Re: [RFC/T/D][PATCH 2/2] Linux/Guest cooperative unmapped page cache control

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Dave Hansen
Date: Monday, June 14, 2010 - 8:33 am

On Mon, 2010-06-14 at 16:01 +0300, Avi Kivity wrote:

You also have to set up the host up properly, and continue to maintain
it in a way that finds and eliminates duplicates.

I saw some benchmarks where KSM was doing great, finding lots of
duplicate pages.  Then, the host filled up, and guests started
reclaiming.  As memory pressure got worse, so did KSM's ability to find
duplicates.

At the same time, I see what you're trying to do with this.  It really
can be an alternative to ballooning if we do it right, since ballooning
would probably evict similar pages.  Although it would only work in idle
guests, what about a knob that the host can turn to just get the guest
to start running reclaim?

-- Dave

--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[RFC/T/D][PATCH 0/2] KVM page cache optimization (v2), Balbir Singh, (Tue Jun 8, 8:51 am)
Re: [RFC/T/D][PATCH 2/2] Linux/Guest cooperative unmapped ..., KAMEZAWA Hiroyuki, (Thu Jun 10, 6:54 pm)
Re: [RFC/T/D][PATCH 2/2] Linux/Guest cooperative unmapped ..., KAMEZAWA Hiroyuki, (Thu Jun 10, 10:08 pm)
Re: [RFC][PATCH 1/2] Linux/Guest unmapped page cache control, KAMEZAWA Hiroyuki, (Sun Jun 13, 5:28 pm)
Re: [RFC][PATCH 1/2] Linux/Guest unmapped page cache control, KAMEZAWA Hiroyuki, (Mon Jun 14, 12:49 am)
Re: [RFC/T/D][PATCH 2/2] Linux/Guest cooperative unmapped ..., Dave Hansen, (Mon Jun 14, 8:33 am)