Messages in this thread | | | From | Paul Menage <> | Date | Tue, 13 Sep 2011 11:46:29 -0700 | Subject | Re: [PATCH] per-cgroup tcp buffer limitation |
| |
On Tue, Sep 13, 2011 at 11:11 AM, Glauber Costa <glommer@parallels.com> wrote: > > What if they are all updated under the same lock ?
Right, that would be the kind of optimization that would remove the need for worrying about whether or not to account it. It would probably mean creating some memcg-specific structures like res-counters that could handle multiple values, since you'd need to update both the kernel charge and the total charge, in this cgroup *and* its ancestors.
Paul
| |