First off, thanks for your work on this! Alex Hornung wrote:
As previously stated this might be a limited approach, but nonetheless it adds features without much overhead or complication. What I would like to hear is suggestions on what to do; do we want stackable (hierarchical) policies? if so, is the proposed approach good enough? if not, what other possibilities are there? what use cases are not covered by the suggested approach but are solved in other possibilites/approaches?
I think that we don't understand the whole matter yet. Probably it is too early to come up with a definitive design, so I suggest only implementing the framework for one scheduler per disk and implementing schedulers for this framework. After a while we might understand requirements and scheduler design better and then can reason about how a possible re-design for stackable/interacting schedulers might look like.
cheers simon -- <3 the future +++ RENT this banner advert +++ ASCII Ribbon /"\ rock the past +++ space for low €€€ NOW!1 +++ Campaign \ / Party Enjoy Relax | http://dragonflybsd.org Against HTML \ Dude 2c 2 the max ! http://golden-apple.biz Mail + News / \
