[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 12 Dec 2016 16:23:22 -0500
From: Josef Bacik <jbacik@...com>
To: Hannes Frederic Sowa <hannes@...essinduktion.org>
CC: Eric Dumazet <eric.dumazet@...il.com>,
Tom Herbert <tom@...bertland.com>,
Linux Kernel Network Developers <netdev@...r.kernel.org>
Subject: Re: Soft lockup in inet_put_port on 4.6
On Mon, Dec 12, 2016 at 1:44 PM, Hannes Frederic Sowa
<hannes@...essinduktion.org> wrote:
> On 12.12.2016 19:05, Josef Bacik wrote:
>> On Fri, Dec 9, 2016 at 11:14 PM, Eric Dumazet
>> <eric.dumazet@...il.com>
>> wrote:
>>> On Fri, 2016-12-09 at 19:47 -0800, Eric Dumazet wrote:
>>>
>>>>
>>>> Hmm... Is your ephemeral port range includes the port your load
>>>> balancing app is using ?
>>>
>>> I suspect that you might have processes doing bind( port = 0) that
>>> are
>>> trapped into the bind_conflict() scan ?
>>>
>>> With 100,000 + timewaits there, this possibly hurts.
>>>
>>> Can you try the following loop breaker ?
>>
>> It doesn't appear that the app is doing bind(port = 0) during normal
>> operation. I tested this patch and it made no difference. I'm
>> going to
>> test simply restarting the app without changing to the SO_REUSEPORT
>> option. Thanks,
>
> Would it be possible to trace the time the function uses with trace?
> If
> we don't see the number growing considerably over time we probably can
> rule out that we loop somewhere in there (I would instrument
> inet_csk_bind_conflict, __inet_hash_connect and inet_csk_get_port).
>
> __inet_hash_connect -> __inet_check_established also takes a lock
> (inet_ehash_lockp) which can be locked from inet_diag code path during
> socket diag info dumping.
>
> Unfortunately we couldn't reproduce it so far. :/
Working on getting the timing info, will probably be tomorrow due to
meetings. I did test simply restarting the app without changing to the
config that enabled the use of SO_REUSEPORT and the problem didn't
occur, so it definitely has something to do with SO_REUSEPORT. Thanks,
Josef
Powered by blists - more mailing lists