On Mar 7, 2012, at 2:33 AM, Jan Beulich wrote:

quoted

quoted

quoted

On 06.03.12 at 18:20, Konrad Rzeszutek Wilk [off-list ref] wrote:

-> XENBUS_MAX_RING_PAGES - why 2? Why not 4? What is the optimal
default size for SSD usage? 16?

What do SSDs have to do with a XenBus definition? Imo it's wrong (and
unnecessary) to introduce a limit at the XenBus level at all - each driver
can do this for itself.

As to the limit for SSDs in the block interface - I don't think the number
of possibly simultaneous requests has anything to do with this. Instead,
I'd expect the request number/size/segments extension that NetBSD
apparently implements to possibly have an effect.

Jan

There's another problem here that I brought up during the Xen
Hack-a-thon.  The ring macros require that the ring element count
be a power of two.  This doesn't mean that the ring will be a power
of 2 pages in size.  To illustrate this point, I modified the FreeBSD
blkback driver to provide negotiated ring stats via sysctl.

Here's a connection to a Windows VM running the Citrix PV drivers:

    dev.xbbd.2.max_requests: 128
    dev.xbbd.2.max_request_segments: 11
    dev.xbbd.2.max_request_size: 45056
    dev.xbbd.2.ring_elem_size: 108  <= 32bit ABI
    dev.xbbd.2.ring_pages: 4
    dev.xbbd.2.ring_elements: 128
    dev.xbbd.2.ring_waste: 2496

Over half a page is wasted when ring-page-order is 2.  I'm sure you
can see where this is going.  :-)

Here are the limits published by our backend to the XenStore:

    max-ring-pages = "113"
    max-ring-page-order = "7"
    max-requests = "256"
    max-request-segments = "129"
    max-request-size = "524288"

Because we allow so many concurrent, large requests in our product,
the ring wastage really adds up if the front end doesn't support
the "ring-pages" variant of the extension.  However, you only need
a ring-page-order of 3 with this protocol to start seeing pages of
wasted ring space.

You don't really want to negotiate "ring-pages" either.  The backends
often need to support multiple ABIs.  I can easily construct a set
of limits for the FreeBSD blkback driver which will cause the ring
limits to vary by a page between the 32bit and 64bit ABIs.

With all this in mind, the backend must do a dance of rounding up,
taking the max of the ring sizes for the different ABIs, and then
validating the front-end published limits taking its ABI into
account.  The front-end does some of this too.  Its way too messy
and error prone because we don't communicate the ring element limit
directly.

"max-ring-element-order" anyone? :-)

--
Justin