From: Pip Cet via "Emacs development discussions." <emacs-devel@gnu.org>
To: Helmut Eller <eller.helmut@gmail.com>
Cc: Stefan Monnier <monnier@iro.umontreal.ca>,
Stefan Kangas <stefankangas@gmail.com>,
emacs-devel@gnu.org
Subject: Re: Merging scratch/no-purespace to remove unexec and purespace
Date: Sat, 21 Dec 2024 22:19:55 +0000 [thread overview]
Message-ID: <87seqghe73.fsf@protonmail.com> (raw)
In-Reply-To: <87o71553yf.fsf@gmail.com>
"Helmut Eller" <eller.helmut@gmail.com> writes:
> On Wed, Dec 18 2024, Helmut Eller wrote:
>
> [...]
>> So the pdumper copies objects from purespace to the dump like normal
>> objects; when loading the dump, purespace stays empty.
>>
>> I had (wrongly) assumed that the pdumper creates a separate section for
>> pure objects. Creating such a section sounds easy enough (hmm, maybe
>> not so easy because of hashtables). Still not sure if it would be worth
>> the effort.
>
> Out of curiosity, I implemented such a section with the attached patch.
> It seems that it would save ~2ms per collection cycle.
Very interesting, thank you for sharing!
I tried everything I could think of to disprove your findings, but while
I did find a minor optimization opportunity in the pdumper mark bits
code (a missing eassume (offset >= 0) / eassume (word_number >= 0)),
this affects both branches equally. I can only conclude that your
observation is accurate, and we now have a number that is still close to
zero, but measurable.
The effect seems to be mostly constant (1-2 ms / GC cycle), but I did
see some slightly larger differences when more objects were on the heap.
Cache effects, probably (PURE_P doesn't have to wait for memory,
pdumper_marked_p_impl does).
(I did run into crashes when running emacs without --batch, but those
are easily fixed and did not affect the performance measurements at
all. I only mention this so that others running tests don't get their
hopes (or fears) up).
Pip
next prev parent reply other threads:[~2024-12-21 22:19 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-17 10:47 Merging scratch/no-purespace to remove unexec and purespace Stefan Kangas
2024-12-17 13:12 ` Gerd Möllmann
2024-12-17 14:20 ` Gerd Möllmann
2024-12-17 14:30 ` Gerd Möllmann
2024-12-17 17:56 ` Gerd Möllmann
2024-12-17 18:50 ` Eli Zaretskii
2024-12-17 18:56 ` Gerd Möllmann
2024-12-18 12:55 ` Andrea Corallo
2024-12-18 14:03 ` Gerd Möllmann
2024-12-18 16:05 ` Pip Cet via Emacs development discussions.
2024-12-18 16:30 ` Gerd Möllmann
2024-12-18 16:25 ` Pip Cet via Emacs development discussions.
2024-12-18 22:27 ` Andrea Corallo
2024-12-19 9:28 ` Pip Cet via Emacs development discussions.
2024-12-19 10:38 ` Andrea Corallo
2024-12-19 10:50 ` Stefan Kangas
2024-12-19 12:08 ` Pip Cet via Emacs development discussions.
2024-12-19 17:55 ` Stefan Kangas
2024-12-19 20:13 ` Pip Cet via Emacs development discussions.
2024-12-20 15:59 ` Stefan Monnier
2024-12-20 16:22 ` Pip Cet via Emacs development discussions.
2024-12-20 17:25 ` Gerd Möllmann
2024-12-20 20:35 ` Andrea Corallo
2024-12-20 20:39 ` Pip Cet via Emacs development discussions.
2024-12-21 6:33 ` Gerd Möllmann
2024-12-21 6:56 ` Andrea Corallo
2024-12-20 20:38 ` Pip Cet via Emacs development discussions.
2024-12-20 20:57 ` Gerd Möllmann
2024-12-20 8:42 ` Pip Cet via Emacs development discussions.
2024-12-18 0:18 ` Stefan Kangas
2024-12-17 19:30 ` Helmut Eller
2024-12-17 20:47 ` Stefan Monnier
2024-12-18 2:15 ` Stefan Kangas
2024-12-18 7:11 ` Helmut Eller
2024-12-18 13:35 ` Pip Cet via Emacs development discussions.
2024-12-18 6:56 ` Helmut Eller
2024-12-21 17:41 ` Helmut Eller
2024-12-21 18:32 ` Gerd Möllmann
2024-12-21 22:19 ` Pip Cet via Emacs development discussions. [this message]
2024-12-22 1:28 ` Stefan Kangas
2024-12-22 11:12 ` Pip Cet via Emacs development discussions.
2024-12-22 13:07 ` Eli Zaretskii
2024-12-22 14:12 ` Pip Cet via Emacs development discussions.
2024-12-22 15:51 ` Stefan Monnier
2024-12-22 17:09 ` Gerd Möllmann
2024-12-22 17:10 ` Pip Cet via Emacs development discussions.
2024-12-22 13:13 ` Pip Cet via Emacs development discussions.
2024-12-22 14:16 ` Helmut Eller
2024-12-18 9:30 ` Pip Cet via Emacs development discussions.
2024-12-18 0:50 ` Po Lu
2024-12-18 2:12 ` Stefan Kangas
2024-12-18 21:26 ` Stefan Monnier
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://www.gnu.org/software/emacs/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87seqghe73.fsf@protonmail.com \
--to=emacs-devel@gnu.org \
--cc=eller.helmut@gmail.com \
--cc=monnier@iro.umontreal.ca \
--cc=pipcet@protonmail.com \
--cc=stefankangas@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://git.savannah.gnu.org/cgit/emacs.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).