Re: Performance of VSTATE_ASSERT_UNLOCKED

["J. Hannken-Illjes" <hannken%eis.cs.tu-bs.de@localhost>]

> On 12. Sep 2017, at 20:52, Joerg Sonnenberger <joerg%bec.de@localhost> wrote:
> 
> Hello Juergen,
> the new VSTATE_ASSERT_UNLOCKED code you added to genfs_lock is very
> heavy as it significantly increases lock contention for something
> already highly contended. I'd like to push the lock down to critical
> cases and try to avoid it for common cases.
> 
> Thoughts?
> 
> Joerg
> <state-assert-perf.diff>

Looks good to me, cannot test anything as I am on vacation.

Please commit and request pullup to -8.

--
J. Hannken-Illjes - hannken%eis.cs.tu-bs.de@localhost - TU Braunschweig (Germany)