[#86787] [Ruby trunk Feature#14723] [WIP] sleepy GC — ko1@...

Issue #14723 has been updated by ko1 (Koichi Sasada).

13 messages 2018/05/01
[#86790] Re: [Ruby trunk Feature#14723] [WIP] sleepy GC — Eric Wong <normalperson@...> 2018/05/01

ko1@atdot.net wrote:

[#87095] [Ruby trunk Feature#14767] [PATCH] gc.c: use monotonic counters for objspace_malloc_increase — ko1@...

Issue #14767 has been updated by ko1 (Koichi Sasada).

9 messages 2018/05/17
[#87096] Re: [Ruby trunk Feature#14767] [PATCH] gc.c: use monotonic counters for objspace_malloc_increase — Eric Wong <normalperson@...> 2018/05/17

ko1@atdot.net wrote:

[ruby-core:87163] Re: [Ruby trunk Feature#14723] [WIP] sleepy GC

From: Eric Wong <normalperson@...>
Date: 2018-05-18 07:32:27 UTC
List: ruby-core #87163
the.codefolio.guy@gmail.com wrote:
> Overall, Sleepy GC gets 169.4 req/sec mean throughput with
> variance of 6.4, while the previous commit gets 177.0 req/sec
> throughput with a variance of 3.8.

Thanks for testing!  I think we will need to work on increasing
granularity of the steps.  The variance actually bothers me a
bit, more.

I'll have to work on increasing granularity of the marking and
sweeping (which may hurt throughput in apps without IO-wait at
all...).  And I won't be around much the next few days..

Also, our malloc accounting is silly expensive(*) and I think
we can do some lazy sweeping before making big allocations

(*) https://bugs.ruby-lang.org/issues/10238

Unsubscribe: <mailto:ruby-core-request@ruby-lang.org?subject=unsubscribe>
<http://lists.ruby-lang.org/cgi-bin/mailman/options/ruby-core>

In This Thread