Messages in this thread | | | Date | Tue, 6 Sep 2011 22:09:46 -0300 | From | Glauber Costa <> | Subject | Re: [PATCH] per-cgroup tcp buffer limitation |
| |
On 09/06/2011 10:08 PM, Paul Menage wrote: > On Mon, Sep 5, 2011 at 7:35 PM, Glauber Costa<glommer@parallels.com> wrote: >> This patch introduces per-cgroup tcp buffers limitation. This allows >> sysadmins to specify a maximum amount of kernel memory that >> tcp connections can use at any point in time. TCP is the main interest >> in this work, but extending it to other protocols would be easy.
Hi Paul,
> The general idea of limiting total socket buffer memory consumed by a > cgroup is a fine idea, but I think it needs to be integrated more > closely with the existing kernel memory cgroup tracking efforts, > especially if you're trying to use as generic a name as "kmem" for it. Can you be more specific?
The generic part of kmem cgroup in this patch is quite simple. I think any other patchset would have a very easy time merging things into it. 90 % is sockets.
> > I agree with Kamezawa's comments that you need a lot more documentation. Working on it right now.
| |