On Wed, Nov 18, 2015 at 05:22:56PM +0100, Michal Hocko wrote:
> On Mon 16-11-15 13:18:10, Johannes Weiner wrote:
> > What load would you test and what would be the baseline to compare it
> > to?
>
> It seems like netperf with a stream load running in a memcg with no
> limits vs. in root memcg (and no other cgroups) should give at least a
> hint about the runtime overhead, no?
Comparing root vs. dedicated group generally doesn't make sense since
you either need containment or you don't. It makes more sense to test
both times inside a memory-controlled cgroup, one with a regular boot,
one with cgroup.memory=nosocket.
So I ran perf record -g -a netperf -t TCP_STREAM multiple times inside
a memory-controlled cgroup, but mostly mem_cgroup_charge_skmem() does
not show up in the profile at all. Once it was there with 0.00%.
I ran another test that downloads the latest kernel image from
kernel.org at 13MB/s (on my i5 laptop) and it looks like this:
0.02% 0.01% irq/44-iwlwifi [kernel.kallsyms] [k] mem_cgroup_charge_skmem
|
---mem_cgroup_charge_skmem
__sk_mem_schedule
tcp_try_rmem_schedule
tcp_data_queue
tcp_rcv_established
tcp_v4_do_rcv
tcp_v4_rcv
ip_local_deliver
ip_rcv
__netif_receive_skb_core
__netif_receive_skb
netif_receive_skb_internal
napi_gro_complete
The runs vary too much for this to be measurable in elapsed time.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>