[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ba532713-7ca6-6497-8c18-31c418d41ee5@aquantia.com>
Date: Mon, 27 May 2019 09:57:18 +0000
From: Igor Russkikh <Igor.Russkikh@...antia.com>
To: David Miller <davem@...emloft.net>
CC: "netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCH net 1/4] net: aquantia: tx clean budget logic error
On 27.05.2019 8:15, David Miller wrote:
> From: Igor Russkikh <Igor.Russkikh@...antia.com>
> Date: Sat, 25 May 2019 09:57:59 +0000
>
>> In case no other traffic happening on the ring, full tx cleanup
>> may not be completed. That may cause socket buffer to overflow
>> and tx traffic to stuck until next activity on the ring happens.
>>
>> This is due to logic error in budget variable decrementor.
>> Variable is compared with zero, and then post decremented,
>> causing it to become MAX_INT. Solution is remove decrementor
>> from the `for` statement and rewrite it in a clear way.
>>
>> Fixes: b647d3980948e ("net: aquantia: Add tx clean budget and valid budget handling logic")
>> Signed-off-by: Igor Russkikh <igor.russkikh@...antia.com>
>
> I think the TX clean budget is a very bad idea.
>
> You should always do as much TX clean work as there is TODO.
Hi David,
This is not about introducing tx clean budget, but about fixing a bug.
tx clean budget logic is present in majority of the drivers as I see,
including igb,ixgbe,mlx5.
I see it as a logical action to limit the time driver spends in napi_poll
under napi budget.
Regards,
Igor
Powered by blists - more mailing lists