From d1c2c408db0e03201c1645a4d699c9c5768cd8e9 Mon Sep 17 00:00:00 2001 From: normal Date: Thu, 4 May 2017 16:47:17 +0000 Subject: 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 --- benchmark/bm_vm_thread_pass_flood.rb | 2 ++ 1 file changed, 2 insertions(+) (limited to 'benchmark/bm_vm_thread_pass_flood.rb') diff --git a/benchmark/bm_vm_thread_pass_flood.rb b/benchmark/bm_vm_thread_pass_flood.rb index 27157d1a6f..a660aafc18 100644 --- a/benchmark/bm_vm_thread_pass_flood.rb +++ b/benchmark/bm_vm_thread_pass_flood.rb @@ -1,3 +1,5 @@ +# n.b. this is a good test for GVL when pinned to a single CPU + 1000.times{ Thread.new{loop{Thread.pass}} } -- cgit v1.2.3