Messages in this thread | | | Date | Thu, 10 Oct 2013 08:27:41 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH 0/6] Optimize the cpu hotplug locking -v2 |
| |
* Andrew Morton <akpm@linux-foundation.org> wrote:
> On Tue, 08 Oct 2013 12:25:05 +0200 Peter Zijlstra <peterz@infradead.org> wrote: > > > The current cpu hotplug lock is a single global lock; therefore > > excluding hotplug is a very expensive proposition even though it is > > rare occurrence under normal operation. > > > > There is a desire for a more light weight implementation of > > {get,put}_online_cpus() from both the NUMA scheduling as well as the > > -RT side. > > > > The current hotplug lock is a full reader preference lock -- and thus > > supports reader recursion. However since we're making the read side > > lock much cheaper it is the expectation that it will also be used far > > more. Which in turn would lead to writer starvation. > > > > Therefore the new lock proposed is completely fair; albeit somewhat > > expensive on the write side. This in turn means that we need a > > per-task nesting count to support reader recursion. > > This is a lot of code and a lot of new complexity. It needs some pretty > convincing performance numbers to justify its inclusion, no?
Should be fairly straightforward to test: the sys_sched_getaffinity() and sys_sched_setaffinity() syscalls both make use of get_online_cpus()/put_online_cpus(), so a testcase frobbing affinities on N CPUs in parallel ought to demonstrate scalability improvements pretty nicely.
[ It's not just about affinities: in particular sys_sched_getaffinity() also gets used as a NR_CPUS runtime detection method in apps, so it matters to regular non-affine loads as well. ]
Thanks,
Ingo
| |