From mboxrd@z Thu Jan  1 00:00:00 1970
From: Richard Cochran <richardcochran@gmail.com>
Subject: Re: Kernel 4.6.7-rt13: Intel Ethernet driver igb causes huge
 latencies in cyclictest
Date: Sat, 15 Oct 2016 00:06:33 +0200
Message-ID: <20161014220633.GA1811@netboy>
References: <584755c2766e4b94a604ece16760fe14@FE-MBX1012.de.bosch.com>
 <20161005155959.GH10625@jcartwri.amer.corp.natinst.com>
 <13c3cd3ffee4490fb22b8de383e51361@FE-MBX1012.de.bosch.com>
 <AAEA33E297BCAC4B9BB20A7C2DF0AB8D8045E418@FMSMSX113.amr.corp.intel.com>
 <29250f87b1d84aacb8aa312935582291@FE-MBX1012.de.bosch.com>
 <20161010193958.GE22235@jcartwri.amer.corp.natinst.com>
 <e9661abf93194ad3849e3864a8361993@FE-MBX1012.de.bosch.com>
 <b77ea8ab312149d2b20a717d3ab0a8dc@FE-MBX1012.de.bosch.com>
 <20161013161839.GV10625@jcartwri.amer.corp.natinst.com>
 <f395ea6cd1274fac83d2744121da7441@FE-MBX1012.de.bosch.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Julia Cartwright <julia@ni.com>,
        "Williams, Mitch A" <mitch.a.williams@intel.com>,
        "Kirsher, Jeffrey T" <jeffrey.t.kirsher@intel.com>,
        "linux-rt-users@vger.kernel.org" <linux-rt-users@vger.kernel.org>,
        Sebastian Andrzej Siewior <sebastian.siewior@linutronix.de>,
        "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
        "intel-wired-lan@lists.osuosl.org" <intel-wired-lan@lists.osuosl.org>,
        Greg <gvrose8192@gmail.com>
To: "Koehrer Mathias (ETAS/ESW5)" <mathias.koehrer@etas.com>
Return-path: <netdev-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <f395ea6cd1274fac83d2744121da7441@FE-MBX1012.de.bosch.com>
Sender: netdev-owner@vger.kernel.org
List-Id: linux-rt-users.vger.kernel.org

On Fri, Oct 14, 2016 at 08:58:22AM +0000, Koehrer Mathias (ETAS/ESW5) wrote:
> @@ -753,7 +756,9 @@ u32 igb_rd32(struct e1000_hw *hw, u32 re
>  	if (E1000_REMOVED(hw_addr))
>  		return ~value;
>  
> +        trace_igb(801);
>  	value = readl(&hw_addr[reg]);
> +        trace_igb(802);

Nothing prevents this code from being preempted between the two trace
points, and so you can't be sure whether the time delta in the trace
is caused by the PCIe read stalling or not.

Thanks,
Richard