LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Yi Sun <yi.y.sun@linux.intel.com>
To: Waiman Long <longman@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Juergen Gross <jgross@suse.com>,
	linux-kernel@vger.kernel.org, x86@kernel.org, tglx@linutronix.de,
	chao.p.peng@intel.com, chao.gao@intel.com,
	isaku.yamahata@intel.com, michael.h.kelley@microsoft.com,
	tianyu.lan@microsoft.com, "K. Y. Srinivasan" <kys@microsoft.com>,
	Haiyang Zhang <haiyangz@microsoft.com>,
	Stephen Hemminger <sthemmin@microsoft.com>,
	"mingo@redhat.com" <mingo@redhat.com>,
	Will Deacon <will.deacon@arm.com>
Subject: Re: [PATCH v1 2/2] x86/hyperv: make HvNotifyLongSpinWait hypercall
Date: Mon, 5 Nov 2018 14:54:31 +0800	[thread overview]
Message-ID: <20181105065431.GF15378@yi.y.sun> (raw)
In-Reply-To: <a6f6590e-bc46-f8d7-f6dc-5464e37a8f52@redhat.com>

On 18-11-01 08:59:08, Waiman Long wrote:
> On 10/31/2018 11:20 PM, Yi Sun wrote:
> > On 18-10-31 18:15:39, Peter Zijlstra wrote:
> >> On Wed, Oct 31, 2018 at 11:07:22AM -0400, Waiman Long wrote:
> >>> On 10/31/2018 10:10 AM, Peter Zijlstra wrote:
> >>>> On Wed, Oct 31, 2018 at 09:54:17AM +0800, Yi Sun wrote:
> >>>>> On 18-10-23 17:33:28, Yi Sun wrote:
> >>>>>> On 18-10-23 10:51:27, Peter Zijlstra wrote:
> >>>>>>> Can you try and explain why vcpu_is_preempted() doesn't work for you?
> >>>>>> I thought HvSpinWaitInfo is used to notify hypervisor the spin number
> >>>>>> which is different with vcpu_is_preempted. So I did not consider
> >>>>>> vcpu_is_preempted.
> >>>>>>
> >>>>>> But HvSpinWaitInfo is a quite simple function and could be combined
> >>>>>> with vcpu_is_preempted together. So I think it is OK to use
> >>>>>> vcpu_is_preempted to make codes clean. I will have a try.
> >>>>> After checking codes, there is one issue to call vcpu_is_preempted.
> >>>>> There are two spin loops in qspinlock_paravirt.h. One loop in
> >>>>> 'pv_wait_node' calls vcpu_is_preempted. But another loop in
> >>>>> 'pv_wait_head_or_lock' does not call vcpu_is_preempted. It also does
> >>>>> not call any other ops of 'pv_lock_ops' in the loop. So I am afraid
> >>>>> we have to add one more ops in 'pv_lock_ops' to do this.
> >>>> Why? Would not something like the below cure that? Waiman, can you have
> >>>> a look at this; I always forget how that paravirt crud works.
> >>> There are two major reasons why the vcpu_is_preempt() test isn't done at
> >>> pv_wait_head_or_lock(). First of all, we may not have a valid prev
> >>> pointer after all if it is the first one to enter the queue while the
> >>> lock is busy. Secondly, because of lock stealing, the cpu number pointed
> >>> by a valid prev pointer may not be the actual cpu that is currently
> >>> holding the lock. Another minor reason is that we want to minimize the
> >>> lock transfer latency and so don't want to sleep too early while waiting
> >>> at the queue head.
> >> So Yi, are you actually seeing a problem? If so, can you give details?
> > Where does the patch come from? I cannot find it through google.
> >
> > Per Waiman's comment, it seems not suitable to call vcpu_is_preempted()
> > in pv_wait_head_or_lock(). So, we cannot make HvSpinWaitInfo notification
> > through vcpu_is_preempted() for such case. Based on that, I suggest to
> > add one more callback function in pv_lock_ops.
> 
> I am hesitant to add any additional check at the spinning loop in
> pv_wait_head_or_lock() especially one that is a hypercall or a callback
> that will take time to execute. The testing that I had done in the past
> indicated that it would slow down locking performance especially if the
> VM wasn't overcommitted at all.
> 
> Any additional slack in pv_wait_node() can be mitigated by the lock
> stealing that can happen. Slack in pv_wait_head_or_lock(), on the other
> hand, will certainly increase the lock transfer latency and impact
> performance. So you need performance data to show that it is worthwhile
> to do so.
> 
Ok, I will make performance test to show if it is worthwhile to call
SpinWaitInfo in pv_wait_head_or_lock.

> As for performance test, the kernel has a builtin locktorture test if
> you configured it in. So show us the performance data with and without
> the patch.

Thank you! I will make performance test for whole patch.

> 
> Cheers,
> Longman

  reply	other threads:[~2018-11-05  6:57 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-19 13:13 [PATCH v1 0/2] Enable HvNotifyLongSpinWait for Hyper-V Yi Sun
2018-10-19 13:13 ` [PATCH v1 1/2] x86/hyperv: get spinlock retry number on Hyper-V Yi Sun
2018-10-19 13:13 ` [PATCH v1 2/2] x86/hyperv: make HvNotifyLongSpinWait hypercall Yi Sun
2018-10-19 14:20   ` Juergen Gross
2018-10-22  1:53     ` Yi Sun
2018-10-22  7:32       ` Juergen Gross
2018-10-22 16:31         ` Waiman Long
2018-10-22 17:15           ` Peter Zijlstra
2018-10-22 17:27             ` Waiman Long
2018-10-22 17:31               ` Peter Zijlstra
2018-10-22 18:01                 ` Waiman Long
2018-10-23  2:57             ` Yi Sun
2018-10-23  8:51               ` Peter Zijlstra
2018-10-23  9:33                 ` Yi Sun
2018-10-31  1:54                   ` Yi Sun
2018-10-31 14:10                     ` Peter Zijlstra
2018-10-31 15:07                       ` Waiman Long
2018-10-31 17:15                         ` Peter Zijlstra
2018-11-01  3:20                           ` Yi Sun
2018-11-01  8:59                             ` Peter Zijlstra
2018-11-01 12:59                             ` Waiman Long
2018-11-05  6:54                               ` Yi Sun [this message]
2018-10-24 16:53   ` Michael Kelley
2018-10-25  2:23     ` Yi Sun
2018-10-31  2:06     ` Yi Sun

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=20181105065431.GF15378@yi.y.sun \
    --to=yi.y.sun@linux.intel.com \
    --cc=chao.gao@intel.com \
    --cc=chao.p.peng@intel.com \
    --cc=haiyangz@microsoft.com \
    --cc=isaku.yamahata@intel.com \
    --cc=jgross@suse.com \
    --cc=kys@microsoft.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=michael.h.kelley@microsoft.com \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=sthemmin@microsoft.com \
    --cc=tglx@linutronix.de \
    --cc=tianyu.lan@microsoft.com \
    --cc=will.deacon@arm.com \
    --cc=x86@kernel.org \
    --subject='Re: [PATCH v1 2/2] x86/hyperv: make HvNotifyLongSpinWait hypercall' \
    /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

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).