On Mon, 2017-05-08 at 15:49 +0800, Shan Wei wrote:
> Indeed, HZ=250. What is the problem about autotuning with HZ=250?
>
You might look at recent patches.
commit 645f4c6f2ebd040688cc2a5f626ffc909e66ccf2
("tcp: switch rcv_rtt_est and rcvq_space to high resolution timestamps")
Thanks.
at 2017/5/5 21:52
> On Fri, 2017-05-05 at 18:22 +0800, wrote:
>>
>> 2017-05-02 23:05 GMT+08:00 Eric Dumazet :
>>
>>
>> Hi Shan
>>
>> 1) Your patch never reached netdev, because it was sent in
>> HTML format.
>>
>> 2) During Linus
On Fri, 2017-05-05 at 18:22 +0800, 单卫 wrote:
>
>
> 2017-05-02 23:05 GMT+08:00 Eric Dumazet :
>
>
> Hi Shan
>
> 1) Your patch never reached netdev, because it was sent in
> HTML format.
>
> 2) During Linus merge window, net-next i
On Tue, 2017-05-02 at 12:57 +0800, 单卫 wrote:
> Current sndbuff/rcvbuff value of new passive connetion inherit from
> listen socket.
> After then, tcp_init_buffer_space() initial them with init_cwnd and
> tcp_should_expand_sndbuf() adjust them according the new cwnd.
>
>
> But, For Operation & Ma