On Tue, 9 Oct 2012, Steven Rostedt wrote: > On Tue, 2012-10-09 at 18:19 +0200, Thomas Gleixner wrote: > > > > > I've started looking at playing with the NAPI code again, and trying to > > > see if I can add an ENAPI interface (Even Newer API), where the driver > > > uses its own interrupt thread, and instead of having the polling in the > > > network softirq, it can do the polling in its own thread. > > > > It's pretty close to the behaviour I enforced with this change. Let's > > play with that and figure out what influence it has on the network > > throughput performance on RT. That needs probably a different > > scheduling scheme than what Carsten needs for his deterministic > > behaviour. > > > > I was actually looking at the change for mainline, not for -rt ;-) I know, but you can utilize RT for figuring out what kind of performance impact (in whatever direction) this modus operandi has. That gives us a better understanding and hopefully improvements for RT, but at the same time a lot of insight in how we should handle this scenario on a non RT kernel. You might try to make the softirq split lock scheme work in CONFIG_RT_BASE as this gives us a way better comparison to mainline behaviour. Thanks, tglx -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
