Before this change, when we encounter a constant cache that is specific
to a lexical scope, we unconditionally exit. This change falls back to
the interpreter's cache in this situation.
This should help constant expressions in `class << self`, which is popular
at Shopify due to the style guide.
This change relies on the cache being warm while compiling to detect the
need for checking the lexical scope for simplicity.
* Implement calls to methods with simple optional params
* Remove unnecessary MJIT_STATIC
See comment for MJIT_STATIC. I added it not knowing whether it's
required because the function next to it has it. Don't use it and wait
for problems to come up instead.
* Better naming, some comments
* Count bailing on kw only iseqs
On railsbench:
```
opt_send_without_block exit reasons:
bmethod 59729 (27.7%)
optimized_method 59137 (27.5%)
iseq_complex_callee 41362 (19.2%)
alias_method 33346 (15.5%)
callsite_not_simple 19170 ( 8.9%)
iseq_only_keywords 1300 ( 0.6%)
kw_splat 1299 ( 0.6%)
cfunc_ruby_array_varg 18 ( 0.0%)
```
Make sure `opt_getinlinecache` is in a block all on its own, and
invalidate it from the interpreter when `opt_setinlinecache`.
It will recompile with a filled cache the second time around.
This lets YJIT runs well when the IC for constant is cold.
Lazily compile out a chain of checks for different known classes and
whether `self` embeds its ivars or not.
* Remove trailing whitespaces
* Get proper addresss in Capstone disassembly
* Lowercase address in Capstone disassembly
Capstone uses lowercase for jump targets in generated listings. Let's
match it.
* Use the same successor in getivar guard chains
Cuts down on duplication
* Address reviews
* Fix copypasta error
* Add a comment
Pass in ec to vm_opt_newarray_{max,min}. Avoids having to
call GET_EC inside the functions, for better performance.
While here, add a test for Array#min/max being redefined to
test_optimization.rb.
Fixes [Bug #18180]
In vm_call_method_each_type, check for c_call and c_return events before
dispatching to vm_call_ivar and vm_call_attrset. With this approach, the
call cache will still dispatch directly to those functions, so this
change will only decrease performance for the first (uncached) call, and
even then, the performance decrease is very minimal.
This approach requires that we clear the call caches when tracing is
enabled or disabled. The approach currently switches all vm_call_ivar
and vm_call_attrset call caches to vm_call_general any time tracing is
enabled or disabled. So it could theoretically result in a slowdown for
code that constantly enables or disables tracing.
This approach does not handle targeted tracepoints, but from my testing,
c_call and c_return events are not supported for targeted tracepoints,
so that shouldn't matter.
This includes a benchmark showing the performance decrease is minimal
if detectable at all.
Fixes [Bug #16383]
Fixes [Bug #10470]
Co-authored-by: Takashi Kokubun <takashikkbn@gmail.com>
Extracted repeated code as update_classvariable_cache. When cvc
table is not set in getclassvariable, an empty table was created
but it has no id and would cause [BUG], so made the code same as
setclassvariable.
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>
Instead of on read. Once it's in the inline cache we never have to make
one again. We want to eventually put the value into the cache, and the
best opportunity to do that is when you write the value.
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 9e5105ca45) [x86_64-darwin19]
built-ruby: ruby 3.1.0dev (2021-03-15T12:12:44Z add-cache-for-clas.. c6be0093ae) [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>
A "return" statement in a Proc in a lambda like:
`lambda{ proc{ return }.call }`
should return outer lambda block. However, the inner Proc can become
orphan Proc from the lambda block. This "return" escape outer-scope
like method, but this behavior was decieded as a bug.
[Bug #17105]
This patch raises LocalJumpError by checking the proc is orphan or
not from lambda blocks before escaping by "return".
Most of tests are written by Jeremy Evans
https://github.com/ruby/ruby/pull/4223
This patch improves the performance of sequential and parallel
execution of rb_equal() (and rb_eql()).
[Bug #17497]
rb_equal_opt (and rb_eql_opt) does not have own cd and it waste
a time to initialize cd. This patch introduces opt_equality_by_mid()
to check equality without cd.
Furthermore, current master uses "static" cd on rb_equal_opt
(and rb_eql_opt) and it hurts CPU caches on multi-thread execution.
Now they are gone so there are no bottleneck on parallel execution.
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.
e7fc353f04 reverted vm_ic_hit_p's signature change made in 53babf35ef,
which broke JIT compilation of getinlinecache.
To make sure it doesn't happen again, I separated vm_inlined_ic_hit_p to
make the intention clear.
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.
separate some fields from rb_ractor_t to rb_ractor_pub and put it
at the beggining of rb_ractor_t and declare it in vm_core.h so
vm_core.h can access rb_ractor_pub fields.
Now rb_ec_ractor_hooks() is a complete inline function and no
MJIT related issue.
Ractor has several restrictions to keep each ractor being isolated
and some operation such as `CONST="foo"` in non-main ractor raises
an exception. This kind of operation raises an error but there is
confusion (some code raises RuntimeError and some code raises
NameError).
To make clear we introduce Ractor::IsolationError which is raised
when the isolation between ractors is violated.
Some tunings.
* add `inline` for vm_sendish()
* pass enum instead of func ptr to vm_sendish()
* reorder initial order of `calling` struct.
* add ALWAYS_INLINE for vm_search_method_fastpath()
* call vm_search_method_fastpath() from vm_sendish()
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.
`cd` is passed to method call functions to method invocation
functions, but `cd` can be manipulated by other ractors simultaneously
so it contains thread-safety issue.
To solve this issue, this patch stores `ci` and found `cc` to `calling`
and stops to pass `cd`.
This speeds up all instance variable access, even when not in
verbose mode. Uninitialized instance variable warnings were
rarely helpful, and resulted in slower code if you wanted to
avoid warnings when run in verbose mode.
Implements [Feature #17055]
C extensions can violate the ractor-safety, so only ractor-safe
C extensions (C methods) can run on non-main ractors.
rb_ext_ractor_safe(true) declares that the successive
defined methods are ractor-safe. Otherwiwze, defined methods
checked they are invoked in main ractor and raise an error
if invoked at non-main ractors.
[Feature #17307]
Performance is probably improved?
$ benchmark-driver -v --rbenv 'before --jit;after --jit' --repeat-count=12 --alternate --output=all benchmark.yml
before --jit: ruby 3.0.0dev (2020-11-27T04:37:47Z master 69e77e81dc) +JIT [x86_64-linux]
after --jit: ruby 3.0.0dev (2020-11-27T05:28:19Z master df6b05c6dd) +JIT [x86_64-linux]
last_commit=Set VM_FRAME_FLAG_FINISH at once
Calculating -------------------------------------
before --jit after --jit
Optcarrot Lan_Master.nes 80.89292998533379 82.19497327502751 fps
80.93130641142331 85.13943315260148
81.06214830270119 87.43757879797808
82.29172808453910 87.89942441487113
84.61206450455929 87.91309779491075
85.44545883567997 87.98026086648694
86.02923132404449 88.03081060383973
86.07411817365879 88.14650206137341
86.34348799602836 88.32791633649961
87.90257338977324 88.57599644892220
88.58006509876580 88.67426384743277
89.26611118140011 88.81669430874207
This should have no bad impact on VM because this function is ALWAYS_INLINE.
Allocating an instance of a class uses the allocator for the class. When
the class has no allocator set, Ruby looks for it in the super class
(see rb_get_alloc_func()).
It's uncommon for classes created from Ruby code to ever have an
allocator set, so it's common during the allocation process to search
all the way to BasicObject from the class with which the allocation is
being performed. This makes creating instances of classes that have
long ancestry chains more expensive than creating instances of classes
have that shorter ancestry chains.
Setting the allocator at class creation time removes the need to perform
a search for the alloctor during allocation.
This is a breaking change for C-extensions that assume that classes
created from Ruby code have no allocator set. Libraries that setup a
class hierarchy in Ruby code and then set the allocator on some parent
class, for example, can experience breakage. This seems like an unusual
use case and hopefully it is rare or non-existent in practice.
Rails has many classes that have upwards of 60 elements in the ancestry
chain and benchmark shows a significant improvement for allocating with
a class that includes 64 modules.
```
pre: ruby 3.0.0dev (2020-11-12T14:39:27Z master 6325866421)
post: ruby 3.0.0dev (2020-11-12T20:15:30Z cut-allocator-lookup)
Comparison:
allocate_8_deep
post: 10336985.6 i/s
pre: 8691873.1 i/s - 1.19x slower
allocate_32_deep
post: 10423181.2 i/s
pre: 6264879.1 i/s - 1.66x slower
allocate_64_deep
post: 10541851.2 i/s
pre: 4936321.5 i/s - 2.14x slower
allocate_128_deep
post: 10451505.0 i/s
pre: 3031313.5 i/s - 3.45x slower
```
This commit adds a debug counter for the case where the inline cache
*missed* but the ivar index table has an entry for that ivar. This is a
case where a polymorphic cache could help
iv tables cannot shrink. If the inline cache was ever set, then there
must be an entry for the instance variable in the iv table. Just set
the iv list on the object to be equal to the iv index table size, then
set the iv.
When the inline cache is written, the iv table will contain an entry for
the instance variable. If we get an inline cache hit, then we know the
iv table must contain a value for the index written to the inline cache.
If the index in the inline cache is larger than the list on the object,
but *smaller* than the iv index table on the class, then we can just
eagerly allocate the iv list to be the same size as the iv index table.
This avoids duplicate work of checking frozen as well as looking up the
index for the particular instance variable name.
Ractor.make_shareable() supports Proc object if
(1) a Proc only read outer local variables (no assignments)
(2) read outer local variables are shareable.
Read local variables are stored in a snapshot, so after making
shareable Proc, any assignments are not affeect like that:
```ruby
a = 1
pr = Ractor.make_shareable(Proc.new{p a})
pr.call #=> 1
a = 2
pr.call #=> 1 # `a = 2` doesn't affect
```
[Feature #17284]
iv_index_tbl manages instance variable indexes (ID -> index).
This data structure should be synchronized with other ractors
so introduce some VM locks.
This patch also introduced atomic ivar cache used by
set/getinlinecache instructions. To make updating ivar cache (IVC),
we changed iv_index_tbl data structure to manage (ID -> entry)
and an entry points serial and index. IVC points to this entry so
that cache update becomes atomically.
Buggy native extensions could have mark functions that cause stack
overflow. When a stack overflow happens during GC, Ruby used to recover
by raising an exception, which runs the interpreter. It's not safe to
run the interpreter during GC since the GC is in an inconsistent state.
This could cause object allocation during GC, for example.
Instead of running the interpreter and potentially causing a crash down
the line, fail fast and abort.
generic_ivtbl is a process global table to maintain instance variables
for non T_OBJECT/T_CLASS/... objects. So we need to protect them
for multi-Ractor exection.
Hint: we can make them Ractor local for unshareable objects, but
now it is premature optimization.
The changes here include:
* Using `FL_TEST_RAW` instead of `FL_TEST` in the first check in
`vm_search_super_method`. While the profile showed us spending a fair
amount of time here, the subsequent benchmarks didn't show much
improvement when adding this. Regardless, we know this does less work
than `FL_TEST` and we know that `FL_TEST_RAW` is safe due to the
previous check so it's a small but accurate optimization.
* Set `mid` only once. Both `vm_ci_new_runtime` and `vm_ci_mid` were
getting the `original_id` for the method entry. We can do this once
and pass the variable to the 2 callers that need it. This also doesn't
have a huge performance improvement but cleans up the code a bit.
Benchmark:
```
| |compare-ruby|built-ruby|
|:----------------|-----------:|---------:|
|vm_iclass_super | 3.540M| 3.940M|
| | -| 1.11x|
```
Co-authored-by: Aaron Patterson <tenderlove@ruby-lang.org>
This PR improves the performance of `super` calls. While working on some
Rails optimizations jhawthorn discovered that `super` calls were slower
than expected.
The changes here do the following:
1) Adds a check for whether the call frame is not equal to the method
entry iseq. This avoids the `rb_obj_is_kind_of` check on the next line
which is quite slow. If the current call frame is equal to the method
entry we know we can't have an instance eval, etc.
2) Changes `FL_TEST` to `FL_TEST_RAW`. This is safe because we've
already done the check for `T_ICLASS` above.
3) Adds a benchmark for `T_ICLASS` super calls.
4) Note: makes a chage for `method_entry_cref` to use `const`.
On master the benchmarks showed that `super` is 1.76x slower. Our
changes improved the performance so that it is now only 1.36x slower.
Benchmark IPS:
```
Warming up --------------------------------------
super 244.918k i/100ms
method call 383.007k i/100ms
Calculating -------------------------------------
super 2.280M (± 6.7%) i/s - 11.511M in 5.071758s
method call 3.834M (± 4.9%) i/s - 19.150M in 5.008444s
Comparison:
method call: 3833648.3 i/s
super: 2279837.9 i/s - 1.68x (± 0.00) slower
```
With changes:
```
Warming up --------------------------------------
super 308.777k i/100ms
method call 375.051k i/100ms
Calculating -------------------------------------
super 2.951M (± 5.4%) i/s - 14.821M in 5.039592s
method call 3.551M (± 4.9%) i/s - 18.002M in 5.081695s
Comparison:
method call: 3551372.7 i/s
super: 2950557.9 i/s - 1.20x (± 0.00) slower
```
Ruby VM benchmarks also showed an improvement:
Existing `vm_super` benchmark`.
```
$ make benchmark ITEM=vm_super
| |compare-ruby|built-ruby|
|:---------|-----------:|---------:|
|vm_super | 21.555M| 37.819M|
| | -| 1.75x|
```
New `vm_iclass_super` benchmark:
```
$ make benchmark ITEM=vm_iclass_super
| |compare-ruby|built-ruby|
|:----------------|-----------:|---------:|
|vm_iclass_super | 1.669M| 3.683M|
| | -| 2.21x|
```
This is the benchmark script used for the benchmark-ips benchmarks:
```ruby
require "benchmark/ips"
class Foo
def zuper; end
def top; end
last_method = "top"
("A".."M").each do |module_name|
eval <<-EOM
module #{module_name}
def zuper; super; end
def #{module_name.downcase}
#{last_method}
end
end
prepend #{module_name}
EOM
last_method = module_name.downcase
end
end
foo = Foo.new
Benchmark.ips do |x|
x.report "super" do
foo.zuper
end
x.report "method call" do
foo.m
end
x.compare!
end
```
Co-authored-by: Aaron Patterson <tenderlove@ruby-lang.org>
Co-authored-by: John Hawthorn <john@hawthorn.email>
This reverts commit eeef16e190.
This also reverts the spec change.
Preventing the SystemStackError would be nice, but there is valid
code that the fix breaks, and it is probably more common than cases
that cause the SystemStackError.
Fixes [Bug #17182]
This commit introduces Ractor mechanism to run Ruby program in
parallel. See doc/ractor.md for more details about Ractor.
See ticket [Feature #17100] to see the implementation details
and discussions.
[Feature #17100]
This commit does not complete the implementation. You can find
many bugs on using Ractor. Also the specification will be changed
so that this feature is experimental. You will see a warning when
you make the first Ractor with `Ractor.new`.
I hope this feature can help programmers from thread-safety issues.
Previously, Method#super_method looked at the called_id to
determine the method id to use, but that isn't correct for
aliased methods, because the super target depends on the
original method id, not the called_id.
Additionally, aliases can reference methods defined in other
classes and modules, and super lookup needs to start in the
super of the defined class in such cases.
This adds tests for Method#super_method for both types of
aliases, one that uses VM_METHOD_TYPE_ALIAS and another that
does not. Both check that the results for calling super
methods return the expected values.
To find the defined class for alias methods, add an rb_ prefix
to find_defined_class_by_owner in vm_insnhelper.c and make it
non-static, so that it can be called from method_super_method
in proc.c.
This bug was original discovered while researching [Bug #11189].
Fixes [Bug #17130]
Without this, if a refinement defines a method that calls super and
includes a module with a module that calls super and has a activated
refinement at the point super is called, the module method super call
will end up calling back into the refinement method, creating a loop.
Fixes [Bug #17007]
Struct assignment using a compound literal is more readable than before,
to me at least. It seems compilers reorder assignments anyways.
Neither speedup nor slowdown is observed on my machine.
eileencodes
Alan Wu
John Hawthorn
Aaron Patterson
Kevin Newton
Maxime Chevalier-Boisvert
Maxime Chevalier-Boisvert
Nobuyoshi Nakada
S.H
Jeremy Evans
Koichi Sasada
Takashi Kokubun
Alan Wu
Aaron Patterson
Benoit Daloze
卜部昌平