[#56333] [CommonRuby - Feature #8723][Open] Array.any? predicate returns true for empty array. — "nurettin (Nurettin Onur TUGCU)" <onurtugcu@...>

12 messages 2013/08/02

[#56368] [ruby-trunk - Bug #8730][Open] "rescue Exception" rescues Timeout::ExitException — "takiuchi (Genki Takiuchi)" <genki@...21g.com>

15 messages 2013/08/04

[#56407] [ruby-trunk - misc #8741][Open] email notification on bugs.ruby-lang.org is broken — "rits (First Last)" <redmine@...>

18 messages 2013/08/05

[#56524] [ruby-trunk - Bug #8770][Open] [PATCH] process.c: avoid EINTR from Process.spawn — "normalperson (Eric Wong)" <normalperson@...>

19 messages 2013/08/10

[#56536] [ruby-trunk - Feature #8772][Open] Hash alias #| merge, and the case for Hash and Array polymorphism — "trans (Thomas Sawyer)" <redmine@...>

24 messages 2013/08/11

[#56544] [ruby-trunk - Bug #8774][Open] rb_file_dirname return wrong encoding string when dir is "." — jiayp@... (贾 延平) <jiayp@...>

10 messages 2013/08/11

[#56569] [ruby-trunk - Feature #8781][Open] Use require_relative() instead of require() if possible — "ko1 (Koichi Sasada)" <redmine@...>

31 messages 2013/08/12
[#56582] [ruby-trunk - Feature #8781] Use require_relative() instead of require() if possible — "drbrain (Eric Hodel)" <drbrain@...7.net> 2013/08/12

[#56584] Re: [ruby-trunk - Feature #8781] Use require_relative() instead of require() if possible — SASADA Koichi <ko1@...> 2013/08/12

(2013/08/13 2:25), drbrain (Eric Hodel) wrote:

[#56636] Re: [ruby-trunk - Feature #8781] Use require_relative() instead of require() if possible — Aaron Patterson <tenderlove@...> 2013/08/16

On Tue, Aug 13, 2013 at 07:38:01AM +0900, SASADA Koichi wrote:

[#56634] [ruby-trunk - Feature #8788][Open] use eventfd on newer Linux instead of pipe for timer thread — "normalperson (Eric Wong)" <normalperson@...>

11 messages 2013/08/16

[#56648] [ruby-trunk - Bug #8795][Open] "Null byte in string error" on Marshal.load — "mml (McClain Looney)" <m@...>

17 messages 2013/08/16

[#56824] [ruby-trunk - Feature #8823][Open] Run trap handler in an independent thread called "Signal thread" — "ko1 (Koichi Sasada)" <redmine@...>

14 messages 2013/08/27

[#56878] [ruby-trunk - misc #8835][Open] Introducing a semantic versioning scheme and branching policy — "knu (Akinori MUSHA)" <knu@...>

11 messages 2013/08/30

[#56890] [ruby-trunk - Feature #8839][Open] Class and module should return the class or module that was opened — "headius (Charles Nutter)" <headius@...>

26 messages 2013/08/30

[#56894] [ruby-trunk - Feature #8840][Open] Yielder#state — "marcandre (Marc-Andre Lafortune)" <ruby-core@...>

14 messages 2013/08/30

[ruby-core:56700] Re: [ruby-trunk - Feature #8788][Open] use eventfd on newer Linux instead of pipe for timer thread

From: Eric Wong <normalperson@...>
Date: 2013-08-17 19:37:43 UTC
List: ruby-core #56700
SASADA Koichi <ko1@atdot.net> wrote:
> (2013/08/16 10:47), normalperson (Eric Wong) wrote:
> > eventfd is a cheaper alternative to pipe for self-notification (signals) on Linux
> > 
> > I will submit patches in the next few days/weeks unless there are objections
> > (or somebody else wants to do it sooner).  I'd also like to cleanup some of the existing #ifdefs in that area while I'm at it.
> 
> Can we see the performance comparison?
> If we can see the clear difference, it can be acceptable.

It's not for speed (signal handling performance should not be a
bottleneck), but halve FD use in userspace and reduce memory use inside
the kernel.

AFAIK, writing to a empty pipe still allocates a 4K page, eventfd avoids
that allocation/deallocation.  Since Ruby is CoW/fork-friendly, this
should allow running more Ruby processes on a system.

I also thought my own code had an FD leak when timer_thread_pipe_low was
introduced.  Maybe this will reduce confusion for users who lsof Ruby
processes, since there are more pipe users than eventfd users.

> (If we can't see any difference, it only increase the source code
> complexity).

I've tried to minimize the impact of my patch and keep the eventfd/pipe
difference minimal.

In This Thread