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.
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.
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);
```
I am trying to study debug counters inside a Rails application.
Accessing debug counters by killing the process is hard because child
processes don't get the same TRAP as the parent, and Rails seems to
intercept calls to `exit`. Adding this method lets me print the debug
counters when I want (at the end of requests for example)
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
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.
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
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
* 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
* 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
* 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
* transient_heap.c, transient_heap.h: implement TransientHeap (theap).
theap is designed for Ruby's object system. theap is like Eden heap
on generational GC terminology. theap allocation is very fast because
it only needs to bump up pointer and deallocation is also fast because
we don't do anything. However we need to evacuate (Copy GC terminology)
if theap memory is long-lived. Evacuation logic is needed for each type.
See [Bug #14858] for details.
* array.c: Now, theap for T_ARRAY is supported.
ary_heap_alloc() tries to allocate memory area from theap. If this trial
sccesses, this array has theap ptr and RARRAY_TRANSIENT_FLAG is turned on.
We don't need to free theap ptr.
* ruby.h: RARRAY_CONST_PTR() returns malloc'ed memory area. It menas that
if ary is allocated at theap, force evacuation to malloc'ed memory.
It makes programs slow, but very compatible with current code because
theap memory can be evacuated (theap memory will be recycled).
If you want to get transient heap ptr, use RARRAY_CONST_PTR_TRANSIENT()
instead of RARRAY_CONST_PTR(). If you can't understand when evacuation
will occur, use RARRAY_CONST_PTR().
(re-commit of r65444)
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65449 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* 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@65446 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* transient_heap.c, transient_heap.h: implement TransientHeap (theap).
theap is designed for Ruby's object system. theap is like Eden heap
on generational GC terminology. theap allocation is very fast because
it only needs to bump up pointer and deallocation is also fast because
we don't do anything. However we need to evacuate (Copy GC terminology)
if theap memory is long-lived. Evacuation logic is needed for each type.
See [Bug #14858] for details.
* array.c: Now, theap for T_ARRAY is supported.
ary_heap_alloc() tries to allocate memory area from theap. If this trial
sccesses, this array has theap ptr and RARRAY_TRANSIENT_FLAG is turned on.
We don't need to free theap ptr.
* ruby.h: RARRAY_CONST_PTR() returns malloc'ed memory area. It menas that
if ary is allocated at theap, force evacuation to malloc'ed memory.
It makes programs slow, but very compatible with current code because
theap memory can be evacuated (theap memory will be recycled).
If you want to get transient heap ptr, use RARRAY_CONST_PTR_TRANSIENT()
instead of RARRAY_CONST_PTR(). If you can't understand when evacuation
will occur, use RARRAY_CONST_PTR().
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65444 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* 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
* 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
Takashi Kokubun
卜部昌平
Kazuhiro NISHIYAMA
Koichi Sasada
Nobuyoshi Nakada
Aaron Patterson
Koichi Sasada
Lourens Naudé
k0kubun
kazu
ko1