Re: [Xen-devel] V4V

[Stefano Stabellini <stefano.stabellini@xxxxxxxxxxxxx>]

On Thu, 24 May 2012, Jean Guyader wrote:
> Some of the downsides to using the shared memory grant method:
> ÂÂÂ - This method imposes an implicit ordering on domain destruction.
> ÂÂÂÂÂ When this ordering is not honored the grantor domain cannot shutdown
> ÂÂÂÂÂ while the grantee still holds references. In the extreme case where
> ÂÂÂÂÂ the grantee domain hangs or crashes without releasing it grantedÂÂÂ
> ÂÂÂÂÂ pages, both domains can end up hung and unstoppable (the DEADBEEFÂÂ
> ÂÂÂÂÂ issue).ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ

Is it still true? This looks like a serious issue.


> ÂÂÂ - You can't trust any ring structures because the entire set of pages
> ÂÂÂÂÂ that are granted are available to be written by the either guest.ÂÂ
> ÂÂÂ - The PV connect/disconnect state-machine is poorly implemented.ÂÂÂÂÂ
> ÂÂÂÂÂ There's no trivial mechanism to synchronize disconnecting/reconnecting
> ÂÂÂÂÂ and dom0 must also allow the two domains to see parts of xenstoreÂÂÂÂ
> ÂÂÂÂÂ belonging to the other domain in the process.ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ

We are starting to see this problem, trying to setup driver domains with
libxl.


> ÂÂÂ - Using the grant-ref model and having to map grant pages on eachÂÂÂÂÂÂ
> ÂÂÂÂÂ transfer cause updates to V->P memory mappings and thus leads toÂÂÂÂÂ
> ÂÂÂÂÂ TLB misses and flushes (TLB flushes being expensive operations).ÂÂÂÂÂ

[snip]

> I've done some benchmarks on V4V and libchan and the results were
> pretty close between the the two if you use the same buffer size in both 
> cases.

It is strange that you cannot see any performance advantages using v4v. I
was expecting quite a difference, especially on new numa machines.

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel