Re: [PATCH 2/3] sched, timer: Use atomics for thread_group_cputimer to improve scalability

[Jason Low <jason.low2@hp.com>]

On Wed, 2015-04-15 at 07:23 -0700, Davidlohr Bueso wrote:
> On Tue, 2015-04-14 at 16:09 -0700, Jason Low wrote:
> > While running a database workload, we found a scalability issue with itimers.
> > 
> > Much of the problem was caused by the thread_group_cputimer spinlock.
> > Each time we account for group system/user time, we need to obtain a
> > thread_group_cputimer's spinlock to update the timers. On larger systems
> > (such as a 16 socket machine), this caused more than 30% of total time
> > spent trying to obtain this kernel lock to update these group timer stats.
> > 
> > This patch converts the timers to 64 bit atomic variables and use
> > atomic add to update them without a lock. With this patch, the percent
> > of total time spent updating thread group cputimer timers was reduced
> > from 30% down to less than 1%. 
> 
> What does 30% less time spent dealing with the thread_group_cputimer's
> spinlock buy us? iow, does this help DB benchmark throughput or such?

Yes, this also helps increase throughput since the scalability issue
causes a performance degradation in the database workload. I currently
don't have the exact  numbers though.