From: Wilco Dijkstra via Libc-alpha <libc-alpha@sourceware.org>
To: Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>,
"libc-alpha@sourceware.org" <libc-alpha@sourceware.org>,
Cupertino Miranda <cupertino.miranda@oracle.com>
Subject: Re: [PATCH] nptl: Disable THP on thread stack if it incurs in large RSS usage
Date: Tue, 16 May 2023 15:38:15 +0000 [thread overview]
Message-ID: <PAWPR08MB8982647EFF03E356D3322EA983799@PAWPR08MB8982.eurprd08.prod.outlook.com> (raw)
In-Reply-To: <4115d7fd-d7a7-cdb1-3833-daf45186480f@linaro.org>
Hi Adhemerval,
>> This still doesn't make sense since if _STACK_GROWS_DOWN, mem == guard, so
>> this will always execute the madvise.
And if !_STACK_GROWS_DOWN, we never execute the madvise. So I don't believe
this is correct, even if it behaves like a nop in some cases.
> Yes, if THP is set to always this is exactly the idea of this patch since
> afaiu the kernel might still back up the stack with large pages if the
> request a size is smaller than the default THP.
If a mmap start/end range does not align to a huge page, you get small pages
at the ends because a huge page does not fit.
> It is only an issue if
> the guard page address is not aligned to THP default size, which will
> potentially trigger issues Cupertino has brought (since we do not prior
> hand which is the mapping flags used on page used to fulfill the allocation).
I don't see the claimed issue happen. What happens is that if you request
huge pages, you get them. And that is what increases the RSS size.
>> As I mentioned, I couldn't find evidence that
>> the claimed scenario of a huge page allocated, written to and then split due to the
>> mprotect exists.
>
> I adapted Cupertino original test to allow specify both the thread stack
>and guard size by command line. Just:
The RSS size difference is not evidence of an issue - you asked for huge pages
and you got them! I verified they are definitely huge pages by counting the TLB
misses when accessing the stack.
>> So the real issue is that the current stack allocation code randomly (based on
>> alignment from previous mmap calls) uses huge pages even for small stacks.
>
> Keep in mind this heuristic is only enabled if THP is set to 'always', meaning
> the kernel will try to back *all* the stack with large pages. The issue is
> when the *guard* page is within a large page.
Why would that be an issue? In that case you can't get a large page.
The question is, under what circumstances are huge pages in stacks beneficial and
in which cases are they not? If have a good answer to that, then we can automatically
do the right thing without needing a tuning.
Cheers,
Wilco
next prev parent reply other threads:[~2023-05-16 15:39 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-20 17:24 [PATCH] nptl: Disable THP on thread stack if it incurs in large RSS usage Adhemerval Zanella via Libc-alpha
2023-05-03 12:42 ` Wilco Dijkstra via Libc-alpha
2023-05-15 17:57 ` Adhemerval Zanella Netto via Libc-alpha
2023-05-16 15:38 ` Wilco Dijkstra via Libc-alpha [this message]
2023-05-16 16:35 ` Adhemerval Zanella Netto via Libc-alpha
2023-05-17 12:49 ` Wilco Dijkstra via Libc-alpha
2023-05-17 13:12 ` Cupertino Miranda via Libc-alpha
2023-05-17 13:20 ` Adhemerval Zanella Netto via Libc-alpha
2023-05-17 14:22 ` Wilco Dijkstra via Libc-alpha
2023-05-17 16:50 ` Adhemerval Zanella Netto via Libc-alpha
2023-05-17 18:16 ` Wilco Dijkstra via Libc-alpha
2023-05-18 13:04 ` Adhemerval Zanella Netto via Libc-alpha
2023-05-23 9:48 ` Wilco Dijkstra via Libc-alpha
2024-01-31 2:03 ` Cristian Rodríguez
2024-01-31 7:54 ` Florian Weimer
2024-01-31 11:30 ` Adhemerval Zanella Netto
2024-01-31 11:43 ` Florian Weimer
2024-03-12 0:55 ` Cristian Rodríguez
2024-01-31 15:18 ` Cristian Rodríguez
2024-02-01 1:26 ` Cristian Rodríguez
2023-05-16 14:30 ` Cupertino Miranda via Libc-alpha
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/libc/involved.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=PAWPR08MB8982647EFF03E356D3322EA983799@PAWPR08MB8982.eurprd08.prod.outlook.com \
--to=libc-alpha@sourceware.org \
--cc=Wilco.Dijkstra@arm.com \
--cc=adhemerval.zanella@linaro.org \
--cc=cupertino.miranda@oracle.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.
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).