ruby/benchmark/bm_vm_thread_pass_flood.rb

# n.b. this is a good test for GVL when pinned to a single CPU

1000.times{
  Thread.new{loop{Thread.pass}}
}

i = 0
while i<10000
  i += 1
end
benchmark/bm_vm_thread_pass_flood.rb: add comment I was about to write off this benchmark while working on GVL improvements on multi-core systems. However I noticed it exposes a weakness in my work-in-progress code when I tested on an old single CPU system. Further testing reveals setting CPU affinity ("schedtool -a 0x1" on Linux) on a modern multi-core system is enough to reproduce the problem exposed by this benchmark. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58571 b2dd03c8-39d4-4d8f-98ff-823fe69b080e 2017-05-04 19:47:17 +03:00			`# n.b. this is a good test for GVL when pinned to a single CPU`

* benchmark/bm_vm4_pass_flood.rb: new benchmark for GVL fairness. * benchmark/bm_vm4_alive_check1.rb: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@32093 b2dd03c8-39d4-4d8f-98ff-823fe69b080e 2011-06-14 22:54:30 +04:00			`1000.times{`
			`Thread.new{loop{Thread.pass}}`
			`}`

* benchmark/bm_vm1_lvar_init.rb: added. This benchmark measures a initialize time of non-used variable. * benchmark/bm_vm1_lvar_set.rb: added. This benchmark measures a local variables initialization time. * benchmark/bm_vm2_bigarray.rb: added. This benchmark mesures a big array literal creation time. * benchmark/bm_vm2_bighash.rb: This benchmark mesures a big hash literal creation time. * benchmark/bm*: change notation "i=0" to "i = 0". git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@35821 b2dd03c8-39d4-4d8f-98ff-823fe69b080e 2012-05-27 18:41:01 +04:00			`i = 0`
* benchmark/bm_vm4_pass_flood.rb: new benchmark for GVL fairness. * benchmark/bm_vm4_alive_check1.rb: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@32093 b2dd03c8-39d4-4d8f-98ff-823fe69b080e 2011-06-14 22:54:30 +04:00			`while i<10000`
			`i += 1`
			`end`