From owner-freebsd-hackers@FreeBSD.ORG  Sat Oct  4 16:02:33 2014
Return-Path: <owner-freebsd-hackers@FreeBSD.ORG>
Delivered-To: freebsd-hackers@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115])
 (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits))
 (No client certificate requested)
 by hub.freebsd.org (Postfix) with ESMTPS id 12FD0CE7;
 Sat,  4 Oct 2014 16:02:33 +0000 (UTC)
Received: from mho-02-ewr.mailhop.org (mho-02-ewr.mailhop.org [204.13.248.72])
 (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits))
 (Client did not present a certificate)
 by mx1.freebsd.org (Postfix) with ESMTPS id D8B2A3BA;
 Sat,  4 Oct 2014 16:02:32 +0000 (UTC)
Received: from [73.34.117.227] (helo=ilsoft.org)
 by mho-02-ewr.mailhop.org with esmtpsa (TLSv1:AES256-SHA:256)
 (Exim 4.72) (envelope-from <ian@FreeBSD.org>)
 id 1XaRmr-0009fx-Jh; Sat, 04 Oct 2014 16:02:25 +0000
Received: from [172.22.42.240] (revolution.hippie.lan [172.22.42.240])
 by ilsoft.org (8.14.9/8.14.9) with ESMTP id s94G2O2H024120;
 Sat, 4 Oct 2014 10:02:24 -0600 (MDT) (envelope-from ian@FreeBSD.org)
X-Mail-Handler: Dyn Standard SMTP by Dyn
X-Originating-IP: 73.34.117.227
X-Report-Abuse-To: abuse@dyndns.com (see
 http://www.dyndns.com/services/sendlabs/outbound_abuse.html for abuse
 reporting information)
X-MHO-User: U2FsdGVkX18RO1IMZKw53K0h4Fh6wy51
X-Authentication-Warning: paranoia.hippie.lan: Host revolution.hippie.lan
 [172.22.42.240] claimed to be [172.22.42.240]
Subject: Re: freebsd 10 kqueue timer regression
From: Ian Lepore <ian@FreeBSD.org>
To: Paul Albrecht <palbrecht@glccom.com>
In-Reply-To: <8587D819-AA2F-4387-A4E9-523014384672@glccom.com>
References: <8ABC0977-FB8F-45E7-ACCC-BFA92EE22E1C@glccom.com>
 <CAJ-VmonJQKWeW7K6+jY6=FpmZrm+6HQOuBmhhjJEapyVpwNFdQ@mail.gmail.com>
 <8587D819-AA2F-4387-A4E9-523014384672@glccom.com>
Content-Type: text/plain; charset="iso-8859-13"
Date: Sat, 04 Oct 2014 10:02:23 -0600
Message-ID: <1412438543.12052.107.camel@revolution.hippie.lan>
Mime-Version: 1.0
X-Mailer: Evolution 2.32.1 FreeBSD GNOME Team Port 
Content-Transfer-Encoding: quoted-printable
X-MIME-Autoconverted: from 8bit to quoted-printable by ilsoft.org id
 s94G2O2H024120
Cc: "freebsd-hackers@freebsd.org" <freebsd-hackers@freebsd.org>,
 Adrian Chadd <adrian@freebsd.org>
X-BeenThere: freebsd-hackers@freebsd.org
X-Mailman-Version: 2.1.18-1
Precedence: list
List-Id: Technical Discussions relating to FreeBSD
 <freebsd-hackers.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/options/freebsd-hackers>, 
 <mailto:freebsd-hackers-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-hackers/>
List-Post: <mailto:freebsd-hackers@freebsd.org>
List-Help: <mailto:freebsd-hackers-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-hackers>,
 <mailto:freebsd-hackers-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Sat, 04 Oct 2014 16:02:33 -0000

On Thu, 2014-10-02 at 13:13 -0500, Paul Albrecht wrote:
> On Oct 2, 2014, at 12:18 PM, Adrian Chadd <adrian@freebsd.org> wrote:
>=20
> > On 2 October 2014 08:07, Paul Albrecht <palbrecht@glccom.com> wrote:
> >>=20
> >> Hi,
> >>=20
> >> What=FFs up with freebsd 10? I=FFm testing some code that uses the k=
queue timer for timing and it doesn=FFt work because the precision of the=
 timer is off.
> >=20
> > Can you provide a test case for it?
>=20
> Here=FFs the code:
>=20
> #include <stdio.h>
> #include <stdlib.h>
> #include <string.h>
> #include <unistd.h>
> #include <errno.h>
> #include <sys/types.h>
> #include <sys/event.h>
> #include <sys/time.h>
>=20
> int
> main(void)
> {
>         int i,msec;
>         int kq,nev;
>         struct kevent inqueue;
>         struct kevent outqueue;
>         struct timeval start,end;
>=20
>         if ((kq =3D kqueue()) =3D=3D -1) {
>                 fprintf(stderr, "kqueue error!? errno =3D %s", strerror=
(errno));
>                 exit(EXIT_FAILURE);
>         }
>         EV_SET(&inqueue, 1, EVFILT_TIMER, EV_ADD | EV_ENABLE, 0, 20, 0)=
;
>=20
>         gettimeofday(&start, 0);
>         for (i =3D 0; i < 50; i++) {
>                 if ((nev =3D kevent(kq, &inqueue, 1, &outqueue, 1, NULL=
)) =3D=3D -1) {
>                         fprintf(stderr, "kevent error!? errno =3D %s", =
strerror(errno));
>                         exit(EXIT_FAILURE);
>                 } else if (outqueue.flags & EV_ERROR) {
>                         fprintf(stderr, "EV_ERROR: %s\n", strerror(outq=
ueue.data));
>                         exit(EXIT_FAILURE);
>                 }
>         }
>         gettimeofday(&end, 0);
>=20
>         msec =3D ((end.tv_sec - start.tv_sec) * 1000) + (((1000000 + en=
d.tv_usec - start.tv_usec) / 1000) - 1000);
>=20
>         printf("msec =3D %d\n", msec);
>=20
>         close(kq);
>         return EXIT_SUCCESS;
> }
>=20
> When I run it on my system I get these results:
>=20
> ./a.out
> msec =3D 1072
> ./a.out
> msec =3D 1071
> ./a.out
> msec =3D 1071
>=20
> Which is over about 3.5 times the wait time per second.
>=20
>=20
> >=20
> > I just chased down one of those recently; maybe it's the same thing
> > (callout() API changes.)
> >=20
> >=20

FYI, I just committed the fix to -current as r272528.  I'll MFC it to
10-stable in 3 days, and then we'll see if it can get into the 10.1
release cycle.

-- Ian