From: Nitesh Narayan Lal <nitesh@redhat.com>
To: Andrea Arcangeli <aarcange@redhat.com>,
Alexander Duyck <alexander.duyck@gmail.com>
Cc: David Hildenbrand <david@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
Subject: Re: [RFC][Patch v8 0/7] KVM: Guest Free Page Hinting
Date: Tue, 19 Feb 2019 07:52:45 -0500 [thread overview]
Message-ID: <962d007f-1bcc-2495-98ab-871160472f78@redhat.com> (raw)
In-Reply-To: <20190219024611.GC24502@redhat.com>
[-- Attachment #1.1: Type: text/plain, Size: 2934 bytes --]
On 2/18/19 9:46 PM, Andrea Arcangeli wrote:
> Hello,
>
> On Mon, Feb 18, 2019 at 03:47:22PM -0800, Alexander Duyck wrote:
>> essentially fragmented them. I guess hugepaged went through and
>> started trying to reassemble the huge pages and as a result there have
>> been apps that ended up consuming more memory than they would have
>> otherwise since they were using fragments of THP pages after doing an
>> MADV_DONTNEED on sections of the page.
> With relatively recent kernels MADV_DONTNEED doesn't necessarily free
> anything when it's applied to a THP subpage, it only splits the
> pagetables and queues the THP for deferred splitting. If there's
> memory pressure a shrinker will be invoked and the queue is scanned
> and the THPs are physically splitted, but to be reassembled/collapsed
> after a physical split it requires at least one young pte.
>
> If this is particularly problematic for page hinting, this behavior
> where the MADV_DONTNEED can be undoed by khugepaged (if some subpage is
> being frequently accessed), can be turned off by setting
> /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none to
> 0. Then the THP will only be collapsed if all 512 subpages are mapped
> (i.e. they've all be re-allocated by the guest).
>
> Regardless of the max_ptes_none default, keeping the smaller guest
> buddy orders as the last target for page hinting should be good for
> performance.
>
>> Yeah, no problem. The only thing I don't like about MADV_FREE is that
>> you have to have memory pressure before the pages really start getting
>> scrubbed with is both a benefit and a drawback. Basically it defers
>> the freeing until you are under actual memory pressure so when you hit
>> that case things start feeling much slower, that and it limits your
>> allocations since the kernel doesn't recognize the pages as free until
>> it would have to start trying to push memory to swap.
> The guest allocation behavior should not be influenced by MADV_FREE vs
> MADV_DONTNEED, the guest can't see the difference anyway, so why
> should it limit the allocations?
>
> The benefit of MADV_FREE should be that when the same guest frees and
> reallocates an huge amount of RAM (i.e. guest app allocating and
> freeing lots of RAM in a loop, not so uncommon), there will be no KVM
> page fault during guest re-allocations. So in absence of memory
> pressure in the host it should be a major win. Overall it sounds like
> a good tradeoff compared to MADV_DONTNEED that forcefully invokes MMU
> notifiers and forces host allocations and KVM page faults in order to
> reallocate the same RAM in the same guest.
This does makes sense.
Thanks for explaining this.
>
> When there's memory pressure it's up to the host Linux VM to notice
> there's plenty of MADV_FREE material to free at zero I/O cost before
> starting swapping.
>
> Thanks,
> Andrea
--
Regards
Nitesh
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2019-02-19 12:52 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 [this message]
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
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=962d007f-1bcc-2495-98ab-871160472f78@redhat.com \
--to=nitesh@redhat.com \
--cc=aarcange@redhat.com \
--cc=alexander.duyck@gmail.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=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).