Issue #14718 has been updated by fweimer (Florian Weimer).


I can reproduce your MALLOC_ARENA_MAX=2 numbers, but my glibc 2.26 numbers are slightly worse (presumably due to the thread cache, which delays coalescing even further):

~~~
count    5000.000000
mean     2299.963311
std       589.499758
min       143.515625
25%      2120.331055
50%      2539.085938
75%      2728.136719
max      2887.113281
~~~

With jemalloc 4.5, I get very similar numbers to glibc 2.26:

~~~
count    5000.000000
mean     2137.653509
std       397.754364
min       178.406250
25%      2053.171875
50%      2148.148438
75%      2347.949219
max      2571.218750
~~~

jemalloc 5.0.1 may be slightly better, but it is not a large change:

~~~
count    5000.000000
mean     1844.086273
std       338.717582
min       176.300781
25%      1848.468750
50%      1935.281250
75%      2011.210938
max      2158.937500
~~~

jemalloc 5.1 is slightly worse, it seems.

~~~
count    5000.000000
mean     2027.594097
std       365.946724
min       176.437500
25%      1967.921875
50%      2073.148438
75%      2245.913086
max      2508.105469
~~~

Based on these tests, untuned current jemalloc shows only a very moderate improvement over untuned glibc.

----------------------------------------
Feature #14718: Use jemalloc by default?
https://bugs.ruby-lang.org/issues/14718#change-73214

* Author: mperham (Mike Perham)
* Status: Open
* Priority: Normal
* Assignee: 
* Target version: 
----------------------------------------
I know Sam opened #9113 4 years ago to suggest this but I'm revisiting the topic to see if there's any movement here for Ruby 2.6 or 2.7.  I supply a major piece of Ruby infrastructure (Sidekiq) and I keep hearing over and over how Ruby is terrible with memory, a huge memory hog with their Rails apps.  My users switch to jemalloc and a miracle occurs: their memory usage drops massively.  Some data points:

https://twitter.com/brandonhilkert/status/987400365627801601
https://twitter.com/d_jones/status/989866391787335680
https://github.com/mperham/sidekiq/issues/3824#issuecomment-383072469

Redis moved to jemalloc many years ago and it solved all of their memory issues too.  Their conclusion: the glibc allocator "sucks really really hard". http://oldblog.antirez.com/post/everything-about-redis-24.html

This is a real pain point for the entire Rails community and would improve Ruby's reputation immensely if we can solve this problem.

---Files--------------------------------
glibc_arena_2.png (7.23 KB)
jemalloc.png (21.1 KB)
glibc-arena-2.log (60.3 KB)
glibc.log (62.3 KB)
jemalloc-3-5.log (58.5 KB)
glibc.png (9.03 KB)


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

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