Issue #10723 has been updated by Guo Xiang Tan.


Eric Wong wrote:
> akr: any comments?  I'll commit my patch in a few days, but I hope we
> can recover more performance.  Thanks.

Hi Eric,

Just wanted to bring your attention to bm_vm_thread_pass_flood. http://rubybench.org/ruby/ruby/commits?result_type=vm_thread_pass_flood

before_patch: 0.079s
after_patch: 0.086

The benchmark got slower after your patch so I thought you might be interested in knowing that. Not really a report but just to bring your attention to it since I don't know c well enough to actually understand how Ruby is implemented. Thank you! :)))

----------------------------------------
Bug #10723: [PERF] bm_tread_create_join 20% slower
https://bugs.ruby-lang.org/issues/10723#change-51540

* Author: Guo Xiang Tan
* Status: Open
* Priority: Normal
* Assignee: Akira Tanaka
* ruby -v: ruby 2.2.0dev (2014-09-21 trunk 47676)
* Backport: 2.0.0: UNKNOWN, 2.1: UNKNOWN, 2.2: UNKNOWN
----------------------------------------
Relevant commits: https://github.com/ruby/ruby/compare/39fd4a8...5697b2f

Chart showing the regression: http://rubybench.org/ruby/ruby/commits?result_type=vm_thread_create_join

For those unable to view the chart, the benchmark results have increased from 1.74~ seconds to 2.1~ seconds.





-- 
https://bugs.ruby-lang.org/