On Tue, Apr 09, 2019 at 03:43:58PM +0200, David Hildenbrand wrote:
> On 09.04.19 15:37, Michael S. Tsirkin wrote:
> > On Tue, Apr 09, 2019 at 03:36:08PM +0200, David Hildenbrand wrote:
> >> On 09.04.19 15:31, Michael S. Tsirkin wrote:
> >>> On Tue, Apr 09, 2019 at 11:20:36AM +0200, David Hildenbran
On 09.04.19 15:37, Michael S. Tsirkin wrote:
> On Tue, Apr 09, 2019 at 03:36:08PM +0200, David Hildenbrand wrote:
>> On 09.04.19 15:31, Michael S. Tsirkin wrote:
>>> On Tue, Apr 09, 2019 at 11:20:36AM +0200, David Hildenbrand wrote:
BTW I like the idea of allocating pages that have already bee
On Tue, Apr 09, 2019 at 03:36:08PM +0200, David Hildenbrand wrote:
> On 09.04.19 15:31, Michael S. Tsirkin wrote:
> > On Tue, Apr 09, 2019 at 11:20:36AM +0200, David Hildenbrand wrote:
> >> BTW I like the idea of allocating pages that have already been hinted as
> >> last "choice", allocating pages
On 09.04.19 15:31, Michael S. Tsirkin wrote:
> On Tue, Apr 09, 2019 at 11:20:36AM +0200, David Hildenbrand wrote:
>> BTW I like the idea of allocating pages that have already been hinted as
>> last "choice", allocating pages that have not been hinted yet first.
>
> OK I guess but note this is just
On Tue, Apr 09, 2019 at 11:20:36AM +0200, David Hildenbrand wrote:
> BTW I like the idea of allocating pages that have already been hinted as
> last "choice", allocating pages that have not been hinted yet first.
OK I guess but note this is just a small window during which
not all pages have been
> With that said I have a few ideas that may help to address the 4
> issues called out above. The basic idea is simple. We use a high water
> mark based on zone->free_area[order].nr_free to determine when to wake
> up a thread to start hinting memory out of a given free area. From
> there we alloca
On 09.04.19 04:44, Michael S. Tsirkin wrote:
> On Fri, Apr 05, 2019 at 05:09:45PM -0700, Alexander Duyck wrote:
>> In addition we will need some way to identify which pages have been
>> hinted on and which have not. The way I believe easiest to do this
>> would be to overload the PageType value so
On Fri, Apr 05, 2019 at 05:09:45PM -0700, Alexander Duyck wrote:
> In addition we will need some way to identify which pages have been
> hinted on and which have not. The way I believe easiest to do this
> would be to overload the PageType value so that we could essentially
> have two values for "B
On Mon, Apr 8, 2019 at 2:21 PM David Hildenbrand wrote:
>
> On 08.04.19 22:51, David Hildenbrand wrote:
> > On 08.04.19 22:10, Alexander Duyck wrote:
> >> On Mon, Apr 8, 2019 at 11:40 AM David Hildenbrand wrote:
> >>>
> >>
> >> In addition we will need some way to identify which pages hav
On 08.04.19 22:51, David Hildenbrand wrote:
> On 08.04.19 22:10, Alexander Duyck wrote:
>> On Mon, Apr 8, 2019 at 11:40 AM David Hildenbrand wrote:
>>>
>>
>> In addition we will need some way to identify which pages have been
>> hinted on and which have not. The way I believe easiest t
On 08.04.19 22:10, Alexander Duyck wrote:
> On Mon, Apr 8, 2019 at 11:40 AM David Hildenbrand wrote:
>>
>
> In addition we will need some way to identify which pages have been
> hinted on and which have not. The way I believe easiest to do this
> would be to overload the PageType v
On 08.04.19 22:10, Alexander Duyck wrote:
> On Mon, Apr 8, 2019 at 11:40 AM David Hildenbrand wrote:
>>
>
> In addition we will need some way to identify which pages have been
> hinted on and which have not. The way I believe easiest to do this
> would be to overload the PageType v
On Mon, Apr 8, 2019 at 11:40 AM David Hildenbrand wrote:
>
> >>>
> >>> In addition we will need some way to identify which pages have been
> >>> hinted on and which have not. The way I believe easiest to do this
> >>> would be to overload the PageType value so that we could essentially
> >>> have
>>> - Define and use counters corresponding to each zone to monitor the
>>> amount of memory freed.
>>> - As soon as the 64MB free memory threshold is hit wake up the kernel
>>> thread which will scan this xbitmap and try to isolate the pages and
>>> clear the corresponding bits. (We still have to
>>>
>>> In addition we will need some way to identify which pages have been
>>> hinted on and which have not. The way I believe easiest to do this
>>> would be to overload the PageType value so that we could essentially
>>> have two values for "Buddy" pages. We would have our standard "Buddy"
>>> p
On Mon, Apr 8, 2019 at 11:19 AM Michael S. Tsirkin wrote:
>
> On Mon, Apr 08, 2019 at 02:09:59PM -0400, Nitesh Narayan Lal wrote:
> > On 4/8/19 12:36 PM, David Hildenbrand wrote:
> > > On 06.04.19 02:09, Alexander Duyck wrote:
> > >> So I am starting this thread as a spot to collect my thoughts on
On 08.04.19 20:09, Nitesh Narayan Lal wrote:
> On 4/8/19 12:36 PM, David Hildenbrand wrote:
>> On 06.04.19 02:09, Alexander Duyck wrote:
>>> So I am starting this thread as a spot to collect my thoughts on the
>>> current guest free page hinting design as well as point out a few
>>> possible things
On Mon, Apr 08, 2019 at 02:09:59PM -0400, Nitesh Narayan Lal wrote:
> On 4/8/19 12:36 PM, David Hildenbrand wrote:
> > On 06.04.19 02:09, Alexander Duyck wrote:
> >> So I am starting this thread as a spot to collect my thoughts on the
> >> current guest free page hinting design as well as point out
On Mon, Apr 8, 2019 at 9:36 AM David Hildenbrand wrote:
>
> On 06.04.19 02:09, Alexander Duyck wrote:
> > So I am starting this thread as a spot to collect my thoughts on the
> > current guest free page hinting design as well as point out a few
> > possible things we could do to improve upon it.
>
On 4/8/19 12:36 PM, David Hildenbrand wrote:
> On 06.04.19 02:09, Alexander Duyck wrote:
>> So I am starting this thread as a spot to collect my thoughts on the
>> current guest free page hinting design as well as point out a few
>> possible things we could do to improve upon it.
>>
>> 1. The curre
On 06.04.19 02:09, Alexander Duyck wrote:
> So I am starting this thread as a spot to collect my thoughts on the
> current guest free page hinting design as well as point out a few
> possible things we could do to improve upon it.
>
> 1. The current design isn't likely going to scale well to multi
On Mon, Apr 08, 2019 at 08:18:35AM -0700, Alexander Duyck wrote:
> On Mon, Apr 8, 2019 at 5:24 AM Nitesh Narayan Lal wrote:
> >
> >
> > On 4/5/19 8:09 PM, Alexander Duyck wrote:
> > > So I am starting this thread as a spot to collect my thoughts on the
> > > current guest free page hinting design
On Mon, Apr 8, 2019 at 5:24 AM Nitesh Narayan Lal wrote:
>
>
> On 4/5/19 8:09 PM, Alexander Duyck wrote:
> > So I am starting this thread as a spot to collect my thoughts on the
> > current guest free page hinting design as well as point out a few
> > possible things we could do to improve upon it
On 4/5/19 8:09 PM, Alexander Duyck wrote:
> So I am starting this thread as a spot to collect my thoughts on the
> current guest free page hinting design as well as point out a few
> possible things we could do to improve upon it.
>
> 1. The current design isn't likely going to scale well to multi
So I am starting this thread as a spot to collect my thoughts on the
current guest free page hinting design as well as point out a few
possible things we could do to improve upon it.
1. The current design isn't likely going to scale well to multiple
VCPUs. The issue specifically is that the zone l
25 matches
Mail list logo
