Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 7 Sep 2019 18:58:13 -0700
From:      Conrad Meyer <cem@freebsd.org>
To:        "Constantine A. Murenin" <cnst++@freebsd.org>
Cc:        "freebsd-arch@freebsd.org" <freebsd-arch@freebsd.org>
Subject:   Re: What value HZ?
Message-ID:  <CAG6CVpU8732Ci0QM7=tBn0ifHf8yO-53FBtvBCF34StBDTCx-A@mail.gmail.com>
In-Reply-To: <CAPKkNb4ETFzD7pXi3=iDUxtSxZSffxFB5q9ZtmsJy2FUuaZB5A@mail.gmail.com>
References:  <201909060119.x861JWrG006910@repo.freebsd.org> <4917d7507b6ea6c360dccda261f53052aa085f2b.camel@freebsd.org> <5EE266EE-E650-48D8-9B0E-E674AD026470@freebsd.org> <3cb6429acc7e520932d2c906d1cac47540156355.camel@freebsd.org> <8F03EA29-0F3F-4321-9241-78F7C924FDE1@freebsd.org> <CANCZdfr6pz19NCLmsua6iGzusotrcHN=u47RH7Y1PdM4rnomZA@mail.gmail.com> <9BC03B61-F8B5-476C-AD34-9DEA5230BFCF@freebsd.org> <CANCZdfqbp%2BU3=0EM2n3bhg4DwXd_PVjvEYjGyQhkE5-MK-3-QA@mail.gmail.com> <CAPKkNb4ETFzD7pXi3=iDUxtSxZSffxFB5q9ZtmsJy2FUuaZB5A@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Hi Constantine,

On Sat, Sep 7, 2019 at 3:05 PM Constantine A. Murenin
<cnst++@freebsd.org> wrote:
>
> For the sake of discussion, I recall that there was a measurable power
> consumption difference between FreeBSD (HZ=3D1000) and OpenBSD (HZ=3D100)=
 when
> I played with a Kill-A-Watt a number of years ago.

Unfortunately, this is an apples to oranges comparison, and perhaps
worse, vague and dated.  It would be more interesting to compare
HZ=3D1000 to HZ=3D100 with an otherwise identical CURRENT FreeBSD system.

As far as I can tell, FreeBSD grew "tickless" timer support in r212541
in 2010 (thanks mav@).  This is easily observed on my idle HZ=3D1000
amd64 system with 'vmstat -i': "cpu0:timer" is firing at an average
rate of 21 Hz =E2=80=94 not 1000.  And that is the most frequent interrupt.

> Would it perhaps be prudent to try to qualify whether, and by how much,
> this change affects power consumption on MIPS/ARM/RISCV, not just whether
> each arch could cope with the change?

If someone has the time and inclination, then of course, it could be
an interesting test to run.

Best,
Conrad



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAG6CVpU8732Ci0QM7=tBn0ifHf8yO-53FBtvBCF34StBDTCx-A>