On Fri, May 13, 2011 at 11:53:08AM +0200, Michal Hocko wrote: > On Thu 12-05-11 16:53:55, Johannes Weiner wrote: > > A page charged to a memcg is linked to a lru list specific to that > > memcg. At the same time, traditional global reclaim is obvlivious to > > memcgs, and all the pages are also linked to a global per-zone list. > > > > This patch changes traditional global reclaim to iterate over all > > existing memcgs, so that it no longer relies on the global list being > > present. > > At LSF we have discussed that we should keep a list of over-(soft)limit > cgroups in a list which would be the first target for reclaiming (in > round-robin fashion). If we are note able to reclaim enough from those > (the list becomes empty) we should fallback to the all groups reclaim > (what you did in this patchset). This would be on top or instead of 6/6. This, 3/6, is indepent of soft limit reclaim. It is mainly in preparation to remove the global LRU. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>