| > So here are the stats using iperf: | > Test 2.6.19rc6+ian | > 2.6.20-acme20 | > Direct connect 87 Mbits 36 Mbits | > Through a Linux router (1.2 ms rtt) 36 Mbit 200 kbits | > (yes that is correct!) | > Through netem (100 ms rtt, 5% loss) 130 kbits 116 kbits (OK) | > | I've been trying to track this down to any individual patch and I'm | going crazy! With my code (2.6.19rc6+my patches) now I'm getting the | same bad numbers as for 2.6.20-acme20 I can confirm this - it seems sometimes as if the code in a fuzzy way needs to `warm up'. Also I can not test at home with my older equipment - DCCP is too demanding on CPU speed; the top performance even with CCID2 is 15Mbits/sec. Therefore the more experience/performance reports come in, the better for understanding what is going on. - To unsubscribe from this list: send the line "unsubscribe dccp" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html