On Fri, 2011-02-04 at 14:09 +0100, Peter Zijlstra wrote: > > You can do that by keeping ->bw_to_write in task_struct and normalize it > by the estimated bdi bandwidth (patch 5), that way, when you next > increment it it will turn out to be lower and the wait will be shorter. The down-side is of course that time will leak from the system on exit, since its impossible to map back to a bdi. -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html