[Intel-wired-lan] [PATCH net-next 4/4] i40e, xsk: move buffer allocation out of the Rx processing loop
Bowers, AndrewX
andrewx.bowers at intel.com
Wed Jul 8 20:45:01 UTC 2020
> -----Original Message-----
> From: Intel-wired-lan <intel-wired-lan-bounces at osuosl.org> On Behalf Of
> Björn Töpel
> Sent: Thursday, July 2, 2020 8:38 AM
> To: intel-wired-lan at lists.osuosl.org
> Cc: netdev at vger.kernel.org; bpf at vger.kernel.org; Topel, Bjorn
> <bjorn.topel at intel.com>; Karlsson, Magnus <magnus.karlsson at intel.com>
> Subject: [Intel-wired-lan] [PATCH net-next 4/4] i40e, xsk: move buffer
> allocation out of the Rx processing loop
>
> From: Björn Töpel <bjorn.topel at intel.com>
>
> Instead of checking in each iteration of the Rx packet processing loop, move
> the allocation out of the loop and do it once for each napi activation.
>
> For AF_XDP the rx_drop benchmark was improved by 6%.
>
> Signed-off-by: Björn Töpel <bjorn.topel at intel.com>
> ---
> drivers/net/ethernet/intel/i40e/i40e_xsk.c | 12 ++++--------
> 1 file changed, 4 insertions(+), 8 deletions(-)
Tested-by: Andrew Bowers <andrewx.bowers at intel.com>
More information about the Intel-wired-lan
mailing list