These warnings pops up a few times a second when a relatively high load is imposed on 10Gbit ethernet, and causing performance degradation. Looking into code, it seems to be related to segmentation offload, GSO, and checksums. The igb and ixgbe modules are out-of-kernel versions from sourceforge. IGB 3.3.6 and IXGBE 3.7.17, latest at the moment. When i've fallen back to the 2.6.39.4 with the same modules, the problems disappear. [ 826.097369] ------------[ cut here ]------------ [ 826.097372] WARNING: at net/core/dev.c:1886 skb_gso_segment+0x2ab/0x320() [ 826.097374] ixgbe: caps=(0x72114bb3, 0x0) len=3150 data_len=0 ip_summed=0 [ 826.097375] Modules linked in: ixgbe igb [ 826.097377] Pid: 0, comm: swapper Tainted: G W 3.0.18 #2 [ 826.097379] Call Trace: [ 826.097379] <IRQ> [<ffffffff8104162c>] ? warn_slowpath_common+0x6c/0xa0 [ 826.097383] [<ffffffff81041715>] ? warn_slowpath_fmt+0x45/0x50 [ 826.097386] [<ffffffff8132353b>] ? skb_gso_segment+0x2ab/0x320 [ 826.097389] [<ffffffff81324f1e>] ? dev_hard_start_xmit+0x21e/0x5f0 [ 826.097391] [<ffffffff8133af53>] ? sch_direct_xmit+0xf3/0x1c0 [ 826.097393] [<ffffffff81325445>] ? dev_queue_xmit+0x155/0x5a0 [ 826.097395] [<ffffffff81274b0a>] ? bond_start_xmit+0x3da/0x470 [ 826.097397] [<ffffffff81366e38>] ? tcp_v4_rcv+0x4c8/0x740 [ 826.097400] [<ffffffff81324f62>] ? dev_hard_start_xmit+0x262/0x5f0 [ 826.097402] [<ffffffff81345db5>] ? ip_local_deliver+0x85/0x110 [ 826.097404] [<ffffffff81325696>] ? dev_queue_xmit+0x3a6/0x5a0 [ 826.097406] [<ffffffff8138a53d>] ? br_dev_queue_push_xmit+0x4d/0x70 [ 826.097408] [<ffffffff8138b11b>] ? br_handle_frame_finish+0x10b/0x1c0 [ 826.097410] [<ffffffff8138b371>] ? br_handle_frame+0x1a1/0x210 [ 826.097412] [<ffffffff81274510>] ? bond_set_carrier+0xa0/0xa0 [ 826.097414] [<ffffffff8138b1d0>] ? br_handle_frame_finish+0x1c0/0x1c0 [ 826.097416] [<ffffffff81322d8d>] ? __netif_receive_skb+0x12d/0x370 [ 826.097419] [<ffffffff81323e48>] ? netif_receive_skb+0x58/0x80 [ 826.097421] [<ffffffff81324249>] ? dev_gro_receive+0x1c9/0x2c0 [ 826.097423] [<ffffffff81324943>] ? napi_gro_receive+0xa3/0xc0 [ 826.097427] [<ffffffffa0064108>] ? ixgbe_poll+0x3f8/0x13f0 [ixgbe] [ 826.097429] [<ffffffff81070800>] ? hotplug_cfd+0x10/0x40 [ 826.097431] [<ffffffff81324541>] ? net_rx_action+0x81/0x120 [ 826.097433] [<ffffffff81046f78>] ? __do_softirq+0x98/0x120 [ 826.097435] [<ffffffff8107ed2a>] ? handle_irq_event_percpu+0x7a/0x140 [ 826.097437] [<ffffffff813a228c>] ? call_softirq+0x1c/0x30 [ 826.097439] [<ffffffff81003f2d>] ? do_softirq+0x4d/0x80 [ 826.097441] [<ffffffff81047266>] ? irq_exit+0x96/0xc0 [ 826.097443] [<ffffffff81003dec>] ? do_IRQ+0x5c/0xd0 [ 826.097445] [<ffffffff813a0d93>] ? common_interrupt+0x13/0x13 [ 826.097446] <EOI> [<ffffffff81009738>] ? mwait_idle+0x58/0x80 [ 826.097450] [<ffffffff810009ec>] ? cpu_idle+0x4c/0x90 [ 826.097452] [<ffffffff8154485b>] ? start_kernel+0x2b0/0x2bb [ 826.097453] ---[ end trace f7478101639067dd ]---
Please reproduce with current kernel.
Lets close this old one maybe. Most probably not valid anymore.