[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20220920000233.58f6a262.quinq@fifth.space>
Date: Tue, 20 Sep 2022 00:02:33 +0200
From: Quentin Rameau <quinq@...th.space>
To: musl@...ts.openwall.com
Subject: Re: The heap memory performance (malloc/free/realloc) is
significantly degraded in musl 1.2 (compared to 1.1)
Hi BaiYang,
> And I mentioned it before: we did massively optimize performance in real-world applications. These are not the focus of our discussion.
And now you're hitting a problem because those micro-non-standard optimizations that worked in some setup
can't be expected to work in a standard way.
This is something not surprising and quite usual with that kind of or programming orientation.
You may know that musl paradigms are quite opposite to that,
one being focused on correctness rather than being bug-compatible with other implementations.
As Rich said, there always might be place for improvement in code,
but that should be proven to work in the majority of cases,
and not at the expanse of stability or correctness.
I assume that if you can come up with such an improvement complying with those requirements,
they would be honestly considered,
but this present problem report have been answered several times
and it seems that the solution to your application problems resides in your application optimizations optimization.
Cheers!
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
