From owner-freebsd-arm@freebsd.org  Wed Sep 13 10:52:12 2017
Return-Path: <owner-freebsd-arm@freebsd.org>
Delivered-To: freebsd-arm@mailman.ysv.freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org
 [IPv6:2001:1900:2254:206a::19:1])
 by mailman.ysv.freebsd.org (Postfix) with ESMTP id 57229E1A0BD
 for <freebsd-arm@mailman.ysv.freebsd.org>;
 Wed, 13 Sep 2017 10:52:12 +0000 (UTC)
 (envelope-from freebsd@theory14.net)
Received: from bacon.theory14.net (bacon.theory14.net [45.55.200.27])
 by mx1.freebsd.org (Postfix) with ESMTP id 302C9826BA
 for <freebsd-arm@freebsd.org>; Wed, 13 Sep 2017 10:52:12 +0000 (UTC)
 (envelope-from freebsd@theory14.net)
Received: from remote.theory14.net (remote.theory14.net [173.79.116.36])
 by bacon.theory14.net (Postfix) with ESMTPSA id 1627D126011;
 Wed, 13 Sep 2017 06:52:11 -0400 (EDT)
Received: from anubis.int.theory14.net (anubis.int.theory14.net
 [192.168.10.50])
 by remote.theory14.net (Postfix) with ESMTPS id D136260D5;
 Wed, 13 Sep 2017 06:52:10 -0400 (EDT)
Content-Type: text/plain; charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 9.3 \(3124\))
Subject: Re: Beaglebone Black + FreeBSD + USB WiFi = WAP?
From: Chris Gordon <freebsd@theory14.net>
In-Reply-To: <20170913070805.6545490.83195.31798@gmail.com>
Date: Wed, 13 Sep 2017 06:52:10 -0400
Cc: freebsd-arm <freebsd-arm@freebsd.org>
Content-Transfer-Encoding: quoted-printable
Message-Id: <C49A9000-DC90-47E5-898D-2BE19B99C8E4@theory14.net>
References: <40EA308E-489D-4A0B-B75A-2CA5A4EC474E@theory14.net>
 <CABx9NuQJWot9xgs1QtzJ87NfgZM=FPhZ+2a-RewDonvGG5LLKg@mail.gmail.com>
 <CABx9NuT1n8ZYPrZTB8vT2sBmT3U75E4UFgAGA3ZOPTotpsUWeg@mail.gmail.com>
 <CABx9NuQB=xBNt6+X=YKw4XVW5u1XysW+o7pqO_9D2RC+F6bKug@mail.gmail.com>
 <20170905141711.6545490.14963.31294@gmail.com>
 <656A5193-7389-476C-AF58-EB013E9155F3@theory14.net>
 <CABx9NuQtXRbN6YPihotuLSnE5cFG-xvRRNYyFSLGxZNPBnKTKQ@mail.gmail.com>
 <E1992F2B-236D-467C-AAEE-B81A59EB1138@theory14.net>
 <CABx9NuTTewBiuesSxWsWsJg2HeRZFPeNU1WSRpqxEALxSUEhkw@mail.gmail.com>
 <C8BC1549-0F48-4244-8240-665276DEBB6A@theory14.net>
 <20170913070805.6545490.83195.31798@gmail.com>
To: Russell Haley <russ.haley@gmail.com>
X-Mailer: Apple Mail (2.3124)
X-BeenThere: freebsd-arm@freebsd.org
X-Mailman-Version: 2.1.23
Precedence: list
List-Id: "Porting FreeBSD to ARM processors." <freebsd-arm.freebsd.org>
List-Unsubscribe: <https://lists.freebsd.org/mailman/options/freebsd-arm>,
 <mailto:freebsd-arm-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-arm/>
List-Post: <mailto:freebsd-arm@freebsd.org>
List-Help: <mailto:freebsd-arm-request@freebsd.org?subject=help>
List-Subscribe: <https://lists.freebsd.org/mailman/listinfo/freebsd-arm>,
 <mailto:freebsd-arm-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Wed, 13 Sep 2017 10:52:12 -0000

Poor performance was still present this morning, but as soon as I =
restarted the network interfaces, everything returned to =E2=80=9Cfull =
speed=E2=80=9D.  This seems to confirm the idea of something happening =
over time in the kernel as opposed to some congestion or other =
environmental factor.  This evening, I=E2=80=99ll look at either =
updating your bug report or opening a new one.

> On Sep 13, 2017, at 3:08 AM, Russell Haley <russ.haley@gmail.com> =
wrote:
>=20
> Need some sort of script to monitor performance of various things.=20
> Netstat
> Load average
>=20
> Dtrace would be good for looking into locks,mem consumption at =
specific calls. Start looking at how long each syscall is taking?

Agree.  At least in my case, it=E2=80=99s something that isn=E2=80=99t a =
problem initially and then builds up/falls over and becomes a problem.

> Have you compared against a linux image on the same unit?

I started to setup the full access point config with Linux for testing, =
but just didn=E2=80=99t have the patience to deal with it.  I=E2=80=99m =
not sure that will reveal much given what I=E2=80=99ve found so far.

Thoughts?

Thanks,
Chris=