From: Peter Zijlstra <peterz@infradead.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: LKML <linux-kernel@vger.kernel.org>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Linus Torvalds <torvalds@linux-foundation.org>,
Darren Hart <darren@dvhart.com>, Ingo Molnar <mingo@kernel.org>,
Michael Kerrisk <mtk.manpages@googlemail.com>,
Davidlohr Bueso <dave@stgolabs.net>, Chris Mason <clm@fb.com>,
"Carlos O'Donell" <carlos@redhat.com>,
Torvald Riegel <triegel@redhat.com>,
Eric Dumazet <edumazet@google.com>
Subject: Re: [patch V2 3/7] futex: Add op for hash preallocation
Date: Thu, 19 May 2016 14:24:57 +0200 [thread overview]
Message-ID: <20160519122457.GB3192@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20160505204354.051976225@linutronix.de>
On Thu, May 05, 2016 at 08:44:05PM -0000, Thomas Gleixner wrote:
> From: Sebastian Siewior <bigeasy@linutronix.de>
>
> The per process hash is allocated on the fly at the first futex operation of a
> process. The size of the hash is determined by a system wide default setting
> controlled by the sys admin, This is suboptimal for RT applications and
> applications with pathological futex abuse,
>
> - For RT applications its important to allocate the per process hash before the
> first futex operation to avoid the allocation on the first futex operation.
>
> - For pathological applications which use gazillions of futexes its useful to
> allocate a hash greater than the default hash size.
>
> Add a futex op which allows to preallocate the hash with the requested
> size. The size is limited by the systemwide maximum hash size, which can be
> set by the admin. The requested size is rounded up to the next order of 2.
>
> The function can be called several times, but ony the first call results in a
> hash allocation of the requested size as there is no non-intrusive way to
> reallocate/rehash in a multithreaded application.
>
> Note, that this call must be issued before the first futex operation in the
> process because that would automatically allocate the default sized hash.
>
> The function returns the actual hash size or 0 if the global hash is used. The
> latter is the case on UP and in the rare case that the allocation failed and
> the global hash is used as a fallback.
OK, so no on-line rehashing possible?
next prev parent reply other threads:[~2016-05-19 12:25 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-05 20:44 [patch V2 0/7] futex: Add support for process private hashing Thomas Gleixner
2016-05-05 20:44 ` [patch V2 1/7] futex: Add some more function commentry Thomas Gleixner
2016-05-06 17:37 ` Darren Hart
2016-05-05 20:44 ` [patch V2 2/7] futex: Hash private futexes per process Thomas Gleixner
2016-05-06 18:09 ` Darren Hart
2016-05-06 21:56 ` Darren Hart
2016-05-07 8:45 ` Thomas Gleixner
2016-05-11 21:08 ` Darren Hart
2016-05-07 8:44 ` Thomas Gleixner
2016-05-11 21:07 ` Darren Hart
2016-05-27 16:36 ` Sebastian Andrzej Siewior
2016-05-19 12:21 ` Peter Zijlstra
2016-05-27 16:52 ` Sebastian Andrzej Siewior
2016-05-30 8:43 ` Peter Zijlstra
2016-05-19 12:24 ` Peter Zijlstra
2016-05-27 17:10 ` Sebastian Andrzej Siewior
2016-05-30 8:58 ` Peter Zijlstra
2016-05-30 11:08 ` Sebastian Andrzej Siewior
2016-05-30 12:06 ` Peter Zijlstra
2016-05-30 13:37 ` Sebastian Andrzej Siewior
2016-05-30 13:49 ` Peter Zijlstra
2016-05-30 13:59 ` Sebastian Andrzej Siewior
2016-05-30 14:02 ` Peter Zijlstra
2016-05-05 20:44 ` [patch V2 4/7] futex: Add sysctl knobs for process private hash Thomas Gleixner
2016-05-06 18:22 ` Darren Hart
2016-05-27 17:33 ` Sebastian Andrzej Siewior
2016-05-05 20:44 ` [patch V2 3/7] futex: Add op for hash preallocation Thomas Gleixner
2016-05-06 18:18 ` Darren Hart
2016-05-07 8:47 ` Thomas Gleixner
2016-05-07 11:40 ` Thomas Gleixner
2016-05-19 12:28 ` Peter Zijlstra
2016-05-19 19:36 ` Darren Hart
2016-05-19 12:24 ` Peter Zijlstra [this message]
2016-05-19 19:38 ` Darren Hart
2016-05-20 4:50 ` Peter Zijlstra
2016-05-19 12:25 ` Peter Zijlstra
2016-05-27 17:27 ` Sebastian Andrzej Siewior
2016-05-30 8:59 ` Peter Zijlstra
2016-05-05 20:44 ` [patch V2 5/7] perf/bench/futex-hash: Support NUMA Thomas Gleixner
2016-05-05 20:44 ` [patch V2 6/7] perf/bench/futex-hash: Support preallocate hash table Thomas Gleixner
2016-05-05 20:44 ` [patch V2 7/7] futex.2: Document hash preallocation opcode Thomas Gleixner
-- strict thread matches above, loose matches on Subject: below --
2016-05-05 19:03 [patch V2 0/7] Sebastian Andrzej Siewior <bigeasy@linutronix.de>, Linus Torvalds <torvalds@linux-foundation.org>, Darren Hart <darren@dvhart.com>, Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@kernel.org>, Michael Kerrisk <mtk.manpages@googlemail.com>, Davidlohr Bueso <dave@stgolabs.net>, Chris Mason <clm@fb.com>, Carlos O'Donell <carlos@redhat.com>, Torvald Riegel <triegel@redhat.com>, Eric Dumazet <edumazet@google.com> Thomas Gleixner
2016-05-05 19:03 ` [patch V2 3/7] futex: Add op for hash preallocation Thomas Gleixner
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=20160519122457.GB3192@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=bigeasy@linutronix.de \
--cc=carlos@redhat.com \
--cc=clm@fb.com \
--cc=darren@dvhart.com \
--cc=dave@stgolabs.net \
--cc=edumazet@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=mtk.manpages@googlemail.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=triegel@redhat.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
all inboxes | Powered by JetHome®