Slashdot Mirror
Mindcraft Study Validated
!ErrorBookmarkNotDefined writes "Another study has appeared validating the
Mindcraft comparison of Linux and NT. This time,
PC week benchmarked Solaris, Linux and NT. Using a monster machine, NT handily defeated Linux. The study found fault with Apache, mostly. (For low-end machines, Linux would easily beat all comers; but how far along is Linux in the highend market?) "
Well, I'd like to see them keep slamming the
servers with hits like that for about a week straight and then we'll see who's servers are still up and running and which machines will require a reboot.
A basic problem, I have with benchmarking practiced in the PC-week and Mind-Craft is that they are looking at a single high powered machine. A real test should look at several different machines of varying processors, disk, and memory configurations.
I would recommend a course in statistics before making such a bold statement that the numbers prove it. Numbers in themselves do not prove anything. A single data point for a quad processor mean nothing for the real user.
Everybody knows that benchmarks are just benchmarks. I would like to compare the situation between NT and Linux servers to that of Mercedes F1 and regular cars.
If you have a good track and fair weather you'll get some pretty fast lap times with the F1 car, tuned to the maximum. This approach is, however, not practical. In a F1 car you get a bumpy ride.
The engine blows after about 1000 km and you have to refuel and change tires every 200 km.
An F1 car will also carry only one person at a time (one prototype with a passenger seat has been built). It's also painful and tough exercise to drive an F1 car.
But, put a little water and a few LARGE bumps into the circuit and the situation changes. In your regular Mercedes you can enjoy the ride and still make the trip in quite a good time, while listening to music and not having to repair the engine and refuel as often. You can even bring along a few friends to make the trip much more enjoyable.
My advice: Don't waste money and time on building a F1 car for the public, instead enjoy the ride that you get from your ordinary Linux.
Looking at the file serving tests.
Isn't this just a problem that Linux can't use the 4x100M cards to make a full duplex 400M pipe.
The Linux performance falls off at around 200M just what I'd expect for 1 card.
Or am I missing some thing obvious?
I think you guys mean RegClean.exe, i didn't see anything about regedit in the last two links to the risk archives.
Does Caldera come pre-configured with crypted password support ?
Did they just forget to run Win95PlainPassword.reg ?
Is it some evil plot by the Linux community to keep the support costs down by keeping the clueless far away from Linux :) ?
When the Webstar was still on the top 3 servers on the net (outnumbering IIS) and was getting slammed in all the benchmarks for all the same reasons that Linux is know.
In reality, Webstar running on a low-end Mac under Apples brain dead TCP/IP stack could saturate a T1 line. Running on Apple's top of the line hardware it could match a Sun box at up to T3 speeds. Yet all the benchmarks were at 100mhz lan speeds and showed Webstar getting butchered when over 50 simultaneously clients started hammering it. Sound familiar?
Back then everyone who knew better stayed quiet (you know, all the geeks who admin server farms and read slashdot all day) since it was "just Apple, so who cares." Maybe if people had complained we wouldn't still be seeing these benchmarks 3 years later.
The shortcomings of the Linux kernel have been known for ages. Linux first appeared in late 1991. In early 1992 already Linus acknowledged that a microkernel design would have been better.
"True, linux is monolithic, and I agree that microkernels are nicer. [...] From a theoretical (and aesthetical) standpoint linux looses."
They had years to fix the shortcomings. Fact is, the linux kernel _architecture_ evolves at a snail-like pace. Just because a new kernel gets release every other day doesn't imply that it evolves in any meaningful way. Don't forget that there's a new release for every new driver and also there's practically NO serious internal testing performed by Linus.
Proprietary kernels probably evolve much faster but you don't get to watch it.
Lastly, good kernel programmers are rare. If you were one of the few would you rather spend your working hours coding for love and Linus or earning good money instead? Fact is, everything about Linux is _mediocre_. No great inspirations, no brilliant minds involved, no breakthrough progress. Many people don't mind that. It's "good enough" for them. I personally can't stand it.
While the mindcraft study does not seem credible ( for a start, it was not independent ) , this study is not severely flawed. However, all the study shows is that linux has its limitations as a high end server.
What is also interesting, however, is that NT is actually a weak value proposition on a high end machine. Take a look, and you'll see that it can't hold a candle to Solaris ( even x86 solaris ) , especially considering Solaris' superior reliability. HAND, -- AC
We need to design and make a real world benchamark. Make a benchmark the has a very relistic mix of static, dynamic, and secure HTML. High and slow speed user connections. Also include content searches like looking up T-Shirts and catalog IDs in a catalog. I also want the client machines to look like a mix of machines, and for them to behave in a manner that is simular to a real user. That is to say, one connection calls for a page, pauses for a random number of seconds, then asks for another page, or does a search, or something. Each page returned will need to have a reasonable mix of images, and other content.
To do this benchmark some things will be needed:
- Server page content - A set of web pages for the server to serve. I'm thinking of something like a catalog retailer.
- DB Content - A database of information that dynamic catalog requests are generated from. This should have entries for all products.
- Client Programs - Simulate the activity of a user. Simulation of slow connections will need to be done. Afterall, not everyone has a T1 or faster to their home. The Client Programs will have knowlege of the site's content, and make dynamic queries based on that content. Queries should be designed to return listings a wide range of numbers of appropriate items.
- The clients will check the resulting returned selection to see if it is complete and correct. Ie, if a query for part number X returns part number Y, it is wrong. Simulairly if a request for "T-Shrits" returns only 5 items where there are 23 T-Shirt items in the DB.
Results will be graded on performance as well as correctness. So if a server one gets 1000hps, but has a 25% error rate, it really only served 750hps, on the other hand if server two did 800hps, and managed 100% accuracy, then it did do 800hps.I have used IIS & Apache/mod_perl. Apache/mod_perl performs better on a P133 than IIS on a PII 200. It's easier to use, more extensible, comes with cool goodies like ImageMagick. UNIX is far easier to develop on than Win32. Just try to make an ISAPI dll/ODBC vs mod_perl/DBI and you will see.
It's stupid to take such a test completely out of context of the real world. Use both, then use the one that sucks less and you will probably use Linux/FreeBSD.
Besides, it's free!
Slashdot regulars do not seem to notice that concurrent with these tests which show Linux speed
performance lagging in certain tests with certain
hardware, the mainstream Windows-loving computer press has run several very long, very positive feature articles about Linux highly recommending it as a server vs. NT. I'm talking about within the last few days, with full knowledge of disappointing comparisons in these tests. One even had a chart with a feature by feature comparison in which Linux came out better. Not to mention the A+ RedHat 6.0 review featured here.
Sites include several ZD subsidiaries, PC Week, etc., CNet, Wired's Web Monkey and others I can't
remember. Check the Linux Center (french or english version) site for a list.
While there is certainly pressure within certain divisions of ZD and the ilk to run performance tests which are tilted towards MS, in general the journalists are being very fair, if not giving Linux the sweetheart treatment. And, at least in the test which is the topic of this thread, Solaris was also thrown in to show perhaps that a
unix system designed for high-end equipment easily beats NT even with hardware and conditions designed to show NT in the best possible light.
NT won't even run on what Linux and Solaris will run on (non-intel) but even in foreign territory
Solaris performed better.
I am not a sysadmin and don't have much knowledge of networking, but business is business. It seems that to make Linux look better, it may be necessary for comapnies basing their business on Linux like RedHat and Caldera to pay for their own tests under conditions highly favourable to Linux - and to publish the results prominently.
IT IS NOT UP TO THE "COMMUNITY" to do any of this.
Linux is not a company, but companies basing their business on Linux are in direct competition with Microsoft.
Mainstream computer journalists have prominently published charts comparing Linux to NT point for point - it seems to counter MS's "challenge" page in which very unfair and dishonest charts comparing NT and Linux were prominently displayed.
Are ZDNet and Wired doing RedHat's job for them?
It seems so.
Whining in posts here about what is wrong with tests showing Linux unfavourably just compounds the damage. It comes across as sour grapes.
Run your own tests and publish the results, email
RedHat and Caldera to do that, or shut up. Hell, nobody cares if you fake the data. Who will know?
I hope the people responsible for the kernel have better sense than to make unwise modifications just to make Linux perform better in certain artificial benchmarks. It seems that a better approcah is just to keep developing in a way which is natural to Linux, and eventually these benchmarks will take care of themselves.
In the meantime, if your heart bleeds for Linux, publish and advertise the many areas in which Linux excells as a server, and thank the journalists in the mainstream media who you seem to hold in contempt for taking the inititive to
do that for you. At least they deserve a thank you.
will take another step forward and then when linus and cox try another kernel release, microsoft
will release yet another.
Linux is currently improving at a much faster rate than NT. How old is NT 3.5 and where was linux when this came out ? How far has NT come since 3.5 ? In terms of the work being done on the kernel, and in terms of third party support, linux has closed the gap, with SMP support appearing in 2.2, and several (big) third parties standing behind linux ( IBM, Dell, Oracle, Corel ).
As for the number of developers
BTW, your point about all the MS developers being too busy with Win95 to work on NT doesn't wash: don't forget, Win95 is about 4 years old now. In 1995, linux was in its infancy.
Face it. ITs lost. linux will continue as a hobby for
linux but in 5 ro 10 years NT will run in your car to your toaster to your hosue security system
Fire away with your predictions, but at present, linux retains a growth in market share, at the expense of NT. What makes you think that the rapid adoption of linux will suddenly halt ? All factors that have the potential to influence growth are on the rise. Factors such as third party support, critical acclaim, availablility of applications, mindshare, large scale deployment, and the OS itself have taken leaps and bounds over the last year, whereas NT has either stayed still or even slipped a little. I wouldn't bet on NT killing linux any time soon.
-- AC
Ok, here's the deal. ISS looks like it kicks the crap out of Apache (speed wise), but I would like to see NT/apache vs. Linux/apache. Guarantee Linux will win easily. Also comparing Microsoft Networking (WinNT) to another (Win32 box) of course WinXX will be faster than Samba to WinXX.
Using stock binary's(Apache) from RedHat or Debian or anywhere ain't gonna cut it.
I think its time the Linux community makes some moves and we show how Linux can compete in the enterprise market, instead of letting these bullshit benchmarks make it look like shit!
So what if NT outperforms Linux on high end hardware... I'm sure that by the time these systems (quad processor 500Mhz PIII) are commonplace in people's homes, Linux will run faster on them than NT does.
So what if Apache is slower than IIS... it is certainly more reliable and configurable than IIS and since the average site doesn't have 100Mbs of bandwidth, raw speed is a moot point.
In the real world, the only companies that can afford the systems tested here are the same ones that can afford to pay for loads of NT licenses and the support staff that would be required to run the servers. Chances are these same companies are already in bed with MS and are using NT anyway. Linux's target audience on the other hand is the little guy, who can't afford all the expensive crap and wants a system that doesn't have to be watched 24/7. Maybe they're a college student or someone with a home business... the point is they understand price/performance tradeoffs, and know how to make the smart decision.
In short, Linux is open, and even if it only performs half as well as its nearest competitor, that makes it twice as good.
Look at the cost.
NT4 server = ~$809.00(5 user pack)
Linux/FreeBSD/etc = Free - unlimited users.
Throw in ~$80 for secure server.
If you want email and such:
Backoffice/Exchange = up to $5000.00 depends on
on number of users.
Sendmail/Imap/Pop = Free
We all know you get what you pay for in this
world. Considering prices, numbers
(which doesn't mean crap anyway) and the reliability of Linux/FreeBSD/etc, free does pretty damn good in this area and in my book. Cost is
the ultimate equalizer.
Why would I spend thousands of dollars
and trade reliability/stability for about a 10 - 20% increase in speed when my speed is adaquate
enough? Are we all stupid?
We should benchmark purchasing stupidity
or gulibity instead.
however, the tests also show that if linux wants to go head to head with the "heavy duty" unix flavours such as Solaris, there's work to be done.
--AC
Linus himself stating that he believed OS design was well understood by the 1970s, and he considers microkernels to be "stupid", plan9 to be "stupid" etc etc.
[...]
While he is undoubtedly a highly talented programmer, I think that there are engineers in the world who are at least, if not more, skilled working for Sun, CMU, Microsoft, DEC and suchlike whose work has proved Linus to be very wrong.
Pardon, could you please tell me exactly which of the above comments (microkernel, plan9) were proven wrong by Microsoft engineers?
I don't want to say Linus is good, everything he says is right etc., but I want to see plain facts.
But for high volume dynamically generated content, for example, or commerce, or databases, NT is more mature and benefits from being developed by engineers rather than hackers. DEC, from whence Cutler came, are very serious about this.
I'm far from saying Win NT should be avoided at all cost - heck, I use what does the job best for me. But do you want to say for very high traffic, dynamic web sites you would like to use Windows NT?
Ok, this is not a server-issue, but it is Microsoft, so here follows a description example of "mature" software and the answer of the question: Why is regedit so big? (The Risks digest, Vol 20;35)
MVS is an IBM mainframe OS. As an OS, it is known for its efficiency, extreme stability, and great process management. It is used in business data centers around the world. It was not deigned to be eaasy-to-use (from the admin level) or easy to program.
VMS is The Other Unix. It was designed by DEC, and Cuttler was the primary architect. It paralleled Unix in many ways, although it was not as consistent in design, nor as easy to use (as a system). However, it has auditing features and access controls that Unix (and Linux) could really use. VMS was designed to control every little security detail, whereas Unix was designed around trust and flexibility.
K&R were hardly "amateurs." They were working at Bell Labs on Multics, which was going to be a "real" multiuser OS. But its design was too boroque, with too much squeezed into the design; so Dennis Ritchie designed a better, simpler system in his spare time. (Bell Labs is a very open environment.)
Now, here's a question to ponder: Multics failed because of its complexity. Can you think of any other operating systems that try to squeeze everything into the OS? If so, can you defend that design in light of history?
Ouch! That hurts! But from what I gather, the link offered for this story is mostly a biased synthetisis of the PCWeek report from a pissed off MCSE.
The real report still has some nice things to say about Linux, and hopefully this whole mess will give us the kick in the butt to start making everything go faster and be better.
As customers, we especially need that all the Linux distributors and hardware resellers start working together instead of wasting time "fighting" each other. An industry-wide consortium to develop better hardware with everyone contributing a fixed percentage of their net profit would be nice. That money could be funnelled to the developers to something such as sourcexchange (http://www.sourcexchange.com).
Still, it wouldn't have been possible just a few months ago to have a comparison of Linux with Solaris, NT, Novell... And since those "mainstream" NOS are often only affordable to bigger corporations, Linux has it's market cut out!
But for high volume dynamically generated content, for example, or commerce, or databases, NT is more mature and benefits from being developed by engineers rather than hackers. DEC, from whence Cutler came, are very serious about this.
Well, this is the biggest load of crap I've read today (I read the ZDNet article last week). By this logic, we should all be running VMS!
Well, they said in the article that Intel was the only platform that ran them all. And, of course, NetWare _only_ runs on Intel platforms. But, NT and Linux can both benefit greatly from the Alpha platform, and anyone who's seriously running Solaris is running it on SPARC. Which, of course, further invalidates the test, because the goal of the benchmark tests were supposedly to wring out all possible speed, but 3 of the 4 OSes were running on sub-optimal platforms (speedwise, anyway).
It's obvious from the way these guys messed around with their Linux and NetWare setups that they didn't know anything about either.
1) Linux:
Well, they used Red Hat 5.2 w/Linux 2.2. Of course, RH5.2 doesn't _come_ with Linux 2.2, so they compiled their own kernel. The possibility they messed up something there is very high. Apache is at a severe disadvantage compared to the other HTTP servers not only because of the lack of multithreading support (which I still wonder _how much slower_ that makes Apache) but also the lack of a reverse cache. Maybe that's Apache's fault, but it is easy to remedy, esp. since Red Hat includes a SQUID RPM.
I especially find it interesting that elsewhere on ZDNet you can find not only the old-news test of NT vs 3 Linux-distros+Apache+Samba (in which Linux/Samba/Apache trounce NT), but also a newer article in which (Caldera, I think) Linux+Apache again do the same to NT. (I can't find the URL right now--I think is was in Smart Reseller?). Just goes to show benchmark results depend as much on the benchmarker as on the benchmarkee.
2) NetWare:
First, these people start off dissing Client 32 (Whose name now, BTW, is simply Novell Client). Am I the only person who realizes that *Microsoft Client* means *Client for Microsoft stuff*? Besides, if Microsoft had implemented NetWare Core Protocol properly in Win9x, Novell wouldn't have *had* to write their own client software. In fact, Novell Client (or Client 32, or whatever) more or less *fixes* things wrong with Win9x networking so things run more smoothly. NC also has an adjustable file cache and can even restore network connections after a server has been rebooted (MS half does this). Novell Client is also a benchmarker's dream since virtually every option can be tuned. NC also enables Novell Directory Services to manage PCs; in fact, it is the _best_ way to manage NT workstations (they sort of glossed over that). What did they focus on? Experimental oplock support. A feature that is not only useless in a shared environment but, more importantly, is a bad test of network throughput since the file is only touched when you open and close it.
And, going back to their opening paragraph, they remark that by porting NDS to other platforms, Novell is "leaving little to drive new...deployments" of NetWare. That's one of the good things about NDS, and is one of the few things driving Novell's return to profitability. You'd think they'd be happy NetWare uses NDS to work in heterogenous environments, especially with their overall conclusion of that no one NOS stands out in every field.
Of course, they did realize the NetWare file-and-print services are still single-processor tasks, even with NetWare's new MPK (multiprocessing kernel), which is a real failure on Novell's part, IMHO.
Let's also assume that both boxes require an equal amount of maintenance (not necessarily so!)... but the Linux admin does it remotely, where the NT admin has to make house calls or wear a beeper. We'll average it out over the course of a year and say that the NT admin spends 2.5 as many hours working, and then let's call it six minutes of maintenance/2200 for the linux box, 15 minutes of maintenance/2200 for the NT box.
- $800+25/2200 = $0.37500 a hit/sec
- $80 +20/2200 = $0.04545 a hit/sec
It is not necessarily _true_ that Linux admins are paid twice what an MCSE earns, or that NT requires only 2.5 times the maintenance in billable hours (remember the 'server in the closet' paradigm linux has always had, unglamourous but low maintenance). However, even slanted towards NT in this heavyhanded way, NT is eight times the cost for the same performance _including_ administration.Good GOD! (!!!) :P
Yah- I laughed! But I don't know whether I should be crying instead! 96 servers? That's an _awful_ lot of their own dogfood to be eating, wouldn't you say?
Meanwhile, here in Brattleboro, somebody has sold the local Co-op a cash register system that all works on W98 (very possibly including some sort of NT server), and they're still struggling with it. It's easy to see those 'uh-oh' dialog boxes popping up and think the whole problem is unreliability, but it's worrying to think that even _if_ the system works perfectly (which it doesn't seem to be doing) the Co-op has no idea what kind of financial trouble it's now in, maintaining and paying off that system. How soon until they are deemed to need another NT server or three?
Laugh _and_ cry. This sort of thing will kill stores you love, and make many people poorer.
Make two distributions.
One, regular Apache, which would be used for actual HTTP serving.
Two, 'Apache Pro!' which is tuned for static page serving at all costs and obliterates any other purpose including reliability, stability, dynamic pages, whatever, just to produce benchmarks.
Then people can go on using Apache for _real_ web servers, but for the benchmarks, you ask them 'Why the hell aren't you using Apache Pro? You trying to handicap the race here?' and get them to use Apache Pro against NT- the 'bytemark version' (!)
Wouldn't that work? It has to be called 'Apache Pro' though, because it has to have the name Apache and it has to seem like the 'more industrial strength' version. _We_ know that it'll be better to just run Apache, but PHBs and test runners will find it impossible not to use Apache Pro- they'll be trapped by their own assumptions of 'upgrading' and 'standards'. It would be much harder to get another webserver used in benchmarks, but if you call it 'Apache Pro'...
Again... Zues!
Did you mean Zeus perhaps?
How many times does the "Linux Community Inc." need to tell these people that Apache wasn't ment for speed!? Why is Apache designated as the One True web server? Benchmarking static Apache vs. static IIS is pointless. Any programmer worth his salt could cook up a few dozen lines of code that would outperform both servers on pure static content.
True, but no webserver should be that horrendous at serving static pages. While not the main purpose of most enterprise servers, some major servers do serve a lot of static data, and most of the rest serve at least a significant amount, so static serving speed is indeed important. Apache needs to improve in this field.
Rather than bitching about the benchmarks, fix Apache, then you won't have to bitch about the benchmarks anymore.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
Friday afternoon, the network slashdot was on was messed up for around five hours. However, after it came back up, the slashdot box itself was down for around 2 hours (I kept getting "connection on port 80 refused" from it, so it was obviously up and responding, just FUBARed).
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
The problem is that they don't want OS benchmarks. They want complete system benchmarks of the OS running with the best webserver available for the platform. For NT that's IIS. For Linux that's Apache. You can't say "no fair, they have a better webserver than Linux does" and expect them to downgrade to Apache for the tests.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
From the Apache homepage, we find that "Apache exists to provide a robust and commercial-grade reference implementation of the HTTP protocol."
To my experience, Apache is the most stable of all web servers, and the only one that comes close to implementing the whole HTTP protocol.
Speed is not the Apache group's primary concern, and folks whose main concern is speed might consider looking elsewhere. Despite that, Apache is more than powerful enough to saturate a T1 with a relatively low end machine (we have saturated a T1 with a Pentium 90/96M RAM running Linux), and a fine tuned Apache can easily outperform just about any other web server (when we load mod_mmap we get performance tens or even hundreds of times what IIS can do on a good day).
Check this out: http://www.zdnet.co m/pcweek/stories/news/0,4153,2256098,00.html
195Mbps vs 114Mbps
Its not all bad news!
Sig (appended to the end of comments you post, 120 chars)
Posted by The Mongolian Barbecue:
1) Performance of NT as massive numeric processor for simulations.
2) Performance of NT as specialized SEM driver.
on second thought screw the second one. its really not possible to go very fast unless you can add speed hacks to your driver.
if NT wins the first one I'll switch! (It never, ever will)
Posted by ZeeC:
I love Linux I run an ISP with it. I am also working for a company that wants to relese linux on their high end Intel boxs (Hint, they are currently supporting NT and do UNIX on relly colorful boxs), anyways I am having a tough time finding drivers and HOWTO's on doing high end stuff with Linux. like Fiber channel scsi, Gigabit eathernet, heck even handling more then 9 scsi drives at a time. The OS needs to grow out of the "Keep a 386 useful" to a higher level now.
You obviously don't understand what is going on here. Code has nothing to do with it. The test data is such that it is static and just the right size to fit in IIS's cache and not the cache of other servers. This test data does not represent anything in the real world.
--Simon
Unless you can point to the DejaNews articles verifying Mindcraft's claims to have asked for help in more than one "appropriate forum", it's hard not to conclude they're flat liars.
--
Xenu loves you!
Comparing (stable, slower) Apache + no Squid to (fast, unstable) IIS instead of something like Zeus or Boa is, in fact, bullshit. Apples and oranges -- or have you never run a goddamn server?
The next question is who has the money to buy a quad Xeon with quad fast Ethernet NICs, but can't scrape together the change to get a gigabit NIC and switch instead? Uh, I'll take "no one" for $1000, Alex.
You're not nearly as realistic as you think.
Remember that what's inside of you doesn't matter because nobody can see it.
The old data I had when I tried to run NT.
:)
NT is the only reason these servers were quad-processor PIII/500's, and NT's resource hogging is exactly the reason that I don't run it on my personal box. I have it running on a P133, and I laugh at it sometimes.
If I had a high-end server, I'd try Linux and NT again, and... well, I bet I'd be laughing at NT pretty soon. It isn't exactly impressive running on uniprocessor PII/400's, but the bluescreens are cute. Really, how much CPU does an OS need just to crash?
pb Reply or e-mail; don't vaguely moderate.
These benchmarks expose nothing new: Microsoft will always try to bend and twist information to suit their needs (the first study was an absolute joke), and Linux has a long way to go before we can call it scalable and SMP friendly. It's just not ready for the enterprise. Not that I'd sleep well at night knowing my systems were running on NT mind you ;).
--
All of these benchmakks remind me of a sucker bet a friend of mine made.
It seems that some guy boasted that his car could outrun anything present over any distance. My friend bet him $20 that he could beat the car on foot. Naturally, the challenge was accepted. My friend then marked the 'course' of 10 feet from start to finish, and the race was run. My friend won. According to that 'benchmark', my friend can outrun the car. (no car can outrun a person in reasonable health for the first 10 feet).
These benchmarks are the same. Now, I know that the next time I want maximum speed for 30 minutes at a time from a web server w/ 4 100baseT cards (and a network that can keep them busy), I should choose NT. Of course, if the constraint is multiple T3 and minimal downtime, Linux and Apache are the way to go. Guess which is the more likely scenario.
>These people haven't a clue what they are benchmarking.
Of course they don't. The people who really know their stuff when it comes to computers wouldn't be caught dead working at places like PC Week. You might've found them working on the staff of the old COMPUTE! or Byte magazines when they really did cover multiple platforms like the Atari,Commodore,Apple machines and PC clones. That kind of knowlege just doesn't exist anymore in today's computer magazines. Just take a look at what's on the magazine racks of your local bookstore or K/Walmart and compare it to what was on those very same shelves 5-10 years ago. It's really quite sad actually.
>Linux' 15 minutes of fame are up. It's time to get serious
You wish. Linux's future is only beginning. NT's "15 minutes of fame" as you put it is what's up. Take a look around you. Nobody's talking about NT dominating anything anymore. Take a look at what the school kids are running on their home machines. It's *NOT* NT. As they enter college they will bring their Linux/Unix knowlege with them. The only reason NT really got a foot in the door was that people was pretty much only familar with Windows back in the early-mid 90's. This is what is changing and why pro-microsoft people like yourself are yesterday's news. Get over it.
Consider then, in your fit of benchmark citing, why it is that stressing a webserver has come to be known by the name of a Linux/Apache driven site and not some NT/IIS driven one...
A Pirate and a Puritan look the same on a balance sheet.
A redundant array of inexpensive machines?
I propose a new buzzword: Redundant Array of Inexpensive Nodes (RAIN)
Same idea as RAID for disks, if a node fails, you just replace it and go on your way.
But for high volume dynamically generated content, for example, or commerce, or databases, NT is more mature and benefits from being developed by engineers rather than hackers. DEC, from whence Cutler came, are very serious about this.
However, for midrange work, linux simply isn't up to par yet. I seem to recall Linus himself stating that he believed OS design was well understood by the 1970s, and he considers microkernels to be "stupid", plan9 to be "stupid" etc etc.
While he is undoubtedly a highly talented programmer, I think that there are engineers in the world who are at least, if not more, skilled working for Sun, CMU, Microsoft, DEC and suchlike whose work has proved Linus to be very wrong. And as such, linux is crippled.
maybe, if you were just serving static documents, you could get a dozen boxes, copy your site to each one and use round robin DNS.
but add in session management, personalisation, real-time news feed, content archives, commerce, access control, extensible templating and dynamic page generation and all that other stuff we do in the real world, and your solution starts to look quite naive.
It shows that NT needs a behemoth computer to run well, whereas it is targeted at the low-end market
which does not use behemoth computers. NT needs the hardware to run well.
Believe me, NT does not run well, for instance, on my 450 Mhz PIII with 128 megs of RAM, all things considered.
Linux has a history of keeping abreast with reality. When nearly everyone has a four or eight CPU monster, then Linux will run like hell on them, and so will applications such as Apache, etc.
When everyone had a 386, Linux ran well on a 386. When everyone had a 486, Linux ran well on that (and still does!). Linux is made to fit a need,
not to participate in olympic events.
I have an 8MB 486 at work on which I need Linux to run well. It does. In all likelihood, NT 4 won't even boot on such a machine. The machine has no keyboard or monitor, yet I can completely administer and upgrade it. NT would be useless on it since it requires a graphical display, mouse and keyboard for administration.
Just having read Andrew Tridgell's discussion on emulating the netbench test, It seems that a modified kernel & samba can thrash NT at all client loads, (albiet at the cost of making risky changes), Im sure even with these changes, It would still be more stable than NT (Which crashed within 24 hours of delivery here!).
take a look at the figures, and an interesting document.
netbetch emulation README
Hong Kong Linux Center home of squidblock, and other cool stuff
From the slashdot stats page:
/.
,hacker Perl another Just)'
uptime: 52mins
Last time I looked it was 3 days. Maybe Rob should explain what's going on with
perl -e 'print scalar reverse q(\)-:
Matt. Want XML + Apache + Stylesheets? Get AxKit.
For those interested in IIS and benchmarking, please take some time to read this rather long article. It's from a friend of mine who was the manager of the O'Reilly WebSite Pro development team. Some of the key issues were that MS made changes to the Winsock API specifically for IIS (AcceptEx, TransmitFile, Fibers and IOCompletionPort). Should Linux do this to make Apache/Zeus faster just for benchmarks, when really it does fine in the real world? No. Of course not.
,hacker Perl another Just)'
The other interesting point is the fact that ZD came up with the IIS benchmarks specifically to show how good IIS is. Such things as fitting the test harness in the cache, and only doing ISAPI dll's for dynamic content (vs CGI on other servers).
There are lies, damn lies, and ZD benchmarks. I'll use what works, and live happy in the fact that I won't have to reboot my server this year.
Matt.
perl -e 'print scalar reverse q(\)-:
Matt. Want XML + Apache + Stylesheets? Get AxKit.
I think we should expect Linux to be slower than NT on 'enterprise-class' machines like that.
Linux was (and is being) developed to scratch an itch, and run on the hardware available. Therefore Linux should run best on *personal* computers, as that's what normal people have.
MS, on the other hand, can buy (or be given by Compaq / IBM / whatever) quad processor PIII's.
Anyway, serving static pages proves nothing. How many intranet pages are static? Almost none I suspect.
This is really starting to get old.
Apache running all CGI is compared against IIS running ISAPI, and - surprise! - IIS kicks Apache's butt. I wonder how things would look if we ran a mod_perl test and compared that to IIS running CGI. "News: Linux/Apache Provides 3.5 Times More Hits Than NT!" I will observe, for the record, that Apache, IIS, and Netscape all provided exactly the same behavior on CGI; no dynamic test was ever done with Apache, so we'll never know, but I bet a mod_perl test on Apache would have produced at least somewhat similar numbers to IIS and Netscape.
And what's all this about Apache modules having to be compiled into the server? My Apache install has a directory full of dynamically loaded shared libraries. Exactly the same way IIS implements ISAPI modules. Only on IIS, you don't have the option of static linking for whatever reasons (less overhead, security, whatever).
I especially loved all the "process vs. thread" crap. Both PC Magazine and Wugnet (yes, the true authorities on Linux) were all over Apache's "process" model vs. IIS's "thread" model. But on CGI, you invoke a new process with each client request, no matter how many servers you've preforked or how many threads are idle. Presto: poor performance, no matter what the preforking parameters are.
You know, I wouldn't be all that surprised if NT beat Linux on this high-end hardware for various things in a fair benchmark. I'm just sick of hearing this kind of drivel from the MS camp. I almost hope Linus & Co. do Mindcraft III just so we can have a decent benchmark to compare against and some future directions for development instead of all this blatant lying.
I can't stop laughing thinking that someone thinks that OS X Server is faster than anything. On a 350 Blue and White G3 here at work (no tuning mind you) MacOS X Server runs so pathetically, I can only cry... Then laugh. Or is it laugh then cry? Dunno... But, really... I must be spoiled by linux by now, cos I found OS X Server sad: too little, too late. The PPC arch only has one hope: Get the LinuxPPC distribution rocking, delvelop like there is no tommorow, Tune for the CPU. -------
You are an Anonymous Coward, with a default score of 0, enlightened one.
Excuse me? Who are they refering to as "the Linux vendor" in this situation? Some company like Penguin Computing? RedHat? Linus?
How about a system of 3 (or any 2n+1) independent computers voting on the status, with a majority making the decision?
Perhaps you were looking for a different word, but NT is certainly not more mature than UNIX. Given that UNIX has been around for more than two decades, and has been used for implementing TCP/IP services from the early days, whereas NT is a relative newcomer, yet to make its own mistakes and learn its own lessons.
Even if NT was to objectively outperform UNIX (which I doubt it would realistically do), it does not inspire as much confidence by its youth and lack of pedigree.
Yes, what a great idea. Introduce a single point of failure to a mission critical system.
those test are like measuring ocean depth in ONE POINT and taken value proclaim as depth of whole ocean!
hany
Michael Surkan, who is usually the first to come to Microsoft's defense, minimizes the significance of PC Week's tests.
3 51,402634,00.html
http://www.zdnet.com/pcweek/stories/columns/0,4
It is surprising that he sings the praises of non NT OSes in their ability to use resources more efficiently on non high-end machines.
-- P.J.
This review was just testing the ability to
deliver static documents. So the configuration
he suggested is valid for the benchmarks he
was responding to.
I think what everyone of these "benchmarks" of
apache are missing is that delivering static
content is the least of the reasons to use apache.
Slashdot is a real example of a dynamic website.
No one is benchmarking dynamic content delivery
thru web servers.
-LL
-- I am not a fanatic, I am a true believer.
So why listen to this kind of crap? ZDNet is obviously going to run a test in such a way as to guarantee their revenue stream will not dry up. So you go on doing what you're doing and don't listen to naysayers.
(On the other hand, PHBs could be another story...)
Sanity.html - Error 404 not found
>but add in session management, personalisation, real-time news feed, content archives, commerce, access control, extensible templating and
>dynamic page generation and all that other stuff we do in the real world, and your solution starts to look quite naive.
(sounds like our site!)
But add in scalability and fault tolerance, and a single-server solution looks pretty nutty, especially if your traffic is already beyond what a single server can handle.
It's better to have a two-tier architecture, with apaches and template building on one tier, and data on the back end. Decent middleware will handle message passing and failover, load balancing, etc.
And, of course, most load balancers can hash packets based on source IP, so session management can be handled on single boxes (although it's better to be able to switch boxes by passing data around).
---- "If we have to go on with these damned quantum jumps, then I'm sorry that I ever got involved" - Erwin Schrodinger
I guess this is a performance benchmark, so waiting for everything to reach peak performance, then quoting the numbers has some validity. But, for a complete review why not push the machines even further? Wouldn't it be even more interesting to see how each OS/server combination handles an overload?
Actually, that would be quite interesting. Take an NT server (I have a copy I would gladly donate for this test) and install Perl, Apache, MySQL and mod_perl. Copy Slashdot over to the new machine and transfer the load and see what happens.
I'd wager that it'd fall all over itself.
The wheel is turning but the hamster is dead.
The wheel is turning, but the hamster is dead.
This study seems to say that apache+linux can deliver 2291 static pages/sec on PII350 and iis 4.0 + NT4SP4 only about 17% of that amount.
Vaadin - the best open source framework for building web applications in Java - no plug
I was thinking about this about the time the mindcraft survey came out. It would be interesting as my company has made some pretty large personalised sites that absolutely rocket on NT. Granted they're not getting 30,000 personalised users per day (or whatever the real figure is).
Two points:
First, why don't we rally a group of smart people around marketing Linux? Can the Bazaar out market the Cathedral? We need some support here.
Secondly, why aren't we running our own tests? I'm sure we can come up with impressive numbers that combat what other OS's are claiming. We need our own numbers, or we can't get the press to listen.
Since when have benchmarks been objective?
NetBSD may some day become the most appropriate solution; it isn't yet. Chuck Cranor has done a very good job on UVM, but it *is not finished*. Of the free Unices, the only one that has a virtual memory system that is state of the art as of today is FreeBSD. NetBSD and OpenBSD will probably get there; I doubt Linux will (due to the very strong defensive reactions Linus' has towards some aspects of the Linux code.) In some ways, I hope I'm wrong - it is a pity if that many people will be left with an inferior VM system :-(
Eivind.
Doubting the existence of evolution is like doubting the existence of China: It just shows that you're uninformed.
Is it possible? This seems to be one of the min things hurting it in these tests. They have always failed to mention the four-ethernet trick, but that is exactly what they are doing.
support gun control: take guns from cops
I've never seen that except on NT servers - always on asp pages. I mean IIS is famous for this. What gives? I've NEVER seen that on Apache.
...
Can't we try the test with linux on hardware that is more optimized?
Why not a test where both sides were allowed to spend $15,000 - software included - for their setup?
All linux people know DEC Tulip cards and 3 Com cards perform best in linux, and Mylex is pretty much the only choice in RAID controllers. The drivers can make all the difference
support gun control: take guns from cops
What does ethernet routing have to do with RAID? (nothing).. Actually ... what does it need a hard drive for? :-)
This contradicts my experience entirely. I do not find NT "faster" for any general purpose netwok duties like this, period.
the fact that you prefer NT's interface only hints to me that you don't know linux very well. I don't know anyone who uses unix and knows it and prefers menu based systems (still there is linuxconf which I use myself sometimes)
support gun control: take guns from cops
/Start Flame Bait
Why, pray tell, are all persons whose opinions disagree with those of the general consenus labelled as trolls? Some people around here sound like they could be my mother (Don't worry if you think you are; she's not computer-literate enough to know what Slashdot is). I use NT everyday, both by force (at work), and by choice (at home on my regular use PC). I've been using Linux since around kernel 1.2 (probably earlier, 1994 is a long ways back), but in all honesty, if NT were priced more like Linux, I'd be running NT Server on my server, rather than Linux.
/End Flame Bait
As for IIS being faster than Apache, of course it is. We all know the performance differences which happen when using fork/exec as opposed to spawning a new thread. There are two remedies for this performance difference. The first is to rewrite the Apache code to run threaded (not a particularly trivial task). The other (at least to bring the NT performance down a bit) would be to run Apache instead of IIS on the NT box.
Wrong. I had it installed on a 486-66 with 32MB (but a lot more disk space), and it worked like a charm. Slow as hell, but it worked.
I'm sure that's the world we want. No OS choice. Windows NT everywhere?
Don't you NT zealots see that statements like this only help Linux?
It gives those of us that actually enjoy computers for what they are more incentive to make sure things don't get worse than they are.
One company running the computer industry is just as bad as the railroad tycoons, or any monopoly that controls every facet of computers. I'm not sure even you would want to live in a world like that unless you were a Microsoft shareholder.
These benchmarks weren't a complete loss to all of those. Hidden in those benchmarks was a rather interesting admission found in this story on Linux Today (note, I don't work for them, but they do have some good stories sometimes):
http://linuxtoday.com/stories/5906.html
This story reveals that Linux with Samba achieved 197Mbps, which was significantly higher than the Mindcraft benchmarks, severely invalidating the original Mindcraft benchmarks. Also, Apache did MUCH better on these benchmarks than on the original Mindcraft tests.
The article also shows that NT achieved only 150Mbps against NT clients, 31% slower than Linux. In tests with 60 clients, Windows NT managed only 110Mbbps throughput, compared with 183Mbps for Samba.
So, we got something out of these benchmarks. Linux serves Samba to NT clients 31% faster than NT on high end hardware!
Now, if we only tested IIS against Zeus to make a more fair benchmark for static tests, Linux wouldn't look so bad after all overall.
I don't see how these new benchmarks validate Mindcraft at all.
heh your "work" probably consists of writing mirc scripts. Go back to school, Anonymous Coward
---
This is really serious and can't be countered by cooking up new benchmarks or bashing pcweek because it's zdnet or whatever. Nor can you hide behind your 486. I mean if we want to see linux as a real player or do we want to look like people holding on to their Amiga 500's? So if caldera redhat debian and everyone else really cares about linux survival I recommend working on a master plan to fix all the flaws of the OS. Linux' 15 minutes of fame are up. It's time to get serious
---
Obviously, in different configurations, different results can be expected. The moral of the story is that if you throw enough money at an NT system, you will be able to exceed the performance of the lower-cost, higher-reliability Linux system.
>As for IIS being faster than Apache, of course it >is. We all know the performance differences which >happen when using fork/exec as opposed to
>spawning a new thread. There are two remedies for >this performance difference. The first is to >rewrite the Apache code to run threaded (not a >particularly trivial task).
Hey - here's a third solution: READ THE APACHE MANUAL, understand that there are supposed to be x servers lying around at any given time (See the Min/MaxSpareServers config option), and if you are going to have a high traffic site, make sure that there are enough spare apache instances to handle the amount of connections you expect. If there were 60 MinSpareServers in their "fair test" on the linux machine, all the fork/exec'ing would be done at the beginning and there would be NO OVERHEAD WHATSOEVER from spawning new processes, because they would be spawned before testing (to have this work effectively, you also have to disable the limit of n requests per child, which is not a bad thing on linux).
The people who did these tests are A. incompetent at apache administration, or B. intentionally distorting their results. If anyone disagrees, please explain why.
2200 hits/second of **HTML**... No one has such a problem, because that's a damn lot of hits, fast -- The problem with NT is UPTIME... Let's subject both OS's on the same hardware to the same load, have them serving cgi/php, and see which one crashes first.... Uptime is a MUCH bigger concern with a webserver than if it can serve 1000 or 2000 _TEXT_ pages per second...
A computer without Microsoft is like ice cream without ketchup.
I used some really sloppy wording up there.
Point remains, though: beat Microsoft by stepping out of the box. Make your own rules. Do the unconventional.
And unconventional would, in this case, be to offer *another* OS and server software as being preferable to both Linux/Apache and NT/IIs.
*At this point in time* Linux/Apache doesn't kick ass in the speed ratings. And speed is the *only* issue in the media eye.
So give what they want. Make 'em realize that there are better OSes for what they want. They want speed -- they ain't gonna find it in NT. They want scalability -- they ain't gonna find it in NT. They want stability -- they ain't gonna find it in NT.
Start making it known that NT is *ALWAYS* outperformed by another OS, and pretty soon NT *ALWAYS* looks like a bad choice.
--
Don't like it? Respond with words, not karma.
It appears that most Linuxheads have finally come around to admit that Linux doesn't perform well as a server. Yet.
But it's pretty well acknowledged that NetBSD kicks ass in that department.
Time for Linux groupies to take the blinders off. Quit getting your shorts in a knot about the unfair Mindcruft tests, quit trying to pit Linux against NT in server applications...
...and start *heavily* promoting NetBSD as the ultimate server solution. Mob the media with it.
As long as you play by Microsoft rules, you lose by Microsoft rules. And fiercely protecting one's "turf" is a Microsoft rule.
Step out of that box. Quit promoing Linux as the be-all and end-all. Promo NetBSD as *the most appropriate solution* to server needs. Promo BeOS as *the most appropriate solution* to multimedia needs. And so on.
This tactic will emphasize to the media that people should make active choices re: their OS needs; emphasize that Windows is not the most appropriate OS for most cases; and emphasize that the Linux community plays big and puts the user first and foremost.
It's a no-lose situation. Choice is the ultimate goal.
--
Don't like it? Respond with words, not karma.
The link to http://www.microsoft.com/ntserver/nts/news/msnw/nt 4vLinux.asp makes it clear.
How serious can such a comparison be, if they link to that FUD story.
--
Raphael Wegmann
Raphael Wegmann
wegmann@psi.co.at
There is no reason why any system would necessarily have to crash under heavy load, it should just become slower. Anything that does cause a system to crash under the ./-effect should be fixed. Isn't this just a lovely torture-test that can be very useful in determining whether a system works reliably or not?
"I love my job, but I hate talking to people like you" (Freddie Mercury)
Every day, ./ chooses a web server on the internet at random. It then presents a link to that server somewhere on the start page, calling it the "benchmark link" or whatever (so people know what it's for). It is then ./-ed by the readers, and at the same time monitored for its uptime. Its server OS and software are determined (if possible, should be) and as the days pass, statistics are put together for the average time a server OS lasted under that strain.
Not entirely serious, but a good "real world" benchmark, and I'd enjoy that.
"I love my job, but I hate talking to people like you" (Freddie Mercury)
Not true, I'm involved in setting up a web system for a large US bank in NYC.
They are doing session management, personalization, dynamic documents and most of the other features you mention, and it is running on a cluster of Solaris (Enterprise 450s) systems.
The archetecture allows the session management information to be shared between the cluster members in real-time.
Of all the comments I've ever posted, this is definately one of them
Use a replication system, I believe all of the major DBs have them available.
Of all the comments I've ever posted, this is definately one of them
It's hard for me to believe that NT is faster than anything from my experiences with it. Few sites that I run across that end in .asp are in any hurry to dish out the content I request.
Anyway. Instead of simply blasting benchmark results that don't match what we expect, we should work to fix the problems in Linux, Apache, Samba or whatever is causing our bottlenecks. The fact that we can do that is one area of significant advantage that we have over NT.
Of all the comments I've ever posted, this is definately one of them
what was the setup used? what NT services were running? what IIS packages were installed? why use apache when zeus is faster? what was the configuration used? anyone want to do a performance vs. dollars chart?
NT for $200? thats workstation. they used server. $800/2200 = ~$0.36 a hit/sec.
redhat=$80/2200 = ~$0.036 a hit/sec
or get a cheapbytes.com disc and:
$2/2200 = ~$0.000909 a hit/sec
please note the monster hardware they had to throw at that to keep up with all those hits.
Linux may not do so well in THIS test but like it was mentioned, the load Linux was able to serve was larger then most business would need and that serving from a few lower-end systems with load balancing would be a better solution.
On to the topic of OS's not tested since you mentioned Be and NetBSD. MS-Ziff Davis did a test of 3 network servers on Intel and one OS (on 1 CPU) bested NT (on 2 CPUs) by 10% and Netware fell even further behind. That OS was OS/2 Warp Server. IBM just announced Warp Server for e-Business just 2 weeks ago and it scales to 64 CPUs with optimizations at 4 CPUs. Why wasn't this system tested? I'll venture that it would have kicked NT's butt on the SELECTED HARDWARE they used to show Linux's weakness. The Ziff Davis press is NOT unbiased and both those articles come from Ziff Davis publications. It just amazes me that a company that is so BIG on e-Business and has just released a OS for such Intel based e-Business was not included in the tests. Before the NT marketing machine went into full steam, after Windows 95 shipped, OS/2 servers were the #2 servers used. Right behind Netware and ahead of the UNIX servers and none of the NT vs System? tests but one included the OS/2 server software. Why is that?
"Anyone who stands out in the middle of a road looks like roadkill to me." --Linus
You read my mind. I have been thinking of this since the MindCrap 'study' was released. I couldn't think of a place to put the hardware after it was done though. I'd like to see it combined into a bewolf system that the general Linux (donating) comminity can use. Like having our own community super computer when benchmarking isn't occuring. I'd throw in a $100 or 2 to build a community testing platform.
I'd also like to see other systems tested like
OS/2 Warp Server and Mac System X Server(x86).
The author of one of the articles mentioning the 'fact' that the 2 new test show NT is better said that Warp Server wasn't included because it isn't widely marketed. Leading me to believe that advertising dollars is what determines the test results. We need to fight this or we will be doomed to turning off our microwave oven by first hitting the Start button!
"Anyone who stands out in the middle of a road looks like roadkill to me." --Linus
I could set up a web site for this poll. Not til Thursday though, Java UG meeting tonight and investment club meeting tomorrow night.
I'll set it up to simply count responses and the amounts. If it looks good I can apply for a non-profit org license or locate a group that might be able to handle this. We'll then have to start finding a location for the equipment and gather users preference for its eventual use after benchmarking life is over. First things first, $200 won't even get us a CPU at this point.
"Anyone who stands out in the middle of a road looks like roadkill to me." --Linus
considering the speed with which linux has progressed in the past year, is there any reason to think it cannot achieve many of the attributes that make the other 'specialty' OS's prominent in their respective areas? With corps like SGI behind the platform imagine the speed of development?
As of today, I would have to agree with you. But Linux is not at it's apex. Other OSs may be.
Linux has wiggle room.
I believe 57.22% of the servers on the internet are running the 'inferior' Apache. I guess everyone is on crack. Hmmm, IIS down 0.21%, Apache up 1.03%. This is pure FUD if you ask me. Microsoft sees the dominance and tries to attack it with this sort of stuff. Please refernce the latest mindcraft survey.
ZDNet's benchmark is relatively correct over several points. I would say they "touch" the reality. I know that because I work with every OS shown in those benchmarks. Well that not completely true... I *worked* with Windows NT. But two months ago I scrapped the last box at my work. (Farewell Microsoft. You recently lost 2500 users. Soon you will loose 3-4000 more).
:)
The article presents some points one may usually find on working either with Linux, Solaris or Novell. However some points are really the result of not caring on doing some tuning. Besides the article is purely biased on the point of "choosing the ONE final high-end".
Somehow the article suggests a person to compare Linux & Solaris. Well sorry both systems have their ++ & --. However I agree that Linux is mostly fitted for an average computer rather than a super-high-end machine like UltraSPARC 4500. Here Solaris beats it.
But does that mean that Linux is not and high-end system? Well let's not forget the cluster systems. Even Linux has a place on top-500 of supercomputers. And it beats some serious machines around there.
Somehow someone may have forgotten here one of the contenders. Novell Netware is a very specific system oriented mostly for a very specific sort of tasks. But it does its job much better than Linux or Solaris. Both in safety and preformance. And don't dare to compare it with NT. One machine now running Novell for the 7th month couldn't even hold a simple transfer of 100Megs over the net. Not talking about preformance (hey Redmonds, I also like to burn some time with my family!)
Really the NT stuff there is pure hype. On my "practical benchmark" NT Servers lived no more than 1 month of real, serious work. After that very sad experience we returned to Novell. On what concerns workstations we recently destroyed every MazDiee soft over 70 machines serving more than 2000 users. And on what concerns "high-end" we don't even dream about Redmond. Everything runs either on Solaris, AIX or Linux.
Some people say that my relation with NT is due to the fact that I didn't taste the "real thing", that I should have been more systematic on "tuning" it. I know only one _real_thing. Two months ago I had several machines running with a miserable preformance and suffering several crashes every day. Now I don't hear complains about slow preformance and the majority of workstations carry uptimes of almost two monthes.
Two monthes ago my wife almost forgot that someone else lived in the same apartment. Now I have some time to share with my family.
Oh besides. Now we have the chance to make an high-end machine out of this workstation stuff
Well, if NT is whomping everybody else in all these categories, why is it that they're not using it over at Hotmail?
Something not very "real world" in this benchmark.
mp
"The secret to strong security: less reliance on secrets." -- Whitfield Diffie
Well, I work for a very large worldwide online/television news organization. Our main web site gets about 130,000 hits/minute on a normal day. That comes out to about 2200 hits/sec. This doesn't include any of our partners, which each generate a good bit of traffic. We have 6 T3s and an OC3 for our bandwidth, and we run multiple servers to balance the load.
What do we run? Netscape web servers on Solaris. When big news like the Starr report came out, all the servers at MSNBC running NT came crashing down under the load, but we didn't. That's what UNIX (and Linux) are about, reliability. Apache can be performance-tuned if you need it to be fast (Netscape's server is the same code base as Apache), but for most of us it's fine as-is. I bet that Microsoft.com doesn't get 2200 hits/sec.
- Vincit qui patitur.
"VB and C++ are the No.1 and No.2 languages for creating dynamic web applications [says Zone Research]" ... I rest my case !!
When I first fell into professional IT I was working in a Windows / Netware shop, and PC Week was my bible -- I read every page, every week, obsessively trying to work out what I didn't know, especially about the Web and Internet. This is back in 1995. Gradually I started hearing about "the PERL scripting language" [sic], located a copy of Llama, and never looked back ...
Please remember, there are a LOT of very ignorant Microsoft/Netware shops out there in corporate land that have never *heard* of Unix except as something for industrial scale / hardcore applications, and they don't begin to consider Linux, Apache, Perl etc. In that context, there's no such thing as bad publicity. Especially as OSS shops start to gain competitive advantage over their M$-fixated competitors.
\a
"None are more hopelessly enslaved than those who falsely believe they are free." -- Goethe
Now since the old win95 kernel is dead and microsoft has trippled the amount of programers and now has every app in kernel space, you ca be sure that NT is going to excell quick and windows2000 will be thee OS that kills linux.
Dear gods, you actualy cite the fact that every MS app is going to be running in ring 0 - kernel space - as a GOOD thing?
The mear fact that MS moved the GUI sub system to ring 0 in NT and 95 is what has lead to the ability of crappy third party programs to nuke your NT or 95 box and get you BOSs.
I am sorry but windows 3.1 to windows 95 is alot more of an improvemnt then linux .8 to 2.0. Windows 95 is more advanced then NT
Excuse me? Windows 3.1 ran atop DOS. Windows 95 ran atop DOS ( don't belive me, install drdos on the box and type win - or disable the auto "win" that is in the IO.SYS file which is now just a hidden ini file. ) Windows 98 is just 95 OSR2 with service packs and IE 4 preinstalled.
Do you even know what NT is? NT is OS/2 ( or the vast majority of it is still identical ) with the windows GUI replacing the IBM GUI, 3.5 had the win 3.1 program manager. 4.0 has the windows 95 GUI. OS/2 was designed to REPLACE the severly outdated DOS arch for a 32bit system. When MS left, IBM continued development with an eye to stability. MS desided to go for ease of use and speed. Hence they merged the video subsystem into the kernel - bloating it to all hell and making it an unstable pice of tripe. I ran a medium sized BBS for five years under OS/2 running 5 copies of a DOS bbs system at once all in VDM's which could be manualy configred. If IBM had done what Sun has done with Solaris - gave it away in binary form - it would have trashed NT's growth.
--
James Michael Keller
"Linux is not our destination, it is simply the open road to tommorow"
The new data would simply corroborate the old data.
What old data?
The only thing I have dug up is a Linux/Samba blurb on ZDNet, where no lab data was given. (It turns out that a member of the Samba team tuned Linux.) That and a bunch of anecdotal evidence that Linux runs faster and better than about anything on a Pentium-90 with 48MB.
I'm not saying that the recent benches are fair by any means, but Linux has gotten larger than a bunch of guys on the Internet. That means that objective data is going to come in (something that hasn't necessarily happened yet, especially on high end x86 hardware), and some of that data is going to be sponsored by competitve vendors, and some of it is going to be cooked.
There isn't a commercial software product available that hasn't withstood this sort of 'objective' marketing attack, and especially when you're dealing with Microsoft, you have to do more than yell and maintain moral superiority. Someone (err, RedHat, Caldera, and SuSe) is going to have to post their own benchmarks and their own data.
(And, yes, Linux has enough commercial interests attached to it that you can count certain distros as commercial operating systems.)
--
Business. Numbers. Money. People. Computer World.
I woudn't say that they are, only that they carry considerably more weight than personal testimonials to those making buying decisions.
(Now that I used the word "Objective", I have the sudden dread that an Ayn Rand person is going to jump on me!)
--
Business. Numbers. Money. People. Computer World.
price/performance and hackability. Intel arch parts are widely available, cheap, and easy to mess with. I'd like to have something else, maybe a PPC box, but I simply can't afford that kind of thing.
-lx
Any suggested resources for studying these topics? Thnaks.
At what price learning? At what cost wisdom? The price is a man's peace of mind, and the cost is his life.
Actually, one of the main reasons I, and many others, were calling it a fraud, was because it purported to compare operating systems, yet used a different web server on each; and apache *is* comparatively slow. I've never seen anyone claim otherwise.
I ate something that disagreed with me. Maybe I should have cooked him first.
I'm a high school senior (at least for 3 more days anyway, then I'm a CS student in college) and I've been using Linux for about a year. I initally started using it to learn Unix for my job (at an all-Unix university research lab) and now I'm one of the resident Linux gurus where I work.
Hopefully this summer I'll actually get around to writing some GNU software of my own rather than just mooching off the work of others (i.e. Linus).
OTOH, I have a large stack of O'Reilly books on my bookshelf, I carry a Palm III, among other things, so I guess that makes me not a very normal high-school student. Luckily I go/went to a private high school so I managed to avoid the obligatory public-school ridicule of those who are different... but I digress.
Anyway, getting back to my point: Many of my friends though, who have tried Linux, really liked it but they couldn't do it at home for whatever reason (no disk space, incompatible video card, etc). Another friend of mine did try it, but went back to windows after learning the hard way what rm -rf * does.
Linux is more popular among hobbyists than you may think. It's definitely popular among people who like to dig deep into their systems and see what intricacies M$ and Apple are trying to hide from you. The students using Linux now are the ones who 10 years ago got yelled at by their parents for taking apart all the electronics around the house.
Where I work the NT boxes BSOD and reboot themselves 3-4 times a day, at a DEAD IDLE.
/. effect?
I set up a Linux web server for someone last February and it's been running continuously for the past 3.5 months w/o a hiccup.
Sure NT might serve more hits, but think of how many hits you drop while NT reboots after a heavy dose of the
Note that none of these performance tests rate uptime in real-world load situations... wonder why?
Anyone want to buy me 96 Proliant 5500s?
I'm a loner Dottie, a Rebel.
Spending the thousands or hundreds of thousands of dollars on amazing fast and powerful hardware that these benchmarks were performed on I wouldnt use linux. I would use Solaris, which excels at high slient loads, scales really well even on non-native systems and has a much better native file system. I think one of the main problems with the poor performance of the UNIX variants is their file system and process by which the file were served. They were using Samba which is basically trying to port Microsoft's file serving methods to unix. Not to mention that NTFS is a very efficient file system even for the largest drives and has impressed me when I have used it. If they were using a native serving system I would guess that the performance would be alot better than it was. The REAL problems in the web serving loads wasnt linux, it was Apache which processes each send request in a different process instead of a thread of a process (AFAIK). ISS performs all serving requests as a threat inside a process, which is a little more stable under very high loads. What I would like to see improved in linux is it's file system, change the native system to a journaling file system, ever had your power die while linux was running and then reboot? fsck took half an hour to check out my 4 gig hdd. This may have been due to my hardware or something I had set wrong, but I would imagine a large RAID system would be killer.
Like the article says, this isn't really NT beating linux. It's more of NT/ISS beating linux/Apache/Samba.
I'm a loner Dottie, a Rebel.
I wouldn't be surprised if Mindcraft picked up some Alphas and used them to show how inferior GNU/Linux is. Of course, we could reply back with some Sun hardware then.
--jon. Postel is dead. May we all mourn his, and our, loss.
I doubt BBN keeps pets in their data center.
--jon. Postel is dead. May we all mourn his, and our, loss.
Yahoo, which gets more hits than any other specific site, runs FreeBSD. I suppose they aren't a commercial site, though.{/sarcasm}
--jon. Postel is dead. May we all mourn his, and our, loss.
Use the write operating system and hardware for your job. If all you want to is stuff out files via HTTP at a tremendous rate, tune Apache and run it on FreeBSD. If you actually want to get some work done, use Solaris/USparc for high-end or GNU/Linux for low-end to medium-end. If you want to run a server for Outlook 98 clients, use NT.
--jon. Postel is dead. May we all mourn his, and our, loss.
It's doubtful that they need to, but hey, when you've got money to burn, why not? (Note that this is one of the advantages of actually making money from your software.) It's a drop in the bucket for them, and has done a good job of countering all the suckers who bought into the "Linux can do it all" hype.
Nice that it's free and all, but lately it sure looks like you get what you paid for. Don't get me wrong, I think it's a good thing that there are good, powerful OSes out there for cheapskates and the underprivileged out there -- I do so hate to come off as elitist -- but when you get out in the cutthroat business world, one realizes that there is a lot more to cost and efficiency than initial costs. And that gives you a hint why Linux has been such a non-player among big business, despite its freeware status.
Ahh yes, the scared thing. You know, I have this theory that it's every nerd's goal in life to have at least one popular entity -- whether a popular person, like a jock, or a popular company, like Microsoft -- afraid of them. Well, certainly not every nerd, but an awful lot of them, if listening to Linux fanatics telling us over and over again how they've got everyone running scared is any indication. Guys, I think you've got some issues from your old school days that you need to work out.
[zico@milan zico]$ whereis eliza
I know it makes you feel all proud and full of yourself, but here's why it's no big deal: Microsoft is afraid of everyone. Yes, that's why they're enormously successful, that's why they sometimes overstep their bounds and get Janet Reno busting their hump, and yes, that's why their stockholders just shake their heads and laugh at people like you.
That's good, I expected Linux to lose to NT as well. Guess neither of us were even close to being disappointed. :)
Yeah, I'm sure Consumer Reports will get to their big Networking OS issue as soon as they're done with their comparison of the AS/400 and the ClearPath HMP IX. Glad you know so much to state who would win, since other outfits actually benchmarking these things are proving you wrong left and right.
Okay, I've gotta hand it to you, you win the lamest argument of the month award. Runner-up: "Why is $any_site_but_a_FreeBSD_one running $any_OS_but_FreeBSD if FreeBSD is soooo cool? Probably because FreeBSD is a POS and it's maintainer$ know it." Must be an awful lot of "uncool" sites out there, since so few commercial ones use FreeBSD.
Cheers,
ZicoKnows@hotmail.com
Slashdot Realist
Admit it folks, if the tables were turned and Linux was beating NT in these benchmarks, we wouldn't be hearing all these excuses about the relevance of the benchmark.
Not that this is a new thing, since it happens every single time that someone shows that Linux might not be the best solution for everything under the sun. Whether it's lack of certain quality applications available on other OSes, or poor performance by Linux on a certain benchmark, we can always be assured of hearing the shriek of, "But nobody needs to do that anyway!"
Uh-huh.
And no, Linux doesn't actually suck at this current benchmark, but it definitely doesn't measure up to NT or Solaris in it.
Cheers,
ZicoKnows@hotmail.com
Slashdot Realist
Agreed. It says quite clear in the Apache's "Why Use Apache?" Doc, that it is not built for speed but stability. All these benchmark people are pretty brain dead, if you ask me.
Even in some "benchmarks" that compare AIX vs NT, NT chures out more static pages than AIX, but chokes on highloads, while AIX just keeps chugging along. I have a good idea that on one and two CPUs, Linux is exactly the same.
If you gave me the choice between stablility and reliablilty vs speed, I would take the stability and reliablilty any day! No one ever got fired for have stable and reliable servers!!
Linux O Muerte!
Hmmm, I seem to recall a story along that line myself.
IIRC, Microsoft tried to convert hotmail over to NT, but it just couldNT handle the server load.
-- 100% MS-Free as of 4-4-1999, 11:47:38 PST. "The lapdance is always better when the stripper is cryin'" Free Kevin,
I wish that they would have continued the load until the graphs started to fall off. Riding it out to peak performance and then stopping doesn't tell the whole story. Most people that use NT say that NT craps out under high loads. That wasn't tested here.
All in all though I think that this is a good test and points out some flaws in Linux and the software that people use on it. Yes folks, Samba doesn't always work right, Apache isn't the best web server for every job and Linux doesn't scale up on multi-processor systems the way the big boys do. Hint: Run these tests on a monster 32+ processor, multi GB RAM computer and see the results--compare with a single CPU 1GB RAM with the same NOS.
The winner in this test, IMHO, is Solaris. All the free publicity for Linux is publicity for UNIX in general. While you might put Linux on a small local server you aren't going to use it on an E10K sized computer.
-- Remember: Wherever you go, there you are!
...unless you make it matter. Remember what Linus said at his keynote address? He said: let's focus on the low end server and desktop market. It may sound "sexy" but we're not focusing on high end machines with bunches of processors.
These are two totally different areas, and Linux was always designed with the lower end in mind. How convenient then for them to do all these tests on huge computers nobody would actually use for a web server, unless they run one of the top 100 sites on the internet! Not to mention the fact that this is more of an apache benchmark than a linux one.
If you run a huge smp machine and want to squeeze every last drop of speed out of it, you probably won't run linux anyway. It's not that linux isn't "good enough", it is designed for a different purpose. For a job like that, you would want Solaris or FreeBSD (still not NT)
NT has its own design purposes, which are different from any unix type system. There are two main design goals I can see in NT: 1. Be easy for even an idiot to maintain, since most of the time all he will have to do to is follow wizards or reboot the machine. 2. Be monolithic and slow, but for benchmarking purposes, have a way for those few people who know the OS inside and out to tweak it to insane levels for one or two particular services at the expense of stability and resembalance to "real life" situations.
Vidi, Vici, Veni
The WinInfo article linked (the study-link) sais "The truth is out there". And I say "The truth is out there - krash krash".
--The knowledge that you are an idiot, is what distinguishes you from one.
What do we run? Netscape web servers on Solaris. When big news like the Starr report came out, all the servers at MSNBC running NT came crashing down under the load, but we didn't.
And I think you've hit it on the head right here. If Linux performs so poorly compared to NT, why is it that sites running NT-based web servers come crashing down when hit with the slashdot effect while Slashdot itself, running on Linux IIRC, stays up under at least a similar load.
"Under real-world conditions, if you drop a cannonball and a feather off a tall building the cannonball will hit the ground first. Any theory that predicts otherwise is useless for practical purposes regardless of how correct it is."
It's funny you should say that, since Quote.com, Inc has been doing all those things you mention using a load-balanced multiple web-server environment. What's more, they've been doing it for at *least* three years.
It's not a naive solution...it's very workable, sensible, and much more affordable than the "one giant box" business model.
Do a little more research...load-balancing is far more involved than just slapping multiple IP addresses into a DNS record.
Netscape's server is the same code base as Apache
Err... No, it isn't. I agree with most of your post, but there are significant differences between Apache and Netscape's server software. Netscape in fact might perform better on the high-end hardware for static pages than Apache does because I believe it uses a different (threading) model than Apache (forking).
I will bet the cost of running these benchmarks that my linux server will out preform the same box running NT.
Here's the specs:
AMD 486 100Mgh
32M Ram
1 gig of Drive space spread across two drives
If NT can out preform me on the same box I'll get down on my knees and kiss Bill Gates' tush.
----
"War doesn't determine who's right, just who's left"
"War doesn't determine who's right, just who's left"
Steven Wright
I'm not going to debating if NT is faster than Solaris or Linux, because i don't really know. I do know that i would rather use a Solaris or Linux box any day, and there is one reason. Mother Fsckin Stability. NT is more stabble than win9x, but it's not as reliable as a good old *nix 'puter.
cheeze always plays the mac
No OS is better than all the others in all categories, this would imply that their competitors were stupid.
Linux seems to be slower than NT as a high end web server. NT is slower than Digital Unix as a high end web server. Someone else may be faster than Digital Unix.
This test shows;
1. Linux is not perfect, and shortcomings will be more obvious as people try to fit it to all tasks.
2. ZD still is a biased magazine. I am sure there are other OSes with enough mind share on the net to merit addition to this roundup. Would it have been too much to include the BSD's or the other Unices. If they want a NT v Linux shoot out they should use more level ground.
In conclusion; Round to Micro$oft and their lackeys.
Woe be on to them, all who rise against poor people, shall perish in a the end. Buju Banton
The study was flawed and apache is slower. The two are not mutually exclusive. It is possible to make something appear worse that it actually is. They were also using Apache's slow performance to deride Linux, such is not good practice.
I'd be willing to go cold turkey on my /. habit for a couple of days for such a worthy cause.
Sheesh, evil *and* a jerk. -- Jade
'nuff said.
Actually ftp.cdrom.com just upgraded to a Xeon 500 (still running FreeBSD) they got from Micron (read: Intel with a Micron sticker on it) with 4GB RAM. The user cap has gone up to 5,000, up from a modest 3,600 or so when it was the PPro. :)
- Chad
Move along troll.....
Barnaby
If you look at the numbers and not just the graphs, aren't these numbers just a little ridiculous? I'm not real sure exactly what is meant by these numbers, but here's my reading of them. I mean at 60 clients linux has 2000 requests per sec, solaris has 5000, and NT has 4000. That means each client is requesting ~30 items/sec for linux, ~83 items/sec for solaris, and ~66 for NT. That's either really quick clicking, or really complicated pages. Then there's the other test, which is more understandable, throughput vs client load. Even so its not bad. Look 300 Mb/sec vs 200 Mb/sec for 60 clients is not bad. Really each client gets about 5Mb/sec or 3Mb/sec. For most uses this is probably fine. I expext that multi-Mb document to take a while to open. Even from my own hard drive. Bandwidth is more of a concern I'd imagine at this point.
That said let's actually look at the graph for a minute. On the WebBench test 60 clients is about the point it seems that NT levels off, can't really tell they cut the graph off. Yet the quote below has you believing different "Solaris and NT had plenty of CPU cycles to spare." And linux wasn't exactly losing any ground at that point - ok a little lower but not much. It seemed to hit a stable point. What about more clients? And then there's the Netbench graph. I mean look at NT plumet. Linux hits 16 clients and levels off at 200 Mbps. Nt hits 48 clients with 350Mbps then falls down to 300Mbps by adding 12 clients. Linux added 44 cleints and lost maybe 50Mbps. To me this looks like linux acts like a marathon runner, getting to a distance then setting cruise and holding steady. NT on the other hand is like s sprinter, burning itself out and working hard quickly but won't last real long. Yeah the sprinter will beat the marathoner in a 1 - 2 mile race, but look out for that 5 - 10 - 26.2 mile race.
My point is you get fine, predictable preformance, regardless of the amount of work asked of linux. Meanwhile NT seems fine for small amounts but the more you ask the less likely you are to get it. I want to see the benchmarks with higher numbers. I'd expect linux to hold around its same mark, and NT to fall steadily. Why 60? Why not 100? 100 is even (ish), why not 50? 60 just seems like an odd number.
-cpd
How about running Slashdot for a few days on an NT box
and see how it compares to the current site?
Goto 'Whats that site running', and look for your
self. http://www.hotmail.com *IS* running:
Apache 1.2.1 on FreeBSD.
While you are there, lookup any other major site to find that almost all of them run NetScape or Apache on either FreeBSD, Linux or Solaris. Period!
http://www.netcraft.com/cgi-bin/Survey/whats
I found this study interesting, and I think it
points out one important area where linux HAS to
improve abd that is file i/o.
My main concern is that NFS prestanda still is really really bad, but this study shows that even file reasing also is significantly slower than for solaris. This might be due to the RAID system but it is an important area.
I still concider linux to lack in some area compared to the best nixes around, however ofcourse it still is much better in some areas. (Mainly important for low end machines)
Copyright 1998 arne Verbatim copying and distribution is permited as long as this message is preserved
These types of "studies", whether accurate or not, make me as livid as the next person, however, aren't we missing the point. For years, whenever any "newbie" ( and Microsoft really is a newbie in the Linux World - they have barely contributed anything to the Gnu/Linux/OSS/Free Software/*BSD (or whatever you wish to call it )Community) said anything about a "feature" they considered "missing", or that something was "not good enough", what was the answer? "Fix it yourself!" (I paraphrase here...) Why, now, have we changed our tune? Our answer, in one voice to Microsoft, and other's like them should be: If you don't like it, then fix it!
The next time one of these comes out, then how's about Everyone who posts on Slashdot, posts "Please, Microsoft, if you don't like it, then please contribute some resources to fixing it, otherwise, shut up!" or something like that.
Microsoft are still in the Business Mould... What do we care!!!!???? [idea for a poll - how many people's income depend on the market share of Linux against NT/Solaris/Netware etc. - OK, so the likes of Redhat/Suse/Caldera etc. do, and I wish them well, but your average kernel hacker is (as Microsoft themselves pointed out) just in it for the recognition/fun etc.
Therefore, Linux will still be around, as long as people still wish to develop it, and when they don't, then it will die, and there will be no one who cares, since we will be all hacking some other OS, or project or something! When NT dies, which I'm sure it will, there will be lots of MS shareholders who do care, and will be most unhappy... Justice!
Eric the Cat
I gave two examples. Someone else says they both involve purchased code, not native MS development. So here's another from a friend of mine:
From the SDK: "Windows 95: MapViewOfFile may require the swapfile to grow. If the swapfile
cannot grow, the function fails."
So, even if I have a file mapped, somehow Windows 95 thinks it needs to page.
Some of MS's applications, ie word and SQL Server, are well done. However their OS, their network protocols, and their server code are terrible.
NT is far less mature than the Unix family, of which Linux is a member. M$ foolishly ignored 30 years of research and accumulated wisdom. As a result, they've been repeating all the old mistakes.
Most of NT (and other M$ code) was written by lower echelon programers, under the direction of computer scientists and managers. Many of them had only recently graduated from MSD training classes. In generaly they were operating under marketing imposed time constraints. This shows in the quality of the product.
If you want proof, try working with the IP routing table metrics under NT, or look at their publicly released code, ie the frontpage extentions for apache. Also look at a security model that requires everyone to buy third party virus scanners.
In contrast, most of Linux was based on an established tradition. Most of the major holes were already known. It was written by people who cared about the quality of their code. They loved programming, and their personal reputations were at stake. Then that code was reviewed publicly, and contributions were fed back to the author.
I forget who said "If I have seen far, it is by standing on the shoulders of giants". M$ forgot it was ever said.
Huh? Excuse me. PC Week has been full of FUD since day 1. I seem to recall that a positive Linux quote used to be a rare thing in there, but negative 'Linux is a fluke' were common. If any mention of Linux happened at all.
Ziff Davis is NOT Linux friendly, since M$ pays for so much advertising. I rarely see a true anti m$ review in there.
as for this article:
as we who read Linux Today, Slashdot, etc, know, that is NOT true. There hasn't been 'refusal'.PC Week subscriber for many years now....
Help achieve Liberty in your lifetime - join the Free State Project - http://www.freestateproject.org
I think that this kind of benchmarks is quite interesting to read, but not so helpful if I were to buy a server: in first place even the "low performance" of linux is able to saturate a more than resonable connection and it is quite sure that a 10Mbit lan is going to have some problems in coping with the stream of data;
secondly I belive that serving *STATIC* html pages is not meaningful at all for "real-world applications". This is not to say that NT cannot outperform linux on high-end hardware or in given configurations, but
I want to stress that this results seem to make little sense. It is more or less like comparing the MIPS rating of two completely different architectures and deducing that one is better than another; not quite so and,
more importantly, everything depends on the kind of task one has to have the machine doing! (for example Alpha processors are just great when we consider Floating Point performance; when running my code -aimed at symbolic calculus and not FP- they outperform intel processors by just a factor of around 2 or 3).
Linux is "work in progress" and bad results should lead people to improve it, rather than complaining on how unfair the test has been (even if the test has been unfair, like this seems to be the case); on the other hand linux
(and the various *BSD) has the huge advantage of a nice standard interface and of the disponibility of a huge code base. Security patches usally are released quicker for
Unix-like systems than for NT and this is a good thing. Now just a remark concerning my experience: when I first tried linux (more than 5 years ago) it was
neither very stable nor exceptionally fast, but it was an unix-like system with OpenLook (that I was using also under Solaris on a SPARC) and it allowed me to share easily my code between the machine at the University and the one I had at home.
The improvements linux has done since then are quite impressive (and nowadays I think I prefer having linux rather than SunOS 7 on a sun4m and I consider it to be definitely better than DU 4) but there is still a long way to go, and even if now it is slower than NT while performing some tasks
stability and "user friendlyness" (at least for somebody that is writing this text in lynx and loves command line!) are things I would not underestimate. Moreover I guess that in 4/5 weeks we will have some patches that address the "lack of performance" these tests have shown.
Monty
I am not quite sure how much one of these crazy systems cost with quad xeons, raid and four nics..
But I think someone should do a comparison that is more like what a business would do and do a comparison for performance per cost.. Just taking a shot in the dark I am figuring one of those test systems that they are using costs about 10k if not more.. So how much performance could be gotten out of a linux for 10k (or whatever that single box costs)?
If it isnt obvious by now, these people are going to keep throwing benchmarks around using the ideal hardware to make NT look good.. but if a benchmark could be done using the hardware that linux really shines on.. What about a cluster of some sort? A redundant array of inexpensive machines?
just as soon as hotmail and msnbc do...
Ex Libris Veritas
http://www.apache.org/docs/misc/perf-tuning.html
"Apache is a general webserver, which is designed to be correct first, and fast second."
That is the first sentence in the performance tuning document.
--- A Jesus Fish eating a Darwin Fish only proves Darwin's point.
The pure humor of it all...
From behind the scenes of www.microsoft.com
Hardware
Six internal Ethernets provide 100 megabits of capacity each
2 OCI2s provide 1.2 gigabits of capacity to the Internet
Runs on Compaq Proliant 5000s and 5500s, with 4 Pentium Pro processors and 512 megabytes (MB) of RAM each.
Software
Microsoft Windows NT Server 4.0
Microsoft Internet Information Server 4.0 (IIS)Microsoft Index Server 2.0
Microsoft SQL Server 7
Other Microsoft tools and applications
Powerful Solutions
www.microsoft.com started out as a single box beneath a developer's desk in 1994, handling about a million hits a
day. That seems almost laughable now. A sleek data center in Redmond, Wash., receives more than 228 million
hits a day while data centers in London and Tokyo shoulder the international load of about 12 million daily hits.
How has the site handled its explosive growth while keeping its hardware to a minimum? How does it administer
one of the largest databases in the world? How does it manage the challenges of a decentralized publishing
environment? How does it come close to achieving 100 percent site availability? The answers lie in the
strength of its software, according to site architects. The whole shebang runs on Microsoft Windows NT 4.0,
IIS 4.0, and SQL 7.0. "Our site showcases Microsoft technology," says systems operations manager Todd
Weeks. "We prove every day that we can run one of the largest sites in the world 100 percent off of
Microsoft technology."
The Challenge
Not only is www.microsoft.com an enormous site with hundreds of thousands of pages of content. Not only
does it receive millions of hits a day. Not only has its growth been unrelenting. Those are some of the
easy challenges, site architects say. One of the most interesting challenges is that www.microsoft.com
functions within a decentralized publishing environment. More than 300 writers and developers working in more
than 51 locations around the world provide information for the site. These content providers are able to update
their sites within the www.microsoft.com umbrella as often as eight times a day. In fact, 5 percent to 6
percent of the site is updated every day. The complexity of that publishing environment is daunting
when you consider that each of the 29 content servers in Redmond contains the nearly 300,000 pages of
information that comprise www.microsoft.com. But the end result is that the information on www.microsoft.com
is as current and up-to-date as possible. A team of about eight people staffs three shifts around the clock
to ensure www.microsoft.com stays up and running 24 hours a day, seven days a week. "Our goal is to make the
site available to users 99.8 percent of the time," Weeks says. So how do we reach that lofty goal of 99.8
percent availability? (The 0.2 percent down time is required for routine maintenance.)
First, the Hardware
The physical architecture behind www.microsoft.com seems surprisingly modest. Twenty-nine servers host
general Web content; 25 servers host SQL, 6 respond to site searches; 3 service download requests along
with another 30 in distributed data centers; and 3 host FTP content. Additional servers overseas handle
some of the international load.
Did you count all of that? That's 96 Compaq Reliant 5000s & 5500s (Quad Pentium Pro boxes with 512Mb RAM) running
www.microsoft.com using NT, IIS, Index Server, and SQL Server.
Standard
This machine is a P6/200 with 1GB of memory & 1/2 terabyte of RAID 5.
The operating system is FreeBSD. Should you wish to get your own copy of
FreeBSD, see the pub/FreeBSD directory or visit http://www.freebsd.org
for more information. FreeBSD on CDROM can be ordered using the WEB at
http://www.cdrom.com/titles/os/freebsd.htm or by sending email to
orders@cdrom.com.
Now, which site do you suppose has set more download records?
--- A Jesus Fish eating a Darwin Fish only proves Darwin's point.
How many times does the "Linux Community Inc." need to tell these people that Apache wasn't ment for speed!? Why is Apache designated as the One True web server? Benchmarking static Apache vs. static IIS is pointless. Any programmer worth his salt could cook up a few dozen lines of code that would outperform both servers on pure static content.
:)
They should benchmark how many dynamic perl generated pages NT can vomit out
--- A Jesus Fish eating a Darwin Fish only proves Darwin's point.
thats the funniest thing ive heard all day, should be a 2, not a -1 . come on, hemos, rob, whoevers moderating...
-- your knees hurt, don't they?
I'll say this. I am equally dumb setting up either NT/IIS or linux/apache. So, I'll just blame the apache group and the linux community for giving me the opportunity to not reboot my webserver over the last year. It's first aniversary is May 23rd. :)
"Well that's a dumb idea" -poignant insight from The Jupiter Group
Somebody please help me out here, because I evidently just don't get it.
Why is SPEED the overwhelming issue? IMHO, there is so much more involved in choosing a server OS. Do we really need to measure the number of milliseconds it takes to rename a file on the server? Isn't that a little silly?
Picking a hardware/operating system configuration is not a drag race. You care about cost. You care about uptime. You care about security. You care about support.
The skills of your existing personnel are important too. If you have a staff of freshly-certified MSCEs, it's very unlikely that you will use a Unix-like system. OTOH, if your network admins love Unix, they will want to work in a familiar environment.
In the end, speed is not really the same thing as "performance". Benchmarks like these provide nice soundbites for the winner (whoever it may be). They also improve magazine sales and web traffic for the publications. If you choose to commit your organization to an operating system based on them, however, then maybe you deserve what you get.
As my mom used to say, "When that lawnmower cuts off your feet, don't come running to me."
Save the whales. Feed the hungry. Free the mallocs.
I don't know that slashdot has actually crashed - I do know that routing from where I am to slashdot has been spotty, and most lately it's been a problem in pbi.net land, which appears to belong to PacBell.
Whois.arin.net lists the coordinator of the netblock where my traces have been dying as ip-admin@pbi.net. Email to that address bounces on a mail loop. Bleah.
--Stafford
An IT department with that sort of a budget will find Linux to be rather useful for some applications, actually. With that size of a budget, one can make an in-house Linux support team. Having such a team and using Linux keeps you from relying on a vendor's support team. Such a team allows you to implement mission-critical bug fixes on your schedule, not that of your vendor. And believe you me, if you are big enough to have a $1B budget, time is measured in thousands of dollars per minute. Waiting a month for a bug that takes a week to fix is expensive.
--The basis of all love is respect
Oh no... I've inadvertently set off a *BSD vs. Linux thread?!? I'm feeling deeply ashamed, that wasn't my intention at all!
..."? The same goes for NT or other systems (although I doubt many people are able to make drastic improvements to NT themselves that way since they don't have the sourcecode...).
But your reply emphasizes my point: benchmarking a webserver isn't enough to make broad claims like "OS-X is faster than OS-Y".
The problem is the incredible amount of different configurations that are possible. Apart from choosing different webservers you also have the possibility to tweak the webserver sourcecode yourself. You can even try to optimize the kernel to improve performance.
Suppose you rigged a Linux system for optimal performance by making a Linux-optimized webserver and a webserving-optimized kernel, would it be fair to say "Linux beat
It's a nice dilemma:
Not allowing customized configurations will have most people complaining the tests were done on a system that doesn't use all the capabilities of that particular system.
If you do permit tweaking kernels and applications for maximum performance there will alsways be people complaining this-and-that could have been improved on by some clever hacking.
I realise that the webserver benchmark is just a small part of the tests, but practically all of the benchmarks make claims like "NT beats Linux" and substantiate that by giving a lot of numbers on how much webpages were served by a Linux server and a NT server.
Apache runs on a whole bunch of other platforms, even on MS-Windows. Probably even NT... Wouldn't it make more sense to make claims like "Apache on NT beats Apache on Linux"?
That wouldn't prove the superiority of NT over Linux either, but it would IMHO make just a little bit more sense...
The same goes for Samba: Samba runs on Linux but also on other systems.
All these tests only test NT-running-some-software versus one-of-many-Linux-distros-running-other-software and then make claims like "NT kicks Linux' ass".
"Linux" is just the kernel... or have I gotten things completely wrong?
Benchmarkers should at least prove that bad scoring is caused by Linux (kernel) and not a program they're running on top of that!
If a webserver running Apache on freeBSD is doing better than Apache on Linux, that would be an indication of shortcomings in the kernel (although some people may dispute that as well).
Ah well, I never really cared for benchmarks anyway...
Really? Then how come I've had a server sitting up and running since installation a year and a half ago, with my site getting around 3-4k unique sessions a day (hey it's only a baby), and the only time it went down was for a memory upgrade.
I don't know what the heck half of you do to NT to make it unstable, but I have never had a the grief you've had, except on a development box with some of the development team writing really dodgy code *grin*
So rebooted many times a day? Rubbish
>190,080,000
>Thats what 2200 hits/sec gets you. You'll
>be doing 190 million hits/day. Pretty damn
>impressive. I'd like to work for you,
>considering the monster bw you'll have.
You fail to distinguish between peak load and average load. One tests at a theoretical peak load in order to ensure functionality in the worst case. This is a basic principle of design in any engineering field.
Of course, PC Week tested only for speed; a more interesting peak load parameter is reliability. As other people have pointed out, NT would suffer in such a comparison.
Sadly, many technology managers seem to regard web servers (and computers and the web in general) as toys, so they judge them like they'd judge a sports car or a speedboat: Speed matters, reliability doesn't.
The issue we face is educating these managers, not some particular benchmark.
--
Some keywords for the NSA in the Lord of the Rings universe: One Ring bind find Sauron quest Nazgul freedom
Well, once the machine is in place, anything can be tested on it :o) - sure, test OS/2... (would be interesting to see..)
/. pages would cover that, wouldn't it? :o)
:o)
As far as what to do with the machine afterwards, I think putting it into full-time service would be the best thing - technology changes so rapidly, it would be pointless to keep it for future benchmarks.. I'd rather see it doing something useful for the community (serving
So I guess the first thing is to suggest a poll... "I would donate $X towards a high-end benchmark server..." - maybe see how much interest there would be in following this through... so far we have $200 pledged
We are nearly there. Just a few years ago, no-one could think that open source software would be included in testing. No one could even think that the open source movement could cause a reputable(?) company like Mindcraft to do tests again.
Just another few years and the suits will start to appreciate the advantages of open source, stability et cetera.
Mark
It's obvious that if you can, replication of servers is always the right solution. This benchmarks are more a feature than a fail.
There are munch more people with a limited budget but a lot of computer power needs, than Mega Hyper Web Sites with zillions of requests a day, and that are the people Linux must serve, that are their "market".
IT's with a billon to spend "shure" don't will ever use Linux. So, why worry, let them take fun seeing how clever their are and let's work for the real problems.
BTW, this was the feature which i convince my boss to jump to Linux. Three old P133 with their tasks well distributed can save a lot of money in monster machines. In our case we have three linux serving samba to 100 clients, one serving Applications (Office and all that) another sharing home directories for all our workstations and a thirth making daily backups of the other two, and to a Tape.
Works perfectly and outperforms a dual P200 NT box we had before (now making more profit of their Hertz as a secondary database Server in Linux, of course).
The three Little pentiums have enough CPU to handle Software RAID (cheap!!) over IDE DISKS (cheaper!!). (If there were curious people out there afraid to try this RAID configuration, I must say that works VERY well...)
As you can see, that all was done with throw away machinery for near 0 cost.
========================
Uh.. neither Spanish
It's obvious that if you can, replication of servers is always the right solution. This benchmarks are more a feature than a fail.
There are munch more people with a limited budget but a lot of computer power needs, than Mega Hyper Web Sites with zillions of requests a day, and that are the people Linux must serve, that are their "market".
An IT with a billon to spend, "shure" don't will ever use Linux. So why worry, let them take fun seeing how clever their are and let's work for the real problems.
BTW, this was the feature which i convince my boss to jump to Linux. Three old P133 with their tasks well distributed can save a lot of money in monster machines. In our case we have three linux serving samba to 100 clients, one serving Applications (Office and all that) another sharing home directories for all our workstations and a thirth making daily backups of the other two, and to a Tape.
Works perfectly and outperforms a dual P200 NT box we had before (now making more profit of their Hertz as a secondary database Server in Linux, of course).
The three Little pentiums have enough CPU to handle Software RAID (cheap!!) over IDE DISKS (cheaper!!). (If there were curious people out there afraid to try this RAID configuration, I must say that works VERY well...)
As you can see, that all was done with throw away machinery for near 0 cost.
========================
Uh.. neither Spanish
I love to bash Microsoft. You know why? One reason is that they rely on FUD about their competitors' products to sell their own. In other words, it's the FUD I hate. So I enjoy it just as much when anti-MS FUD gets shredded as when pro-MS FUD does. It's amazing all the lame excuses I'm seeing now that people's cherished false claims have been disproven.
I particularly love the bit about how a farm of small boxes is better than a single big box for availability reasons. This is only true if the boxes in question are in some sort of HA arrangement, and the fact of the matter is that HA on Linux lags _way_ behind HA on AIX, Solaris, HP-UX or Digital UNIX. The "no big boxes" schtick is just more FUD.
As for the "Linus is so smart, no he's not" thread and microkernels: Linux has proven many times that he needs to grow up as an OS designer. Sure, existing microkernels suck because they use inefficient IPC interfaces between modules, and Linux avoids all that overhead, but there's a little excluded-middle thing going on here. One doesn't have to be entirely monolithic and non-modular like Linux to avoid the faults of IPC-based microkernels. I've worked with a bunch of UNIX kernels plus NT, and Linux is _the biggest_ pain in the ass as far as implementing a self-contained module. Damn good thing I can change the core code, because that's the only way to do many important things even though it doesn't have to be that way. Modularity is _still_ a good thing, and something Linux sorely lacks (though it has improved a lot and I expect will continue to improve).
Slashdot - News for Herds. Stuff that Splatters.
Isn't this one of the things FastCgi is supposed to be fixing, instead of launching one process per perl script, it launched one perl interpeteror and passes it all the perl scripts, hence less overhead, and more speed (with the drawback that the scripts have to explicitly free memory and be slightly modified) (with a loop about the script)
Not quite thread like, but definitly not on process per cgi request.
--
Exigo spamos et dona ferentes
Guess they don't read Slashdot much.
:)
And Slashdot can hardly be called pro-Linux or anti-Microsoft, right?
Cheers
Alastair
-- "I believe the human being and the fish can coexist peacefully." - George W. Bush, 29 September 2000
190,080,000
Thats what 2200 hits/sec gets you. You'll be doing 190 million hits/day. Pretty damn impressive. I'd like to work for you, considering the monster bw you'll have.
I'd basically ignore any current benchmarks because they're based of versions of linux that have known issues.
You're also comparing a multi-process server, which works faster at lower loads, to a multi-threaded server, which scales better, although might not/does not return documents back faster.
I'd like to see the avg connection times on these things.
Uh...how about 'cluster with fail-over'?
Inferno Man
In my (very limited, workstation-only) experience with NT, I've found that it either a) runs beautifully or b) crashes like crazy. My '95 box at home is the same way. There doesn't seem to be a middle ground of any kind. And since so much of what makes Windows tick is undocumented to the point of being unconfigurable (Looked at your Registry lately? What the hell are all those cryptic hex values?), when your box becomes unstable, your only recourse is to reinstall and pray.
--
I use 2 operating systems on my home computers. One of which is for games and the other I use for its stability and reliability among other things. I am, or course, speaking of Windows 98 and Linux. I get things done well this way and I don't see any need for Windows NT at all. If I want to run an os with good networking support which is nicely customizable and would like to make use of its great developmental utilities, well I'm most always in linux. Good thing for windows and its support for my Riva 128 card so I can get my hands on q3, at least until windows crashes and I'm back to linux as to not get to pissed off over something that makes no sense at all. I don't like to put up with windows' problems. Oh well...
It was posted twice, because the testing was done twice. the testing that linux performed badly on (high end servers) was the same testing that mindcraft did several weeks ago. the article is showing what we expected, that linux performes much better than NT on low end machines.
Isaac Newton, I think.
Java: the COBOL of the new millenium.
There is nothing special about "engineers" that makes them better than "hackers". Those labels are not even exclusive; the best hacker I know has an engineering degree. You do not know what a hacker is, if you think they are necessarily unaware of computer science and engineering principles; and in my experience, the more eager a person is to call themself a "software engineer", the less competent they are.
As for Cutler, his work on VMS doesn't give me great confidence in him. VMS is stable and useful to some, but it's far from being my favorite OS. He may be awfully serious about it; he may be awfully serious about NT, too, but that doesn't mean I want to spend any time using it, or that it meets my needs.
Linus has a proven track record of writing solid code and coordinating a massive development effort. He does not just say that microkernels are stupid--he demonstrates by example that the monolithic approach is still viable. As elegant as I think microkernel architectures are, Linux is still what runs on my servers.
Java: the COBOL of the new millenium.
Ah, but the PC Week test was just static documents! Redhat 6.0 comes with an RPM for Squid, but instead of installing that, they use Apache and then gripe about how expensive it is to fork for each request.
It's unclear to me what use there is for a web server that is eating bandwidth about the way ftp.cdrom.com does, anyway. That doesn't strike me as a typical "enterprise application". That part of the benchmark is obviously contrived.
Java: the COBOL of the new millenium.
The numbers get even more interesting when comparing the results of NetWare with and without Opp Locks. When we turned on Opp Locks, NetWare's overall performance improved by about 40 percent.
However, this gain is deceiving. With Opp Locks enabled, almost every operation in NetWare actually slows by 25 percent. The exception is file write operations, which are faster by 300 percent. Because writing files takes up almost 40 percent of the NetBench test, it's no wonder we saw a huge overall performance boost in our results.
These people haven't a clue what they are benchmarking. Opportunistic locks allow the client to do whatever it likes to a file (or regions thereof) without synchronizing with the server. Of course write speed increases; the network isn't involved anymore! You haven't increased server performance one whit, but rather prevented more than one client from opening the file for writing at the same time.
Java: the COBOL of the new millenium.
>ALo pc magazine said linux sucks so I chose to >believe it.
First of all it appears that you have made your decision just based on what someone else says.
Second pc magazine,hence the name,was created about new prebuilt pcs,so why are they comparing servers in the first place?
Don't beleive everything you read and do a little of your own research because you sound very ignorant.
Actually, Hotmail is still on Apache/FreeBSD, but your basic point is correct. Numerous very large and reliable sites run on NT/IIS (see list below). Try to find a large site on the net running Linux; there aren't a whole lot. DejaNews is the biggest I can think of, and it's notoriously slow and unreliable.
NT Sites:
www.microsoft.com
www.dell.com
www.gateway.com
www.ebay.com
www.onsale.com
www.buy.com
www.disney.com
www.compaq.com
www.nasdaq.com
www.nfl.com
www.espn.com
www.exxon.com
www.ml.com (Merril Lynch)
www.shopping.com
www.forbes.com
www.intel.com
and, of course, www.drudgereport.com, which actually appears to be running on Windows 2000/IIS5.
In fact, if you look at commerce sites on the web, IIS is by far the most popular server.
LJS
All deoends on how you define "traffic". Commerce sites do a lot more complex work than the average search engine.
In any event, www.microsoft.com and www.msn.com handle more traffic than any search engine, except Yahoo I suppose. And the work they do is far more complex than Yahoo, which largely serves static pages.
LJS
>>Microsofts website and now zdnet, dell, nasdaq clearly show that NT is one of the most scalable os's ever thaks to i/o async.
Basically, I agree, except that very little at ZDNet runs on NT. Only a few outsourced things like the auctions.
I have used Linux running on top of the L4 microkernel, and it is not crippled.
Check out the web page of the L4/Linux project:
http://os.inf.tu-dresden.de/L4/LinuxOnL4/
I've done my own comparisions at work between Solaris x86, NT 4.0, and Linux. All I can say is Solaris and Linux performed much better than NT when it came to fileserving, serving up web pages, and being reliable.
I trust Solaris with serving DNS, web pages, sendmail, FTPing, Telneting, Samba, and running an IRC server all off of one machine with only 64Megs of RAM (Sun hardware). I wouldn't trust NT any farther than I could throw the box!
What I want to know is why the hell are we screwing around with piss ant little Intel boxes? Anything implemented on IA32 is still, in my view, a toy.
Lets use some real machines in these tests. I'd like to see how NT stacks up against Linux on a high end Alpha.
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
For a high-end site, the database should be on a single, huge box (probably not running Linux) that all the http servers use to store state.
The ``high-end web server market'' is a myth. You are better off with a bunch of servers and some form of load balancing.
Hmm...
I'm reading the PCMag test and I see that they are using a kernel 2.0.35 and a Stronghold Webserver...
How good was the 2.0.* series at Multiprocessing?
and, Isn't Stronghold slower than Apache due to the security issues?
And why do they only test (as it seems to me) static webpages... aren't dynamic ones a better way of showing what the server/OS is good for?
(I think I saw a note on apacheweek ( http://www.apacheweek.com) that Apache in fact did perform better than other servers w. dynamic pages than static ones... (I might be wrong here))
I also see much people saying that Apache is slow (I know it wasn't made for performance) Therefore I'd like to see a test comparing Apache under different OSes... Linux, *BSD, Solaris, NT (when the NT version is stable) and so on...
/Droid
Now what about 1 pentium III 500, and only 512Mb ram, And run the benchmarks for 1 week, this is what we are running and the NT box has had to reboot twice now. Something about when it gets up to 50,000,000 hits it just likes to die, hmmm... We have the servers doing file copying and massave web hits for 4 days now. We havn't even touch the linux box since we have started. The linux box seams to be doing about 48% better then the NT box. I don't know whats wrong here, But anytime we do a benchmark Linux comes out on top. I guess it's a matter of how much Microsoft will pay ZDNet to run benchmarks. Source : ADN Labs
Got shack?
ShackCentral Network
Worlds best gaming network!!!