mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
b9007b6c54
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.
|
||
|---|---|---|
| .. | ||
| _attributes.erb | ||
| _c_expr.erb | ||
| _comptime_insn_stack_increase.erb | ||
| _copyright.erb | ||
| _insn_entry.erb | ||
| _insn_len_info.erb | ||
| _insn_name_info.erb | ||
| _insn_operand_info.erb | ||
| _insn_sp_pc_dependency.erb | ||
| _insn_type_chars.erb | ||
| _leaf_helpers.erb | ||
| _mjit_compile_insn.erb | ||
| _mjit_compile_insn_body.erb | ||
| _mjit_compile_ivar.erb | ||
| _mjit_compile_pc_and_sp.erb | ||
| _mjit_compile_send.erb | ||
| _notice.erb | ||
| _sp_inc_helpers.erb | ||
| _trace_instruction.erb | ||
| insns.inc.erb | ||
| insns_info.inc.erb | ||
| mjit_compile.inc.erb | ||
| opt_sc.inc.erb | ||
| optinsn.inc.erb | ||
| optunifs.inc.erb | ||
| vm.inc.erb | ||
| vmtc.inc.erb | ||