On Tue, 2015-06-09 at 10:45 -0700, Martin KaFai Lau wrote: > On Tue, Jun 09, 2015 at 10:06:25AM -0700, Eric Dumazet wrote: > > I've been working on this, but still can get the bug triggering in > > tcp_fragment(), no matter what (Neal patch , yours, mine...) > Can you describe the test case that can reproduce it?
This might not be easy : I used a 40Gb testbed and following. Warning triggers in about 30 minutes, but this might be related to some unrelated traffic. echo 4 >/proc/sys/net/ipv4/tcp_min_tso_segs echo 0 >/proc/sys/kernel/timer_migration echo fq >/proc/sys/net/core/default_qdisc tc qd replace dev eth1 root mq ./super_netperf 1500 --google-pacing-rate 3028000 -H lpaa24 -l 10000 & You might implement the pacing stuff using regular netperf with for ETH in eth1 do tc qd del dev $ETH root 2>/dev/null tc qd add dev $ETH root handle 1: mq for i in `seq 1 16` do slot=$( printf %x $(( i )) ) tc qd add dev $ETH parent 1:$slot fq maxrate 3028000 done done (Change eth1 by eth0 or something, and 16 by number of TX queues.) -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
