From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Cooper Subject: Re: [PATCH RFC 00/10] Xen balloon page compaction support Date: Fri, 17 Oct 2014 13:35:46 +0100 Message-ID: <54410D22.2000403@citrix.com> References: <1413388459-4663-1-git-send-email-wei.liu2@citrix.com> <543EA6C0.20903@citrix.com> <20141015170043.GF29948@zion.uk.xensource.com> <543EAB90.2010009@citrix.com> <1413451617.2012.7.camel@citrix.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1413451617.2012.7.camel@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Ian Campbell Cc: boris.ostrovsky@oracle.com, stefano.stabellini@eu.citrix.com, Wei Liu , david.vrabel@citrix.com, xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org On 16/10/14 10:26, Ian Campbell wrote: > On Wed, 2014-10-15 at 18:14 +0100, Andrew Cooper wrote: >> On 15/10/14 18:00, Wei Liu wrote: >>> On Wed, Oct 15, 2014 at 05:54:24PM +0100, Andrew Cooper wrote: >>>> On 15/10/14 16:54, Wei Liu wrote: >>>>> Hi all >>>>> >>>>> This is a prototype to make Xen balloon driver work with balloon page >>>>> compaction. The goal is to reduce guest physical address space fragmentation >>>>> introduced by balloon pages. Having guest physical address space as contiguous >>>>> as possible is generally useful (because guest can have higher order pages), and >>>>> it should also help improve HVM performance (provided that guest kernel knows >>>>> how to use huge pages -- Linux has hugetlbfs and transparent huge page). >>>> After you have defragmented guest physical memory, does Linux use >>>> 2MB/1GB superpages more readily? >>>> >>> That's completely up to the guest. Having contiguous guest physical >>> address space is prerequisite. >>> >>>> On what basis do you think this will improve HVM performance? The HAP >>>> tables still remain fragmented after ballooning. >>>> >>> That's the other side of this problem and orthogonal to this patch >>> series. It should be fixed separately on the hypervisor side, presumably >>> with similar mechanism to coalesce HAP table in hypervisor. >> You can't rearrange the memory of any domain with passthrough, or any >> subregion which is mapped by another domain. Even if the underlying >> pages are in order, > That's fine. This work still improves things for plenty of other > domains. > > I suspect with a suitable amount of cunning it might be possible to do > this for domains with passthrough using smmu. Whether it is worth the > time and effort (since I certain concede it won't be easy) I don't know. x86 IOMMUs do not support restarable faults, and given the timing constraints in the PCI spec, there is no obvious way to gain support like this. As a result, it is impossible for Xen to move a page, while maintaining DMA read and write coherency for devices. ~Andrew