Re: aim7 performance regression by commit 5a50508 report from LKP

[Ingo Molnar <mingo@kernel.org>]

* Yuanhan Liu <yuanhan.liu@linux.intel.com> wrote:

> [...]

Very nice measurements and analysis, thanks!

> As stated above, anybody can have a chance to own the lock in 
> mutex once somebody release the lock. Well, there is only one 
> to own the lock in rwsem write lock, and the one is known 
> already: the one in the head of wait list. That would result 
> to more contention in rwsem write lock case, especially if the 
> one _will_ own the lock is not running now.

I think we should allow lock-steal between rwsem writers - that 
will not hurt fairness as most rwsem fairness concerns relate to 
reader vs. writer fairness.

Am I correct to assume that all relevant users in this workload 
are down_write() users?

You can see the type of lock use in:

   perf record -g
   perf report

I bet that allowing rwsem writer lock-steal would improve other 
workloads as well.

Thanks,

	Ingo