| Message ID | 1494515392-30826-1-git-send-email-vyasevic@redhat.com |
|---|---|
| State | Accepted, archived |
| Delegated to: | David Miller |
| Headers | show |
From: Vladislav Yasevich <vyasevich@gmail.com> Date: Thu, 11 May 2017 11:09:52 -0400 > Macvlan always turns on offload features that have sofware > fallback (NETIF_GSO_SOFTWARE). This allows much higher guest-guest > communications over macvtap. > > However, macvtap does not turn on these features for vlan tagged traffic. > As a result, depending on the HW that mactap is configured on, the > performance of guest-guest communication over a vlan is very > inconsistent. If the HW supports TSO/UFO over vlans, then the > performance will be fine. If not, the the performance will suffer > greatly since the VM may continue using TSO/UFO, and will force the host > segment the traffic and possibly overlow the macvtap queue. > > This patch adds the always on offloads to vlan_features. This > makes sure that any vlan tagged traffic between 2 guest will not > be segmented needlessly. > > Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com> Indeed, this makes us more consistent with how we handle non-vlan features in macvtap. Applied, thanks.
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index b34eaaa..346ad2f 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -789,10 +789,12 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu) */ static struct lock_class_key macvlan_netdev_addr_lock_key; -#define ALWAYS_ON_FEATURES \ - (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \ +#define ALWAYS_ON_OFFLOADS \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST) +#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX) + #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \ @@ -827,6 +829,7 @@ static int macvlan_init(struct net_device *dev) dev->features |= ALWAYS_ON_FEATURES; dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; + dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->gso_max_size = lowerdev->gso_max_size; dev->gso_max_segs = lowerdev->gso_max_segs; dev->hard_header_len = lowerdev->hard_header_len;
Macvlan always turns on offload features that have sofware fallback (NETIF_GSO_SOFTWARE). This allows much higher guest-guest communications over macvtap. However, macvtap does not turn on these features for vlan tagged traffic. As a result, depending on the HW that mactap is configured on, the performance of guest-guest communication over a vlan is very inconsistent. If the HW supports TSO/UFO over vlans, then the performance will be fine. If not, the the performance will suffer greatly since the VM may continue using TSO/UFO, and will force the host segment the traffic and possibly overlow the macvtap queue. This patch adds the always on offloads to vlan_features. This makes sure that any vlan tagged traffic between 2 guest will not be segmented needlessly. Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com> --- drivers/net/macvlan.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)