Just so you know the context, I'm coming at this from the point of view of an embedded call server designer. Mark Hahn wrote:Fairness is good because it promotes predictability. See the "deterministic" section below. If you have nice 19 be sufficiently low priority, then the difference between "using cpu if otherwise idle" and "gets a little bit of cpu even if not totally idle" is unimportant. Starvation is a very *bad* thing when you don't want it. In my environment, latency *matters*. If a packet doesn't get processed in time, you drop it. With mainline it can be quite tricky to tune the latency, especially when you don't want to resort to soft realtime because you don't entirely trust the code thats running (because it came from a third party vendor). Determinism is really important. It almost doesn't matter what the behaviour is, as long as we can predict it. We model the system to determine how to tweak the system (niceness, sched policy, etc.), as well as what performance numbers we can advertise. If the system is non-deterministic, it makes this modelling extremely difficult--you end up having to give up significant performance due to worst-case spikes. If the system is deterministic, it makes it much easier to predict its actions. Chris -
| Greg Kroah-Hartman | [PATCH 001/196] Chinese: Add the known_regression URI to the HOWTO |
| Linus Torvalds | Re: Dual-Licensing Linux Kernel with GPL V2 and GPL V3 |
| Andrew Morton | 2.6.25-mm1 |
| Vladislav Bolkhovitin | Re: Integration of SCST in the mainstream Linux kernel |
git: | |
| David Miller | [GIT]: Networking |
| David Miller | Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Gerrit Renker | [PATCH 0/37] dccp: Feature negotiation - last call for comments |
| Natalie Protasevich | [BUG] New Kernel Bugs |
