Messages in this thread | | | Subject | Re: Spinlocks: Factor our GENERIC_LOCKBREAK in order to avoid spin with irqs disable | From | Petr Tesarik <> | Date | Thu, 26 Jun 2008 11:17:47 +0200 |
| |
On Wed, 2008-06-25 at 19:51 -0700, Jeremy Fitzhardinge wrote: > [...] > I'm experimenting with adding pvops hook to allow you to put in new > spinlock implementations on the fly. If nothing else, it will be useful > for experimenting with different algorithms. But it definitely seems > like the old unfair lock algorithm played much better with a virtual > environment, because the next cpu to get the lock is the next one the > scheduler gives time, rather than dictating an order - and the scheduler > should mitigate the unfairness that ticket locks were designed to solve.
We really should paravirtualize spin locks, because there's always something better to do than just burn time spinning. But in a non-virtualized environment, tickets (or a similar scheme) should be preserved.
We should probably re-think the whole locking scheme, because spinlocks were designed to be held for a short period of time. This was a fair assumption when they were introduced, but obviously it is now false in many cases (such as virtualization).
Ticket-based spinlocks have actually already changed the original design, so why not implement a generic "lock scheduler" on top of spinlock_t and rwlock_t?
Petr Tesarik
| |