From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: Pavel Machek <pavel@ucw.cz>
Cc: Florian Weimer <fweimer@redhat.com>, carlos <carlos@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Boqun Feng <boqun.feng@gmail.com>,
Thomas Gleixner <tglx@linutronix.de>,
linux-kernel <linux-kernel@vger.kernel.org>,
libc-alpha <libc-alpha@sourceware.org>
Subject: Re: Restartable Sequences system call merged into Linux
Date: Thu, 14 Jun 2018 13:38:00 -0000 [thread overview]
Message-ID: <956816108.13001.1528983496098.JavaMail.zimbra@efficios.com> (raw)
In-Reply-To: <20180614132557.GA15201@amd>
----- On Jun 14, 2018, at 9:25 AM, Pavel Machek pavel@ucw.cz wrote:
> Hi!
>
>> >> >>>> It should be noted that there can be only one rseq TLS area registered per
>> >> >>>> thread,
>> >> >>>> which can then be used by many libraries and by the executable, so this is a
>> >> >>>> process-wide (per-thread) resource that we need to manage carefully.
>> >> >>>
>> >> >>> Is it possible to resize the area after thread creation, perhaps even
>> >> >>> from other threads?
>> >> >>
>> >> >> I'm not sure why we would want to resize it. The per-thread area is fixed-size.
>> >> >> Its layout is here: include/uapi/linux/rseq.h: struct rseq
>> >> >
>> >> > Looks I was mistaken and this is very similar to the robust mutex list.
>> >> >
>> >> > Should we treat it the same way? Always allocate it for each new thread
>> >> > and register it with the kernel?
>> >>
>> >> That would be an efficient way to do it, indeed. There is very little
>> >> performance overhead to have rseq registered for all threads, whether or
>> >> not they intend to run rseq critical sections.
>> >
>> > People with slow / low memory machines would prefer not to see
>> > overhead they don't need...
>>
>> In terms of memory usage, if people don't want the extra few bytes of memory
>> used by rseq in the kernel, they should use CONFIG_RSEQ=n.
>>
>> In terms of overhead, let's have a closer look at what it means: when a thread
>> is registered to rseq, but does not enter rseq critical sections, only this
>> extra work is done by the kernel:
>>
>> - rseq_preempt(): on preemption, the scheduler sets the TIF_NOTIFY_RESUME thread
>> flag, so rseq_handle_notify_resume() can check whether it's in a rseq critical
>> section when returning to user-space,
>> - rseq_signal_deliver(): on signal delivery, rseq_handle_notify_resume() checks
>> whether it's in a rseq critical section,
>> - rseq_migrate: on migration, the scheduler sets TIF_NOTIFY_RESUME as well,
>
> Yes, this is not likely to be noticeable.
>
> But the proposal wanted to add a syscall to thread creation, right?
> And I believe that may be noticeable.
Fair point! Do we have a standard benchmark that would stress this ?
If it ends up being noticeable overhead, I wonder whether we could extend clone() with a
new CLONE_RSEQ flag so glibc could pass a pointer to the rseq TLS area through an extra
argument to the clone system call rather than do an extra syscall on thread creation ?
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
next prev parent reply other threads:[~2018-06-14 13:38 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-11 19:49 Mathieu Desnoyers
2018-06-11 19:55 ` Florian Weimer
2018-06-11 20:04 ` Mathieu Desnoyers
2018-06-12 13:11 ` Florian Weimer
2018-06-12 16:31 ` Mathieu Desnoyers
2018-06-13 8:23 ` Florian Weimer
2018-06-14 12:28 ` Pavel Machek
2018-06-14 13:02 ` Mathieu Desnoyers
2018-06-14 13:26 ` Pavel Machek
2018-06-14 13:32 ` Florian Weimer
2018-06-14 13:46 ` Mathieu Desnoyers
2018-06-15 5:10 ` Florian Weimer
2018-06-15 17:44 ` Mathieu Desnoyers
2018-06-14 13:38 ` Mathieu Desnoyers [this message]
2018-06-14 13:50 ` Pavel Machek
2018-06-14 14:01 ` Florian Weimer
2018-06-14 14:36 ` Mathieu Desnoyers
2018-06-14 14:41 ` Florian Weimer
2018-06-14 15:09 ` Mathieu Desnoyers
2018-06-15 5:09 ` Florian Weimer
2018-06-15 17:50 ` Mathieu Desnoyers
2018-06-15 5:07 ` Florian Weimer
2018-06-13 11:48 ` Heiko Carstens
2018-06-13 16:14 ` Mathieu Desnoyers
2018-06-13 19:53 ` Mathieu Desnoyers
2018-07-11 16:03 ` Stefan Liebler
2018-07-11 16:23 ` Adhemerval Zanella
2018-07-11 17:19 ` Florian Weimer
2018-07-11 17:42 ` Adhemerval Zanella
2018-07-11 17:45 ` Florian Weimer
2018-07-11 17:59 ` Adhemerval Zanella
2018-07-12 8:08 ` Stefan Liebler
2018-07-11 19:05 ` Carlos O'Donell
2018-07-12 8:10 ` Szabolcs Nagy
2018-07-13 13:22 ` Stefan Liebler
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
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=956816108.13001.1528983496098.JavaMail.zimbra@efficios.com \
--to=mathieu.desnoyers@efficios.com \
--cc=boqun.feng@gmail.com \
--cc=carlos@redhat.com \
--cc=fweimer@redhat.com \
--cc=libc-alpha@sourceware.org \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=pavel@ucw.cz \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/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).