Re: [PATCH v4 09/14] memcg: kmem accounting lifecycle management

2012-10-16 Thread Kamezawa Hiroyuki
(2012/10/12 17:41), Michal Hocko wrote: On Fri 12-10-12 11:47:17, Glauber Costa wrote: On 10/11/2012 05:11 PM, Michal Hocko wrote: On Mon 08-10-12 14:06:15, Glauber Costa wrote: Because kmem charges can outlive the cgroup, we need to make sure that we won't free the memcg structure while charg

Re: [PATCH v4 09/14] memcg: kmem accounting lifecycle management

2012-10-12 Thread Michal Hocko
On Fri 12-10-12 11:47:17, Glauber Costa wrote: > On 10/11/2012 05:11 PM, Michal Hocko wrote: > > On Mon 08-10-12 14:06:15, Glauber Costa wrote: > >> Because kmem charges can outlive the cgroup, we need to make sure that > >> we won't free the memcg structure while charges are still in flight. > >>

Re: [PATCH v4 09/14] memcg: kmem accounting lifecycle management

2012-10-12 Thread Glauber Costa
On 10/11/2012 05:11 PM, Michal Hocko wrote: > On Mon 08-10-12 14:06:15, Glauber Costa wrote: >> Because kmem charges can outlive the cgroup, we need to make sure that >> we won't free the memcg structure while charges are still in flight. >> For reviewing simplicity, the charge functions will issue

Re: [PATCH v4 09/14] memcg: kmem accounting lifecycle management

2012-10-11 Thread Michal Hocko
On Mon 08-10-12 14:06:15, Glauber Costa wrote: > Because kmem charges can outlive the cgroup, we need to make sure that > we won't free the memcg structure while charges are still in flight. > For reviewing simplicity, the charge functions will issue > mem_cgroup_get() at every charge, and mem_cgro

[PATCH v4 09/14] memcg: kmem accounting lifecycle management

2012-10-08 Thread Glauber Costa
Because kmem charges can outlive the cgroup, we need to make sure that we won't free the memcg structure while charges are still in flight. For reviewing simplicity, the charge functions will issue mem_cgroup_get() at every charge, and mem_cgroup_put() at every uncharge. This can get expensive, ho