Matthew Dillon dillon at
Tue Jan 11 17:01:19 PST 2011

    I agree, I don't think it would be beneficial to spend it on adding
    work for > 63 cores at this time.  We have plenty to do just tuning the
    system up for the 48 cores we can test on now.

    Priorities for the project:

	* Interrupt routing.
	* SMP performance (vm_token, other semi-global tokens).
	* Virtualization Support (drivers et all).
	* Stabilization / bug-fixing.

    Nice things to have that are within reach:

	* More reliable USB infrastructure.
	* continuing work on dmirror, soft-raid, etc (storage subsystems).
	* HAMMER filesystem compression.


More information about the Kernel mailing list