These boot blips are not the biggest issue in the world. But, it is
fully under the guest's control and I think the guest has some
responsibility to provide *some* mitigation for it.
It sounds more like an exercise in preliminary optimization at this
point. If it's a real problem we can still worry about it later.
1. Do background acceptance, as opposed to relying 100% on demand-driven
acceptance. Guarantees a limited window in which blips can occur.
Like Kirill wrote this was abandoned because it always allocates all
memory on the host even if the guest doesn't need it.
2. Do acceptance based on user input, like from sysfs.
You can easily do that by running "memhog" at boot. No need for anything
in the kernel.
BTW I believe this is also configurable at the guest BIOS level.
3. Add a command-line argument to accept everything up front, or at
least before userspace runs.
Same.
4. Add some statistic for how much unaccepted memory remains.
Yes that makes sense. We should have statistic counters for all of this.
Also I agree with your suggestion that we should get the slow path out
of the zone locks/interrupt disable region. That should be easy enough
and is an obvious improvement.
-Andi