Re: [PATCH v2 net-next 00/14] mlx4: order-0 allocations and page recycling

On Sun, 2017-02-12 at 18:31 +0200, Tariq Toukan wrote:

On 09/02/2017 6:56 PM, Eric Dumazet wrote:

quoted

quoted

Default, out of box.

Well. Please report :

ethtool  -l eth0
ethtool -g eth0

$ ethtool -g p1p1
Ring parameters for p1p1:
Pre-set maximums:
RX:             8192
RX Mini:        0
RX Jumbo:       0
TX:             8192
Current hardware settings:
RX:             1024
RX Mini:        0
RX Jumbo:       0
TX:             512

We are using 4096 slots per RX queue, this is why I could not reproduce
your results.

A single TCP flow easily can have more than 1024 MSS waiting in its
receive queue (typical receive window on linux is 6MB/2 )

I mentioned that having a slightly inflated skb->truesize might have an
impact in some workloads. (charging for 2048 bytes per MSS instead of
1536), but this is not related to mlx4 and should be tweaked in TCP
stack instead, since this 2048 bytes (half a page on x86) strategy is
now well spread.