Re: regression caused by cgroups optimization in 3.17-rc2
From: Dave Hansen
Date: Tue Sep 09 2014 - 14:23:23 EST
On 09/09/2014 07:50 AM, Johannes Weiner wrote:
> The mctz->lock is only taken when there is, or has been, soft limit
> excess. However, the soft limit defaults to infinity, so unless you
> set it explicitly on the root level, I can't see how this could be
> mctz->lock contention.
>
> It's more plausible that this is the res_counter lock for testing soft
> limit excess - for me, both these locks get inlined into check_events,
> could you please double check you got the right lock?
I got the wrong lock. Here's how it looks after mainline, plus your free_pages_and_swap_cache() patch:
Samples: 2M of event 'cycles', Event count (approx.): 51647128377
+ 60.60% 1.33% page_fault2_processes [.] testcase â
+ 59.14% 0.41% [kernel] [k] page_fault â
+ 58.72% 0.01% [kernel] [k] do_page_fault â
+ 58.70% 0.08% [kernel] [k] __do_page_fault â
+ 58.50% 0.29% [kernel] [k] handle_mm_fault â
+ 40.14% 0.28% [kernel] [k] do_cow_fault â
- 34.56% 34.56% [kernel] [k] _raw_spin_lock â
- _raw_spin_lock â
- 78.11% __res_counter_charge â
res_counter_charge â
try_charge â
- mem_cgroup_try_charge â
+ 99.99% do_cow_fault â
- 10.30% res_counter_uncharge_until â
res_counter_uncharge â
uncharge_batch â
uncharge_list â
mem_cgroup_uncharge_list â
release_pages â
+ 4.75% free_pcppages_bulk â
+ 3.65% do_cow_fault â
+ 2.24% get_page_from_freelist â
> You also said that this cost hasn't been there before, but I do see
> that trace in both v3.16 and v3.17-rc3 with roughly the same impact
> (although my machines show less contention than yours). Could you
> please double check that this is in fact a regression independent of
> 05b843012335 ("mm: memcontrol: use root_mem_cgroup res_counter")?
Here's the same workload on the same machine with only Johannes' revert applied:
- 35.92% 35.92% [kernel] [k] _raw_spin_lock â
- _raw_spin_lock â
- 49.09% get_page_from_freelist â
- __alloc_pages_nodemask â
+ 99.90% alloc_pages_vma â
- 43.67% free_pcppages_bulk â
- 100.00% free_hot_cold_page â
+ 99.93% free_hot_cold_page_list â
- 7.08% do_cow_fault â
handle_mm_fault â
__do_page_fault â
do_page_fault â
page_fault â
testcase â
So I think it's probably part of the same regression.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/