On 18/12/15 15:47, Ian Campbell wrote:
> On Fri, 2015-12-18 at 14:09 +, David Vrabel wrote:
>> This series adds the qrwlocks from Linux.
>
> This really means "replace existing rwlock implementation with qrwlocks",
> right? i.e. you aren't actually adding a new set of rwlock primitives here,
>
On Fri, 2015-12-18 at 14:09 +, David Vrabel wrote:
> This series adds the qrwlocks from Linux.
This really means "replace existing rwlock implementation with qrwlocks",
right? i.e. you aren't actually adding a new set of rwlock primitives here,
you are just switching out the implementation beh
This series adds the qrwlocks from Linux. These are fair; under
contention both readers and writers will be queued and obtain the lock
in FIFO order (due to the fairness of the internal ticket lock).
The implementation is all in C and thus architecture independent.
Compared to the Linux implemen