Messages in this thread |  | | | Subject | Re: [net-next RFC V2 PATCH 0/5] Multiqueue support in tun/tap | | From | Ben Hutchings <> | | Date | Mon, 19 Sep 2011 15:45:51 +0100 |
| |
On Sat, 2011-09-17 at 14:02 +0800, Jason Wang wrote: [...] > 2 Current implementation may also get regression for single session > packet transmission. > > The reason is packets from each flow were not handled by the same > queue/vhost thread. > > Various method could be done to handle this: > > 2.1 hack the guest driver, and store the queue index into the rxhash and > use it when choosing tx in guest. This need some hack to store the > rxhash into sk and pass it in to skb again in > skb_orphan_try(). sk_rxhash is only used by RPS now, so some more > clean method is needed. [...]
I have previously suggested doing this as a general rule. However, I now think we can do much better with accelerated RFS and automatic XPS (but the latter is not yet implemented). For virtio_net, accelerated RFS would effectively push the guest's RFS socket map out to the host.
Ben.
-- Ben Hutchings, Staff Engineer, Solarflare Not speaking for my employer; that's the marketing department's job. They asked us to note that Solarflare product names are trademarked.
|  |