On Mon, Nov 8, 2010 at 5:45 PM, "Oleg A. Arkhangelsky" <sysoleg@xxxxxxxxx> wrote: > > > 08.11.2010, 09:34, "Changli Gao" <xiaosuo@xxxxxxxxx>: > >> When conntrack is enabled, we can cache dst_entry into the >> corresponding conntrack to eliminate the subsequence >> ip_route_input_noref() calls for the same connection. The current > > Any performance gains? How much? > I have tested between my host OS and virtual OS runs on virtualbox. Here is the result. xiaosuo@gentux src $ netperf -t TCP_RR -H 10.13.150.50 -l 60 TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.13.150.50 (10.13.150.50) port 0 AF_INET Local /Remote Socket Size Request Resp. Elapsed Trans. Send Recv Size Size Time Rate bytes Bytes bytes bytes secs. per sec 16384 87380 1 1 60.00 5625.71 16384 87380 xiaosuo@gentux src $ netperf -t TCP_RR -H 10.13.150.50 -l 60 TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.13.150.50 (10.13.150.50) port 0 AF_INET Local /Remote Socket Size Request Resp. Elapsed Trans. Send Recv Size Size Time Rate bytes Bytes bytes bytes secs. per sec 16384 87380 1 1 60.00 5614.79 16384 87380 The former is with nf_rtcache enabled. -- Regards, Changli Gao(xiaosuo@xxxxxxxxx) -- To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
