[ruby-core:62683] [ruby-trunk - Feature #9113] Ship Ruby for Linux with jemalloc out-of-the-box

Issue #9113 has been updated by Eric Wong.


 [e-mail] wrote:
 >  [1/1] Test_StringModifyExpand#test_modify_expand_memory_leak = 0.02 s
 >    1) Failure:
 >    Test_StringModifyExpand#test_modify_expand_memory_leak
 >    [/home/ew/ruby/test/-ext-/string/test_modify_expand.rb:7]:
 >    rb_str_modify_expand().
 >    size: 14307328 => 31084544..
 >    Expected 2.1726309762381906 to be < 1.5.
 >  
 >  It looks like certain allocation patterns are worse with jemalloc, but
 >  I think real-world apps use less memory.
 
 I can update this to limit=2.2 to workaround the failure and commit my
 original patch soon.  Any comment/objections?
 
 Platform maintainers for non-GNU/Linux may enable jemalloc detection if
 they feel comfortable, but I don't want to potentially break things
 behind their backs.  For example, I cannot test/fix OSX problems, but I
 have read using non-standard malloc is a difficult problem on that
 platform (but possible).

----------------------------------------
Feature #9113: Ship Ruby for Linux with jemalloc out-of-the-box
https://bugs.ruby-lang.org/issues/9113#change-46811

* Author: Sam Saffron
* Status: Feedback
* Priority: Normal
* Assignee: 
* Category: build
* Target version: 
----------------------------------------
libc's malloc is a problem, it fragments badly meaning forks share less memory and is slow compared to tcmalloc or jemalloc. 

both jemalloc and tcmalloc are heavily battle tested and stable. 

2 years ago redis picked up the jemalloc dependency see: http://oldblog.antirez.com/post/everything-about-redis-24.html 

To quote antirez:
``
But an allocator is a serious thing. Since we introduced the specially encoded data types Redis started suffering from fragmentation. We tried different things to fix the problem, but basically the Linux default allocator in glibc sucks really, really hard. 
``

--- 

I recently benched Discourse with tcmalloc / jemalloc and default and noticed 2 very important thing: 

median request time reduce by up to 10% (under both)
PSS (proportional share size) is reduced by 10% under jemalloc and 8% under tcmalloc.

We can always use LD_PRELOAD to yank these in, but my concern is that standard distributions are using a far from optimal memory allocator. It would be awesome if the build, out-of-the-box, just checked if it was on Linux  (eg: https://github.com/antirez/redis/blob/unstable/src/Makefile#L30-L34 ) and then used jemalloc instead. 

---Files--------------------------------
0001-configure.in-add-with-jemalloc-option.patch (1.29 KB)


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