Hello,
I'm on 4.0.6 with CentOS 7.3.
The hypervisor is an old blade BL685c G1 and the network adapters used to provide network to vm are
07:04.0 Ethernet controller: Broadcom Limited NetXtreme BCM5715S Gigabit Ethernet (rev a3)
07:04.1 Ethernet controller: Broadcom Limited NetXtreme BCM5715S Gigabit Ethernet (re
managed by tg3 kernel module, as I see in messages:
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.0 eth0: Tigon3 [partno(011276-001) rev 9003] (PCIX:133MHz:64-bit) MAC address 00:1c:c4:46:ef:73
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.0 eth0: attached PHY is 5714 (1000Base-SX Ethernet) (WireSpeed[0], EEE[0])
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.0 eth0: RXcsums[1] LinkChgREG[0] MIirq[0] ASF[0] TSOcap[1]
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.0 eth0: dma_rwctrl[76148000] dma_mask[40-bit]
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.1 eth1: Tigon3 [partno(011276-001) rev 9003] (PCIX:133MHz:64-bit) MAC address 00:1c:c4:46:ef:74
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.1 eth1: attached PHY is 5714 (1000Base-SX Ethernet) (WireSpeed[0], EEE[0])
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.1 eth1: RXcsums[1] LinkChgREG[0] MIirq[0] ASF[0] TSOcap[1]
Jan 21 18:53:33 ovmsrv05 kernel: tg3 0000:07:04.1 eth1: dma_rwctrl[76148000] dma_mask[40-bit]
The 2 adapters are in bonding active-backup mode.
They are on vlan, so on hypervisor I have bond1.65 device and in vm the virtual interface is untagged
[root@ovmsrv05 ~]# ifconfig bond1.65
bond1.65: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
ether 00:1c:c4:46:ef:73 txqueuelen 1000 (Ethernet)
RX packets 4368 bytes 257675 (251.6 KiB)
RX errors 0 dropped 0 overruns 0 frame 0
TX packets 238 bytes 28146 (27.4 KiB)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
[root@ovmsrv05 ~]#
Currently Active Slave: enp7s4f0
After a few minutes I loose connectivity with the guest. In this case if I go in guest console and ping the gateway, the connection is resumed. And I can maintain it if I leave the ping running, otherwise after a little I again loose connectivity.
I suspect it is not important but the guest is Oracle Linux 6.5 with 3.8.13-16.2.1.el6uek.x86_64 kernel. The adapter for the vnic is the default; the qemu-kvm command line generated contains this:
-netdev tap,fd=29,id=hostnet0,vhost=on,vhostfd=30 -device virtio-net-pci,netdev=hostnet0,id=net0,mac=00:1a:4a:16:01:51,bus=pci.0,addr=0x3
I seem to remember some years ago when I used the same blades with plain qemu-kvm/libvirt I had to make up an ethtool setting for similar problems, but I don't remember what it was... and possibly I used bnx2 kernel module with the other embedded network interfaces, I'm not sure...
Currently, the configuration for adapter on the blade is
[root@ovmsrv05 ~]# ethtool -k enp7s4f0
Features for enp7s4f0:
rx-checksumming: on
tx-checksumming: on
tx-checksum-ipv4: on
tx-checksum-ip-generic: off [fixed]
tx-checksum-ipv6: off [fixed]
tx-checksum-fcoe-crc: off [fixed]
tx-checksum-sctp: off [fixed]
scatter-gather: on
tx-scatter-gather: on
tx-scatter-gather-fraglist: off [fixed]
tcp-segmentation-offload: off
tx-tcp-segmentation: off [requested on]
tx-tcp-ecn-segmentation: off [fixed]
tx-tcp6-segmentation: off [fixed]
udp-fragmentation-offload: off [fixed]
generic-segmentation-offload: on
generic-receive-offload: on
large-receive-offload: off [fixed]
rx-vlan-offload: on [fixed]
tx-vlan-offload: on [fixed]
ntuple-filters: off [fixed]
receive-hashing: off [fixed]
highdma: on
rx-vlan-filter: off [fixed]
vlan-challenged: off [fixed]
tx-lockless: off [fixed]
netns-local: off [fixed]
tx-gso-robust: off [fixed]
tx-fcoe-segmentation: off [fixed]
tx-gre-segmentation: off [fixed]
tx-ipip-segmentation: off [fixed]
tx-sit-segmentation: off [fixed]
tx-udp_tnl-segmentation: off [fixed]
tx-mpls-segmentation: off [fixed]
fcoe-mtu: off [fixed]
tx-nocache-copy: off
loopback: off
rx-fcs: off [fixed]
rx-all: off [fixed]
tx-vlan-stag-hw-insert: off [fixed]
rx-vlan-stag-hw-parse: off [fixed]
rx-vlan-stag-filter: off [fixed]
busy-poll: off [fixed]
tx-sctp-segmentation: off [fixed]
l2-fwd-offload: off [fixed]
hw-tc-offload: off [fixed]
[root@ovmsrv05 ~]#