linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Boqun Feng <boqun.feng@gmail.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>,
	linux-kernel@vger.kernel.org, mingo@redhat.com,
	dave@stgolabs.net, will.deacon@arm.com, Waiman.Long@hpe.com,
	benh@kernel.crashing.org
Subject: Re: [PATCH] locking/osq: Drop the overload of osq lock
Date: Sat, 25 Jun 2016 23:21:30 +0800	[thread overview]
Message-ID: <20160625152130.GA2452@insomnia> (raw)
In-Reply-To: <20160625142447.GK30154@twins.programming.kicks-ass.net>

[-- Attachment #1: Type: text/plain, Size: 1941 bytes --]

On Sat, Jun 25, 2016 at 04:24:47PM +0200, Peter Zijlstra wrote:
> On Sat, Jun 25, 2016 at 01:42:03PM -0400, Pan Xinhui wrote:
> > An over-committed guest with more vCPUs than pCPUs has a heavy overload
> > in osq_lock().
> > 
> > This is because vCPU A hold the osq lock and yield out, vCPU B wait
> > per_cpu node->locked to be set. IOW, vCPU B wait vCPU A to run and
> > unlock the osq lock. Even there is need_resched(), it did not help on
> > such scenario.
> > 
> > To fix such bad issue, add a threshold in one while-loop of osq_lock().
> > The value of threshold is somehow equal to SPIN_THRESHOLD.
> 
> Blergh, virt ...
> 
> So yes, lock holder preemption sucks. You would also want to limit the
> immediate spin on owner.
> 
> Also; I really hate these random number spin-loop thresholds.
> 
> Is it at all possible to get feedback from your LPAR stuff that the vcpu
> was preempted? Because at that point we can add do something like:
> 

Good point!

> 
> 	int vpc = vcpu_preempt_count();
> 
> 	...
> 
> 	for (;;) {
> 
> 		/* the big spin loop */
> 
> 		if (need_resched() || vpc != vcpu_preempt_count())

So on PPC, we have lppaca::yield_count to detect when an vcpu is
preempted, if the yield_count is even, the vcpu is running, otherwise it
is preempted(__spin_yield() is a user of this).

Therefore it makes more sense we

		if (need_resched() || vcpu_is_preempted(old))

here, and implement vcpu_is_preempted() on PPC as

bool vcpu_is_preempted(int cpu)
{
	return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1)
}

Thoughts?

Regards,
Boqun

> 			/* bail */
> 
> 	}
> 
> 
> With a default implementation like:
> 
> static inline int vcpu_preempt_count(void)
> {
> 	return 0;
> }
> 
> So the compiler can make it all go away.
> 
> 
> But on virt muck it would stop spinning the moment the vcpu gets
> preempted, which is the right moment I'm thinking.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 473 bytes --]

  reply	other threads:[~2016-06-25 15:17 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-25 17:42 [PATCH] locking/osq: Drop the overload of osq lock Pan Xinhui
2016-06-25 14:24 ` Peter Zijlstra
2016-06-25 15:21   ` Boqun Feng [this message]
2016-06-25 16:09     ` Peter Zijlstra
2016-06-25 16:13       ` Peter Zijlstra
2016-06-25 17:27         ` panxinhui
2016-06-25 19:12           ` Peter Zijlstra
2016-06-26  4:59             ` panxinhui
2016-06-27  7:55               ` Peter Zijlstra
2016-06-27 10:19                 ` xinhui
2016-06-25 16:28       ` Boqun Feng
2016-06-25 18:28         ` Peter Zijlstra
2016-06-25 16:15     ` Peter Zijlstra
2016-06-25 16:45       ` Boqun Feng
2016-06-25 17:27         ` panxinhui
2016-06-25 19:20           ` Peter Zijlstra
2016-06-25 19:29             ` Peter Zijlstra
2016-06-26  2:26             ` Boqun Feng
2016-06-26  5:21             ` panxinhui
2016-06-26  6:10               ` Boqun Feng
2016-06-26  6:58                 ` panxinhui
2016-06-26 14:11                   ` Boqun Feng
2016-06-26 15:54                     ` panxinhui
2016-06-26  6:59                 ` Boqun Feng
2016-06-26  7:08                   ` panxinhui
2016-06-26 14:29                     ` Boqun Feng
2016-06-26 15:11                       ` panxinhui
2016-06-27  6:45                   ` Boqun Feng
2016-06-27  7:36                     ` xinhui
2016-06-27  8:09                     ` Peter Zijlstra
2016-06-27 10:31                       ` Boqun Feng

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=20160625152130.GA2452@insomnia \
    --to=boqun.feng@gmail.com \
    --cc=Waiman.Long@hpe.com \
    --cc=benh@kernel.crashing.org \
    --cc=dave@stgolabs.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=will.deacon@arm.com \
    --cc=xinhui.pan@linux.vnet.ibm.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 NNTP newsgroup(s).