[ruby-core:87014] [Ruby trunk Feature#14718] Use jemalloc by default?

[dennisb55@hotmail.com]

Issue #14718 has been updated by bluz71 (Dennis B).


shyouhei (Shyouhei Urabe) wrote:
> This literally means we have to bug fix jemalloc.  Please no.

It's a judgement call of which is more likely, theoretical jemalloc bugs or Ruby-on-Linux memory fragmentation?

Carrying an extra dependency is a burden for the Ruby maintainers, yes.
But likewise, memory fragmentation on the Linux platform for long-lived Ruby processes is a real burden some users carry.

The Firefox browser (for a decade), Redis (for seven years) and the Rust programming language all considered Linux memory fragmentation to be a bug which they fixed by switching to jemalloc.

Legacy jemalloc versions (say 3.6 to around 4.1) are battle-tested and rock-solid with Ruby (and many other technologies).

> Be warned; you are entering a field of persecuting minorities.  Please respect others.  This is not a matter of majority versus minority.  If you insist it is, I have to stand for diversity.
> 
> Everyone are equally important in our community.  Thank you.

You are taking offence where no offence was intended. All Ruby users matters including those that experience memory fragmentation on the Linux platform.

This graph explains the situation with clarity:

![jemalloc](https://www.mikeperham.com/images/jemalloc.jpg)

----------------------------------------
Feature #14718: Use jemalloc by default?
https://bugs.ruby-lang.org/issues/14718#change-71980

* 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.



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