"Rafael J. Wysocki" <rjw@xxxxxxx> writes: > Well, I'd say it's necessary for correctness, perhaps not for the CPU, but in > general. If Y is the max, then the subsystem that requested X may easily > starve whoever requested the Y by using all of the bandwidth it asked for. Hmm.. congestion is an issue for latency requests as well. I've viewed the current PM QoS handling system level requests. If we want some kind of resource reservation/provisioning that could probably be layered on top of system level requests, no? --Antti _______________________________________________ linux-pm mailing list linux-pm@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/linux-pm
