[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <bf90043d-e592-1cb1-182d-1cc805b68050@redhat.com>
Date: Tue, 2 Apr 2019 22:32:58 +0200
From: David Hildenbrand <david@...hat.com>
To: "Michael S. Tsirkin" <mst@...hat.com>
Cc: Alexander Duyck <alexander.duyck@...il.com>,
Nitesh Narayan Lal <nitesh@...hat.com>,
kvm list <kvm@...r.kernel.org>,
LKML <linux-kernel@...r.kernel.org>,
linux-mm <linux-mm@...ck.org>,
Paolo Bonzini <pbonzini@...hat.com>, lcapitulino@...hat.com,
pagupta@...hat.com, Yang Zhang <yang.zhang.wz@...il.com>,
Rik van Riel <riel@...riel.com>, dodgen@...gle.com,
Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
dhildenb@...hat.com, Andrea Arcangeli <aarcange@...hat.com>,
Dave Hansen <dave.hansen@...el.com>
Subject: Re: On guest free page hinting and OOM
On 02.04.19 21:49, Michael S. Tsirkin wrote:
> On Tue, Apr 02, 2019 at 08:21:30PM +0200, David Hildenbrand wrote:
>> The other extreme is a system that barely frees (MAX_ORDER - X) pages,
>> however your thread will waste cycles scanning for such.
>
> I don't think we need to scan as such. An arch hook
> that queues a job to a wq only when there's work to
> do will fix the issue, right?
>
Well, even a system that is basically idle can theoretically free a
handful of pages every now and then you would like to report. There
would have to be a mechanism to detect if pages worth hinting have been
freed and need processing, IOW something like a callback after buddy
merging we are already dealing with.
That can then be a simple flag which the hinting thread considers (e.g.
wake up every X seconds to check if there is work) or kicking the
hinting thread like you suggest.
--
Thanks,
David / dhildenb
Powered by blists - more mailing lists