>>> On 19.05.15 at 12:27, wrote:
> On 18/05/15 16:49, Jan Beulich wrote:
> On 18.05.15 at 17:33, wrote:
>>> On 18/05/15 11:16, Jan Beulich wrote:
>>> On 14.05.15 at 13:21, wrote:
> void _spin_lock(spinlock_t *lock)
> {
> +spinlock_tickets_t tickets = { .tail = 1, };
>>>
On 18/05/15 16:49, Jan Beulich wrote:
On 18.05.15 at 17:33, wrote:
>> On 18/05/15 11:16, Jan Beulich wrote:
>> On 14.05.15 at 13:21, wrote:
void _spin_lock(spinlock_t *lock)
{
+spinlock_tickets_t tickets = { .tail = 1, };
>>>
>>> This breaks the build on gcc 4.3.x (d
>>> On 18.05.15 at 17:33, wrote:
> On 18/05/15 11:16, Jan Beulich wrote:
> On 14.05.15 at 13:21, wrote:
>>> void _spin_lock(spinlock_t *lock)
>>> {
>>> +spinlock_tickets_t tickets = { .tail = 1, };
>>
>> This breaks the build on gcc 4.3.x (due to tail being a member of an
>> unnamed st
On 18/05/15 11:16, Jan Beulich wrote:
On 14.05.15 at 13:21, wrote:
>> void _spin_lock(spinlock_t *lock)
>> {
>> +spinlock_tickets_t tickets = { .tail = 1, };
>
> This breaks the build on gcc 4.3.x (due to tail being a member of an
> unnamed structure member of a union).
I don't have a
>>> On 14.05.15 at 13:21, wrote:
> void _spin_lock(spinlock_t *lock)
> {
> +spinlock_tickets_t tickets = { .tail = 1, };
This breaks the build on gcc 4.3.x (due to tail being a member of an
unnamed structure member of a union).
Jan
___
Xen-deve
At 12:21 +0100 on 14 May (1431606100), David Vrabel wrote:
> Replace the byte locks with ticket locks. Ticket locks are: a) fair;
> and b) peform better when contented since they spin without an atomic
> operation.
>
> The lock is split into two ticket values: head and tail. A locker
> acquires
Replace the byte locks with ticket locks. Ticket locks are: a) fair;
and b) peform better when contented since they spin without an atomic
operation.
The lock is split into two ticket values: head and tail. A locker
acquires a ticket by (atomically) increasing tail and using the
previous tail va
