From: Eric Dumazet
Date: Tue, 19 Apr 2016 17:49:50 -0700
> On Tue, 2016-04-19 at 20:36 -0400, David Miller wrote:
>> From: Eric Dumazet
>> Date: Mon, 18 Apr 2016 13:56:12 -0700
>>
>> > 1 % packet losses are common today, and at 100Gbit speeds, this
>> > translates to ~80,000 losses per second.
On Tue, 2016-04-19 at 20:36 -0400, David Miller wrote:
> From: Eric Dumazet
> Date: Mon, 18 Apr 2016 13:56:12 -0700
>
> > 1 % packet losses are common today, and at 100Gbit speeds, this
> > translates to ~80,000 losses per second. If we are unlucky and
> > first MSS of a 45-MSS TSO is lost, we ar
From: Eric Dumazet
Date: Mon, 18 Apr 2016 13:56:12 -0700
> 1 % packet losses are common today, and at 100Gbit speeds, this
> translates to ~80,000 losses per second. If we are unlucky and
> first MSS of a 45-MSS TSO is lost, we are cooking 44 MSS segments
> at rtx instead of a single 44-MSS TSO p
On Mon, Apr 18, 2016 at 1:56 PM, Eric Dumazet wrote:
> Linux TCP stack painfully segments all TSO/GSO packets before retransmits.
>
> This was fine back in the days when TSO/GSO were emerging, with their
> bugs, but we believe the dark age is over.
>
> Keeping big packets in write queues, but also
Linux TCP stack painfully segments all TSO/GSO packets before retransmits.
This was fine back in the days when TSO/GSO were emerging, with their
bugs, but we believe the dark age is over.
Keeping big packets in write queues, but also in stack traversal
has a lot of benefits.
- Less memory overhe
