Re: [PATCH v2 2/2] virtio-ring: Allocate indirect buffers from cache when possible

On Thu, Sep 06, 2012 at 05:27:23PM +0930, Rusty Russell wrote:

"Michael S. Tsirkin" [off-list ref] writes:

quoted

Yes without checksum net core always linearizes packets, so yes it is
screwed.
For -net, skb always allocates space for 17 frags + linear part so
it seems sane to do same in virtio core, and allocate, for -net,
up to max_frags + 1 from cache.
We can adjust it: no _SG -> 2 otherwise 18.

But I thought it used individual buffers these days?

Yes for receive, no for transmit. That's probably why
we should have the threshold per vq, not per device, BTW.

-- 
MST

"Michael S. Tsirkin" [off-list ref] writes:

On Thu, Sep 06, 2012 at 05:27:23PM +0930, Rusty Russell wrote:

quoted

"Michael S. Tsirkin" [off-list ref] writes:

quoted

Yes without checksum net core always linearizes packets, so yes it is
screwed.
For -net, skb always allocates space for 17 frags + linear part so
it seems sane to do same in virtio core, and allocate, for -net,
up to max_frags + 1 from cache.
We can adjust it: no _SG -> 2 otherwise 18.

But I thought it used individual buffers these days?

Yes for receive, no for transmit. That's probably why
we should have the threshold per vq, not per device, BTW.

Can someone actually run with my histogram patch and see what the real
numbers are?

I'm not convinced that the ideal 17-buffer case actually happens as much
as we think.  And if it's not happening with this netperf test, we're
testing the wrong thing.

Thanks,
Rusty.