lkml.org 
[lkml]   [2011]   [Dec]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] virtio-ring: Use threshold for switching to indirect descriptors
On 12/06/2011 02:03 PM, Rusty Russell wrote:
> On Tue, 06 Dec 2011 11:58:21 +0200, Avi Kivity <avi@redhat.com> wrote:
> > On 12/06/2011 07:07 AM, Rusty Russell wrote:
> > > Yes, but the hypervisor/trusted party would simply have to do the copy;
> > > the rings themselves would be shared A would say "copy this to/from B's
> > > ring entry N" and you know that A can't have changed B's entry.
> >
> > Sorry, I don't follow. How can the rings be shared? If A puts a gpa in
> > A's address space into the ring, there's no way B can do anything with
> > it, it's an opaque number. Xen solves this with an extra layer of
> > indirection (grant table handles) that cost extra hypercalls to map or
> > copy.
>
> It's not symmetric. B can see the desc and avail pages R/O, and the
> used page R/W. It needs to ask the something to copy in/out of
> descriptors, though, because they're an opaque number, and it doesn't
> have access. ie. the existence of the descriptor in the ring *implies*
> a grant.
>
> Perhaps this could be generalized further into a "connect these two
> rings", but I'm not sure. Descriptors with both read and write parts
> are tricky.

Okay, I was using a wrong mental model of how this works. B must be
aware of the translation from A's address space into B. Both qemu and
the kernel can do this on their own, but if B is another guest, then it
cannot do this except by calling H.

vhost-copy cannot work fully transparently, because you need some memory
to copy into. Maybe we can have a pci device with a large BAR that
contains buffers for copying, and also a translation from A addresses
into B addresses. It would work something like this:

A prepares a request with both out and in buffers
vhost-copy allocates memory in B's virtio-copy BAR, copies (using a
DMA engine) the out buffers into it, and rewrites the out descriptors to
contain B addresses
B services the request, and updates the in addresses in the
descriptors to point at B memory
vhost-copy copies (using a DMA engine) the in buffers into A memory

> > > I'm just not sure how the host would even know to hint.
> >
> > For JBOD storage, a good rule of thumb is (number of spindles) x 3.
> > With less, you might leave an idle spindle; with more, you're just
> > adding latency. This assumes you're using indirects so ring entry ==
> > request. The picture is muddier with massive battery-backed RAID
> > controllers or flash.
> >
> > For networking, you want (ring size) * min(expected packet size, page
> > size) / (link bandwidth) to be something that doesn't get the
> > bufferbloat people after your blood.
>
> OK, so while neither side knows, the host knows slightly more.
>
> Now I think about it, from a spec POV, saying it's a "hint" is useless,
> as it doesn't tell the driver what to do with it. I'll say it's a
> maximum, which keeps it simple.
>

Those rules of thumb always have exceptions, I'd say it's the default
that the guest can override.

--
error compiling committee.c: too many arguments to function



\
 
 \ /
  Last update: 2011-12-07 14:41    [W:0.167 / U:0.192 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site