Robert, Very interesting results - i would like to comment; but let me post my results first.
I recompiled all kernels from scratch and made sure that flow control was off in all cases. I still test with two flows .. will get to something like 32K flows perhaps tommorow (keeping my fingers crossed that i will have the hardware and time): kernel 2.6.11.7 (native e1000): 446Kpps kernel 2.6.14 (native e1000): 452kpps Kernel 2.6.14 + e1000-6.2.15 prefetch off copybreak off: 451Kpps kernel 2.6.14 + e1000-6.2.15 prefetch off copybreak on: 450Kpps Kernel 2.6.14 + e1000-6.2.15 prefetch on copybreak off: 460Kpps kernel 2.6.14 + e1000-6.2.15 as is (prefetch on copybreak on): 485Kpps Conclusion: ----------- 1) Let me say that there is performance improvement and it has to do with prefetching. I agree with Roberts analysis that only _some_ prefetches are valuable. Robert has narrowed them down, I will try to validate further. *** Note, this was my contention as well all along against this patch based on experiences from D Mosbergers changes. 2) copybreak _does not_ add any value. In my case it doesnt seem to harm but i dont see why i should turn it on at all. Note, however that as soon as i turn copybreak off, the numbers go down ;-> Now for some obtuse theory as to why this happens: I think the reason that prefetch + copybreak together have higher numbers is because the copybreak code provides a cycle-mask that makes the prefetches useful. i.e if you used X cycles more before using the prefetched data, you will end up benefiting from the prefetch. It doesnt matter if the code was doing copybreak or just looped killing a few cycles. so copybreak is just a useless cycle chewer. And this is why ***prefetching is dangerous***. To prove this theory i am gonna run tests that add a simple loop which counts down from some number X to 0. I will try to increment X algorithmically and see where it becomes useful etc. Hopefully i can do this quickly before i get pulled cheers, jamal - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
