate an inline method cache by invalidating corresponding method entries (MEs) * Instead of using class serials, we set "invalidated" flag for method entry itself to represent cache invalidation. * Compare with using class serials, the impact of method modification (add/overwrite/delete) is small. * Updating class serials invalidate all method caches of the class and sub-classes. * Proposed approach only invalidate the method cache of only one ME. See [Feature #16614] for more details.
2020-01-08 16:14:01 +09:00
#define RB_DEBUG_COUNTER_ADD(type, num) ((void)0)
#define RB_DEBUG_COUNTER_SETMAX(type, num) 0
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
#endif
refactoring debug_counter. * debug_counter.h: add comments for each counters. * debug_counter.h: add some counters (see added comments for details). * obj_newobj * obj_newobj_slowpath * obj_newobj_wb_unprotected * obj_hash_empty * obj_hash_under4 * obj_hash_ge4 * obj_hash_ge8 * heap_xmalloc * heap_xrealloc * heap_xfree * gc.c: add some debug counters (see the above list). * debug_counter.c (rb_debug_counter_show_results): accept a header message. * signal.c (ruby_default_signal): show debug counter results and malloc info (rb_malloc_info_show_results()) before SIGNAL exit. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64841 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-25 18:13:29 +00:00
void rb_debug_counter_show_results(const char *msg);
add debug_counter access functions. These functions are enabled only on USE_DEBUG_COUNTER=1.
2019-12-25 01:32:37 +09:00
RUBY_SYMBOL_EXPORT_BEGIN
size_t ruby_debug_counter_get(const char **names_ptr, size_t *counters_ptr);
void ruby_debug_counter_reset(void);
void ruby_debug_counter_show_at_exit(int enable);
RUBY_SYMBOL_EXPORT_END
add performance counting mechanism for MRI debug/tuning purpose. * How to enable this feature? * define USE_DEBUG_COUNTER as 1. * you can disable to output the result with RUBY_DEBUG_COUNTER_DISABLE environment variable even if USE_DEBUG_COUNTER == 1. * How to add new counter? * add COUNTER(<name>) line on debug_counter.h. * include "debug_counter.h" * insert RB_DEBUG_COUNTER_INC(<name>) line on your favorite place. * counter output example: [RUBY_DEBUG_COUNTER] mc_inline_hit 999 [RUBY_DEBUG_COUNTER] mc_inline_miss 3 [RUBY_DEBUG_COUNTER] mc_global_hit 23 [RUBY_DEBUG_COUNTER] mc_global_miss 273 [RUBY_DEBUG_COUNTER] mc_global_state_miss 3 [RUBY_DEBUG_COUNTER] mc_class_serial_miss 0 [RUBY_DEBUG_COUNTER] mc_cme_complement 0 [RUBY_DEBUG_COUNTER] mc_cme_complement_hit 0 [RUBY_DEBUG_COUNTER] mc_search_super 1384 [RUBY_DEBUG_COUNTER] ivar_get_hit 0 [RUBY_DEBUG_COUNTER] ivar_get_miss 0 [RUBY_DEBUG_COUNTER] ivar_set_hit 0 [RUBY_DEBUG_COUNTER] ivar_set_miss 0 [RUBY_DEBUG_COUNTER] ivar_get 431 [RUBY_DEBUG_COUNTER] ivar_set 465 * mc_... is related to method caching. * ivar_... is related to instance variable accesses. * compare with dtrace/system tap features, there are completely no performacne penalties when it is disabled. * This feature is supported only on __GNUC__ compilers. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@57676 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2017-02-21 08:18:15 +00:00
#endif /* RUBY_DEBUG_COUNTER_H */
Reference in New Issue Copy Permalink