From owner-freebsd-questions@freebsd.org  Tue Aug  4 21:18:09 2015
Return-Path: <owner-freebsd-questions@freebsd.org>
Delivered-To: freebsd-questions@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 15F519B3D34
 for <freebsd-questions@mailman.ysv.freebsd.org>;
 Tue,  4 Aug 2015 21:18:09 +0000 (UTC) (envelope-from terje@elde.net)
Received: from rand.keepquiet.net (keepquiet.net [144.76.43.178])
 (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits))
 (Client CN "keepquiet.net", Issuer "PositiveSSL CA 2" (verified OK))
 by mx1.freebsd.org (Postfix) with ESMTPS id D00E5D99
 for <freebsd-questions@freebsd.org>; Tue,  4 Aug 2015 21:18:07 +0000 (UTC)
 (envelope-from terje@elde.net)
Received: from [10.130.11.103] (cm-84.210.87.28.getinternet.no [84.210.87.28])
 (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits))
 (No client certificate requested)
 (Authenticated sender: terje@elde.net)
 by rand.keepquiet.net (Postfix) with ESMTPSA id 02171E29;
 Tue,  4 Aug 2015 21:17:58 +0000 (UTC)
References: <CAP1HOmSuohyh=mUQ=BChrsuysPQK=v3hdPAays-zn-zadZUKjA@mail.gmail.com>
In-Reply-To: <CAP1HOmSuohyh=mUQ=BChrsuysPQK=v3hdPAays-zn-zadZUKjA@mail.gmail.com>
Mime-Version: 1.0 (1.0)
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain;
	charset=us-ascii
Message-Id: <3C5A26BE-DC2E-457C-A205-B572FC19325E@elde.net>
Cc: "freebsd-questions@freebsd.org" <freebsd-questions@freebsd.org>
X-Mailer: iPhone Mail (10B500)
From: Terje Elde <terje@elde.net>
Subject: Re: pw operations slow under zfs load
Date: Tue, 4 Aug 2015 23:17:58 +0200
To: javocado <javocado@gmail.com>
X-BeenThere: freebsd-questions@freebsd.org
X-Mailman-Version: 2.1.20
Precedence: list
List-Id: User questions <freebsd-questions.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/options/freebsd-questions>, 
 <mailto:freebsd-questions-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-questions/>
List-Post: <mailto:freebsd-questions@freebsd.org>
List-Help: <mailto:freebsd-questions-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-questions>, 
 <mailto:freebsd-questions-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Tue, 04 Aug 2015 21:18:09 -0000

On 4. aug. 2015, at 23:07, javocado <javocado@gmail.com> wrote:

> So, what's going on here? How does a busy pool with it's own set of drives=

> (which operate off an HBA) affect the speed of operations involving the
> boot volume (a UFS-formatted SSD connected to the mobo)?

First thing that springs to mind is that it's not just a matter of simple IO=
. There's also locking (see man-page for flock and/or lockf). Could this be a=
s simple as whatever is causing the work-load on your ZFS-volume holding a s=
hared lock, on something pw wants to grab an exclusive lock on, prior to doi=
ng the actual change?

Terje=