From: Eric Dumazet
Date: Sun, 20 Nov 2016 09:24:36 -0800
> From: Eric Dumazet
>
> While stressing a 40Gbit mlx4 NIC with busy polling, I found false
> sharing in mlx4 driver that can be easily avoided.
>
> This patch brings an additional 7 % performance improvement in UDP_RR
> workload.
>
> 1
On 20/11/2016 7:24 PM, Eric Dumazet wrote:
From: Eric Dumazet
While stressing a 40Gbit mlx4 NIC with busy polling, I found false
sharing in mlx4 driver that can be easily avoided.
This patch brings an additional 7 % performance improvement in UDP_RR
workload.
1) If we received no frame durin
On Sun, 2016-11-20 at 09:24 -0800, Eric Dumazet wrote:
> /* Current cpu is not according to smp_irq_affinity -
> - * probably affinity changed. need to stop this NAPI
> - * poll, and restart it on the right CPU
> + * probably affinity changed. N
From: Eric Dumazet
While stressing a 40Gbit mlx4 NIC with busy polling, I found false
sharing in mlx4 driver that can be easily avoided.
This patch brings an additional 7 % performance improvement in UDP_RR
workload.
1) If we received no frame during one mlx4_en_process_rx_cq()
invocation, n
