All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: Rafael Aquini <aquini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org, linux-mm@kvack.org,
	Peter Zijlstra <peterz@infradead.org>,
	Andi Kleen <andi@firstfloor.org>,
	Minchan Kim <minchan@kernel.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: [PATCH v11 5/7] virtio_balloon: introduce migration primitives to balloon pages
Date: Wed, 7 Nov 2012 11:58:10 -0800	[thread overview]
Message-ID: <20121107115810.1ae286ac.akpm@linux-foundation.org> (raw)
In-Reply-To: <265aaff9a79f503672f0cdcdff204114b5b5ba5b.1352256088.git.aquini@redhat.com>

On Wed,  7 Nov 2012 01:05:52 -0200
Rafael Aquini <aquini@redhat.com> wrote:

> Memory fragmentation introduced by ballooning might reduce significantly
> the number of 2MB contiguous memory blocks that can be used within a guest,
> thus imposing performance penalties associated with the reduced number of
> transparent huge pages that could be used by the guest workload.
> 
> Besides making balloon pages movable at allocation time and introducing
> the necessary primitives to perform balloon page migration/compaction,
> this patch also introduces the following locking scheme, in order to
> enhance the syncronization methods for accessing elements of struct
> virtio_balloon, thus providing protection against concurrent access
> introduced by parallel memory migration threads.
> 
> ...
>
> @@ -122,18 +128,25 @@ static void set_page_pfns(u32 pfns[], struct page *page)
>  
>  static void fill_balloon(struct virtio_balloon *vb, size_t num)
>  {
> +	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
> +
> +	static DEFINE_RATELIMIT_STATE(fill_balloon_rs,
> +				      DEFAULT_RATELIMIT_INTERVAL,
> +				      DEFAULT_RATELIMIT_BURST);
> +
>  	/* We can only do one array worth at a time. */
>  	num = min(num, ARRAY_SIZE(vb->pfns));
>  
> +	mutex_lock(&vb->balloon_lock);
>  	for (vb->num_pfns = 0; vb->num_pfns < num;
>  	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
> -		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY |
> -					__GFP_NOMEMALLOC | __GFP_NOWARN);
> +		struct page *page = balloon_page_enqueue(vb_dev_info);
> +
>  		if (!page) {
> -			if (printk_ratelimit())
> +			if (__ratelimit(&fill_balloon_rs))
>  				dev_printk(KERN_INFO, &vb->vdev->dev,
>  					   "Out of puff! Can't get %zu pages\n",
> -					   num);
> +					   VIRTIO_BALLOON_PAGES_PER_PAGE);
>  			/* Sleep for at least 1/5 of a second before retry. */
>  			msleep(200);
>  			break;

linux-next's fill_balloon() has already been converted to
dev_info_ratelimited().  I fixed everything up.  Please check the result.

WARNING: multiple messages have this Message-ID (diff)
From: Andrew Morton <akpm@linux-foundation.org>
To: Rafael Aquini <aquini@redhat.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	Rusty Russell <rusty@rustcorp.com.au>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Rik van Riel <riel@redhat.com>, Mel Gorman <mel@csn.ul.ie>,
	Andi Kleen <andi@firstfloor.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Minchan Kim <minchan@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: [PATCH v11 5/7] virtio_balloon: introduce migration primitives to balloon pages
Date: Wed, 7 Nov 2012 11:58:10 -0800	[thread overview]
Message-ID: <20121107115810.1ae286ac.akpm@linux-foundation.org> (raw)
In-Reply-To: <265aaff9a79f503672f0cdcdff204114b5b5ba5b.1352256088.git.aquini@redhat.com>

On Wed,  7 Nov 2012 01:05:52 -0200
Rafael Aquini <aquini@redhat.com> wrote:

> Memory fragmentation introduced by ballooning might reduce significantly
> the number of 2MB contiguous memory blocks that can be used within a guest,
> thus imposing performance penalties associated with the reduced number of
> transparent huge pages that could be used by the guest workload.
> 
> Besides making balloon pages movable at allocation time and introducing
> the necessary primitives to perform balloon page migration/compaction,
> this patch also introduces the following locking scheme, in order to
> enhance the syncronization methods for accessing elements of struct
> virtio_balloon, thus providing protection against concurrent access
> introduced by parallel memory migration threads.
> 
> ...
>
> @@ -122,18 +128,25 @@ static void set_page_pfns(u32 pfns[], struct page *page)
>  
>  static void fill_balloon(struct virtio_balloon *vb, size_t num)
>  {
> +	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
> +
> +	static DEFINE_RATELIMIT_STATE(fill_balloon_rs,
> +				      DEFAULT_RATELIMIT_INTERVAL,
> +				      DEFAULT_RATELIMIT_BURST);
> +
>  	/* We can only do one array worth at a time. */
>  	num = min(num, ARRAY_SIZE(vb->pfns));
>  
> +	mutex_lock(&vb->balloon_lock);
>  	for (vb->num_pfns = 0; vb->num_pfns < num;
>  	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
> -		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY |
> -					__GFP_NOMEMALLOC | __GFP_NOWARN);
> +		struct page *page = balloon_page_enqueue(vb_dev_info);
> +
>  		if (!page) {
> -			if (printk_ratelimit())
> +			if (__ratelimit(&fill_balloon_rs))
>  				dev_printk(KERN_INFO, &vb->vdev->dev,
>  					   "Out of puff! Can't get %zu pages\n",
> -					   num);
> +					   VIRTIO_BALLOON_PAGES_PER_PAGE);
>  			/* Sleep for at least 1/5 of a second before retry. */
>  			msleep(200);
>  			break;

linux-next's fill_balloon() has already been converted to
dev_info_ratelimited().  I fixed everything up.  Please check the result.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Andrew Morton <akpm@linux-foundation.org>
To: Rafael Aquini <aquini@redhat.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	Rusty Russell <rusty@rustcorp.com.au>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Rik van Riel <riel@redhat.com>, Mel Gorman <mel@csn.ul.ie>,
	Andi Kleen <andi@firstfloor.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Minchan Kim <minchan@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: [PATCH v11 5/7] virtio_balloon: introduce migration primitives to balloon pages
Date: Wed, 7 Nov 2012 11:58:10 -0800	[thread overview]
Message-ID: <20121107115810.1ae286ac.akpm@linux-foundation.org> (raw)
In-Reply-To: <265aaff9a79f503672f0cdcdff204114b5b5ba5b.1352256088.git.aquini@redhat.com>

On Wed,  7 Nov 2012 01:05:52 -0200
Rafael Aquini <aquini@redhat.com> wrote:

> Memory fragmentation introduced by ballooning might reduce significantly
> the number of 2MB contiguous memory blocks that can be used within a guest,
> thus imposing performance penalties associated with the reduced number of
> transparent huge pages that could be used by the guest workload.
> 
> Besides making balloon pages movable at allocation time and introducing
> the necessary primitives to perform balloon page migration/compaction,
> this patch also introduces the following locking scheme, in order to
> enhance the syncronization methods for accessing elements of struct
> virtio_balloon, thus providing protection against concurrent access
> introduced by parallel memory migration threads.
> 
> ...
>
> @@ -122,18 +128,25 @@ static void set_page_pfns(u32 pfns[], struct page *page)
>  
>  static void fill_balloon(struct virtio_balloon *vb, size_t num)
>  {
> +	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
> +
> +	static DEFINE_RATELIMIT_STATE(fill_balloon_rs,
> +				      DEFAULT_RATELIMIT_INTERVAL,
> +				      DEFAULT_RATELIMIT_BURST);
> +
>  	/* We can only do one array worth at a time. */
>  	num = min(num, ARRAY_SIZE(vb->pfns));
>  
> +	mutex_lock(&vb->balloon_lock);
>  	for (vb->num_pfns = 0; vb->num_pfns < num;
>  	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
> -		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY |
> -					__GFP_NOMEMALLOC | __GFP_NOWARN);
> +		struct page *page = balloon_page_enqueue(vb_dev_info);
> +
>  		if (!page) {
> -			if (printk_ratelimit())
> +			if (__ratelimit(&fill_balloon_rs))
>  				dev_printk(KERN_INFO, &vb->vdev->dev,
>  					   "Out of puff! Can't get %zu pages\n",
> -					   num);
> +					   VIRTIO_BALLOON_PAGES_PER_PAGE);
>  			/* Sleep for at least 1/5 of a second before retry. */
>  			msleep(200);
>  			break;

linux-next's fill_balloon() has already been converted to
dev_info_ratelimited().  I fixed everything up.  Please check the result.


  reply	other threads:[~2012-11-07 19:58 UTC|newest]

Thread overview: 98+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-11-07  3:05 [PATCH v11 0/7] make balloon pages movable by compaction Rafael Aquini
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05 ` [PATCH v11 1/7] mm: adjust address_space_operations.migratepage() return code Rafael Aquini
2012-11-07  3:05   ` Rafael Aquini
2012-11-07 19:56   ` Andrew Morton
2012-11-07 19:56     ` Andrew Morton
2012-11-07 19:56     ` Andrew Morton
2012-11-07 21:39     ` Rafael Aquini
2012-11-07 21:39     ` Rafael Aquini
2012-11-07 21:39       ` Rafael Aquini
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05 ` [PATCH v11 2/7] mm: redefine address_space.assoc_mapping Rafael Aquini
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05   ` Rafael Aquini
2012-11-07  3:05 ` [PATCH v11 3/7] mm: introduce a common interface for balloon pages mobility Rafael Aquini
2012-11-07  3:05   ` Rafael Aquini
2012-11-07 21:02   ` Andrew Morton
2012-11-07 21:02     ` Andrew Morton
2012-11-07 21:02     ` Andrew Morton
2012-11-07 21:34     ` Rafael Aquini
2012-11-07 21:34     ` Rafael Aquini
2012-11-07 21:34       ` Rafael Aquini
2012-11-09 12:11   ` Mel Gorman
2012-11-09 12:11   ` Mel Gorman
2012-11-09 12:11     ` Mel Gorman
2012-11-09 14:53     ` Rafael Aquini
2012-11-09 14:53     ` Rafael Aquini
2012-11-09 14:53       ` Rafael Aquini
2012-11-09 16:23       ` Mel Gorman
2012-11-09 16:23         ` Mel Gorman
2012-11-09 17:58         ` Rafael Aquini
2012-11-09 17:58         ` Rafael Aquini
2012-11-09 17:58           ` Rafael Aquini
2012-11-09 16:23       ` Mel Gorman
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05 ` [PATCH v11 4/7] mm: introduce compaction and migration for ballooned pages Rafael Aquini
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05   ` Rafael Aquini
2012-11-09 12:16   ` Mel Gorman
2012-11-09 12:16     ` Mel Gorman
2012-11-20 23:33     ` Andrew Morton
2012-11-20 23:33       ` Andrew Morton
2012-11-20 23:33       ` Andrew Morton
2012-11-27 11:59       ` Rafael Aquini
2012-11-27 11:59         ` Rafael Aquini
2012-11-27 11:59       ` Rafael Aquini
2012-11-09 12:16   ` Mel Gorman
2012-11-07  3:05 ` [PATCH v11 5/7] virtio_balloon: introduce migration primitives to balloon pages Rafael Aquini
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05   ` Rafael Aquini
2012-11-07 19:58   ` Andrew Morton [this message]
2012-11-07 19:58     ` Andrew Morton
2012-11-07 19:58     ` Andrew Morton
2012-11-07 22:02     ` Rafael Aquini
2012-11-07 22:02     ` Rafael Aquini
2012-11-07 22:02       ` Rafael Aquini
2012-11-07 23:02   ` Rusty Russell
2012-11-07 23:02     ` Rusty Russell
2012-11-07 23:02     ` Rusty Russell
2012-11-08  0:11     ` Andrew Morton
2012-11-08  0:11       ` Andrew Morton
2012-11-08  0:11       ` Andrew Morton
2012-11-08  0:32       ` Rafael Aquini
2012-11-08  0:32         ` Rafael Aquini
2012-11-08  0:32       ` Rafael Aquini
2012-11-10 15:53       ` Michael S. Tsirkin
2012-11-10 15:53         ` Michael S. Tsirkin
2012-11-10 15:53       ` Michael S. Tsirkin
2012-11-08  0:34     ` Rafael Aquini
2012-11-08  0:34       ` Rafael Aquini
2012-11-12  7:49       ` Rusty Russell
2012-11-12  7:49         ` Rusty Russell
2012-11-12  7:49         ` Rusty Russell
2012-11-08  0:34     ` Rafael Aquini
2012-11-10 15:53   ` Michael S. Tsirkin
2012-11-10 15:53     ` Michael S. Tsirkin
2012-11-10 15:53   ` Michael S. Tsirkin
2012-11-07  3:05 ` [PATCH v11 6/7] mm: introduce putback_movable_pages() Rafael Aquini
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05   ` Rafael Aquini
2012-11-07  3:05 ` [PATCH v11 7/7] mm: add vm event counters for balloon pages compaction Rafael Aquini
2012-11-07  3:05 ` Rafael Aquini
2012-11-07  3:05   ` Rafael Aquini
2012-11-09 12:20   ` Mel Gorman
2012-11-09 12:20     ` Mel Gorman
2012-11-09 12:20     ` Mel Gorman
2012-11-09 14:58     ` Rafael Aquini
2012-11-09 14:58       ` Rafael Aquini
2012-11-20 23:29       ` Andrew Morton
2012-11-20 23:29         ` Andrew Morton
2012-11-20 23:29         ` Andrew Morton
2012-11-09 14:58     ` Rafael Aquini
2012-11-10 15:55   ` Michael S. Tsirkin
2012-11-10 15:55     ` Michael S. Tsirkin
2012-11-11 19:22     ` Rafael Aquini
2012-11-11 19:22       ` Rafael Aquini
2012-11-11 19:22     ` Rafael Aquini
2012-11-10 15:55   ` Michael S. Tsirkin

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=20121107115810.1ae286ac.akpm@linux-foundation.org \
    --to=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=aquini@redhat.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=mst@redhat.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    --cc=virtualization@lists.linux-foundation.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.