vrouter kernel oops, needed to reboot compute nodes

Hey,

we are load testing our 1.20 installation with like 50-200 parallel VMs spawnings. Maybe related or not we had today a kernel oops on most of the compute nodes and they only started working after we rebooted all server nodes (not VMs)

[1041796.641356] Write: Encode sandesh vr_interface_req FAILED(4)
[1041814.272462] BUG: unable to handle kernel NULL pointer dereference at (null)
[1041814.288716] IP: [<ffffffffa03e3efe>] vr_nexthop_add+0xee/0xa40 [vrouter]
[1041814.296190] PGD 2362007067 PUD 3690dc5067 PMD 0
[1041814.303985] Oops: 0000 [#1] SMP
[1041814.312422] Modules linked in: vhost_net vhost macvtap macvlan vrouter(OX) sch_fq_codel xt_multiport xt_LOG xt_limit xt_comment dm_multipath scsi_dh nbd kvm_intel ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle xt_tcpudp bridge ip6table_filter ip6_tables iptable_filter ip_tables ebtable_nat ebtables x_tables btrfs raid6_pq xor ufs qnx4 hfsplus hfs minix ntfs msdos jfs xfs libcrc32c ipmi_devintf isofs x86_pkg_temp_thermal intel_powerclamp coretemp kvm gpio_ich crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel ioatdma aes_x86_64 lrw gf128mul glue_helper ablk_helper ipmi_si wmi cryptd acpi_power_meter hpwdt lpc_ich serio_raw hpilo mac_hid bonding 8021q garp stp mrp llc lp parport psmouse ixgbe tg3 dca ptp pps_core hpsa mdio [last unloaded: vrouter]
[1041814.462111] CPU: 3 PID: 16572 Comm: contrail-vroute Tainted: G OX 3.13.0-39-generic #66-Ubuntu
[1041814.498742] Hardware name: HP ProLiant DL380 Gen9, BIOS P89 08/26/2014
[1041814.518731] task: ffff881fcf833000 ti: ffff883fd139a000 task.ti: ffff883fd139a000
[1041814.560085] RIP: 0010:[<ffffffffa03e3efe>] [<ffffffffa03e3efe>] vr_nexthop_add+0xee/0xa40 [vrouter]
[1041814.604351] RSP: 0018:ffff883fd139b708 EFLAGS: 00010287
[1041814.628038] RAX: 0000000000000030 RBX: ffff881f13188c00 RCX: ffff88129b951600
[1041814.676670] RDX: 0000000000000000 RSI: 00000000000001a0 RDI: ffff881fcf0988a0
[1041814.728896] RBP: ffff883fd139b740 R08: 0000000000000121 R09: 0000000000000002
[1041814.782495] R10: ffff88129b9517a0 R11: ffffffffa03d7574 R12: ffff881fd086f240
[1041814.836890] R13: 000000000000001a R14: 0000000000000000 R15: ffff88129b951790
[1041814.891509] FS: 00007f414ae07700(0000) GS:ffff881fffa60000(0000) knlGS:0000000000000000
[1041814.947152] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1041814.974929] CR2: 0000000000000000 CR3: 0000003fa8497000 CR4: 00000000001427e0
[1041815.028982] Stack:
[1041815.055115] 0000000000000190 0000000000000019 ffffffffa03f5000 ffff881f13188c00
[1041815.107808] 0000000000000166 ffff883fd139ba24 ffff8815cb6ba018 ffff883fd139b758
[1041815.160335] ffffffffa03e4ab5 ffffffffa03f5000 ffff883fd139b9d0 ffffffffa03d7fba
[1041815.212822] Call Trace:
[1041815.238305] [<ffffffffa03e4ab5>] vr_nexthop_req_process+0x75/0x90 [vrouter]
[1041815.290678] [<ffffffffa03d7fba>] sandesh_decode_one+0x10a/0x1d0 [vrouter]
[1041815.317098] [<ffffffffa03d9e00>] ? thrift_transport_flush+0x20/0x20 [vrouter]
[1041815.368593] [<ffffffffa03d9e10>] ? thrift_memory_buffer_is_open+0x10/0x10 [vrouter]
[1041815.420643] [<ffffffffa03d9e20>] ? thrift_memory_buffer_open+0x10/0x10 [vrouter]
[1041815.473130] [<ffffffffa03d9e60>] ? thrift_memory_buffer_flush+0x10/0x10 [vrouter]
[1041815.525141] [<ffffffffa03d9e30>] ? thrift_memory_buffer_close+0x10/0x10 [vrouter]
[1041815.577636] [<ffffffffa03d9ef0>] ? thrift_memory_buffer_read+0x90/0x90 [vrouter]
[1041815.629568] [<ffffffffa03d9e40>] ? thrift_memory_buffer_read_end+0x10/0x10 [vrouter]
[1041815.682221] [<ffffffffa03d9e50>] ? thrift_memory_buffer_write_end+0x10/0x10 [vrouter]
[1041815.735105] [<ffffffffa03d8e80>] ? thrift_binary_protocol_write_message_begin+0x80/0x80 [vrouter]
[1041815.788777] [<ffffffffa03d8ce0>] ? thrift_binary_protocol_write_message_end+0x10/0x10 [vrouter]
[1041815.844465] [<ffffffffa03d8e00>] ? thrift_binary_protocol_read_double+0x10/0x10 [vrouter]
[1041815.900441] [<ffffffffa03d8cd0>] ? thrift_protocol_skip+0x270/0x270 [vrouter]
[1041815.955932] [<ffffffffa03d8cf0>] ? thrift_binary_protocol_write_sandesh_end+0x10/0x10 [vrouter]
[1041816.012625] [<ffffffffa03d8d00>] ? thrift_binary_protocol_write_struct_begin+0x10/0x10 [vrouter]
[1041816.070684] [<ffffffffa03d8fc0>] ? thrift_binary_protocol_write_bool+0x20/0x20 [vrouter]
[1041816.129169] [<ffffffffa03d8d10>] ? thrift_binary_protocol_write_struct_end+0x10/0x10 [vrouter]
[1041816.188289] [<ffffffffa03d8ea0>] ? thrift_binary_protocol_write_sandesh_begin+0x20/0x20 [vrouter]
[1041816.246070] [<ffffffffa03d8ec0>] ? thrift_binary_protocol_write_field_stop+0x20/0x20 [vrouter]
[1041816.304325] [<ffffffffa03d8d20>] ? thrift_binary_protocol_write_field_end+0x10/0x10 [vrouter]
[1041816.362549] [<ffffffffa03d8f40>] ? thrift_binary_protocol_write_map_begin+0x80/0x80 [vrouter]
[1041816.420901] [<ffffffffa03d8d30>] ? thrift_binary_protocol_write_map_end+0x10/0x10 [vrouter]
[1041816.479479] [<ffffffffa03d9020>] ? thrift_binary_protocol_write_field_begin+0x60/0x60 [vrouter]
[1041816.538316] [<ffffffffa03d8d40>] ? thrift_binary_protocol_write_list_end+0x10/0x10 [vrouter]
[1041816.596566] [<ffffffffa03d8fa0>] ? thrift_binary_protocol_write_list_begin+0x60/0x60 [vrouter]
[1041816.655115] [<ffffffffa03d9030>] ? thrift_binary_protocol_write_set_begin+0x10/0x10 [vrouter]
[1041816.713960] [<ffffffffa03d91d0>] ? thrift_binary_protocol_write_binary+0x80/0x80 [vrouter]
[1041816.772927] [<ffffffffa03d9250>] ? thrift_binary_protocol_write_u16+0x40/0x40 [vrouter]
[1041816.831039] [<ffffffffa03d9060>] ? thrift_binary_protocol_write_byte+0x30/0x30 [vrouter]
[1041816.889020] [<ffffffffa03d9210>] ? thrift_binary_protocol_write_i16+0x40/0x40 [vrouter]
[1041816.947991] [<ffffffffa03d9280>] ? thrift_binary_protocol_write_i32+0x30/0x30 [vrouter]
[1041817.006503] [<ffffffffa03d90c0>] ? thrift_binary_protocol_write_i64+0x60/0x60 [vrouter]
[1041817.064818] [<ffffffffa03d92b0>] ? thrift_binary_protocol_write_u32+0x30/0x30 [vrouter]
[1041817.122620] [<ffffffffa03d8d50>] ? thrift_binary_protocol_write_set_end+0x10/0x10 [vrouter]
[1041817.180604] [<ffffffffa03d92c0>] ? thrift_binary_protocol_write_ipv4+0x10/0x10 [vrouter]
[1041817.238177] [<ffffffffa03d9150>] ? thrift_binary_protocol_write_uuid_t+0x30/0x30 [vrouter]
[1041817.296926] [<ffffffffa03d92c0>] ? thrift_binary_protocol_write_ipv4+0x10/0x10 [vrouter]
[1041817.354911] [<ffffffffa03d9120>] ? thrift_binary_protocol_write_u64+0x60/0x60 [vrouter]
[1041817.412690] [<ffffffffa03d93e0>] ? thrift_binary_protocol_read_message_begin+0xd0/0xd0 [vrouter]
[1041817.470454] [<ffffffffa03d8d70>] ? thrift_binary_protocol_read_message_end+0x10/0x10 [vrouter]
[1041817.528117] [<ffffffffa03d9310>] ? thrift_binary_protocol_write_string+0x50/0x50 [vrouter]
[1041817.585381] [<ffffffffa03d8d60>] ? thrift_binary_protocol_write_double+0x10/0x10 [vrouter]
[1041817.642525] [<ffffffffa03d8d80>] ? thrift_binary_protocol_read_sandesh_end+0x10/0x10 [vrouter]
[1041817.700197] [<ffffffffa03d8da0>] ? thrift_binary_protocol_read_struct_begin+0x20/0x20 [vrouter]
[1041817.757625] [<ffffffffa03d9540>] ? thrift_binary_protocol_read_list_begin+0x90/0x90 [vrouter]
[1041817.816164] [<ffffffffa03d8db0>] ? thrift_binary_protocol_read_struct_end+0x10/0x10 [vrouter]
[1041817.873858] [<ffffffffa03d9400>] ? thrift_binary_protocol_read_sandesh_begin+0x20/0x20 [vrouter]
[1041817.931824] [<ffffffffa03d8dc0>] ? thrift_binary_protocol_read_field_end+0x10/0x10 [vrouter]
[1041817.989595] [<ffffffffa03d94b0>] ? thrift_binary_protocol_read_map_begin+0xb0/0xb0 [vrouter]
[1041818.047447] [<ffffffffa03d8dd0>] ? thrift_binary_protocol_read_map_end+0x10/0x10 [vrouter]
[1041818.105155] [<ffffffffa03d95d0>] ? thrift_binary_protocol_read_field_begin+0x90/0x90 [vrouter]
[1041818.163003] [<ffffffffa03d8de0>] ? thrift_binary_protocol_read_list_end+0x10/0x10 [vrouter]
[1041818.220774] [<ffffffffa03d95e0>] ? thrift_binary_protocol_read_set_begin+0x10/0x10 [vrouter]
[1041818.279004] [<ffffffffa03d9630>] ? thrift_binary_protocol_read_bool+0x50/0x50 [vrouter]
[1041818.336699] [<ffffffffa03d9680>] ? thrift_binary_protocol_read_byte+0x50/0x50 [vrouter]
[1041818.394349] [<ffffffffa03d96d0>] ? thrift_binary_protocol_read_i16+0x50/0x50 [vrouter]
[1041818.452346] [<ffffffffa03d9720>] ? thrift_binary_protocol_read_i32+0x50/0x50 [vrouter]
[1041818.510599] [<ffffffffa03d97a0>] ? thrift_binary_protocol_read_i64+0x80/0x80 [vrouter]
[1041818.568591] [<ffffffffa03d97f0>] ? thrift_binary_protocol_read_u16+0x50/0x50 [vrouter]
[1041818.626210] [<ffffffffa03d9850>] ? thrift_binary_protocol_read_ipv4+0x10/0x10 [vrouter]
[1041818.683970] [<ffffffffa03d9840>] ? thrift_binary_protocol_read_u32+0x50/0x50 [vrouter]
[1041818.741524] [<ffffffffa03d8df0>] ? thrift_binary_protocol_read_set_end+0x10/0x10 [vrouter]
[1041818.799014] [<ffffffffa03d99e0>] ? thrift_binary_protocol_read_binary+0xe0/0xe0 [vrouter]
[1041818.856252] [<ffffffffa03d9900>] ? thrift_binary_protocol_read_uuid_t+0x30/0x30 [vrouter]
[1041818.913682] [<ffffffffa03d99e0>] ? thrift_binary_protocol_read_binary+0xe0/0xe0 [vrouter]
[1041818.970998] [<ffffffffa03d98d0>] ? thrift_binary_protocol_read_u64+0x80/0x80 [vrouter]
[1041819.028430] [<ffffffffa03d7e90>] ? sandesh_hdr_free+0x10/0x10 [vrouter]
[1041819.057317] [<ffffffffa03d8136>] sandesh_decode+0x46/0x90 [vrouter]
[1041819.085783] [<ffffffffa03e04f4>] sandesh_proto_decode+0x24/0x30 [vrouter]
[1041819.113894] [<ffffffffa03dff6e>] vr_message_request+0x3e/0x60 [vrouter]
[1041819.141608] [<ffffffffa03df9c6>] netlink_trans_request+0x56/0x190 [vrouter]
[1041819.195580] [<ffffffff8165227d>] genl_family_rcv_msg+0x18d/0x370
[1041819.222732] [<ffffffff81652460>] ? genl_family_rcv_msg+0x370/0x370
[1041819.249292] [<ffffffff816524f1>] genl_rcv_msg+0x91/0xd0
[1041819.275505] [<ffffffff81650579>] netlink_rcv_skb+0xa9/0xc0
[1041819.301493] [<ffffffff81650a78>] genl_rcv+0x28/0x40
[1041819.326611] [<ffffffff8164fb85>] netlink_unicast+0xd5/0x1b0
[1041819.351267] [<ffffffff8164ff80>] netlink_sendmsg+0x320/0x760
[1041819.375083] [<ffffffff8164ce24>] ? netlink_rcv_wake+0x44/0x60
[1041819.398608] [<ffffffff8164de82>] ? netlink_recvmsg+0x1a2/0x3a0
[1041819.421220] [<ffffffff8160a70b>] sock_sendmsg+0x8b/0xc0
[1041819.443257] [<ffffffff81199cd9>] ? mpol_misplaced+0x189/0x250
[1041819.465128] [<ffffffff8160a3fe>] ? move_addr_to_kernel.part.16+0x1e/0x60
[1041819.487162] [<ffffffff8160afc1>] ? move_addr_to_kernel+0x21/0x30
[1041819.508068] [<ffffffff8160af93>] ___sys_sendmsg+0x3c3/0x3d0
[1041819.528547] [<ffffffff8172ade4>] ? __do_page_fault+0x204/0x560
[1041819.548497] [<ffffffff810a0175>] ? set_next_entity+0x95/0xb0
[1041819.567917] [<ffffffff8160b692>] __sys_sendmsg+0x42/0x80
[1041819.586865] [<ffffffff8160b6e2>] SyS_sendmsg+0x12/0x20
[1041819.605307] [<ffffffff8172f7ed>] system_call_fastpath+0x1a/0x1f
[1041819.623204] Code: 00 0f b7 d2 83 fa 01 76 5b 83 ea 02 b8 10 00 00 00 48 8d 72 02 48 c1 e6 04 eb 0b 66 90 48 83 c0 10 48 39 f0 74 3e 48 8b 54 01 08 <80> 3a 06 75 ed f6 42 03 04 74 e7 48 89 51 08 49 8b 54 24 20 8b
[1041819.677043] RIP [<ffffffffa03e3efe>] vr_nexthop_add+0xee/0xa40 [vrouter]
[1041819.694572] RSP <ffff883fd139b708>
[1041819.711435] CR2: 0000000000000000
[1041819.758469] ---[ end trace f622e76c06d15ca7 ]---