search for: vxlan

...hem different. Version 1.0 of the virtio spec [1] says in Section 5.1.6.2.1 Driver Requirements: Packet Transmission: "The driver MUST NOT set the VIRTIO_NET_HDR_F_DATA_VALID bit in flags." The above changes clearly do that, but maybe I'm mis-reading the spec here. The changes break VXLAN in some setups (we discovered it on Google Could Engine, see below). We are trying to establish if this is an issue with the GCE backend implementation, or if the above commit should be amended to revert to the old behaviour (set VIRTIO_NET_HDR_F_NEEDS_CSUM if ip_summed==CHECKSUM_PARTIAL, otherwise...

...hem different. Version 1.0 of the virtio spec [1] says in Section 5.1.6.2.1 Driver Requirements: Packet Transmission: "The driver MUST NOT set the VIRTIO_NET_HDR_F_DATA_VALID bit in flags." The above changes clearly do that, but maybe I'm mis-reading the spec here. The changes break VXLAN in some setups (we discovered it on Google Could Engine, see below). We are trying to establish if this is an issue with the GCE backend implementation, or if the above commit should be amended to revert to the old behaviour (set VIRTIO_NET_HDR_F_NEEDS_CSUM if ip_summed==CHECKSUM_PARTIAL, otherwise...

....0 of the virtio spec [1] says in Section 5.1.6.2.1 Driver > Requirements: Packet Transmission: "The driver MUST NOT set the > VIRTIO_NET_HDR_F_DATA_VALID bit in flags." The above changes clearly > do that, but maybe I'm mis-reading the spec here. > > The changes break VXLAN in some setups (we discovered it on Google > Could Engine, see below). We are trying to establish if this is an > issue with the GCE backend implementation, or if the above commit > should be amended to revert to the old behaviour (set > VIRTIO_NET_HDR_F_NEEDS_CSUM if ip_summed==CHECKSU...

...0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc pfifo_fast master ovs-system state UNKNOWN group default qlen 1000 link/ether fe:54:00:54:14:f8 brd ff:ff:ff:ff:ff:ff inet6 fe80::fc54:ff:fe54:14f8/64 scope link valid_lft forever preferred_lft forever I use ovs to create vxlan networks and add VMs to the ovs bridge. Because of the limitations of vxlan, I need to set the mtu of vm to 1450. How to set the MTU of VM? Thanks. Below some information about my hypervisor: root@ubuntu-192:~# virsh -V Virsh command line tool of libvirt 3.4.0 See web site at http://libvirt.org/...

...would like to *add more physical nodes later* when I need the resources. This is what I have done so far: - Installed latest Ubuntu 18.04, with latest version of libvirt and supporting software from ubuntu's apt repo. - Each node can reach the other via its own eth0. - Each node has a working vxlan0, which can ping the other via its vxlan0, so it looks like the vxlan config is working. (I used *ip link add vxlan0 type vxlan...*) - Configured route on Host1 like so: *ip route add 192.168.2.0/24 <http://192.168.2.0/24> via 172.20.0.1* - Configured route on Host2 also: *ip route add 192.16...

.../xxx/gro_flush_timeout to 1000 nsec, Rick Jones reported following results. One VM of each on a pair of OpenStack compute nodes with E5-2650Lv3 CPUs and Intel 82599ES-based NICs. So, two "before" and two "after" VMs. The OpenStack compute nodes were running OpenStack Kilo, with VxLAN encapsulation being used through OVS so no GRO coming-up the host stack. The compute nodes themselves were running a 3.14-based kernel. Single-stream netperf, CPU utilizations and thus service demands are based on intra-guest reported CPU. Throughput Mbit/s, bigger is better...

.../xxx/gro_flush_timeout to 1000 nsec, Rick Jones reported following results. One VM of each on a pair of OpenStack compute nodes with E5-2650Lv3 CPUs and Intel 82599ES-based NICs. So, two "before" and two "after" VMs. The OpenStack compute nodes were running OpenStack Kilo, with VxLAN encapsulation being used through OVS so no GRO coming-up the host stack. The compute nodes themselves were running a 3.14-based kernel. Single-stream netperf, CPU utilizations and thus service demands are based on intra-guest reported CPU. Throughput Mbit/s, bigger is better...

...or me, I intend for each guest to be *"stationary" to each host*. Each node's *eth0* is connected via IPSec (unicast and transport mode) to the other. This is to encrypt the communication between all nodes because it travels over the internet. Additionally, each node currently has a *vxlan0* interface in the *172.20.0.0/24 <http://172.20.0.0/24>* network which allows them to be all on the same "LAN". I have attached a simple diagram illustrating this setup, also available here: https://i.imgur.com/jc7bc6b.png . I would *prefer* to use the DHCP that comes "built-i...

...40e 0000:1a:00.0: MSI-X vector limit reached, attempting to redistribute vectors kernel: [ 23.133699] i40e 0000:1a:00.0: Added LAN device PF0 bus=0x1a dev=0x00 func=0x00 kernel: [ 23.134414] i40e 0000:1a:00.0: Features: PF-id[0] VFs: 32 VSIs: 34 QP: 56 RSS FD_ATR FD_SB NTUPLE CloudF DCB VxLAN NVGRE PTP VEPA kernel: [ 23.148085] i40e 0000:1a:00.1: fw 3.1.57069 api 1.5 nvm 3.33 0x80000f09 255.65535.255 kernel: [ 23.151729] i40e 0000:1a:00.1: MAC address: 28:41:c6:fb:c3:a3 kernel: [ 23.160694] i40e 0000:1a:00.1: MSI-X vector limit reached, attempting to redistribute vecto...

...using openvswitch). We have the luxury of multiple 10G NICs between our hosts, so we've separated out the management network from the guest network, simply to ensure that we retain administrative access to the hosts via ssh. If you want to live a little more dangerously, you could use VLAN or VXLAN on one NIC - or you could spend a few dollars on an extra network card on each host for the peace of mind! For the project that's been live for two years: we presently run four hosts on the lab's production network (another two on its acceptance-test network, and another one as a "kic...

...1000 nsec, > Rick Jones reported following results. > > One VM of each on a pair of OpenStack compute nodes with E5-2650Lv3 CPUs > and Intel 82599ES-based NICs. So, two "before" and two "after" VMs. > The OpenStack compute nodes were running OpenStack Kilo, with VxLAN > encapsulation being used through OVS so no GRO coming-up the host > stack. The compute nodes themselves were running a 3.14-based kernel. > > Single-stream netperf, CPU utilizations and thus service demands are > based on intra-guest reported CPU. > > Throughput Mbit/s, bi...

...: > Dear all: > I start a VM with MTU size 1450, and login VM to check the mtu size, but > this setting didn't work. > > [snip] > However, the actual mtu size of VM is still 1500, as following: > > root@ubuntu-zhf:~# ip addr > > [snip] > I use ovs to create vxlan networks and add VMs to the ovs bridge. Because of the limitations of vxlan, I need to set the mtu of vm to 1450. > > How to set the MTU of VM? Thanks. > You have to set it inside guest OS. So I presume still in /etc/network/interfaces file for Ubuntu (see also "man interfaces&quot...

Add MDB net device operations that will be invoked by rtnetlink code in response to received RTM_{NEW,DEL,GET}MDB messages. Subsequent patches will implement these operations in the bridge and VXLAN drivers. Signed-off-by: Ido Schimmel <idosch at nvidia.com> --- include/linux/netdevice.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ee483071cf59..23b0d7eaaadd 100644 --- a/include/linux/netdevice.h...

...ge: Add vlan id to multicast groups bridge: Add vlan support to static neighbors bridge: Add vlan support for local fdb entries bridge: Separate egress policy bitmap drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 +- drivers/net/macvlan.c | 2 +- drivers/net/vxlan.c | 3 +- include/linux/netdevice.h | 6 +- include/uapi/linux/if_bridge.h | 11 + include/uapi/linux/neighbour.h | 1 + include/uapi/linux/rtnetlink.h | 1 + net/8021q/vlan_core.c...

...t/vmxnet3/vmxnet3_ethtool.c @@ -635,5 +635,5 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { void vmxnet3_set_ethtool_ops(struct net_device *netdev) { - SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops); + netdev->ethtool_ops = &vmxnet3_ethtool_ops; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 82355d5..457359c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2706,7 +2706,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, return -EEXIST; } - SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops); + dev->ethtool_ops = &vxl...

...t/vmxnet3/vmxnet3_ethtool.c @@ -635,5 +635,5 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { void vmxnet3_set_ethtool_ops(struct net_device *netdev) { - SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops); + netdev->ethtool_ops = &vmxnet3_ethtool_ops; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 82355d5..457359c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2706,7 +2706,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, return -EEXIST; } - SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops); + dev->ethtool_ops = &vxl...

...t/vmxnet3/vmxnet3_ethtool.c @@ -635,5 +635,5 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { void vmxnet3_set_ethtool_ops(struct net_device *netdev) { - SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops); + netdev->ethtool_ops = &vmxnet3_ethtool_ops; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 82355d5..457359c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2706,7 +2706,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, return -EEXIST; } - SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops); + dev->ethtool_ops = &vxl...

...t/vmxnet3/vmxnet3_ethtool.c @@ -635,5 +635,5 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { void vmxnet3_set_ethtool_ops(struct net_device *netdev) { - SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops); + netdev->ethtool_ops = &vmxnet3_ethtool_ops; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 82355d5..457359c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2706,7 +2706,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, return -EEXIST; } - SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops); + dev->ethtool_ops = &vxl...

...t/vmxnet3/vmxnet3_ethtool.c @@ -635,5 +635,5 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { void vmxnet3_set_ethtool_ops(struct net_device *netdev) { - SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops); + netdev->ethtool_ops = &vmxnet3_ethtool_ops; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 82355d5..457359c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2706,7 +2706,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, return -EEXIST; } - SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops); + dev->ethtool_ops = &vxl...

...@@ static const struct ethtool_ops vmxnet3_ethtool_ops = { > > void vmxnet3_set_ethtool_ops(struct net_device *netdev) > { > - SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops); > + netdev->ethtool_ops = &vmxnet3_ethtool_ops; > } > diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c > index 82355d5..457359c 100644 > --- a/drivers/net/vxlan.c > +++ b/drivers/net/vxlan.c > @@ -2706,7 +2706,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, > return -EEXIST; > } > > - SET_ETHTOOL_OPS...