On 04/11/2013 12:07 PM, Eric Blake wrote:
On 04/11/2013 09:45 AM, Paolo Bonzini wrote:
Il 11/04/2013 17:35, Michael R. Hines ha scritto:
Nevertheless, the initial "burst" of the bulk phase round is still
important to optimize, and I would like to know if the maintainer
would accept this API for disabling the scan or not
I'm not a maintainer, but every opinion counts... and my opinion is "not
yet". Maybe for 1.6, and only after someone else tried it out. That's
why it's important to merge the code early.
Agreed on that point - it's always easier to add an interface later,
when we have field usage suggesting that it would be useful, than it is
to remove an interface once provided, but where field usage says it is
never tweaked from the default.
Having a knob for disabling zero detection might make sense in the
future, but no need to rush it into 1.5 and regret the design, and no
need to hold up getting RDMA into 1.5 just because of a debate about a
knob that can be deferred to a later release when we've had more time to
play with RDMA.
Agreed, so what about my second proposal?
Disabling zero detection "on demand" if and only if RDMA is enabled
and if and only if chunk registration is disabled?
- Michael
