[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <38876115ff2bd4756eca5d8d8f93a48e@linux.dev>
Date: Thu, 20 Apr 2023 02:49:12 +0000
From: "Yajun Deng" <yajun.deng@...ux.dev>
To: "Eric Dumazet" <edumazet@...gle.com>
Cc: jhs@...atatu.com, xiyou.wangcong@...il.com, jiri@...nulli.us,
davem@...emloft.net, kuba@...nel.org, pabeni@...hat.com,
netdev@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] net: sched: print jiffies when transmit queue time
out
April 19, 2023 8:02 PM, "Eric Dumazet" <edumazet@...gle.com> wrote:
> On Wed, Apr 19, 2023 at 1:56 PM Yajun Deng <yajun.deng@...ux.dev> wrote:
>
>> Although there is watchdog_timeo to let users know when the transmit queue
>> begin stall, but dev_watchdog() is called with an interval. The jiffies
>> will always be greater than watchdog_timeo.
>>
>> To let users know the exact time the stall started, print jiffies when
>> the transmit queue time out.
>>
>> Signed-off-by: Yajun Deng <yajun.deng@...ux.dev>
>> ---
>>
>> atomic_long_inc(&txq->trans_timeout);
>> break;
>> }
>> @@ -522,8 +522,9 @@ static void dev_watchdog(struct timer_list *t)
>>
>> if (unlikely(some_queue_timedout)) {
>> trace_net_dev_xmit_timeout(dev, i);
>> - WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
>> - dev->name, netdev_drivername(dev), i);
>> + WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): \
>> + transmit queue %u timed out %lu jiffies\n",
>> + dev->name, netdev_drivername(dev), i, some_queue_timedout);
>
> If we really want this, I suggest we export a time in ms units, using
> jiffies_to_msecs()
OK.
Powered by blists - more mailing lists