KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Nitesh Narayan Lal <nitesh@redhat.com>
To: Alexander Duyck <alexander.duyck@gmail.com>
Cc: kvm list <kvm@vger.kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-mm <linux-mm@kvack.org>,
	virtio-dev@lists.oasis-open.org,
	Paolo Bonzini <pbonzini@redhat.com>,
	lcapitulino@redhat.com, Pankaj Gupta <pagupta@redhat.com>,
	"Wang, Wei W" <wei.w.wang@intel.com>,
	Yang Zhang <yang.zhang.wz@gmail.com>,
	Rik van Riel <riel@surriel.com>,
	David Hildenbrand <david@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	dodgen@google.com, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	dhildenb@redhat.com, Andrea Arcangeli <aarcange@redhat.com>,
	john.starks@microsoft.com, Dave Hansen <dave.hansen@intel.com>,
	Michal Hocko <mhocko@suse.com>,
	cohuck@redhat.com
Subject: Re: [RFC][Patch v12 1/2] mm: page_reporting: core infrastructure
Date: Thu, 15 Aug 2019 09:15:37 -0400
Message-ID: <09c6fbef-fa53-3a25-d3d6-460b9b6b2020@redhat.com> (raw)
In-Reply-To: <CAKgT0UfavuUT4ZvfxVdm3h25qc86ksxPO=GFpFkf8zbGAjHPvg@mail.gmail.com>


On 8/14/19 12:11 PM, Alexander Duyck wrote:
> On Wed, Aug 14, 2019 at 8:49 AM Nitesh Narayan Lal <nitesh@redhat.com> wrote:
>>
>> On 8/12/19 2:47 PM, Alexander Duyck wrote:
>>> On Mon, Aug 12, 2019 at 6:13 AM Nitesh Narayan Lal <nitesh@redhat.com> wrote:
>>>> This patch introduces the core infrastructure for free page reporting in
>>>> virtual environments. It enables the kernel to track the free pages which
>>>> can be reported to its hypervisor so that the hypervisor could
>>>> free and reuse that memory as per its requirement.
>>>>
>>>> While the pages are getting processed in the hypervisor (e.g.,
>>>> via MADV_DONTNEED), the guest must not use them, otherwise, data loss
>>>> would be possible. To avoid such a situation, these pages are
>>>> temporarily removed from the buddy. The amount of pages removed
>>>> temporarily from the buddy is governed by the backend(virtio-balloon
>>>> in our case).
>>>>
>>>> To efficiently identify free pages that can to be reported to the
>>>> hypervisor, bitmaps in a coarse granularity are used. Only fairly big
>>>> chunks are reported to the hypervisor - especially, to not break up THP
>>>> in the hypervisor - "MAX_ORDER - 2" on x86, and to save space. The bits
>>>> in the bitmap are an indication whether a page *might* be free, not a
>>>> guarantee. A new hook after buddy merging sets the bits.
>>>>
>>>> Bitmaps are stored per zone, protected by the zone lock. A workqueue
>>>> asynchronously processes the bitmaps, trying to isolate and report pages
>>>> that are still free. The backend (virtio-balloon) is responsible for
>>>> reporting these batched pages to the host synchronously. Once reporting/
>>>> freeing is complete, isolated pages are returned back to the buddy.
>>>>
>>>> Signed-off-by: Nitesh Narayan Lal <nitesh@redhat.com>
>> [...]
>>>> +}
>>>> +
>>>> +/**
>>>> + * __page_reporting_enqueue - tracks the freed page in the respective zone's
>>>> + * bitmap and enqueues a new page reporting job to the workqueue if possible.
>>>> + */
>>>> +void __page_reporting_enqueue(struct page *page)
>>>> +{
>>>> +       struct page_reporting_config *phconf;
>>>> +       struct zone *zone;
>>>> +
>>>> +       rcu_read_lock();
>>>> +       /*
>>>> +        * We should not process this page if either page reporting is not
>>>> +        * yet completely enabled or it has been disabled by the backend.
>>>> +        */
>>>> +       phconf = rcu_dereference(page_reporting_conf);
>>>> +       if (!phconf)
>>>> +               return;
>>>> +
>>>> +       zone = page_zone(page);
>>>> +       bitmap_set_bit(page, zone);
>>>> +
>>>> +       /*
>>>> +        * We should not enqueue a job if a previously enqueued reporting work
>>>> +        * is in progress or we don't have enough free pages in the zone.
>>>> +        */
>>>> +       if (atomic_read(&zone->free_pages) >= phconf->max_pages &&
>>>> +           !atomic_cmpxchg(&phconf->refcnt, 0, 1))
>>> This doesn't make any sense to me. Why are you only incrementing the
>>> refcount if it is zero? Combining this with the assignment above, this
>>> isn't really a refcnt. It is just an oversized bitflag.
>>
>> The intent for having an extra variable was to ensure that at a time only one
>> reporting job is enqueued. I do agree that for that purpose I really don't need
>> a reference counter and I should have used something like bool
>> 'page_hinting_active'. But with bool, I think there could be a possible chance
>> of race. Maybe I should rename this variable and keep it as atomic.
>> Any thoughts?
> You could just use a bitflag to achieve what you are doing here. That
> is the primary use case for many of the test_and_set_bit type
> operations. However one issue with doing it as a bitflag is that you
> have no way of telling that you took care of all requesters.

I think you are right, I might end up missing on certain reporting
opportunities in some special cases. Specifically when the pages which are
part of this new reporting request belongs to a section of the bitmap which
has already been scanned. Although, I have failed to reproduce this kind of
situation in an actual setup.

>  That is
> where having an actual reference count comes in handy as you know
> exactly how many zones are requesting to be reported on.


True.

>
>>> Also I am pretty sure this results in the opportunity to miss pages
>>> because there is nothing to prevent you from possibly missing a ton of
>>> pages you could hint on if a large number of pages are pushed out all
>>> at once and then the system goes idle in terms of memory allocation
>>> and freeing.
>>
>> I was looking at how you are enqueuing/processing reporting jobs for each zone.
>> I am wondering if I should also consider something on similar lines as having
>> that I might be able to address the concern which you have raised above. But it
>> would also mean that I have to add an additional flag in the zone_flags. :)
> You could do it either in the zone or outside the zone as yet another
> bitmap. I decided to put the flags inside the zone because there was a
> number of free bits there and it should be faster since we were
> already using the zone structure.

There are two possibilities which could happen while I am reporting:
1. Another request might come in for a different zone.
2. Another request could come in for the same zone and the pages belong to a
    section of the bitmap which has already been scanned.

Having a per zone flag to indicate reporting status will solve the first
issue and to an extent the second as well. Having refcnt will possibly solve
both of them. What I am wondering about is that in my case I could easily
impact the performance negatively by performing more bitmap scanning.


-- 
Thanks
Nitesh


  reply index

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-12 13:12 [RFC][PATCH v12 0/2] mm: Support for page reporting Nitesh Narayan Lal
2019-08-12 13:12 ` [RFC][Patch v12 1/2] mm: page_reporting: core infrastructure Nitesh Narayan Lal
2019-08-12 18:47   ` Alexander Duyck
2019-08-12 20:04     ` Nitesh Narayan Lal
2019-08-20 14:11       ` Nitesh Narayan Lal
2019-08-12 20:05     ` David Hildenbrand
2019-08-13 10:30       ` Nitesh Narayan Lal
2019-08-13 10:34         ` David Hildenbrand
2019-08-13 10:42           ` Nitesh Narayan Lal
2019-08-13 10:44             ` David Hildenbrand
2019-08-13 23:14           ` Alexander Duyck
2019-08-14  7:07             ` David Hildenbrand
2019-08-14 12:49               ` [virtio-dev] " Nitesh Narayan Lal
2019-08-14 15:49     ` Nitesh Narayan Lal
2019-08-14 16:11       ` Alexander Duyck
2019-08-15 13:15         ` Nitesh Narayan Lal [this message]
2019-08-15 19:22           ` Nitesh Narayan Lal
2019-08-15 23:00             ` Alexander Duyck
2019-08-16 18:35               ` Nitesh Narayan Lal
2019-08-30 15:15     ` Nitesh Narayan Lal
2019-08-30 15:31       ` Alexander Duyck
2019-08-30 16:05         ` Nitesh Narayan Lal
2019-09-04  8:40           ` [virtio-dev] " David Hildenbrand
2019-10-10 20:36   ` Alexander Duyck
2019-10-11 11:02     ` Nitesh Narayan Lal
2019-08-12 13:12 ` [RFC][Patch v12 2/2] virtio-balloon: interface to support free page reporting Nitesh Narayan Lal
2019-08-14 10:29   ` Cornelia Huck
2019-08-14 11:47     ` Nitesh Narayan Lal
2019-08-14 13:42       ` Cornelia Huck
2019-08-14 14:01         ` Nitesh Narayan Lal
2019-08-12 13:13 ` [QEMU Patch 1/2] virtio-balloon: adding bit for page reporting support Nitesh Narayan Lal
2019-08-12 13:13   ` [QEMU Patch 2/2] virtio-balloon: support for handling page reporting Nitesh Narayan Lal
2019-08-12 15:18     ` Alexander Duyck
2019-08-12 15:26       ` Nitesh Narayan Lal
2019-09-11 12:30 ` [RFC][PATCH v12 0/2] mm: Support for " David Hildenbrand

Reply instructions:

You may reply publically 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=09c6fbef-fa53-3a25-d3d6-460b9b6b2020@redhat.com \
    --to=nitesh@redhat.com \
    --cc=aarcange@redhat.com \
    --cc=alexander.duyck@gmail.com \
    --cc=cohuck@redhat.com \
    --cc=dave.hansen@intel.com \
    --cc=david@redhat.com \
    --cc=dhildenb@redhat.com \
    --cc=dodgen@google.com \
    --cc=john.starks@microsoft.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=lcapitulino@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=mst@redhat.com \
    --cc=pagupta@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=riel@surriel.com \
    --cc=virtio-dev@lists.oasis-open.org \
    --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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git