Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Sm@rtReseller and good Linux Press

Hemos posted more than 15 years ago | from the you-best-respect-me dept.

Linux 93

David E. Smith writes "The five millionth ZDNet publication, Sm@rtReseller, has a neat Linux article. Basically, given the same hardware, they ran three different Linux distributions and Windows NT and benchmarked them. Guess who won. "

cancel ×

93 comments

Numerical results (0)

Anonymous Coward | more than 15 years ago | (#2028092)

Nice article, but where are the graphs, charts and numbers?

Anyone have the chart? (0)

Anonymous Coward | more than 15 years ago | (#2028093)

The graph with the benchmarking results in it was missing. Anyone have an url to the graph, or the actual performance numbers?

Windows NT requires 16 GB disk space....... (0)

Anonymous Coward | more than 15 years ago | (#2028094)

http://www.zdnet.com/sr/stories/special/0,4936,219 6127,00.html

That about says it all.....

follow the links (0)

Anonymous Coward | more than 15 years ago | (#2028095)

follow the links in the sidebar at the upper right hand corner. it's there, and boy does NT look bad... :-) especially when you consider the price, the bundled dev tools, and the hardware requirements. nothing new to Linux admins, but it should open the eyes of NT converts.

Not Enough Clients (0)

Anonymous Coward | more than 15 years ago | (#2028096)

This was an enlightening article, but I wish they had tested with more clients. 30 clients is a fairly trivial network. How about 100 clients? Will the trends hold true?

In the web server comparison, the article states that compilation and the quality of the binary are the reasons for the performance difference of Apache on the three distros. Is this true? I thought they all used gcc. Or am I just completely misunderstanding their point? Can anyone enlighten me on this?

Hardware support (0)

Anonymous Coward | more than 15 years ago | (#2028097)

I had a generic s3 trio64+ card that caused NT to blue screen on install. I had to go out and get a matrox card to complete the install.

please read the article..... (0)

Anonymous Coward | more than 15 years ago | (#2028098)

and you will find your answer to the apache question. it is clearly stated on the same page as the graph.

Windows NT requires 16 GB disk space....... (0)

Anonymous Coward | more than 15 years ago | (#2028099)

that must be a mistake.

really, the size of an OS is really no longer a real big issue for most servers; back in the day when 500mb drives were common, yes, but not any longer. NT Server installs just fine in 400mb or so, give or take some. however, I really enjoy how Linux can really be pared down to almost nothing, while NT has a larger "bare minimum" footprint.

just rcompile with -02 and pentium setting :) (0)

Anonymous Coward | more than 15 years ago | (#2028100)

if your ead the article instead of just looking at the graphs you would have noticed that they had different versions of apache. this is where the biggest performance discrepancies come in but apache does have compile time options and many config tweaks that can make a big difference on performance under different circumstances. please read the documentation that come with apache for furthur information.

Almost unfair... (0)

Anonymous Coward | more than 15 years ago | (#2028101)

Aside from any issues of kernel efficiency or stability, Linux had one advantage in this test that's almost unfair: It wasn't running X-Windows. The Linux servers didn't have to deal with the extra overhead of running a GUI on a machine that (ideally) an operator will only have to touch the console occasionally; NT did. Boo hoo.


I've seen a lot of Microsoft supporters blathering about having a separate GUI running on top of a character-based operating system; after all, look at Win 3.X/DOS. What a load of BS. One lousy implementation does not prove that the concept is wrong.

Numerical results (0)

Anonymous Coward | more than 15 years ago | (#2028102)

There is a little box in the upper right hand corner of the article linking to all the charts.

Their mimimum hardware requirements were way off, BTW. The NT listings were ludicrously high. But even with NT's true minimum requirements, Linux can still scale to even lower hardware still.

Not missing (0)

Anonymous Coward | more than 15 years ago | (#2028103)

Please read the page. The links are right there in the article.

Graphs, yes; and it's amazingly realistic for ZD (0)

Anonymous Coward | more than 15 years ago | (#2028104)


Go carefully here.

There is an antitrust case going on right now and ZD's masters are desperate to demonstrate there is competition in the industry.

Expect this article to be submitted in evidence in the near future.

No way... (0)

Anonymous Coward | more than 15 years ago | (#2028105)

Not to argue for MS, but 1.6GB or .16GB, but it doesn't take 16GB to run NT.

Different compilations of Apache (0)

Anonymous Coward | more than 15 years ago | (#2028106)

So what you're saying is that the Apache code base for each distribution was different. That makes sense!

Yes! (0)

Anonymous Coward | more than 15 years ago | (#2028107)

Who says you have to let your webserver play
around in kernel space to get the maximum
performace! Go Linux!

Would Like to See Novell (0)

Anonymous Coward | more than 15 years ago | (#2028108)

It would be nice to see how NetWare would place in this comparison. I understand that it too is faster than NT, but how does is compare to Linux with Samba? Does anyone have any figures &/or experience comparing NetWare & Linux file sharing performance?

and all those whose main entitle is themselves... (0)

Anonymous Coward | more than 15 years ago | (#2028109)

To quote that bully kid from The Simpsons:

"Haa ha!"

not necesarily (0)

Anonymous Coward | more than 15 years ago | (#2028110)

NT doesn't load the necessary DLL's for the full Windows GUI until you log in. NT at the login screen is roughly equivalent to running X with xdm .

About stress testing (0)

Anonymous Coward | more than 15 years ago | (#2028111)

I used to work for a major testing firm who's name most people here would probably recognize. I was tasked many moons ago to run a test of three operating systems. NT was supposed to be tested against Netware & OS2. It came in dead last. Those results were never published because the lab was owned by a big publisher, and MS threatened to pull ads.

Another interesting point, NT dropped off like a brick after a little more than 40 clients. Keep in mind, this was on 10Mbps ethernet. The other servers chugged along just fine. I wonder how soon NT would have dropped off at 100Mbps? This version of NT was 3.5 and then tested again with slightly better results with Pre-release 3.51 (Daytona IIRC). Even Daytona was no match for the competition.

I would really like to see an extension of this testing to give us more verbose results. Where does NT drop off? Linux? How much more performance is available through tuning? (not changing source code mind you)

How much better is the 2.2 kernel with Samba 2.0?

These are all questions I am eager to see answered quantitatively.

Gotta love this quote (0)

Anonymous Coward | more than 15 years ago | (#2028112)

"According to ZDLabs' results (see test charts), each of the commercial Linux releases ate NT's lunch."

That's hillarious. Nice fodder to dispell FUD.

But it would be nice to see. (0)

Anonymous Coward | more than 15 years ago | (#2028113)

Even if the protocols are different and Novell uses NCP, the performance graph would be interesting.

You could even test Novell's webserver (although I have not been very impressed with it. If you run BoarderManager, it rocks).

And Smart Reseller also had an article about migrating from NetWare4.11. It costs 3X as much to move to NT as it does to move to NetWare5.0.

:)

They should also benchmark WarpServer, just to be inclusive. :)

Then let EVERYONE see which server is best for their needs.

Do they need fast web serving?

Do they need fast file serving?

Do they need fast application serving?

Definitely fair (0)

Anonymous Coward | more than 15 years ago | (#2028114)

A server ISN'T supposed to run a GUI. I run a SAMBA/sendmail/diald/Apache/php3 server for a bunch of dorky dos/windows puters. A 486 with 8 meg of ram, a freebie box that was put together with garage sale stuff.

I just came back to work after being out of the office for three weeks, and Ugly was still running. Even the Social Workers in the office couldn't kill it.

Apache & reverse DNS lookup (0)

Anonymous Coward | more than 15 years ago | (#2028115)


The default used to be to enable this to make the log files more readable - at a 50% cost in performance! My guess, though, is that they disable it out of the box now.

Mark

Someone will give Linux preferential treatment (0)

Anonymous Coward | more than 15 years ago | (#2028116)


Yes, they still promote NT but I'll bet this will change by summertime, if things keep going like they are.

Who'd a thunk it back in 1996???

Mark

Different compilations of Apache (0)

Anonymous Coward | more than 15 years ago | (#2028117)

Thanks for the clarification. I was trying to agree, but apparently my vague language got in the way. :)

My original confusion was that the article seemed to imply that the Apache binaries generated on the various distros would be different. That is, I read the article to say that if all things (code version, compiler flags, etc.) were the same, the binaries would be more efficient on some distros than others. Since they didn't specifically mention that the versions of Apache were different, I assumed they would be the same. Being new to Linux, I had completely overlooked the impact of the libc5 vs. glibc libraries.

Thanks for the info.

I will play the part of the FUDpuppet. (0)

Anonymous Coward | more than 15 years ago | (#2028118)

"But NT can be administered by anyone familiar with Windows."

"But Linux is legacy Unix code."

"Well, if you want to pay some Unix geek $250K a year......."

"Where are you going to go for support?"

"It's a school project type OS."

Prepare yourself for these arguements.

Linux is based upon proven, stable practices. The practices are old but the code is new and can be shown in that Linux is already 64bit while NT is still trying to catch up.

NT is easier to admin if you don't have any problems. Unix people are generally more expensive, but each Unix person can administer at least 2x as many servers as the average NT admin can. That means that if you have 2 or more NT admins, you're wasting money. Besides, you can always connect with a contractor (I'm one) for a very reasonable monthly or hourly rate.

Where do you go for support now? www.bugnet.com refused to give MS the award for patches or responsiveness to issues brought to their attention. Linux is patched within 48 hours of any bug being detected (sometimes less than 1 hour).

Practice your rebutals to the FUD you'll be facing and keep pushing the stability and reliability issues.

You don't need help if you're not in trouble.

If you use Linux, you're not in trouble.

Python not included?!!?! (0)

Anonymous Coward | more than 15 years ago | (#2028119)

Waddaya mean Python not included?
I bought RH5.1 a year ago and it included python...

I don't know about SUSE and Caldera, though...

SIGH! Reread it, the tests *were* at 100Mb (0)

Anonymous Coward | more than 15 years ago | (#2028120)

Each had 64MB of memory and a 4GB IDE disk drive. An
Intel Corp. EtherExpress Pro 100B network interface card connected the server
to our client network, which is driven by a pair of Synoptics (now Nortel
Networks) 28115 Fast Ethernet switches. All tests ran at a network speed of
100Mbps.

Engineering benchmarking? (0)

Anonymous Coward | more than 15 years ago | (#2028121)

Has anybody seen similar tests done for engineering/scientific applications?
Like finite element analysis, or intensive simulation or something?

How about for compiling the same code. Such as Java or C without graphics.

Microsoft's Fault (0)

Anonymous Coward | more than 15 years ago | (#2028122)

Amen, brother!

I interviewed for a job at MS once for a QA position in the NT display drivers group.

I asked the guy straight-up why they let graphics drivers run in priviledged (kernel) mode. He said that people complained NT 3.51 was "too slow". What he meant to say is that MS went for style over substance. NT 3.51 video drivers ran in non-priviledged (user) mode. Sure, this IS a little slower, but a buggy video driver won't bluescreen your box. A LOT of bluescreens are caused by bad video drivers in NT 4.

This was MS decision, but admins are the ones getting screwed. If you don't want to run X on your Linux server, more power to you.

Speed diff among distributions (0)

Anonymous Coward | more than 15 years ago | (#2028123)

Can sombody explain to me why the speed difference was so huge? I expected it to be more or less the same, or close. Of course everything depends on how distros are configured, but still it just doesn't seem reasonable. Comments?

Try a 3dfx card some time (0)

Anonymous Coward | more than 15 years ago | (#2028124)


NT won't even see it. Not even the workstation.

they did (0)

Anonymous Coward | more than 15 years ago | (#2028125)

Check out benchmarks at www.calderasystems.com. They were running Netscape-something.

Graphs, yes; and it's amazingly realistic for ZD (0)

Anonymous Coward | more than 15 years ago | (#2028126)

Be afraid. Very afraid.

Tuning => bad benchmark (0)

Anonymous Coward | more than 15 years ago | (#2028127)

Because then it becomes an argument about how knowledgable they are about the versions, and how well they tuned each version.

Out of the box may not be realistic or best, but it is somewhat objective and more likely to be repeatable.

Regards,
Ben Tilly

Hardware support (0)

Anonymous Coward | more than 15 years ago | (#2028128)

Funny thing is that in some instances Linux have
better hardware support than Windows 9x! I had
recently ungraded a motherboard on my computer
to atx and dual booted Win98 and Linux on it.
The doze mode feature worked well in Linux to
my surprize and still to my surprize the feature
doesn't work since it BSODs on restart!

Same thing happened when I tried to change the
video card. It is a major pain changing video
cards on a preconfigured Windows box.

Novell *has* samba available... (0)

Anonymous Coward | more than 15 years ago | (#2028129)

Its not really well known, apparently it got ported RIGHT as MS decided that Novell was too dangerous, and then Novell was not going to be concilatory.

http://www.gurdon.com/novell/netware4/samba/

Now, this would measure SMB (ick, yuck, bleah) networking. Which is handy, but crappy.

I'd be interested in Novell with SMB, but Novell with NCP (Netware Core Protocol) ought to toast any of those in performance. (Novell is VERY fast)

(I'm waiting for Novell to get off their ass and start writing client code for Linux)

Addison

New ms marketing slogan (0)

Anonymous Coward | more than 15 years ago | (#2028130)

Widnows NT is fast and scaleable.Infact its so scaleable that its only twice as slow as linux. ONLY twice as slow. Wow, what an improvement from windows98 that was unstable and 4 times slower then linux.

Go with windows. Its twice as fast under heavy loads and can handle requests oly half the speed of freeware.

look at the upper right corner of the page (0)

Anonymous Coward | more than 15 years ago | (#2028131)

the website was designed poorly. ITs under related stories on the upper right hand corner. IT should of said links. It was a mistake. ITs just pure benchmarking results for the current story. I emailed the web master on this

Ms crippled iis performance on purpose (0)

Anonymous Coward | more than 15 years ago | (#2028132)

Hmmm now how are we going to make more money. WAIT! I know. Instead of having everyone pay for a high performance web server with 4.0 we can charge our customers twice by fits 1.) Including iis for free with NT server 4.0
2.) crippling the NT 4.0 version so all the users will go frantic into buying NT 5.0.

This will therfor force customers to pay for NT twice and it will hide the benifits of linux.

What a user hears when the press says "NT 5.0 is easier to use and alot foster with large memory and disk caching will improve performance" is we need NT 5.0. All of our 4.0 machines really suck. WOW twice the performance aaaaaaa! Give me! here is my wallet.

After awaiting for the promiseware for awhile the user will then hear "linux is almost 250% faster then NT 4.0". What the nt slave user will hear form the same article is " linux faster then 4.0 but that not fair because 4.0 is outdating NT 5.0 is twice as fast. Therefor NT5.0 is just a s good"

You see if we cripple nt 4.0 and physcological manipulate the consumer then they will be hooked on upgrades that they believe will be faster.

Just look at the hype with windows95 . We at Microsoft talked about premptive multitasking and compared it to nix for so long that consumers thought windows95 was suppior to unix ans was more stable. Even the administrators believed this after our pawn zdnet over hyped it.

MY cousin in Tampa works at a unix help desk (0)

Anonymous Coward | more than 15 years ago | (#2028133)

there are unix jobs. the whole southern culture likes to stick with something more once they invested alot of time and money. THey are just more laid back and conservative. They were also the last to switch to clones rather then pure IBM machines

Replace those *LEGACY* NT systems! (0)

Anonymous Coward | more than 15 years ago | (#2028134)

heh.. it'd be cool if all the booths at LinuxWorldExpo hawked Linux as a "smooth upgrade for your legacy NT systems in your enterprise!"

Mail Server Performance (0)

Anonymous Coward | more than 15 years ago | (#2028135)

What I would really like to see is a mail-server
benchmark...

How does sendmail compare with MS Exchange Server ?

I've been told that if you are going to install
exchange-server, you should buy a fast 2 processor
machine, with 128 Mb of RAM, etc...

I'm currently using a fantastic mail server:
it's a 486 DX4/100 with 20Mb or RAM, a 4 Gb IDE HardDrive, a ISDN card and a Ethernet card.
It's serving email for 20 people, and also working as a proxy/web server (apache with proxy module).
The 486 runs just fine: the bottleneck is in the ISDN card... I never had a crash in two years...

NT will never beat this: I removed the graphic card , monitor, mouse and keyboard (and disabled
the BIOS warnings) and now I administer the system
from my workstation using telnet.

ZDNet FUD (0)

Anonymous Coward | more than 15 years ago | (#2028136)

Linux is hard to install, Linux do not support all your hardware... I'm getting tired of this stupid site's FUD.

ZD,still:Misleading Comparisons, Wrong Information (0)

Anonymous Coward | more than 15 years ago | (#2028137)

While the article is much better than what we are used to from ZDnet, is has clear weaknesses.

1.) Samba comparisons are useless without presenting the actual release number. Which Samba in which distro.

2.) SuSE comes with Python, unlike what they said, it come with a database (Adabas D, and AFAIk PostgreSQL) and offers support in the US via Linuxcare. The comprehensiveness of the distro could have been mentioned as well.

Maybe they just wanted to show some preference for US distros (ironically, Caldera originates from not far away from SuSE in Bavaria, they just bought LST some time ago)

Mine works fine under NT WS (0)

Anonymous Coward | more than 15 years ago | (#2028138)

As does quake, quake2, unreal and 1/2 life
NT is my main gaming platform, as I have the
seems to do better than 95 esp. w. multiplayer
Q2


I load linux to screw around w. perl and stuff

Yeah (0)

Anonymous Coward | more than 15 years ago | (#2028139)

Comments like "But Linux is a worthy contender" as well as a few at the end get me a little suspicious about zdnet's motives.

Not Enough Clients (0)

Anonymous Coward | more than 15 years ago | (#2028140)

This benchmark (unfortunately doesn't include Linux, compares NT4 and Netware 5) uses higher-end hardware and goes upto 144 client systems.

NT peaked at 176Mb/s with 2 100Mb/s cards on a dual processor.

It would be interesting to see Linux tested on the same hardware, with 1 and 2 processors.

http://www.mindcraft.com/whitepapers/nts4nw5file svr.html

I think they should tune more... (0)

Anonymous Coward | more than 15 years ago | (#2028141)

This benchmark (unfortunately doesn't include Linux, compares NT4 and Netware 5) uses higher-end hardware and goes upto 144 client systems.

NT peaked at 176Mb/s with 2 100Mb/s cards on a dual processor.

It would be interesting to see Linux tested on the same hardware, with 1 and 2 processors.

Novell performance (0)

Anonymous Coward | more than 15 years ago | (#2028142)

This benchmark (unfortunately doesn't include Linux, compares NT4 and Netware 5) uses higher-end hardware and goes upto 144 client systems.

NT peaked at 176Mb/s with 2 100Mb/s cards on a dual processor.

It would be interesting to see Linux tested on the same hardware, with 1 and 2 processors.

BTW, Novell was slower ;>

http://www.mindcraft.com/whitepapers/nts4nw5file svr.html

More stressful results (0)

Anonymous Coward | more than 15 years ago | (#2028143)

This benchmark (unfortunately doesn't include Linux, compares NT4 and Netware 5) uses higher-end hardware and goes upto 144 client systems.

NT peaked at 176Mb/s with 2 100Mb/s cards on a dual processor.

It would be interesting to see Linux tested on the same hardware, with 1 and 2 processors.

BTW, NT wasn't stone last, Novell was slower and NT didn't drop off after 40 clients ;>

http://www.mindcraft.com/whitepapers/nts4nw5file svr.html

File Servers, NT, & such (0)

Anonymous Coward | more than 15 years ago | (#2028144)

This benchmark (unfortunately doesn't include Linux, compares NT4 and Netware 5) uses higher-end hardware and goes upto 144 client systems.

NT peaked at 176Mb/s with 2 100Mb/s cards on a dual processor.

It would be interesting to see Linux tested on the same hardware, with 1 and 2 processors.

BTW, Novell was slower and NT wasn't last ;> So much for the 'most effecient' protocol that Novell has.

http://www.mindcraft.com/whitepapers/nts4nw5file svr.html

P.S
There are at least 3 different companies that offer NFS for NT (client and server implementations). Microsoft even licensed one of them and includes it in their recently released 'Unix services' pack.

Graphs, yes; and it's amazingly realistic for ZD (1)

Pasc (59) | more than 15 years ago | (#2028145)

Steven,

Please don't take these anti-ZD criticisms personally. We've dealt with FUD from Jesse Berst and the likes for years. S@R, as you point out, has been very fair when doing reviews of Linux (with a few exceptions.) Unfortunately, the bulk of ZD articles comparing Linux and NT have been slightly to extremely FUD-filled. Thanks for proving that journalistic integrity still exists at ZD.

--
Pasc

Tuned apps comparison (1)

KMSelf (361) | more than 15 years ago | (#2028146)

It would also be interesting to see performance figures for the tested systems (as well as OS/2, and Novell) where custom tuning has been applied to the systems and applications -- runtime options in the case of IIS, compilation options and runtime options in the case of Samba and Apache.

The value of OSS is the code. Use it!

hmmmm.. (1)

drwiii (434) | more than 15 years ago | (#2028147)

Of course, you do know that Microsoft is paying for all this good press [zdnet.com] , right?

(Microsoft's) Maritz told Judge Jackson that a flurry of new applications and new vendors supporting Linux meant that relatively unsophisticated consumers would soon be using the operating system. As a result, he said, Microsoft would have to work diligently to keep pace with the market.

Microsoft produced a half-dozen magazine and newspaper articles to support its contention.

IIS vs. Apache and Linux vs. NT (1)

Trepidity (597) | more than 15 years ago | (#2028148)

It'd be interesting to see how much of that performance lead is due to the fact that Linux is faster than NT, and how much of it is due to the fact that Apache is faster than IIS.

Perhaps they should try some tests with NT using the win32 version of Apache.

SB16 PnP (1)

Frandsen (816) | more than 15 years ago | (#2028149)

I have seen NT do the bluescreen thing with a SB16 PnP.. had to rely on the repair disk.. my kingdom for a CLI in such a situation....

No kidding (1)

heroine (1220) | more than 15 years ago | (#2028150)

And Linux 2.0 was a dog compared to Linux 2.2 in terms of speed. My personal Linux box is the fastest web server in all of central Florida even though the suits will never ever hire a non-Windows user here.

Substantial dynamic content test difficulties (1)

Chemical Serenity (1324) | more than 15 years ago | (#2028151)

It'd be nice to do an apples to apples comparison when delivering dynamic content via CGI/PHP/ASP/Whatever, but there are too many variables to account for to give a clear picture of how well a server might respond.

Probably the best you could hope for is a very very minimal one-liner 'hello world!' program executed in the various different platforms to check how well the web server speeds through the calling process... 'best' here wouldn't describe very accurate results of course, just the best you could hope for. ;)

When it comes right down to it, nothing beats full scale implementation and use in the target environment... and if you REALLY want to have that comparitive execution thing going, get the same developer to create multiple versions of your program, run them all in parallel on equivalent hardware, and measure away. The numbers won't be terribly accurate, but for the price of multiply redundant programs you can have the luxury of choosing which one feels the best.

The samba printing test would be interesting. I've run SMB in corporate environments and have had very little complaint, but it'd be nice to see how well it'd work under a heavy-duty printer workload (Say, running a linux box as a rasterizer/spooler pushing 2400dpi 11x17 lino pages in a newspaper or printhouse somewhere). Anyone in the printing industry willing to fess up to a linux rasterizer box in the closet? ;)

--
rickf@transpect.SPAM-B-GONE.net (remove the SPAM-B-GONE bit)

Apache performance (1)

Matts (1628) | more than 15 years ago | (#2028152)

Can anyone explain the different Apache performance figures? I'm running Apache 1.3.3 at work for a project, and we'd like to get the best possible performance out of it. Hopefully someone will reply with "Just recompile with -02 and pentium settings" ???
--

WebBench (1)

Matts (1628) | more than 15 years ago | (#2028153)

WebBench is freely available to download from www.zdbop.com. It contains static and dynamic content tests.
--

Laughing my ass off (1)

lefty (1872) | more than 15 years ago | (#2028154)

So how does Linux *really* stack up against the Evil Empire's wanna-be-server VMS ripoff.


"The answer: Linux with Apache beats NT 4.0 with IIS, hands down. SuSE, the least effective Linux, is 16 percent faster than IIS, and Caldera, the leader, is 50 percent faster."


Laugh with me [zdnet.com] , unless of course you're a M$ FUDster, then we'll be laughing at YOU!


Now, how about those file server stats [zdnet.com] . ZD sums it up by saying "...Linux kicks NT's butt."


Now, I'd like to see some other alternative OSs put against Linux. Maybe BSD?


Anyway, it's great that this has finally come out. We all knew Linux was superior, even the M$ marketdroids. It's been a long time in the coming. Ironic, we have ZDNet to thank =].

Infoworld: OS/2 on 1 CPU is faster than NT on 4 (1)

timur (2029) | more than 15 years ago | (#2028155)

Back in 1996, Infoworld compared OS/2 Warp Server with NT. They found that OS/2 was faster on one CPU than NT was on 4.

Performance comparisons against NT always give the same result. What I would really like to see is an OEM offer two different systems for the same task, one running Linux and the other NT. Let them say that these two systems are comparable in the number of clients they can serve. And let them show that the Linux-based server is cheaper and uses older hardware. Now THAT will get people's attention.

Unfortunately, although major OEM's are beginning to offer Linux as pre-loads for servers, I have yet to see any of them PROMOTE Linux over NT. After all, a person can buy a cheaper system if he uses Linux - and that means that OEM's can't charge a premium for top-of-the-line hardware.


--
Timur "too sexy for my code" Tabi, timur@tabi.org, http://www.tabi.org

I think they should tune more... (1)

sheldon (2322) | more than 15 years ago | (#2028156)

I'd be particularly curious to see the same tests run on a tuned environment.

Say a Proliant 6500, Quad processor, 512 Meg RAM, 100 gigs on RAID-5, etc...

That's going to be a fairly standard corporate server, and it'd be curious to see the results with say 500 client computers.

Unfortunately only a few places are going to have the hardware to do such benchmarking. I understand that Compaq has such a lab available.

Also I don't believe there was mention of what kind of netbench test that was, it must have just been static content? What about dynamic content from asp or php or cgi or whatever?

I'd also be curious how one might try to benchmark Samba as a print server. Most companies don't just install servers for file sharing, but also for printer sharing...

Illegal Benchmarking (1)

way_out (2820) | more than 15 years ago | (#2028157)

This is funny. According to law in about all civilised nations it's illegal to have an agreement that itself breaks the law. Checking your own *purchased* machine against another is something no company can forbid.

Just imagine a car factory forbidding the owner to bechmark it against another car.

Nobody would buy it

This is Great! (1)

mdxi (3387) | more than 15 years ago | (#2028158)

This article totally kicked my ass...I can't believe it's on ZDNet of all places! I printed out all the graphs because I'm afraid this article will disappear overnight :)

I liked the linux-to-linux-to-linux comparisons but really wished more infor had been given as to WHY some distros perform better at certain tasks. I assume it's build differences, but I'd like to know what tricks you can use to speed up a certain program at compile-time.

Still, this rocks! Print out the graphs and show them to your boss!

--

Almost unfair... (1)

warmcat (3545) | more than 15 years ago | (#2028159)

If the GUI - X or Windows - is idle, then it doesn't suck any CPU to speak of.

File Servers, NT, & such (1)

Passacaglia (3824) | more than 15 years ago | (#2028160)

Yes, it's always apples and oranges. Linux wasn't running a GUI, which accounts at least partly for its better performance. But, it was speaking to WinXX clients in their native language with their filesystem, while NT (as far as I know) won't do NFS. Once I heard John Blair speak and he claimed that Linux was not the best platform for Samba. All in all, I think the upshot is not that Linux is so good (pardon; it is so good) but that NT is so bad, like the comparison mentioned above with OS/2 points out. Netware doesn't do SMB, but I understand that it has the most efficient fileserver protocol, better than SMB or NFS.

NT so often comes out last in performance compared to _anything_ else. It is difficult to understand why folks defend it, even here on /.

Almost unfair... (1)

vendull (4435) | more than 15 years ago | (#2028161)

Actually, the memory used by X will be migrated to disk (swapped out) if is idle long enough, and the other processes can make use of the RAM it occupies. So really, the only thing it will end up using is some disk space...

No graphs? (1)

David E. Smith (4570) | more than 15 years ago | (#2028162)

If nothing else, the graphs were in the print edition of the article. (Let's hear it for free subscriptions. :) The graphs, and there's only two of them, basically show this:

For Windows file serving, NT peaks at 8 clients and lags behind after that. Caldera peaks at 8, but much higher than NT (about 30 Mbits/sec vs. NT's 22 or so). Red Hat is basically a shadow to the Caldera line until 30 or so clients, where it is a little bit ahead. SuSE peaks at 12 or so. At the end of the graph, with 32 clients, NT has long since bottomed out at about 10 Mb/s while all three Linux distro's are still going strong in the 20-25 range.

For Web serving, all the lines stay pretty much level across the graph. At 32 clients, Caldera is still handling 70+ requests a second, Red Hat about 60, SuSE about 50, and NT about 45.

As others have said, Linux would have been even better if it had been tuned somewhat. (It'd be interesting to see how the NT box works when properly tuned also, just to make it a fairer fight.)

Graphs, yes; and it's amazingly realistic for ZD (1)

David E. Smith (4570) | more than 15 years ago | (#2028163)

Sm@rtReseller is only about a year old; the current print issue, where I found the hardcopy of the same article, says "Volume 2 Issue 2." It has some interesting articles, all slanted towards biz of course. (The same issue has an article on how to configure cron, and a columnist ranting about Windows 98. Maybe there is hope for at least a small part of the soulless monolith known as ZD after all...)

Right. Do things in the proper place. (1)

Vermeer (4832) | more than 15 years ago | (#2028164)

Why would you want to go to the server room to
do things with your server? You can have your own
GUI on your own PC with Netscape... to administrate Samba remotely, a possibility now standard included.

So, no need to run X on the server. Just Apache,
which one probably would do anyway. Or an X-server on your PC. There's many ways to do a thing. But bolting a GUI to a server OS is *really* crazy.

Absolutely! (1)

edgy (5399) | more than 15 years ago | (#2028165)

That's what I did!

And I got the contract! 100 client samba server to go, on hardware that is so much more than would ever be necessary.

No Subject Given (1)

Drew M. (5831) | more than 15 years ago | (#2028166)

This article makes me happy :)

Finally, a published article truly telling the world how much Linux kicks NT's butt. Too bad they didn't tell how many times NT crashed to the gound during the tests. I bet it was more than a few.

[drew@s196-237 drew]$ queso 127.0.0.1
127.0.0.1:80 * Linux 2.0.35 to 2.0.9999 :)
[drew@s196-237 drew]$

Graphs, yes; and it's amazingly realistic for ZD (1)

A nonymous Coward (7548) | more than 15 years ago | (#2028167)

Follow the related links to find the graphs.

I was amazed at the lack of FUD, the lack on install nonsense, and the generally very down to earth tone of the entire article. Did ZD just start up this Sm@rt Reseller, or just buy it? Maybe they haven't had a chance yet to destroy it. I've seen it around for a few months, which may mean ZD stuff hasn't come out of the print pipeline yet.

--

No graphs? (1)

Signal 11 (7608) | more than 15 years ago | (#2028168)



So much for credibility. Go ZDNet. :/



--

ZD to review competing OSS (1)

malx (7723) | more than 15 years ago | (#2028169)

This article is important not because it shows
Linux beating NT but because it compares competing
OSS. For ZD and other commercial magazines to
survive they must have competing products to review. If they are ever going to support OSS
they too need a way to make money off it. Comparing different OSS products (Redhat versus Caldera, Sendmail versus Exim, or even Apache built with GCC versus Apache built with PGCC) is the way ZD can profit from OSS.
And guess what, if they benchmark properly they'd actually be doing something useful.


Linux VS NT hardware support (1)

Midnight Coder (8953) | more than 15 years ago | (#2028170)

My company recently purchased a suite of new Dell machines. NT BSOD when attempting to boot and install using the CD-ROM drive.

Linux (RH 5.2) works fine.

Engineering benchmarking? (1)

Axe (11122) | more than 15 years ago | (#2028171)

Yeah, it was on the same PII machine (2.0.36 , glibc, vs NT4.0 SP4 with fixes and runtime from VC6.0) JDK 1.1.7a and 1.2 under NT (with JIT) vs 1.1.7a under Linux.

Graphs, yes; and it's amazingly realistic for ZD (1)

sjvn (11568) | more than 15 years ago | (#2028172)

Oh please. Check out my track record--it's on the Web and in the magazine databases. I was running Unix and dissing Microsoft--when they deserve it which they usually do--for years. Check out, the Sm@rt Reseller masthead, see who's working with me in techno? A lady named Esther Schindler, better known to some of you as the OS/2 Goddess. S@R technology department calls 'em the way they see 'em. Always has, always will.

Steven, Senior Technology Editor, S@R

It's a typo (1)

sjvn (11568) | more than 15 years ago | (#2028173)

The NT disk space number should be 1 Gigabyte and it will be Real Soon Now. And before anyone mentions that you can run it on less--or Linux either for that matter--they were all set up as network file/Web servers.

Steven, Senior Technology Editor, S@R

Skin grafts advised (1)

sjvn (11568) | more than 15 years ago | (#2028174)

Nah, it's rhino hide, I was just snorting and kicking at the bugs. ;-)

Steven

Illegal Benchmarking (1)

Wag the Dog (12835) | more than 15 years ago | (#2028175)

I was just reading the NT EULA yesterday and they specifically forbid benchmarking their products without prior written approval of Microsoft. I wonder if it was obtained for these tests...

Not Enough Clients (1)

raistlinne (13725) | more than 15 years ago | (#2028176)

It also depends on what cpu they compiled it for. Redhat compiles with no cpu optimization, i.e. no -i486, -mpentium, etc. I think that that was what a new dist called somethin glike Stampede was partially about, compiling everything without debugging symbols and for pentiums. Those CPU optimizations can significantly affect performance. That being said, I don't know what cpu optimizations each dist uses. Also, it's not a given that everyone optimizes with -O, -O1, -O2, -O3, etc.

I think they should tune more... (1)

raistlinne (13725) | more than 15 years ago | (#2028177)

I don't know what NT does on SMP, but Linux 2.0.x uses BFL, big grained SMP, which is a big disadvantage. 2.2, by contrast, should really look nice on SMP systems, especially bigger ones. Of course, 2.2 dists aren't going to be out for a few months, so that will take a while. It will be fun to see, though, especially given Apache's multi-process architecture.

will this be used in court? (1)

cmoss (14324) | more than 15 years ago | (#2028178)

On the one hand you can be sure that MS is looking for articles that support their contention that they are not a monopoly.

On the other hand they don't want to add any legitimacy to any real competition.

I don't think this article would do their case any good. How can you explain the ability to charge $800+ for a file server that is outperformed (2.5x) by a $50 linux distribution!

MS is in a position where they want to portray Linux as immature potential future competitor. To do this they don't need any articles that actually include facts. They want articles that talk about how great it is if you are a Unix genius but otherwise it's impossible to install.

CM

Windows NT requires 16 GB disk space....... (1)

kevinT (14723) | more than 15 years ago | (#2028179)

There was a table showing which version of Apache for each distribution. They apparently used the distribution's straight without any recompiles or anything. A couple of the versions were 1.30 and one was 1.31. (See the link on how they stack up).

"Linux kicks NT's butt." --ZDNet Sm@rt Reseller (1)

phred (14852) | more than 15 years ago | (#2028180)

Duly noted.

:)

--------

Almost unfair... (1)

JamesHenstridge (14875) | more than 15 years ago | (#2028181)

Or more likely just VM (if the other tasks are more active).

Hardware support (1)

Mad Hatter (16140) | more than 15 years ago | (#2028182)

Quoting article:
"Where Linux does fall behind, however, is driver support and hardware discovery. Although Linux hardware support is improving, you must check each version's supported hardware list to be certain that all of your customers' components will function properly."

The same is true of NT, I saw a video card installed in an NT system thet caused a bluescreen every time you booted. Not only that, it hosed the install and required a complete reinstall, every time. The installer later found out thet NT did not support the card. Unfortunately I do not remember what video card it was.


"Trouble is, just because it's obvious doesn't mean it's true"

not really unfair (1)

Mad Hatter (16140) | more than 15 years ago | (#2028183)

It's a feature of the OS that allows you to tune it to what you are doing. Besides, even if you did run X as long as you had nothing that required X updates running I doubt it would really make that much of a difference (though I could be completely wrong here).

"Trouble is, just because it's obvious doesn't mean it's true"

Graphs, yes; and it's amazingly realistic for ZD (1)

Vidar Hokstad (87953) | more than 15 years ago | (#2028184)

Sm@rt Reseller has been fairly decent for a long time. They had a biased pro-Microsoft opinion article a while back about the Microsoft vs DOJ trial, and when I pointed it out, and wrote a rebuttal it took only a few hours before I got a really excited mail from the editor that wanted to print it... :) And I wasn't very nice to the guy who wrote the original article.

In the few cases where I've seen FUD filled articles there, it has been opinion pieces, clearly marked as such, and they have been quick to include articles representing the opposing view.

Imagine, actual journalism from a ZD publication :-)

Check for New Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...