[#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

[email protected] 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

[email protected] wrote:

[ruby-core:87164] Re: [Ruby trunk Feature#14718] Use jemalloc by default?

From: Eric Wong <normalperson@...>
Date: 2018-05-18 07:59:24 UTC
List: ruby-core #87164
[email protected] wrote:
> P.S. I doubt that glibc will ever be *fixed* since the current
> behaviour suits the customers Red Hat services and Red Hat
> themselves are the effective maintainers of glibc.

Reading some glibc mailing list (libc-alpha) posts last year,
I remember excessive RSS usage is one of the areas they're
tackling due to user complaints.

Heck, I even seem to even recall a half-hearted proposal a few
years ago to use jemalloc in glibc.

I should also note the newish glibc 2.26 has the thread-caching
malloc as a build-time option, so it should reduce contention on
arenas and allow using fewer arenas.

We also have regular contributions from Red Hat employees
to Ruby, so I think RH does care about Ruby to some degree;
and I don't think the allocation patterns for Ruby would be
too different from a lot of existing software.

(I have no affiliation with Red Hat, past or present)

Unsubscribe: <mailto:[email protected]?subject=unsubscribe>
<http://lists.ruby-lang.org/cgi-bin/mailman/options/ruby-core>

In This Thread

Prev Next