Messages in this thread | | | Date | Mon, 22 Feb 2010 13:15:49 -0800 (PST) | From | David Rientjes <> | Subject | Re: [RFC] [PATCH 0/2] memcg: per cgroup dirty limit |
| |
On Mon, 22 Feb 2010, Vivek Goyal wrote:
> dirty_ratio is easy to configure. One system wide default value works for > all the newly created cgroups. For dirty_bytes, you shall have to > configure each and individual cgroup with a specific value depneding on > what is the upper limit of memory for that cgroup. >
Agreed, it makes sense for each memcg to have a dirty_ratio that defaults to whatever vm_dirty_ratio does, and export that constant via linux/writeback.h. dirty_bytes would then use the same semantics as globally so that if it is set to 0, the finer-granuality is disabled by default and we use memcg->dirty_ratio instead.
> Secondly, memory cgroup kind of partitions global memory resource per > cgroup. So if as long as we have global dirty ratio knobs, it makes sense > to have per cgroup dirty ratio knob also. >
It has a good default, too: whatever ratio of memory that was allowed to be dirty before the memcg limit was set is still allowed by default.
| |