[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CALzJLG-pjeZnOQ3FfZMLCz5KC-eXWWrTZS4yNi-+UYY=2T549A@mail.gmail.com>
Date: Thu, 30 Jun 2016 17:47:19 +0300
From: Saeed Mahameed <saeedm@....mellanox.co.il>
To: Eric Dumazet <eric.dumazet@...il.com>
Cc: Saeed Mahameed <saeedm@...lanox.com>,
"David S. Miller" <davem@...emloft.net>,
Linux Netdev List <netdev@...r.kernel.org>,
Eric Dumazet <edumazet@...gle.com>,
Tom Herbert <tom@...bertland.com>,
Mohamad Haj Yahia <mohamad@...lanox.com>
Subject: Re: [PATCH net] net: poll tx timeout only on active tx queues
On Thu, Jun 30, 2016 at 5:28 PM, Eric Dumazet <eric.dumazet@...il.com> wrote:
> On Thu, 2016-06-30 at 16:58 +0300, Saeed Mahameed wrote:
>> - for (i = 0; i < dev->num_tx_queues; i++) {
>> + for (i = 0; i < dev->real_num_tx_queues; i++) {
>> struct netdev_queue *txq;
>>
>> txq = netdev_get_tx_queue(dev, i);
>
> Strange, why don't you change all others helpers that are using
> num_tx_queues ?
>
which other helpers ?
since this function assumes that all tx queues are started and if a
non real_txq is stopped for more that timeout period it will start
shouting call traces and warnings.
> Which driver had a problem with this code ?
non yet.
currently all the device driver call netif_tx_start_all_queues(dev)
on open to W/A this issue. which is strange since only
real_num_tx_queues are active.
Powered by blists - more mailing lists