From mboxrd@z Thu Jan  1 00:00:00 1970
From: Paolo Abeni <pabeni@redhat.com>
Subject: Re: Fw: [Bug 199963] New: UDP rx_queue incorrect calculation in
 /proc/net/udp
Date: Thu, 07 Jun 2018 18:28:47 +0200
Message-ID: <e99d1e6e54b59831eef6113aff9a740769cf96a7.camel@redhat.com>
References: <20180607073918.5626370d@xeon-e3>
Mime-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
To: Stephen Hemminger <stephen@networkplumber.org>,
        netdev@vger.kernel.org
Return-path: <netdev-owner@vger.kernel.org>
Received: from mx3-rdu2.redhat.com ([66.187.233.73]:56776 "EHLO mx1.redhat.com"
        rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP
        id S1753410AbeFGQ2t (ORCPT <rfc822;netdev@vger.kernel.org>);
        Thu, 7 Jun 2018 12:28:49 -0400
In-Reply-To: <20180607073918.5626370d@xeon-e3>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

On Thu, 2018-06-07 at 07:39 -0700, Stephen Hemminger wrote:
> 
> Begin forwarded message:
> 
> Date: Thu, 07 Jun 2018 13:21:23 +0000
> From: bugzilla-daemon@bugzilla.kernel.org
> To: stephen@networkplumber.org
> Subject: [Bug 199963] New: UDP rx_queue incorrect calculation in /proc/net/udp
> 
> 
> https://bugzilla.kernel.org/show_bug.cgi?id=199963
> 
>             Bug ID: 199963
>            Summary: UDP rx_queue incorrect calculation in /proc/net/udp
>            Product: Networking
>            Version: 2.5
>     Kernel Version: Kernels >= 4.15
>           Hardware: All
>                 OS: Linux
>               Tree: Mainline
>             Status: NEW
>           Severity: normal
>           Priority: P1
>          Component: IPV4
>           Assignee: stephen@networkplumber.org
>           Reporter: trevor.francis@46labs.com
>         Regression: No
> 
> since upgrading to any kernel >= 4.15 the rx_queue in /proc/net/udp is now
> reporting a queue, regardless of system load and regardless of what
> applications are running on it. The tx_queue is always 0, but rx_queue has
> seemingly random spikes of udp queueing. This is observed across hundreds of
> servers with either varying or no workload.
> 
> netstat -nl|grep ^udp
> udp 4352 0 0.0.0.0:68 0.0.0.0:*
> 
> sl local_address rem_address st tx_queue rx_queue tr tm->when retrnsmt uid
> timeout inode ref pointer drops
> 14645: 3500007F:0035 00000000:0000 07 00000000:0000C900 00:00000000 00000000
> 101 0 3367 2 ffff8da177fdcc00 0

after:

commit 0d4a6608f68c7532dcbfec2ea1150c9761767d03
Author: Paolo Abeni <pabeni@redhat.com>
Date:   Tue Sep 19 12:11:43 2017 +0200

    udp: do rmem bulk free even if the rx sk queue is empty

rmem can be a non-0, small, value even if the rx queue is empty,
because it reports the (forward) allocated memory for this socket, not
the queue length in bytes. 

I'll cook a patch to fix the above.

Cheers,

Paolo