All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: David Gibson <david@gibson.dropbear.id.au>
Cc: qemu-devel@nongnu.org, qemu-ppc@nongnu.org,
	David Hildenbrand <david@redhat.com>
Subject: Re: [Qemu-devel] [PATCH 1/5] virtio-balloon: Remove unnecessary MADV_WILLNEED on deflate
Date: Thu, 28 Feb 2019 08:36:58 -0500	[thread overview]
Message-ID: <20190228083317-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <20190214043916.22128-2-david@gibson.dropbear.id.au>

On Thu, Feb 14, 2019 at 03:39:12PM +1100, David Gibson wrote:
> When the balloon is inflated, we discard memory place in it using madvise()
> with MADV_DONTNEED.  And when we deflate it we use MADV_WILLNEED, which
> sounds like it makes sense but is actually unnecessary.
> 
> The misleadingly named MADV_DONTNEED just discards the memory in question,
> it doesn't set any persistent state on it in-kernel; all that's necessary
> to bring the memory back is to touch it.  MADV_WILLNEED in contrast
> specifically says that the memory will be used soon and faults it in.
> 
> This patch simplify's the balloon operation by dropping the madvise()
> on deflate.  This might have an impact on performance - it will move a
> delay at deflate time until that memory is actually touched, which
> might be more latency sensitive.  However:
> 
>   * Memory that's being given back to the guest by deflating the
>     balloon *might* be used soon, but it equally could just sit around
>     in the guest's pools until needed (or even be faulted out again if
>     the host is under memory pressure).
> 
>   * Usually, the timescale over which you'll be adjusting the balloon
>     is long enough that a few extra faults after deflation aren't
>     going to make a difference.
> 
> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
> Reviewed-by: David Hildenbrand <david@redhat.com>
> Reviewed-by: Michael S. Tsirkin <mst@redhat.com>

I'm having second thoughts about this. It might affect performance but
probably won't but we have no idea.  Might cause latency jitter after
deflate where it previously didn't happen.  This kind of patch should
really be accompanied by benchmarking results, not philosophy.

> ---
>  hw/virtio/virtio-balloon.c | 5 ++---
>  1 file changed, 2 insertions(+), 3 deletions(-)
> 
> diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
> index a12677d4d5..43af521884 100644
> --- a/hw/virtio/virtio-balloon.c
> +++ b/hw/virtio/virtio-balloon.c
> @@ -35,9 +35,8 @@
>  
>  static void balloon_page(void *addr, int deflate)
>  {
> -    if (!qemu_balloon_is_inhibited()) {
> -        qemu_madvise(addr, BALLOON_PAGE_SIZE,
> -                deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
> +    if (!qemu_balloon_is_inhibited() && !deflate) {
> +        qemu_madvise(addr, BALLOON_PAGE_SIZE, QEMU_MADV_DONTNEED);
>      }
>  }
>  
> -- 
> 2.20.1

  reply	other threads:[~2019-02-28 13:37 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-14  4:39 [Qemu-devel] [PATCH 0/5] Improve balloon handling of pagesizes other than 4kiB David Gibson
2019-02-14  4:39 ` [Qemu-devel] [PATCH 1/5] virtio-balloon: Remove unnecessary MADV_WILLNEED on deflate David Gibson
2019-02-28 13:36   ` Michael S. Tsirkin [this message]
2019-03-05  0:52     ` David Gibson
2019-03-05  2:29       ` Michael S. Tsirkin
2019-03-05  5:03         ` David Gibson
2019-03-05 14:41           ` Michael S. Tsirkin
2019-03-05 23:35             ` David Gibson
2019-03-06  0:14               ` Michael S. Tsirkin
2019-03-06  0:58                 ` David Gibson
2019-02-14  4:39 ` [Qemu-devel] [PATCH 2/5] virtio-balloon: Corrections to address verification David Gibson
2019-02-22  9:08   ` [Qemu-devel] [Qemu-ppc] " Greg Kurz
2019-02-24 23:37     ` David Gibson
2019-02-25  9:26       ` Greg Kurz
2019-02-26 23:20         ` David Gibson
2019-02-28  9:09           ` Greg Kurz
2019-02-14  4:39 ` [Qemu-devel] [PATCH 3/5] virtio-balloon: Rework ballon_page() interface David Gibson
2019-02-14  4:39 ` [Qemu-devel] [PATCH 4/5] virtio-balloon: Use ram_block_discard_range() instead of raw madvise() David Gibson
2019-02-14  4:39 ` [Qemu-devel] [PATCH 5/5] virtio-balloon: Safely handle BALLOON_PAGE_SIZE < host page size David Gibson
2019-03-05 16:06   ` [Qemu-devel] [PULL 23/26] " Peter Maydell
2019-03-05 23:33     ` David Gibson
2019-02-28 13:39 ` [Qemu-devel] [PATCH 0/5] Improve balloon handling of pagesizes other than 4kiB Michael S. Tsirkin
2019-03-05  0:53   ` David Gibson
2019-03-05  2:13     ` Michael S. Tsirkin
2019-03-05  4:55       ` David Gibson
  -- strict thread matches above, loose matches on Subject: below --
2019-02-22  2:40 [Qemu-devel] [PULL 00/26] pci, pc, virtio: fixes, cleanups, tests Michael S. Tsirkin
2019-02-22 15:47 ` Peter Maydell
2019-02-22 15:53   ` Michael S. Tsirkin
2019-02-22 16:34     ` Peter Maydell
2019-02-24  0:34     ` Michael S. Tsirkin
2019-02-24 10:21       ` Peter Maydell
2019-02-24 16:41         ` Michael S. Tsirkin
2019-02-25 16:23           ` Philippe Mathieu-Daudé
2019-02-25 17:27             ` Peter Maydell
2019-02-24 22:49     ` David Gibson
2019-02-25 15:19 ` [Qemu-devel] [PULL v2 resend " Michael S. Tsirkin
2019-03-04 10:55   ` Paolo Bonzini
2019-03-04 13:38     ` Peter Maydell

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=20190228083317-mutt-send-email-mst@kernel.org \
    --to=mst@redhat.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=david@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.