linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexander Duyck <alexander.duyck@gmail.com>
To: David Hildenbrand <david@redhat.com>
Cc: Nitesh Narayan Lal <nitesh@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	kvm list <kvm@vger.kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	lcapitulino@redhat.com, pagupta@redhat.com, wei.w.wang@intel.com,
	Yang Zhang <yang.zhang.wz@gmail.com>,
	Rik van Riel <riel@surriel.com>,
	dodgen@google.com, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	dhildenb@redhat.com, Andrea Arcangeli <aarcange@redhat.com>
Subject: Re: [RFC][Patch v8 0/7] KVM: Guest Free Page Hinting
Date: Tue, 19 Feb 2019 13:57:14 -0800	[thread overview]
Message-ID: <CAKgT0Uc5CXZLUAqR8G4=aMmsfu2SMHfvGUjwPBmDCPT839Q-rg@mail.gmail.com> (raw)
In-Reply-To: <eadcb5c5-2252-80f4-e396-0d2bbbd53694@redhat.com>

On Tue, Feb 19, 2019 at 10:32 AM David Hildenbrand <david@redhat.com> wrote:
>
> >>> This essentially just ends up being another trade-off of CPU versus
> >>> memory though. Assuming we aren't using THP we are going to take a
> >>> penalty in terms of performance but could then free individual pages
> >>> less than HUGETLB_PAGE_ORDER, but the CPU utilization is going to be
> >>> much higher in general even without the hinting. I figure for x86 we
> >>> probably don't have too many options since if I am not mistaken
> >>> MAX_ORDER is just one or two more than HUGETLB_PAGE_ORDER.
> >>
> >> THP is an implementation detail in the hypervisor. Yes, it is the common
> >> case on x86. But it is e.g. not available on s390x yet. And we also want
> >> this mechanism to work on s390x (e.g. for nested virtualization setups
> >> as discussed).
> >>
> >> If we e.g. report any granularity after merging was done in the buddy,
> >> we could end up reporting everything from page size up to MAX_SIZE - 1,
> >> the hypervisor could ignore hints below a certain magic number, if it
> >> makes its life easier.
> >
> > For each architecture we can do a separate implementation of what to
> > hint on. We already do that for bare metal so why would we have guests
> > do the same type of hinting in the virtualization case when there are
> > fundamental differences in page size and features in each
> > architecture?
> >
> > This is another reason why I think the hypercall approach is a better
> > idea since each architecture is likely going to want to handle things
> > differently and it would be a pain to try and sort that all out in a
> > virtio driver.
>
> I can't follow. We are talking about something as simple as a minimum
> page granularity here that can easily be configured. Nothing that
> screams for different implementations. But I get your point, we could
> tune for different architectures.

I was thinking about the guest side of things. Basically if we need to
define different page orders for different architectures then we start
needing to do architecture specific includes. Then if we throw in
stuff like the fact that the first level of KVM can make use of the
host style hints then that is another thing that will be a difference
int he different architectures. I'm just worried this stuff is going
to start adding up to a bunch of "#ifdef" cruft if we are trying to do
this as a virtio driver.

> >
> >>>
> >>> As far as fragmentation my thought is that we may want to look into
> >>> adding support to the guest for prioritizing defragmentation on pages
> >>> lower than THP size. Then that way we could maintain the higher
> >>> overall performance with or without the hinting since shuffling lower
> >>> order pages around between guests would start to get expensive pretty
> >>> quick.
> >>
> >> My take would be, design an interface/mechanism that allows any kind of
> >> granularity. You can than balance between cpu overead and space shifting.
> >
> > The problem with using "any kind of granularity" is that in the case
> > of memory we are already having problems with 4K pages being deemed
> > too small of a granularity to be useful for anything and making
> > operations too expensive.
>
> No, sorry, s390x does it. And via batch reporting it could work. Not
> saying we should do page granularity, but "to be useful for anything" is
> just wrong.

Yeah, I was engaging in a bit of hyperbole. I have had a headache this
morning so I am a bit cranky.

So I am assuming the batching is the reason why you also have a
arch_alloc_page then for the s390 so that you can abort the hint if a
page is reallocated before the hint is processed then? I just want to
confirm so that my understanding of this is correct.

If that is the case I would be much happier with an asynchronous page
hint setup as this doesn't deprive the guest of memory while waiting
on the hint. The current logic in the patches from Nitesh has the
pages unavailable to the guest while waiting on the hint and that has
me somewhat concerned as it is going to hurt cache locality as it will
guarantee that we cannot reuse the same page if we are doing a cycle
of alloc and free for the same page size.

> >
> > I'm open to using other page orders for other architectures. Nothing
> > says we have to stick with THP sized pages for all architectures. I
> > have just been focused on x86 and this seems like the best fit for the
> > balance between CPU and freeing of memory for now on that
> > architecture.
> >
> >> I feel like repeating myself, but on s390x hinting is done on page
> >> granularity, and I have never heard somebody say "how can I turn it off,
> >> this is slowing down my system too much.". All we know is that one
> >> hypercall per free is most probably not acceptable. We really have to
> >> play with the numbers.
> >
> > My thought was we could look at doing different implementations for
> > other architectures such as s390 and powerPC. Odds are the
> > implementations would be similar but have slight differences where
> > appropriate such as what order we should start hinting on, or if we
> > bypass the hypercall/virtio-balloon for a host native approach if
> > available.
> >
> >> I tend to like an asynchronous reporting approach as discussed in this
> >> thread, we would have to see if Nitesh could get it implemented.
> >
> > I agree it would be great if it could work. However I have concerns
> > given that work on this patch set dates back to 2017, major issues
> > such as working around device assignment have yet to be addressed, and
> > it seems like most of the effort is being focused on things that in my
> > opinion are being over-engineered for little to no benefit.
>
> I can understand that you are trying to push your solution. I would do
> the same. Again, I don't like a pure synchronous approach that works on
> one-element-at-a-time. Period. Other people might have other opinions.
> This is mine - luckily I don't have anything to say here :)
>
> MST also voted for an asynchronous solution if we can make it work.
> Nitesh made significant improvements since the 2017. Complicated stuff
> needs time. No need to rush. People have been talking about free page
> hinting since 2006. I talked to various people that experimented with
> bitmap based solutions two years ago.

Now that I think I have a better understanding of how the s390x is
handling this I'm beginning to come around to the idea of an
asynchronous setup. The one thing that has been bugging me about the
asynchronous approach is the fact that the pages are not available to
the guest while waiting on the hint to be completed. If we can do
something like an arch_alloc_page and that would abort the hint and
allow us to keep the page available while waiting on the hint that
would be my preferred way of handling this.

> So much to that, if you think your solution is the way to go, please
> follow up on it. Nitesh seems to have decided to look into the
> asynchronous approach you also called "great if it could work". As long
> as we don't run into elementary blockers there, to me it all looks like
> we are making progress, which is good. If we find out asynchronous
> doesn't work, synchronous is the only alternative.

I plan to follow up in the next week or so.

> And just so you don't get me wrong: Thanks for looking and working on
> this. And thanks for sharing your opinions and insights! However making
> a decision about going your way at this point does not seem reasonable
> to me. We have plenty of time.

I appreciate the feedback. Sorry if I seemed a bit short. As I
mentioned I've had a headache most of the morning which hasn't really
helped my mood.

Thanks.

- Alex

  reply	other threads:[~2019-02-19 21:57 UTC|newest]

Thread overview: 116+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-04 20:18 [RFC][Patch v8 0/7] KVM: Guest Free Page Hinting Nitesh Narayan Lal
2019-02-04 20:18 ` [RFC][Patch v8 1/7] KVM: Support for guest free page hinting Nitesh Narayan Lal
2019-02-05  4:14   ` Michael S. Tsirkin
2019-02-05 13:06     ` Nitesh Narayan Lal
2019-02-05 16:27       ` Michael S. Tsirkin
2019-02-05 16:34         ` Nitesh Narayan Lal
2019-02-04 20:18 ` [RFC][Patch v8 2/7] KVM: Enabling guest free page hinting via static key Nitesh Narayan Lal
2019-02-08 18:07   ` Alexander Duyck
2019-02-08 18:22     ` Nitesh Narayan Lal
2019-02-04 20:18 ` [RFC][Patch v8 3/7] KVM: Guest free page hinting functional skeleton Nitesh Narayan Lal
2019-02-04 20:18 ` [RFC][Patch v8 4/7] KVM: Disabling page poisoning to prevent corruption Nitesh Narayan Lal
2019-02-07 17:23   ` Alexander Duyck
2019-02-07 17:56     ` Nitesh Narayan Lal
2019-02-07 18:24       ` Alexander Duyck
2019-02-07 19:14         ` Michael S. Tsirkin
2019-02-07 21:08   ` Michael S. Tsirkin
2019-02-04 20:18 ` [RFC][Patch v8 5/7] virtio: Enables to add a single descriptor to the host Nitesh Narayan Lal
2019-02-05 20:49   ` Michael S. Tsirkin
2019-02-06 12:56     ` Nitesh Narayan Lal
2019-02-06 13:15       ` Luiz Capitulino
2019-02-06 13:24         ` Nitesh Narayan Lal
2019-02-06 13:29           ` Luiz Capitulino
2019-02-06 14:05             ` Nitesh Narayan Lal
2019-02-06 18:03       ` Michael S. Tsirkin
2019-02-06 18:19         ` Nitesh Narayan Lal
2019-02-04 20:18 ` [RFC][Patch v8 6/7] KVM: Enables the kernel to isolate and report free pages Nitesh Narayan Lal
2019-02-05 20:45   ` Michael S. Tsirkin
2019-02-05 21:54     ` Nitesh Narayan Lal
2019-02-05 21:55       ` Michael S. Tsirkin
2019-02-07 17:43         ` Alexander Duyck
2019-02-07 19:01           ` Michael S. Tsirkin
2019-02-07 20:50           ` Nitesh Narayan Lal
2019-02-08 17:58             ` Alexander Duyck
2019-02-08 20:41               ` Nitesh Narayan Lal
2019-02-08 21:38                 ` Michael S. Tsirkin
2019-02-08 22:05                   ` Alexander Duyck
2019-02-10  0:38                     ` Michael S. Tsirkin
2019-02-11  9:28                       ` David Hildenbrand
2019-02-12  5:16                         ` Michael S. Tsirkin
2019-02-12 17:10                       ` Nitesh Narayan Lal
2019-02-08 21:35               ` Michael S. Tsirkin
2019-02-04 20:18 ` [RFC][Patch v8 7/7] KVM: Adding tracepoints for guest page hinting Nitesh Narayan Lal
2019-02-04 20:20 ` [RFC][QEMU PATCH] KVM: Support for guest free " Nitesh Narayan Lal
2019-02-12  9:03 ` [RFC][Patch v8 0/7] KVM: Guest Free Page Hinting Wang, Wei W
2019-02-12  9:24   ` David Hildenbrand
2019-02-12 17:24     ` Nitesh Narayan Lal
2019-02-12 19:34       ` David Hildenbrand
2019-02-13  8:55     ` Wang, Wei W
2019-02-13  9:19       ` David Hildenbrand
2019-02-13 12:17         ` Nitesh Narayan Lal
2019-02-13 17:09           ` Michael S. Tsirkin
2019-02-13 17:22             ` Nitesh Narayan Lal
     [not found]               ` <286AC319A985734F985F78AFA26841F73DF6F1C3@shsmsx102.ccr.corp.intel.com>
2019-02-14  9:34                 ` David Hildenbrand
2019-02-13 17:16         ` Michael S. Tsirkin
2019-02-13 17:59           ` David Hildenbrand
2019-02-13 19:08             ` Michael S. Tsirkin
2019-02-14  9:08         ` Wang, Wei W
2019-02-14 10:00           ` David Hildenbrand
2019-02-14 10:44             ` David Hildenbrand
2019-02-15  9:15             ` Wang, Wei W
2019-02-15  9:33               ` David Hildenbrand
2019-02-13  9:00 ` Wang, Wei W
2019-02-13 12:06   ` Nitesh Narayan Lal
2019-02-14  8:48     ` Wang, Wei W
2019-02-14  9:42       ` David Hildenbrand
2019-02-15  9:05         ` Wang, Wei W
2019-02-15  9:41           ` David Hildenbrand
2019-02-18  2:36             ` Wei Wang
2019-02-18  2:39               ` Wei Wang
2019-02-15 12:40           ` Nitesh Narayan Lal
2019-02-14 13:00       ` Nitesh Narayan Lal
2019-02-16  9:40 ` David Hildenbrand
2019-02-18 15:50   ` Nitesh Narayan Lal
2019-02-18 16:02     ` David Hildenbrand
2019-02-18 16:49   ` Michael S. Tsirkin
2019-02-18 16:59     ` David Hildenbrand
2019-02-18 17:31       ` Alexander Duyck
2019-02-18 17:41         ` David Hildenbrand
2019-02-18 23:47           ` Alexander Duyck
2019-02-19  2:45             ` Michael S. Tsirkin
2019-02-19  2:46             ` Andrea Arcangeli
2019-02-19 12:52               ` Nitesh Narayan Lal
2019-02-19 16:23               ` Alexander Duyck
2019-02-19  8:06             ` David Hildenbrand
2019-02-19 14:40               ` Michael S. Tsirkin
2019-02-19 14:44                 ` David Hildenbrand
2019-02-19 14:45                   ` David Hildenbrand
2019-02-18 18:01         ` Michael S. Tsirkin
2019-02-18 17:54       ` Michael S. Tsirkin
2019-02-18 18:29         ` David Hildenbrand
2019-02-18 19:16           ` Michael S. Tsirkin
2019-02-18 19:35             ` David Hildenbrand
2019-02-18 19:47               ` Michael S. Tsirkin
2019-02-18 20:04                 ` David Hildenbrand
2019-02-18 20:31                   ` Michael S. Tsirkin
2019-02-18 20:40                     ` Nitesh Narayan Lal
2019-02-18 21:04                       ` David Hildenbrand
2019-02-19  0:01                         ` Alexander Duyck
2019-02-19  7:54                           ` David Hildenbrand
2019-02-19 18:06                             ` Alexander Duyck
2019-02-19 18:31                               ` David Hildenbrand
2019-02-19 21:57                                 ` Alexander Duyck [this message]
2019-02-19 22:17                                   ` Michael S. Tsirkin
2019-02-19 22:36                                   ` David Hildenbrand
2019-02-19 19:58                               ` Michael S. Tsirkin
2019-02-19 20:02                                 ` David Hildenbrand
2019-02-19 20:17                                   ` Michael S. Tsirkin
2019-02-19 20:21                                     ` David Hildenbrand
2019-02-19 20:35                                       ` Michael S. Tsirkin
2019-02-19 12:47                         ` Nitesh Narayan Lal
2019-02-19 13:03                           ` David Hildenbrand
2019-02-19 14:17                             ` Nitesh Narayan Lal
2019-02-19 14:21                               ` David Hildenbrand
2019-02-18 20:53                     ` David Hildenbrand
2019-02-23  0:02 ` Alexander Duyck
2019-02-25 13:01   ` Nitesh Narayan Lal

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='CAKgT0Uc5CXZLUAqR8G4=aMmsfu2SMHfvGUjwPBmDCPT839Q-rg@mail.gmail.com' \
    --to=alexander.duyck@gmail.com \
    --cc=aarcange@redhat.com \
    --cc=david@redhat.com \
    --cc=dhildenb@redhat.com \
    --cc=dodgen@google.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=lcapitulino@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=nitesh@redhat.com \
    --cc=pagupta@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=riel@surriel.com \
    --cc=wei.w.wang@intel.com \
    --cc=yang.zhang.wz@gmail.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).