On Thu, Mar 17, 2011 at 08:46:23AM -0700, Curt Wohlgemuth wrote: > But if one of one's goals is to provide some sort of disk isolation based on > cgroup parameters, than having at most one stream of write requests > effectively neuters the IO scheduler. If you use any kind of buffered I/O you already fail in that respect. Writeback from balance_dirty_page really is just the wort case right now with more I/O supposed to be handled by the background threads. So if you want to implement isolation properly you need to track the originator of the I/O between the copy to the pagecache and actual writeback. -- 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>