[PATCH] randomized delay in locking primitives, take 2

Slawa Olhovchenkov slw at zxy.spb.ru
Mon Aug 1 11:25:09 UTC 2016

On Mon, Aug 01, 2016 at 02:16:59PM +0300, Andriy Gapon wrote:

> Mateusz,
> just out of curiosity, have you tried to explore alternative spinlock
> implementations like a ticket lock?   It would be interesting to see if
> there are any improvements to be gained there.

Effective ticket lock implementation as I see limited to 256 (255?)
concurent locks. And anyway may be need randomize delay (QPI bus on
x86 have very limited performance).

More information about the freebsd-current mailing list