[Top] [All Lists]

NTools ENewsFlash -- Report: NT 3.5x Faster Than Linux

To: (Ariel Faigon)
Subject: NTools ENewsFlash -- Report: NT 3.5x Faster Than Linux
From: Raj Mathur <>
Date: Thu, 15 Apr 1999 10:36:04 +0530 (IST)
Cc: (SGI/Linux mailing list)
In-reply-to: <>
References: <>
>>>>> "Ariel" == Ariel Faigon <> writes:

    Ariel> [I'm forwarding a message that bounced.  Just thought some
    Ariel> people may be interested.  To add to what Eric wrote,
    Ariel> another thing that I find strange is that they are
    Ariel> comparing NT 3.5 rather than the latest NT 4.x to Linux.  I
    Ariel> also believe some of the results are missing crucial
    Ariel> details, like how the two very different web servers were
    Ariel> configured (e.g. standalone vs from inetd, ssi turned on
    Ariel> etc.) who paid for the report, full disclosures...  --
    Ariel> Ariel]


[About 3/4th way down the report]

Mindcraft, Inc. conducted the performance tests described in this
report between March 10 and March 13, 1999. Microsoft Corporation
sponsored the testing reported herein.

[Lookee who paid for it! ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^]

Mindcraft certifies that the results reported accurately represent the
file-server performance of Microsoft Windows NT Server 4.0 and Red Hat
Linux 5.2 upgraded to the Linux 2.2.2 kernel with Samba 2.0.1 running
on a Dell PowerEdge 6300/400 as measured by NetBench 5.01. Also, we
certify that the Web-server performance reported for Windows NT Server
4.0 with IIS 4 and for Red Hat Linux 5.2 upgraded to the Linux 2.2.2
kernel with Apache 1.3.4 accurately represent the WebBench 2.0
measurements we made on a Dell PowerEdge 6300/400.

Our test results should be reproducible by others using the same test
lab configuration, the same Dell computer, and the software
configurations and modifications documented in this report.

[End snippet]

    Ariel> April 14, 1999 : :Hi All, : :As most of you know, when some
    Ariel> important news hits the :wires we will inform you
    Ariel> immediately. This morning I :found something in my in-box
    Ariel> that will definitely throw :some more gasoline on the
    Ariel> raging 'NT vs Linux' fire.  : :I quickly read through the
    Ariel> report and could not find :anything wrong with it at first
    Ariel> observation. The numbers :seem to be correct, as they are
    Ariel> using an industry standard :benchmark that I have used
    Ariel> myself as well, the ZD bench.  : :Oh, before I forget,
    Ariel> Novell actually wrote a rebuttal :against that last report
    Ariel> that SMS is better than ZEN.  :Interesting reading, and
    Ariel> this gives the Novell POV:
    Ariel> : :
    Ariel> :But here comes today's bomb in the NT vs Linux battle.
    Ariel> :One wonders who pays for these tests but I will ask the
    Ariel> :CEO of MindCraft and report on that in the next coming
    Ariel> :newsletter. Here goes!  : : :LOS GATOS, Calif., April
    Ariel> 13. Today, Mindcraft released the results :of a study
    Ariel> comparing the performance of Red Hat Linux 5.2 (updated :to
    Ariel> the Linux 2.2.2 kernel) and Microsoft Windows NT Server 4.0
    Ariel> :operating systems. According to the report, Windows NT
    Ariel> Server :provides over three and a half times the
    Ariel> performance of Linux as a :Web server.  Furthermore, the
    Ariel> report shows that when testing Windows :NT Server and Linux
    Ariel> as file servers, Windows NT Server provides over :two and a
    Ariel> half times the performance of Linux.  The full report,
    Ariel> :including all of the details needed to reproduce the
    Ariel> tests, is on :Mindcraft's Web site at: :
    Ariel> :  :
    Ariel> :Using benchmarks from Ziff-Davis Benchmark Operation
    Ariel> (ZDBOp), the :report compares the peak performance levels
    Ariel> of both Windows NT :Server and Linux configured both as a
    Ariel> file server and a Web server.  : :All tests were performed
    Ariel> on a standard Dell PowerEdge 6300/400 server :with four
    Ariel> 400-MHz Xeon CPUs, 1GB RAM (960MB for Linux -- this is the
    Ariel> :default maximum amount of RAM that Linux supports).  To
    Ariel> simulate a :client load, Mindcraft used 144 physical client
    Ariel> test systems; half :were running Windows 95 and the other
    Ariel> half were running Windows 98.  : :Both Linux and Windows NT
    Ariel> Server were tuned to perform optimally under :each of the
    Ariel> two workloads.  "We started the tests using standard Red
    Ariel> Hat :Linux 5.2 but had to update it because it does not
    Ariel> support hardware RAID :controllers and SMP at the same
    Ariel> time," said Mindcraft's president, Bruce :Weiner.  "Linux
    Ariel> definitely takes more time and resources to tune and to
    Ariel> :configure than Windows NT Server.  You have to search the
    Ariel> Net to find the :latest kernel and driver versions to get
    Ariel> the highest performance and most :reliable modules. Then
    Ariel> when you're done, Linux fails to deliver the same :level of
    Ariel> performance as Windows NT Server on enterprise-class
    Ariel> servers."  : :Mindcraft's report shows that using ZDBOp's
    Ariel> WebBench 2.0 Web server :benchmark, Windows NT Server and
    Ariel> Internet Information Server (IIS) 4.0 :reach a peak of
    Ariel> 3,771 requests/second and 22.4 Megabits/second(Mbps) of
    Ariel> :throughput. The report goes on to show that Linux and the
    Ariel> Apache 1.3.4 :Web server reach a peak of 1,000
    Ariel> request/second and 5.9 Mbps of :throughput.  The WebBench
    Ariel> 2.0 tests also revealed that there are problems :with
    Ariel> Linux/Apache at high client loads. "The Linux/Apache Web
    Ariel> server :performance collapsed with a WebBench load above
    Ariel> 160 client test threads, :while Windows NT Server/IIS
    Ariel> continued to increase performance up through :288 client
    Ariel> test threads without reaching their peak performance," adds
    Ariel> :Mindcraft's Bruce Weiner.  : :To simulate a file server
    Ariel> workload, Mindcraft used ZDBOp's NetBench :5.01 benchmark.
    Ariel> The testing revealed that Windows NT Server performance
    Ariel> :peaked at 286.7 Mbps with 112 clients, while Linux running
    Ariel> Samba 2.0.1 :peaked at 114.6 Mbps with only 48 clients.
    Ariel> "The integration of the SMB :file sharing protocol with the
    Ariel> multi-processor kernel is a key performance :win for
    Ariel> Windows NT Server," said Weiner. "Customers benefit every
    Ariel> day from :the superior scalability of Windows NT Server,
    Ariel> which delivers vital file :and web services at two to three
    Ariel> times the performance of Linux as shown :in these
    Ariel> benchmarks," said Edmund Muth, Group Product Manager,
    Ariel> Microsoft :Corporation. "Empirical data like this helps
    Ariel> customers and planners make :informed decisions, and
    Ariel> showcases the industrial strength technology and :mature
    Ariel> engineering of the Windows NT Server operating system."  :
    Ariel> :About Mindcraft : :Mindcraft is a service-oriented,
    Ariel> independent test lab. The company was :founded in 1985 to
    Ariel> provide high quality services and products to vendors :and
    Ariel> end users who want to test software, system, and network
    Ariel> products.  :Mindcraft is committed to work to promote
    Ariel> standards in our industry.  :Mindcraft is the only test lab
    Ariel> to be a member of the Standard Performance :Evaluation
    Ariel> Corporation (SPEC).
    Ariel> :-------------------------------------- : :That's all for
    Ariel> this NewsFlash!  : :Warm regards, : :Stu : : :[]
    Ariel> This is a posting from the :nt-list, To unsubscribe, send a
    Ariel> blank email :to
    Ariel> :For
    Ariel> killer servers at unbelievable prices check out:
    Ariel> : : :

    Ariel> -- Peace, Ariel

<Prev in Thread] Current Thread [Next in Thread>