IETF Logo Mail Archive

Re: [Ntp] [EXT] virtual server for ntp server

"Windl, Ulrich" <u.windl@ukr.de> Wed, 27 March 2024 07:44 UTC

Return-Path: <u.windl@ukr.de>
X-Original-To: ntp@ietfa.amsl.com
Delivered-To: ntp@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 14AAEC14F75F for <ntp@ietfa.amsl.com>; Wed, 27 Mar 2024 00:44:46 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.907
X-Spam-Level:
X-Spam-Status: No, score=-1.907 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DC_PNG_UNO_LARGO=0.001, HTML_MESSAGE=0.001, RCVD_IN_ZEN_BLOCKED_OPENDNS=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01] autolearn=ham autolearn_force=no
Received: from mail.ietf.org ([50.223.129.194]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id qQ2bHyZaphzm for <ntp@ietfa.amsl.com>; Wed, 27 Mar 2024 00:44:44 -0700 (PDT)
Received: from mail01.ukr.de (mail01.ukr.de [193.175.194.181]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id EEFA0C14F74A for <ntp@ietf.org>; Wed, 27 Mar 2024 00:44:38 -0700 (PDT)
X-CSE-ConnectionGUID: s9ceOx/eSqy/Kwa5ivDxyQ==
X-CSE-MsgGUID: bQT2/92YR7msuWK2qIqBaA==
X-ThreatScanner-Verdict: Negative
X-IronPort-AV: E=McAfee;i="6600,9927,11025"; a="707958"
X-IronPort-AV: E=Sophos;i="6.07,158,1708383600"; d="png'150?scan'150,208,217,150";a="707958"
Received: from unknown (HELO ukr-excmb04.ukr.local) ([172.24.6.64]) by dmz-infcsg01.ukr.dmz with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Mar 2024 08:44:34 +0100
Received: from ukr-excmb03.ukr.local (172.24.6.63) by ukr-excmb04.ukr.local (172.24.6.64) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.1.2507.37; Wed, 27 Mar 2024 08:44:34 +0100
Received: from ukr-excmb03.ukr.local ([fe80::1cb4:6e0c:6da4:a8a0]) by ukr-excmb03.ukr.local ([fe80::1cb4:6e0c:6da4:a8a0%4]) with mapi id 15.01.2507.037; Wed, 27 Mar 2024 08:44:34 +0100
From: "Windl, Ulrich" <u.windl@ukr.de>
To: Renzo Marengo <buckroger2011@gmail.com>, "ntp@ietf.org" <ntp@ietf.org>
Thread-Topic: [EXT] [Ntp] virtual server for ntp server
Thread-Index: AQHaf6F808LSsLzuu0uNIUkc80qWU7FLKrZw
Date: Wed, 27 Mar 2024 07:44:34 +0000
Message-ID: <6479b84ba19b400281dd4211c9b1f6fd@ukr.de>
References: <CAMmfGZRc-VmnwYe4ijoCycdCpgRi1OZaiiYDehd4FMQQk3mQdQ@mail.gmail.com>
In-Reply-To: <CAMmfGZRc-VmnwYe4ijoCycdCpgRi1OZaiiYDehd4FMQQk3mQdQ@mail.gmail.com>
Accept-Language: de-DE, en-US
Content-Language: de-DE
X-MS-Has-Attach: yes
X-MS-TNEF-Correlator:
x-originating-ip: [172.24.3.1]
Content-Type: multipart/mixed; boundary="_006_6479b84ba19b400281dd4211c9b1f6fdukrde_"
MIME-Version: 1.0
Archived-At: <https://mailarchive.ietf.org/arch/msg/ntp/XookaxOPQUiTNwZY-H1Q6W_ED0U>
Subject: Re: [Ntp] [EXT] virtual server for ntp server
X-BeenThere: ntp@ietf.org
X-Mailman-Version: 2.1.39
Precedence: list
List-Id: Network Time Protocol <ntp.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/ntp>, <mailto:ntp-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/ntp/>
List-Post: <mailto:ntp@ietf.org>
List-Help: <mailto:ntp-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/ntp>, <mailto:ntp-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 27 Mar 2024 07:44:46 -0000

Hi!


Interestingly „Network Time Protocol Best Current Practices“ does not make a statement about that, but if you think logically:

Assume you have one CPU core and two virtual machine wanting to read the time in a busy loop; how smooth are you expecting the time to be?

Then make another experiment: Read the CPU’s cycle counter and compare it to “wall time”; would you see a constant rate (CPU cycles compared to elapsed wall time)?



So if you don’t over-commit a physical CPU, it might work well enough, but dedicated hardware will run with better statistics, I guess.



The comparison isn’t quite fair, but here are some Offset statistics:

First an old off-the-shelf PC located in a non temperature-controlled room having an even older DCF-77 reference clock (startum-1).

Next an old physical host that is a general-purpose server that also runs NTP (stratum-2).

Finally a virtual server (VMware) that runs as stratum-3.

The last two are housed in a temperature-controlled machine room.

All three are running basically the same operating system (SLES12) and NTP version.



Kind regards,

Ulrich

From: ntp <ntp-bounces@ietf.org> On Behalf Of Renzo Marengo
Sent: Friday, March 15, 2024 11:04 AM
To: ntp@ietf.org
Subject: [EXT] [Ntp] virtual server for ntp server

I'm not able to find official document which suggests to not implement ntp server using virtual machine; I'd like to know reasons but specially what RFC shows this recommendation.

v2.23.0 | Report a Bug | By Email