On Tue 04-06-13 23:27:05, Balbir Singh wrote: > > OK, let me summarize. The primary intention is to get rid of the current > > soft reclaim infrastructure which basically bypasses the standard > > reclaim and tight it directly into shrink_zone code. This also means > > that the soft reclaim doesn't reclaim at priority 0 and that it is > > active also for the targeted (aka limit) reclaim. > > > > Does this help? > > > > Yes. What are the limitations of no-priority 0 reclaim? I am not sure I understand the question. What do you mean by limitations? The priority-0 scan was always a crude hack. With a lot of pages in on the LRU it might cause huge big stalls during direct reclaim. There are workloads which benefited from such an aggressive reclaim - e.g. streaming IO but that doesn't justify this kind of reclaim. -- Michal Hocko SUSE Labs -- To unsubscribe from this list: send the line "unsubscribe cgroups" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
