Displaying 3 results from an estimated 3 matches for "59f3a11e".
2013 Dec 30
0
[PATCH net-next 3/3] net: auto-tune mergeable rx buffer size for improved performance
...I guess this 1% difference is in the noise, right?
> Could you share data about host CPU utilization during
> these runs please?
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.linuxfoundation.org/pipermail/virtualization/attachments/20131230/59f3a11e/attachment-0002.html>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.linuxfoundation.org/pipermail/virtualization/attachments/20131230/59f3a11e/attachment-0003.html>
2013 Dec 23
2
[PATCH net-next 3/3] net: auto-tune mergeable rx buffer size for improved performance
On Mon, Dec 16, 2013 at 04:16:29PM -0800, Michael Dalton wrote:
> Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag
> allocators") changed the mergeable receive buffer size from PAGE_SIZE to
> MTU-size, introducing a single-stream regression for benchmarks with large
> average packet size. There is no single optimal buffer size for all
>
2013 Dec 23
2
[PATCH net-next 3/3] net: auto-tune mergeable rx buffer size for improved performance
On Mon, Dec 16, 2013 at 04:16:29PM -0800, Michael Dalton wrote:
> Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag
> allocators") changed the mergeable receive buffer size from PAGE_SIZE to
> MTU-size, introducing a single-stream regression for benchmarks with large
> average packet size. There is no single optimal buffer size for all
>