Slashdot Mirror
Mac OS X out and faster than Linux?
Steve Bergman
sent us a link to a Linux Today Article
that talks about claims that MacOS X Outperforms Linux
running Apache on machines under $5k. What do you think?
Anyone have some numbers?
← Back to Stories (view on slashdot.org)
That's not an article, it's a stinking press release. Lame. On the positive side, X Server is $99 for Apple Developers.
Apple sucks, Jobs sucks, iMacs suck, Yosemites suck, and Linux rules. Don't EVER let me hear any of you say different.
...
Hey, read this quick, because it's about to be vaporized
Since MacOS X is based on BSD 4.4, how does it compare against a similar FreeBSD machine? I thought that the BSD's network stack was currently faster than Linux's.
Linux really suck at networking so it's not a suprise, not that I would ever use MacOS X anyway =)
(The reason why MacOS is so fast is because it's based on *BSD code, take a look at this for example, if you didn't already know, and you want some facts.)
Do you know how much Alpha hardware you can pick up for 5K? A heavily configured 633 MHz machine with at least 128 megs and ultra 2 drives. I don't even have to read the article to know they're full of crap. Funny has anyone seen any G3 vs Alpha benchmarks?
ALPHAPOWERED
http://www.alphalinux.org
In the fine print it says that it was compared to a RedHat Linux box. Being that RedHat is the slowest implementation of Linux out there, especially out of the box, this is not suprising.
no it can't do any of those things but you have to agree it is infinitely sexier than the old mac's and most pc's
Cut him some slack.
Nobody at Apple ever said the iMac was 1000 times faster than anything. Steve Jobs said that G3 processor in the iMac blew away the fastest PC available (at the time of his comment) which was apparently a PII 450. And it didn't really. Except in some integer tests. I agree that the claim is somewhat disingenuous, but it's not a big a deal as people have made it out to be, IMHO. I have an iMac and love it.
Errr, it'd be real nice to benchmark on a single, standard piece of hardware rather than the wildly varying systems they name.
Obviously, given the above, it's not worth any further consideration.
that must be a typo!
Webserver Benchmarks
... basically, 64 million hits a day.
All machines have same RAM, same speed ethernet, same type of disk, same version of Apache:
Dell PowerEdge 2300 running RedHat - $4200
Dell PowerEdge 2300 running NT - $5000 (Steve joked $800 "NT Tax")
Apple Power Macintosh G3/400, Mac OS X Server - $5000
Sun UltraSparc 10S - $8500
[bbum@codefab.com if anyone cares to reply]
Benchmarks from Ziff Davis WebBench 2.0:
Dell/NT - 300 hits/sec
Dell/RedHat - 500 hits/sec
Sun - 600 hits/sec
Apple - 740 hits/sec
Also-- get a clue folks... Apple doesn't know dick about Unix support. But Apple isn't Apple anymore-- it is NeXT and NeXT knows *a lot* about managing heterogenous Unix environments and supporting Unix across multiple architectures...
Call it RedHat or Gnome anything, and these same people would be drooling.
Hey, fine. Don't use it. I will, because I know it works.
I noticed this at the bottom of the story about mac OS X
NOTE: Apple, the Apple logo, Macintosh, Mac OS, Power Macintosh and WebObjects are registered
trademarks of Apple Computer, Inc. Open Source is a trademark of Apple Computer, Inc.
What the HELL is this???
No one on /. is going to give a shit about this. They're still going to bitch and complain about Apple.
Typical response really.
The Purchase of NeXT was, in effect, a reverse takeover of Apple. Jobs is CEO and Chairman of the Board, and something like seven of the top nine executives are NeXTies. These people know what they are doing. All of the Apple flames I've seen here recently sound like whistling in the dark to me.
Uh free software guys and gals, looks like we need to lean on Jobs over this one. If we let him tm Open Source he'll try other crap. The context of the textual references are the same as we use here in /. "Darwin the Open Source release of OSX" etc.
Apple, you cannot(should not) trademark our buzzwords!
Steve you have 24hrs to change that and to show you we're serious, you have 12hrs.
Personally, I don't trust Apple (or any other company) to publish fair benchmarks of their products. That aside, I would take issue with your assertion that Apple computers come "headache-free". These past few months since the release of the blue G3's have seen an avalanche of G3 horror stories, beginning with system 8.5 "upgrade" disk desdtruction, the bad driver for the ATI rage 128, and continuing problems with SCSI devices, in particular scanners. I have one friend who sent her G3 350 back to the co. she bought it from. my brother works on a (so far) non-SCSI G3 350 and reports a high level of instability by comparison to the G3 233 he used before. I am surprised that more mention of this crap hasn't been heard here at Slashdot, but I guess most folk here don't own Macs. I would say that the benchmark offered by Apple shows one thing above all: The low (and sadly accurate) estimate of their customers' technical savvy. Most of us who use Apples just do not use them for stuff that is related to compsci, OK? To let you know where I'm coming from: I am a past Apple owner and will be buying a G3 in the near future. I hope Apple will continue to grow and thrive in the future, but I don't like hearing BS from them and their moronic adherents who'll repeat any tall-tale they read in a Cupertino press-release.
Apple I believe owns a trademark to the word Open Source that they acquired from some supplier of NeXT systems or some such thing. It's in a different category than the Open Source certification mark that's held by ESR and friends, which allows them the right to give official branding status to anything that calls itself Open Source. I am not sure however, how this would apply to Apple as the holder of the same phrase in a different trademark category. It would seem that Apple has some right to the phrase, but if they try to pass off its usage as meaning the same thing as the Open Source definition written by Bruce Perens, they might be violating trademark. Mind you, convincing a court of this would be difficult. But unfortunately it seems to mean that in practice, Apple can run around and call anything they want Open Source, and not have to abide by the real definition of Open Source. Shameful in my opinion.
It's not on the copy of the press release on Apple's website:
s xserver.html
http://www.apple.com/pr/library/1999/mar/16maco
Forget the performance of the machines. Forget that Linux is free. The reason Apple sells so well is the fact that any brain-dead moron can buy an Apple system, install it himself with little more than a screwdriver and a can of Coke, and be running in a few hours. I like Linux, but before Linux can start becoming a full mainstream operating system for the average Joe consumer, it needs a pretty front end and a rock-solid installation process. KDE just doesn't cut it right now...
Apple finally delivers the full-blown modern microkernel-based, multiuser, preemptive multitasking, protected memory, command-line capable, Unix OS with the friendly GUI on it, just what you've spent years flaming them for not delivering.
:(
That's right! It -sounds- pretty damn awesome. I want to try it and see if the hype is true, though. *sigh* too bad it only runs on brand new G3s and costs $500....
Speaking as someone who worked for BNR, errr, Northern Telecom, errrr, Nortel, errrr, Nortel Networks for a few years, we were told that MS paid Nortel and 'undisclosed' sum of money for the right to use the NT trademark. Seems that Nortel was switching over to the "Nortel - Northern Telecom" logo from the "NT" logo anyhow, so it was a good idea at the time.
Probably an alphabetical listing. This is considered "good form" in most journalistic circles.
Well, that really doesnt tell us that its faster then Linux. All it shows is that its faster then INTEL. I knew that for about 2 years. Apple has this thing about throwing decieving benchmarks out, but i guess everybody does that.
Anyway, I've begun to like apple less and less, when i see its users spreading FUD about linux like:
"If you strip the GUI from Linux, you have nothing, a useless OS"
I think, they all just need to eat less paint chips.
This is like comparing apples and oranges. How about Installing Linux on EXACTLY the same PowerPC and then benchmark it against MacOS X?
The bit about Open Source being an Apple trademark is not on any of Apple's materials. This was apparently added in by an overzealous editor at News Alert...
Ok, that's a G3/400, 256 RAM, 2 9GB 10,000 rpm Ultra 2 drives, 24x CD, 5 (yes 5!) 100 Mb/s Ethernet ports. ANd MacOS X server. This price includes support and comes with most of the same stuff Linux does. Except the GUI probably makes some sense, as oppsed to KDE.
/. won't mail my freaking password!!
Now if this were NT, it'd be WAY more expensive... Nt 4.0 ($899) BackOffice ($3000+)....
AC post cause
it's a typo. we hope. this thread has already been discussed at least twice here.
my theory is that whoever is passed all these press releases to put on the internet simply runs a spell check program on the releases, and if it comes across anything it had never seen before, such as "open source", it assumes it's a new technology.
Al Gore: claims he invented the internet.
Apple: places a small note at the bottom of a page somewhere saying they trademarked open source.
Microsoft: claims to have invented the web browser, then quietly patents Style Sheets and the doorknob.
If you think MacOS X is (equals) BSD you haven't done your homework, really, even tried. MacOS X _contains_ BSD layer.
>Why didn't they run the benchmark agains LinuxPPC on the same box?
Why did they run these benchmarks in the first place? To compare with alternatives, serious ones. How many web servers run LinuxPPC??
>Beware the Reality Distortion Field.
Where is the distortion now?
Even though Apple's boards are different the processors are the same as IBM's (740's). IBM's servers (RS/6000 and AS/400) do very well with AIX, Apache and Java.
Apple Open Transport (TCP/IP stack) is much faster than NT's.
All of the above can be found in various trade magazines over the past 6 months.
The G3 still would have been killed by a comparably priced Alpha-based linux machine from Microway.
This just teaches us all a lesson. Want to look good, go stand next to an ugly person.
give'em a break, they tested against the most well known common altenative configurations, even a company like apple only has so many resources to draw upon, do you think they have a room full of an infinite number of monkeys,OS's and PCs???!!
Better they waste there time debugging code than comparing it...
Your English is really quite poor, isn't it?
WebBench and NetBench ran on both the G3 and the comparison platforms, as the sentence clearly conveys. Apple simply used WebBench to compare against one set of systems and NetBench to compare against another (presumably because only NetBench was available to run on the NT machine).
Please to learn to read before posting such drivel.
OK, I go for politics, not software qualities
Everyone of you says "Linux rules" while objecting "Microsoft rules"
Linux community think they're the saints, but I don't really see the difference from MS supporters
Linux is good but its people's minds have long gone beyond the objective, justice bottom lines.
Do you pray to Linus Torvalds every night?
Do you thank Linus Torvalds for food?
Do you go to your closest LUG instead of church on Sundays?
Face it, Linux is now a religion, not just a software. And I think a world like this is worst than "Windows everywhere"
Is there a point to this...?
Oh, so Apple made OS X eh? ;-).
I also would have liked to see a PPC Linux/OS X comparison. This would have been much closer to the truth. And also with FreeBSD (if it is possible), - THAT might have been revealing.
Anyway this is Marketing BS.
Alphas are faster for *floating point*, sure. Their integer performance isn't all that impressive, given the blistering clock speeds. Unless you've hacked Apache to run on the floating point unit, an Alpha box running Linux might well be slower.
Oops, I forgot. Alpha is the One True Microprocessor. Never mind.
Not much science here?
If you hand in a paper with only one data point (instead of several) to your biology teacher, you'll probably get an F.
Besides, since when are press releases bound to serve the scientific method?
Record for the mark "Open Source":
Record for the trademark "Open Source"
Status of the mark "Open Source":
Thank you for your request. Here are the latest results.
If you require additional information about the application status, contact the Trademark Assistance Center (703) 308-9000 (M-F 8:30 a.m. to 5:00 p.m. EST). You could also contact SOPHIA S. KIM, Trademark Examining Attorney. Click here to find out the examiner's phone number.
Serial Number: 75439502
Registration Number: (NOT AVAILABLE)
Trademark (words only): OPEN SOURCE
Current Status: A non-final action has been mailed. This is a letter from the examining attorney requesting additional information and/or making an initial refusal. However, no final determination as to the registrability of the mark has been made.
Date of Status: SEP 17,1998
I doubt you'd recognize the "truth" if it bit you on the ass.
Everyone knows FreeBSD always has been and always will be architecture-bound (it only runs on Intel). Perhaps you were thinking of NetBSD, which isn't even close to an official distribution on the PowerPC architecture?
WebBench for *nix, NetBench for NT. WebBench doesn't run on NT, does it?
LinuxPPC doesn't run on the blue G3. Please do your homework before you spew.
Don't keep the cases on your computers long enough to worry about sexy eh....wow, you must be a "hacker" or something.
More than likely this benchmark is cooked.
Notice that they don't give full specs on the
machines they're comparing, only that they're
comparing a G3 (With who knows how much RAM, etc.) to a Poweredge and a Solaris box.. How do we
know that they don't have slower drives, slower
ethernet cards, etc., that are pushing down the performance specs?
On the bright side though, at least there is YET ANOTHER *NIX-based OS out there competing with M$.
I just like talking out of my ass about stuff I "think" they're saying.
Also, how fast do Alphas run WebObjects?
is FreeBSD. this is yet another example of why BSD will win i nthe end and crush the silly torvalds dog.
FreeBSD: breakfast of champions. Linux: tool of fools.
Actually the integer performance is about twice as fast. It is the floating piont that is about on par with the pII.
mmh... let's see...
NeXTSTEP, OpenStep, WebObjects, MAE, A/UX, AIX, Mac X...
No support for Unix software?... that is better than most software companies..
And I didnt even mention MkLinux...
There are already directories named i386 in many modules...
I guess they've been nice enough to give us access to what they've done for that mather...
Now just make it more compatible with different hardware and we might get the Whole Mac OS X on Intel hardware... would be nice....
You know: Unicode support, a nice gui... drag and drop... nice programming tools...
It is a big deal to me!!
Slashdot seems to just become a "hehehehe....let's kick Apple around some more....hehehehe.....yeah..." type of place.
No matter WHAT Apple does, people here, for the most part, are not going to like it.
If they suddenly make ALL they're software Open Source...people will complain.
If they suddenly make all they're hardware open, and post specs on all they're equipment...people will complain here.
If they start cloning, if they cancel cloning, if they use Unix for their base OS, if they come out with a new computer, if they do ANYTHING at all...people here will bitch and moan.
Let's face it, in the eyes of most of the people here, Apple is damned if they do, damned if they don't.
But hey, if it makes all the insecure people here feel better about their lives by cutting down something else...more power to ya. At least it keeps you off the streets and out of the post offices.
Now I'm not saying that a G3 400 couldn't beat a 400 mhz pc with the same ATI card, but I will say this "test" is about as foobar as it could be possibly be. Anyone who pays even a little attention to the world of computer gaming will see (at least) three huge errors in the "methodology". (I'll let others squabble about which error is the most egregious and glaring.) What is most outrageous about it isn't so much that Jobs got up before a world audience and told a whopper, it is more outrageous THAT THERE WASN'T A SINGLE INSTANCE OF CRITICISM ON THIS FRAUD FROM THE MAC PRESS. NOT A PEEP!! THEY JUST REPEATED THE WHOLE THING VERBATIM AND ADDED EXCLAMATION POINTS. It is only the existence and industry-dominance of massive fraud-artists such as XX that makes something like this unremarkable, I guess.
Stuff like this will not get better and the products will not get better until Apple's customer base becomes more computer-literate. It's only their ignorance that allows Apple to pull this kind of crap --and the Apple-oriented press to parrot it as truth. Apple customers pay a premium price for good hardware, they should expect to be treated better by the company they support! It seems that you will have to demand better, since Jobs and co. think it is easy enough to take advantage of you.
Yes, they're dieing off. And the dieing is in what now.....it's 15th year? Wow, sure is dieing slow!
Give me a break.
They also compared it to a system with Solaris. You can do one of two things.
1. Comlain that Apple isn't fair with the benchmarks.
2. Complain and run your own benchmarks on all the systems Apple did and any dream machine of your own to disprove them.
Guess which one people listen to?
Mac OS X Server requires 64MB of RAM, 1GB hard
drive and a CD-ROM drive.
This is conisderably greater than the published
min Spec of NT4.0 (Let alone Linux)
>
Well, I would enjoy seeing anyone do anything real
on an NT4 box that doesn't have at least 64mb of
ram and a 1gb drive. Same with linux, at least if
you aren't using the command line (GUI overhead).
80mb ram seems a good NT mininmum.
FreeBSD, NetBSD, whatever, Apple appropriated it.
Which is fine under its license and everything,
but I'm left a little queasy. The APIs are going to get messed around and the poor crapple users are going to be paying for every feature, for as long as their cherished corporate disaster can sucker investment capital.
Theres the issue of bugfixes. Are they going to happen? Its up to Apple, so maybe not for months. There is a lag factor introduced (and will they be patches, or upgrades?).
So Apple suceeded in porting some nice but rather staid and insular OS to their computers? Maybe they borrowed a good thing, but maybe they just built a more stable version of NT. And how exiting is that?
Viva GPL!
Damn good point.
Given Apple's tendency to 'twist' the numbers, I
wouldn't take those benchmarks too eriously,
although I find Mac OS Server quite exciting
>
Welcome to the real world, where everyone
twists the numbers and the marketing departments
rule. Even linux is getting a real marketing
department, slashdot notwithstandaing. Complaining
about this stuff is like complaining about the lack
of sunshine.
The original poster appears quite correct in the interpretation of Apple's marketing hyperbole. And you have erroneously extracted more information out of it than is really there.
To criticize his interpretation with such pejorative language, even if you felt yours was a "better" interpretation, is indicative of something worse, a lack of fairmindedness and a tendancy to post with ones head up their butt.
For what it's worth, its not "Please to learn to read", but instead "Please learn to read".
Cheers,
Noah Webster
I agree with the previous post. And history tells us how open-minded new religions can be... That was sarcasm btw. New religions are violent cruel, and bigotted. Let's not Linux become a new religion. Lets not become so steeped in Linux-think that we believe all other OS's are worthless. The key reason I use Linux in the first place is that I now have more of a choice; I want more Os's, AmigaOS, BeOs, etc -- not just Linux replacing Windows.
Alphas integer performance are a little more than half their fp performance. On ev56 533LX the spec marks for integer is like 16 and fp is like 28.
The ev6 has triple the performance at the same clock speed. You want to put an Apple against a
ev6? I'll bet my house on it.
Yeah, very eloquent, jackass.
Why not fuck yourself?
hey, yes you spreading invalid info.
MkLinux IS NOT DEAD, there might be "just one" *inside* Apple working on it, but there are several outside. and new kernels are released every few month. check out globegate.utm.edu for the latest kernels for MkLinux.
And IF Apple kills MkLinux, the source is still outside of Apple, and ppl will continue to do work on it.
however, there are no plans to make a "DR4" release, since the LinuxPPC and MkLinux distro only differs with a few RPMS (the kernels and some minor other stuff). there are plans to include both MkLinux kernals and LinuxPPC on the same CD (remember, they're binary compatible)
You crying little fucking babies.
Any time something comes out that claims to be better than Linux you guys immediately bash it, claiming it is nothing more than hype and media lies. Grow the fuck up, jackass. "Oh, waaaaahhhhh, someone's bashing Linux, I think I'm going to cry, waaaaahhhhhh." You guys can dish it out but you sure can't take it. I hope OS X *is* faster than Linux. Maybe a few of you trolls will finally shut the hell up.
obviously you havent studied NT administration.
All of the non hardware related things e.g. networking can be remotley administered. If you need to add a user to a domain then all you need is the user for domains software on any client and the admin passwd for the PDC
I happen to like NetWare!
;-)
Fuck Apple. Fuck Steve Jobs. Another proprietary
garbage vendor.
>
You lame-ass ignorant shit. Maybe if you actually
had a brain, you'd realize that the whole computer
industry is based on "proprietary garbage". That
monitor you're staring into isn't open source.
And if you had even a couple of live neurons,
you'd realize that the three companies that
brought computing to where it is today are
Apple, IBM, and Microsoft.
Too bad the medicos don't trawl slashdot...they'd
be able to cart you away to use you as a
relatively unused stash of body parts that
could be used by someone who actually has a clue.
Although I haven't seen the product myself, Apple's MOSX FAQ specifically states that administration can be done through remote telnet. All the usual config files are still available. In other words, the pretty pictures are optional.
(1) more hardware support than NT
(2) idiot proof installs like SuSe and Red Hat
(3) a real idiot proof install with the new Caldera
(4) hit the check mark next to Apache! Wow, it installs on most distros, boy that was hard
that you are actually an Apple user and advocate. Judging frm the stupid shit you say, you have got to be an MS plant sent to Slashdot to bring discredit and derision upon the heads of real Apple people. Or maybe you're just young and foolish, I dunno. Apple has an abysmal history of attempting to do the Unix thing, accompanied every step of the way by constant Unix trashmouthing and vituperation. I wish them all success with OSX, but if they want to attract sysadmins and devers to OSX they will be well advised to drop the blatant bullshit of comparisons like the one under discussion today! This is bad enough in the desktop world (where I guess people are supposed to be stupid and love being lied to); it just is very very bad form in the server world where need I remind you Apple is at best a rank amateur and johnny-come-really-damn-lately, not to say an abject loser. They only hurt themselves. And with advocates like you they don't need any enemies.
Apple was formed on April Fools Day 1976. I think that's when they incorporated. So that makes them almost 23 years old and definitely not dying.
BTW - their first product sold for a list price of $666.66
bwah ha ha ha!
>Well, I would enjoy seeing anyone do anything real
>on an NT4 box that doesn't have at least 64mb of
>ram and a 1gb drive. Same with linux, at least
>if you aren't using the command line
>(GUI overhead).
These days unluckily so.
Am I alone who thinks it's a pity?
Mac OS X Server can be remotely administered just like any other Unix. This is from the Mac OS Server FAQ:
I wouldn't be surprised if you could run VNC off of Mac OS X Server as well.
Some of these grade-school level comments defeat the reason I read /., which is to exchange opinions and information.
I know this will just attract flames, but personally I would prefer a more intelligent debate than to read fuck Apple, fuck Steve Jobs, fuck Apple.
There are some smart people here, unfortunately you have to wade through a lot of crap to get to the good stuff.
It might be helpful for the more hostile among us to review the "important stuff" below the post comment box.
These flame wars are just so uncool.
Just my opinion, so don't bother flaming.
This has me thinking that Mac-heavy businesses like ad agencies are going to want to continue to use Apple hardware, and will choose to hire someone to set up file servers and such, and want the features of OS X. Think of the consulting gigs, surrounded by graphic design hotties...
It's the convergence of *nix and hot women!!!
You are right.
Apple has lost *all* credibility by making such stupid claims. I don't even know why people bother listening to them any more.
I like how they don't mention that there's no better free server OS, and how they give lesser hardware to the Sun machine, and how the Mac X server's hardware rocks, while they don't even mention the other configs. I'd like to see these things side-by-side, with the same hardware (processor excluded, of course), and then see the numbers...
http://www.newsalert.com/bin/story?StoryId=CnU820b WbtefxmduX
Apparently Apple doesn't know how to effectively price hardware...
MacOS Rumors says it's solid. According to them, OS X has been pounded on and it stayed up (and didn't slow down); go there to read the full report.
read this for the actual story:
9 99/Feb/0110.html
http://www.nfr.net/nfr/mail-archive/nfr-users/1
There is a BSD API which lets you transfer large chunks of raw packets off the network, which Linux does not have. Unless you are doing network sniffing, WHICH IS WHAT NFR IS SOLELY ABOUT, this has no relevance to web serving or any other type of network performance.
In fact, the lack of "device driver hooks" as described in the above message is one more reason why Linux could be faster for general purpose networking.
MkLinux has been in development by Apple since 1995. Well, development financed by Apple anyway.
www.mklinux.apple.com
They should just go back to ProDos.
Why don't they put the G3 with OS X up against
Linux running on a dual (or quad depending on the
costs) pent pro box? Or Even an Alpha 600MHz...
after they try a few more cpu options that Linux
can run on.. THEN see how OS X compairs
actually, I bet OS X is full of security holes and root exploits. Can you say unaudited crusty old BSD code?
:)
The source release is just a way to get people to do their security audit for them. But that's actually a good thing
You people need to read the benchmark:
Test systems:
G3 PowerPC @ 450MHz, 1MB L2
256MB RAM
Dual 9GB Ultra2 SCSI HDs
Five 100MBit Ethernet ports (1 built-in, four more on a single PCI card)
for $5000
---
Competing systems had same RAM, same speed Ethernet, same type of disk, and same version of Apache.
Competition:
Dell PowerEdge 2300 running RedHat - List price $4200
Dell PowerEdge 2300 running NT - List price $500 (Steve joked about the $800 "NT tax")
Apple PowerMac, specs above
Sun UltraSparc 10S - $8500
Results from ZD WebBench 2.0:
Dell/NT - 300 hits/sec
Dell/RH - 500 hits/sec
Sun - 600 hits/sec
Apple - 740 hits/sec
Read it, before you knock it.
Mac OS X is a BSD and NeXTSTEP based OS with some "classic" Mac OS compatibility. It's a real, and now open source OS.
Might I remind you that Apple has been supporting MkLinux (www.mklinux.apple.com) development since 1995?
Apple is not a threat to Linux: they are a compliment to it.
Fortunately, there are a lot of worthwhile posts on Slashdot (and by worthwhile, I don't necessarily mean slavishly uncritical of the other OSes). The OS Fascists seem to be under half of all Slashdot posters (that's still a lot, though), so hopefully they're not representative of the Linux community in general.
Umm... let's see.
NTBDC with DHCP Services (something worthy.)
Pentium 200 MMX
32MB RAM
500 MB Fat-16 Partition
Don't need not CD-ROM Drive
If your big corporation needs well-supported desktops and actually prefers proprietary parts (what the R&D leaves you with), go for it. But who buys 25,000 Web servers?
The point is, Apple is making bang/buck noises about running Apache but is spending lots of their Intel budget on things that that don't help run Apache. I'm certain a $5,000 cluster of M-IIs (Redundant Array of Inexpensive Servers[TM][R][C]) would run circles around both of them.
X may be bloated, but Linux is not X. If you use a lightweight window manager it's not that bad at all.
;(
I WANT! I WANT! I WANT a lightweight.. not even window manager, but whole GUI!
Like say, QNX' Photon or so...
And handy development tools for it.
And applications even.
I can dream on, though
But the train is moving other way.
And linux is trying hard to be "Better Windows than MS Windows". Know where it's from?
You lame-ass ignorant shit. Maybe if you actually had a brain, you'd realize that the whole computer industry is based on "proprietary garrbage". That monitor you're staring into isn't open source.
It's lame, pig ignorant, greedy fucks like you who drive monopolies like MS and wannabe's like Apple. Your sorry ass attampt at a flame was duly ignored.
Proprietary software inhibits a customers right to share information with other people. It's one thing to do this with OS', it's another to play vendor lock-in with file formats and drivers. Apple is a leader in this file format lock-in game. I'll be impressed when Appple releases the specs for Quick Time, until then they are just another arrogant, filthy corporation.
If you want to lie down like a slave and accept Steve Job's cock in your ass, you can have it. Falme all you want, it doesn't change the fact that you are a pussy.
ME!
:P
Gimme 5K and I'll build a non-exportable munition.
It won't fun OS X though. Too bad
-kabloie
I happen to think Chicago is a very nice font.
http://advisor.gartner.com/n_inbox/hotcontent/hc_2 121999_3.html
I WANT! I WANT! I WANT a lightweight.. not even window manager, but whole GUI!
Like say, QNX' Photon or so..
The BeOS runs great with only 32MB of RAM.
uh-huh, and PIII makes "Internet work faster"
Makes one wonder why people still using x86s?
;-)
It's business and don't blame RMS for not liking it..
PPC's rock on RC5 key cracking.
Considering that they are comparing themselves to machines that cost about half as much, yes merely complaining is justified. This is like their Photoshop/G3 vs. PII benchmarks all over again.
You can buy a lot of Xeon, Alpha and Sparc for 5 grand.
You're blowing my high...
I was trying to be juvenile and rude!
Whatever, FINE, bring logic into it.
;-)
The numbers that Apple uses to back up their claims that MacOS X Server is the fastest webserver under $5000 come from one of Steve Jobs infamous 'bake-offs' at the MacOS X Server introduction yesterday. We all know that these numbers are subject to reality-distortion, and we realize that you can build a Linux server with similar performance to the Dell PowerEdge 2300 for far less than $5000, but Jobs is trying to compare it to something that's actually sold by a competitor.
So basically, without throwing previous bias into the mix, it just means Apple's got a reasonable server solution now. Whether it fits your needs, you think it'll sell/get used, or disagree with the minor details of the benchmark comparison, that's all you have to take away from it:
Macnn X Server Intro (benchmarks are about halfway down the page)
>You guys can dish it out but you sure can't take >it. I hope OS X *is* faster than Linux. Maybe a >few of you trolls will finally shut the hell up.
And in order to do that we'll have to see the numbers from a benchmarking between LinuxPPC
Kernel 2.2.0 vs Mac OS X done on the same system. And only then would you shut us up.
..until we tweaked our code, and came out with something faster. (darn competition it's just
bad for everyone isn't it =). OS X being faster than Linux won't make everyone jump the Linux boat, but it will make most of our programmers more determined.
Q: Is hurd far enough a long to concieve a
hurd OS X comparision?
Nice bit of detective work there, Wag the Dog
..ANJOU
Are you done yet? Apple has released a very powerful, very easy to configure, partially Open-Source, Unix-based server operating system. But that's not important to you; because they also claimed that one of their systems was faster than another system. Have you ever claimed that you were better than someone else at something? Hypocrite.
Write off Apple. Write off OS X. Write off any damn thing. You won't be missed.
do you use an os for its features or do you use it for the people who use it are *cool* ?
Yeah, well, after just having done the rounds with the CPU vendors (Sun, HP, IBM, Digital) and having them all show the same graphs with the names rearranged showing their own CPU as being twice as fast as the competitors... I just have a cynical bent when it comes to vendor driven benchmarks.
Choose your competition wisely and you can always claim some product in your product line beats a specific other product in someone elses product line at a specific pricing level on some form of benchmark.
"- e.g. there are distinct trademarks for "Apple" for computers and "Apple" for music. "
Actually Apple paid the Beatles big money to use the trademark "Apple". It was probably just being on the safe side, but they did do it. There was a clause that Apple could use the name as long as they stayed out of "music". With the advent of QuickTime they had to renegotiate.
This kind of looks like an obsolete comparison and the tests were not scalable. It would be nice to benchmark the servers and bring up more and more clients and increase the load like zdlabs did when comparing NT to linux. It was only after 14 clients when linux majorly began kicking butt at 250% faster then NT. Scalability is very important in the server market and mac osx might only be the fastest os of all with 10 clients but it might really fall after 15 and a large amount of clients better represents real-world computing.
So Apple's Mac OS X is not modern? Where else can you get Plug 'N Play, WebObjects, a *nix microkernal, and top shelf GUI? Not Linux, Not Solaris, Not NT, Not Anywhere.
Baloney. The PC's tested were in the same cost ballpark as the Mac. Same Ultra2 SCSI drives, same high speed network cards, etc.
The limitation on SMP is with the G3 CPU. The G4 is due out at mid-year; rumors have it that Apple is already showing 2 cpu G4 prototypes with Mac OS X Server.
You can get a 667MHz Alpha, fully loaded with top-of-the-notch components and loads of RAM for under $5k. That surely beats MacOS X.
-- John Goerzen
Lamers - Read the rest of the thread. This kind of knee jerk stuff makes me really wonder about the quality of slashdotter's.
Amen my brother! I can't wait till them ev6's ;)
come down in price. very soon
www.alphalinux.org
KDE isn't the only GUI for Linux!
To give you an example the current box I am running at home is a system w/asus mb, 64mb sdram, 233 pentium +mmx, 4gig western digital drive, 24x toshiba, sb 64awe and a diamond viper which cost me about $830 or so and it's been up over 190 days.
You may call this a cheap box ... but others would call it a bullet proof server that didn't cost me an arm and a leg. This system makes systems from dell and others such "first-tier" vendors look like cheap "Saturday night specials".
--sidster
Linux can be what you want it to be.. You want every program under the sun on your linux box fine. You want linux without a lot of extra crap fine. You can compile a big fat kernel to support a SH*Tload of options and hardware not a problem. Compiling up a streamlined kernel with only option you need, not a problem. Don't you understand that linux is so comfigurable you can make it what you want it to be. But no matter what comfiguration you are using I bet it is still gonna be faster than NT or mac OS X, on the same platform...
If apple ships boxes with more than one mouse button i'n gonna snap and kick first linux user in the nuts. And i'm serious too!
I didn't know there was a linux GUI? is that different than the FreeBSD GUI?? gee I thought XFree86 was the Xwindows GUI that most linux boxes used.... heh heh...
It rumored that Apple is working on just that, maybe even better.
cause LinuxPPC doesnt work on the same machine. NEXT!
Well, LinuxPPC works on some PPC, right? Or else we wouldn't be talking about it? How about firing up OSX on that same machine and running your benchmarks?
Didn't think so.
check your facts jack
webobjects be damned. use php3
http://www.php.net
here is the cost of a 600MHz Alpha running Red Hat Linux, this machine would blow the doors of the Mac G3.
Samsung PC164-LX ALPHA, 2MB Cache, ATX
Samsung Alpha 21164, 600MHz
256MB 32x72-PC100 168pin DIMM, 100MHz SDRAM, ECC, 10ns
Axxion DL-17 Mid-Tower, 6 Bay, ATX, 2 fans
Quantum Power Lab 400W ATX PC164, soft switch
1.44MB, 3.5in Mitsumi
Adaptec 3950U2 PCI, 2-Ch. U2W SCSI, 80MB/s
2 IBM UltraStar 9LZX-DRVS, 9.1GB, U2W LVD, 4MB, 5.6ms
Teac 32X SCSI, Caddyless
2 Kingston Etherx KNE100TX 10/100MBps (DEC 21140)
ATI 3D Charger 4MB SGRAM PCI
RightTouch 6600 101Key
Logitech Mouseman PS/2 (3-button)
Red Hat Commercial Linux 5.2 - Alpha
Cash Price: $ 4667.99 plus shipping
I forged myself." (W.Churchill, edited)
belbo (once again too lazy to log in)
Just picked up one from the grocery store shell. On the front page they confirmed the results of ZD Labs benchmarks.
Much of the core of Mac OS X is based on Nextstep/Openstep which if you haven't forgotten yet, ran on x86 and Sparc.
However, Apple has chosen not to release X Server on x86 for reasons only Apple knows.
Benny
I'm a unix user, but I admit...the Apple hardware is faster than intel hardware. OS X server is *probably* just as fast as any unix machine (minus overhead for the gui), and I guarantee it's faster than NT. However, Steve's quote: "Mac OS X server is a powerful web server..." is ludicrous...Mac OS X server is running on powerful hardware, which is running a powerful *3rd PARTY* web server. Furthermore, if you're comparing the performance of $5000 machines...you should be sure that all the machines are $5000. You don't need a $4000 copy of Back Office to run an Apache web server on NT.
I have to agree with this post. I have been reading Slashdot for about a year now and have never replied to any post on here because I don't want to have to put up with the overall attitude of users that would want to flame me for saying any littlest thing that would upset them. I for one would like to think of myself as someone who can listen to what others say in stride and with an open mind. I think the way people act and talk on here IS the overall attitude of the Linux community.
I use Mac OS, Win 95/98, WinNT, and Unix at work. I have been in the computing industry for more than a decade now and with all the people I have come in contact with, it is you, the Linux community, who have come off the worse overall to me. Now I know there are Linux gurus out there who are not this way, but overall you try to put yourselves overall everyone else and if they don't go with you on something then they are wrong and in doing so the enemy to you.
Now in no way am I saying I don't like Linux, I'm saying I don't like the overall attitude of the Linux community. If you guys do plan on staying in the game and increasing your marketshare, you really do need to change your attitude as you are turning people off from the platform.
Everything in this world is not about Linux, its about growth, knowledge, and helping one another to become more valuable assets to each other in the world. How far could we go if we would all work together, be smart, and realize the person next to you can be one of your greatest assets, friends, etc... instead of an enemy you don't know? People have finally starting doinf this over the last 100 years, and more so in the last 15-20 years. That is why we have accomplished so much more in that amount of time than all of the history before then. Lets try not to push that progress back with your comments, talk, and overall attitude.
I said my peace.BR.
Jason Carter
jcarter@block.com
I agree. Right now I have a dual boot MacOS/LinuxPPC G3. I'm planning on getting a cheapy intel box & installing FreeBSD on it. When that happens, I'm deleting the LinuxPPC partition on my Mac, mostly because too much of the Linux "community" really turns me off.
-moJ, too lazy to login.
1) Because MOX won't run on most machines.
2) I suspect MOX will be cheaper
3) MOX will be a 1.0, could have teething pains
4) Just to piss off Archie Comics.
1) Because MOX won't run on most machines.
2) I suspect MOX will be more expensive
3) MOX will be a 1.0, could have teething pains
4) Just to piss off Archie Comics.
Since when does a PII 450 cost $5000. You could get atleast a dual PII 450 for that cost, if not a dual Xeon. Also, did anyone notice how they didn't compare LinuxPPC to MacOS X? Seems to me like they're afraid of an equal playing field.
We get the best performance with NetBSD.
We use Secure Solaris and OpenBSD for fast and secure networking.
*BSD based systems have been proven over and over again to have the best performance. Still, a real man uses whatever system he likes.
Good point-- I think *real* power users use the OS suited to the task. I believe that the strengths of Unix are best realized in the server arena and soon will become a decent 'desktop' OS.
;-)
:-)
I use Mac OS for my 'desktop' OS because for me, it's more productive. Although my machine is dual boot MkLinux.
I hope computing doesn't go the way of shoes and cola, i.e. what is fashionable. It's already happening (iMac is an example, but I think it is still a very functional machine and more expandable than some people would like to admit).
I can't wait to get a OS X Server up and running and see what it can do.
nice link -- i like it better than the bs in the submission. i have always liked apple, and if they want to toot their horn a bit (even if they have a rep with, ahem, odd benchmarking) so be it.
for example, i wouldn't be suprised if the dell machine is a relatively slow server for the price, whether running nt or redhat. maybe they picked it on that basis.
at any rate, i'm so glad to see Mr. Jobs turning apple around. i only wish they didn't have to crawl in bed with billgatus to survive.
i love linux, and on a price comaparison, it's the winner. whatever happens, as a software engineer, i sure hope this helps to reduce microshaft's market share.
Internal Server Error
The server encountered an internal error or misconfiguration and was unable to complete your request.
Please contact the server administrator, malda@slashdot.org and inform them of the time the error occurred, and anything you might have
done that may have caused the error.
More information about this error may be available in the server error log.
I think they compared to MkLinux, which runs on top of Mach, which creates extra added layer. Otherwise Linux will be faster... unless, again Apple uses some propietary hardware tricks to accelerate OSXServer
I think the point of the test was to show what the G3 could do in *stock* form VS a PC from a well known manufacturer which *needed* an old crummy Voodo2 card just to come close to the 3D rendering ability of the Mac.
Joe Average consumer is not going to build his/her own custom box with a go fast video card. I do think Apple does get carried away with it's marketing but they arn't very far from the truth. A G3 *is* faster overall than a PII/PIII in benchmarks and many (but not all) realworld applications.
Given that we live in a democracy, and you have free will, you aren't obligated to buy any of Apple's wares. Isn't this country great?!? Meanwhile, I'm saving up for a G3 400.
It comes with Rage128 because of the simple fact that it is the onl video card that will work in the 66 MHz PCI slot the G3.
Name me another one.
OS X server is SLIGHTLY unproven. That BSD/NeXTSTEP core is in fact a lot better proven than the software that most of us are using today.
As far as them being a player in the rest of the non-Mac world, who cares? A market share of 10% in the PC universe is a lot of customers.
As far as SMTP, DNS, SMB, I think you are missing two points.
1) Some of these are already available free third party (like Samba).
2). How much is an unlimited user license for Win NT going to cost you??????
Maybe it's not 100% GPL, but it's a hell of a lot better than closed.
Just think - if they do find a security hole, you WON'T have to wait for an Apple fix.
Take that, NT.
Dont think so!
Apple has a lot of non-G3 hardware in the market that represents a real customer base for OS upgrades. To not make Mac OS 8.x, 9 and 10 would be to walk away from a big cash cow.
In addition Carbon developers want the biggest market for their apps.
All apple is aiming for is trying to get their hardware to infiltrate small and large businesses. Apple is trying to say comprable solutions from Dell, Apple, and Sun. Apple wouldn't care if LinuxPPC was on there for them they just sell hardware. OS X is abot 5-10% slower as of now. OS X client is going to be much faster because of an apple patented memory allocation trick that will speed up the system and NuKernal which was supposed to be revolutionary.Avie Tevanian works for them he created the mach kernal and knows how to speed it up and Mach is highly superior in design , it is like havinig Linus work at RedHat, their distro would be the best.
I agree about the PIII - it's nothing but hype and vapour. But so is Mac OS X. I can't believe Apple is stupid enough to make such unrealistic claims, even though time after time they've been proven to be full of shit.
What's that biting my ass?
Oh... it's Truth!
I think someone is calling you back in #amigarules
- don't kick a farmer while he is milking the cows
I hear they're basing their userland off OpenBSD, which I hear is pretty secure.
I'm proud of having worked for Apple and I hope this message doesn't sour my chances of going back, but I HAVE to respond to this: Apple went through STRENUOUS pains to make these benchmarks as honest as possible. The systems were configured as advertised. When one vendor's server (I won't name names, but let "Horrendous Pain" suffice) wouldn't give numbers in line with the known baseline, it was tossed out and replaced by machines that could cut it. Not to put too fine a point on it, but it's MY integrity you impugn, in part, because *I* helped set those tests up.
It's easy to sit back and accuse a company of lying and chicanery when you don't know what the hell you're talking about, but you're also accusing the individuals involved and I want to let you know that I don't appreciate it.
As far as I'm concerned, you can go buy yourself a Pentium box. Use the Apple equipment as a suppository, if there's any room left beside your head.
www.stepwise.com has a good articl for you.
Andrew Stone and Scott Anguish have the angle for you....
(-Matt McCabe)
Then they would have run it on the EXACT same hardware, and no complaints can be made about different configurations
But, maybe they did do just that and perhapse found that Linux was faster.
(Just some speculation)
Tee-hee tee-hee .. looks like Mr CrankyAC has Steve Jobs' cock in his ass!
Now that I must admit, is an EXCELLENT point.
Cheap box/irrelevant.
Most company's of size and school systems have to buy froma vendor of which they know the reputation and from which they can expect no problem getting machines in quantity and quantity support. This describes the suppliers like Dell, Compaq, IBM and Apple of the world, not Computer Success at the corner of Main and Nowhere.
Barring the few exceptions, this applies to all comapnies/schools larger than a few hundred (maybe dozen) seats.
Ironically the really small (hoem or SOHO) market goes for this same type of vendor, but for different reasons.
For both types of buyers, the $500 difference between a home-brewed and major-manufacturer system isn't worth the difference.
To be explicit, there is room in the above for lots of people to buy and have good experiences with home-brew systems. That doesn't change the relevance of the Apple v.s Dell vs. Joe Bob argument.
(Strangely, my buddy just called who got a new bare-bones/home-brew yesterday. He just found that the PS is dead. It happens.)
-Matt McCabe
Mac OS X would wet its self it it had to compete with this:
Microway's Alpha Powered PowerMAX Special featuring the "Screamer-LX" (for NT or Linux) with 4 MB SRAM Cache and 256 MB SDRAM.
533 MHz...$4,695
Since when does a PII 450 cost $5000. You could get atleast a dual PII 450 for that cost, if not a dual Xeon.
I'm tired of this bitching about "I can build a faster machine for half the price". That's the point, you can build. We don't want to build anything. The big selling point here is I can plonk down $5000, take it out of the box... ONE box, and be up and running in under half an hour, even if supposing I know little about UNIX or NT. Show me any Intel box for any price which can make the same claim. Hahh.
Also, did anyone notice how they didn't compare LinuxPPC to MacOS X? Seems to me like they're afraid of an equal playing field.
No, they're being consistent. There's no Macintosh on which both X Server and LinuxPPC are officially supported by Apple, so they couldn't well quote a benchmark where they do that... they'd have to be running one or the other on an unsupported machine, which certainly you'd be complaining about, too.
>My primary motivation is cost/benefit. When I introduced myself to linux there was NT and commercial Unices. All where way too expensive. I needed a solution I could afford. I was amazed that the twist of human fate had occured. Imagine a radical new development paradigm had occurred in my lifetime, and it was given away for free! Was I dreaming?!
----------
I only have to ask... as a small businessman, how much is your time worth?
The admin tools on top of MacOS X Server are, IMHO, second to none for ease of use in administering a Unix server. (I was a member of the beta testing team for MOSXS from last June until they shut down the test program in late Dec, and for good reason. I've extensive development and networking experience on several variants of Unix, WinNT, and MacOS.)
You can't get these for Linux. People have been griping about how Linux is free, MacOS X Server is so expensive (um, folks, $500 for an unlimited client server, the development tools, all the admin tools, etc, is dirt *cheap*), etc, etc, when the thing that everyone forgets is that you still need to put in the time.
Think of it this way - Apple is open sourcing the core OS (Darwin). The core OS is indeed free. You're paying the $499 for the admin tools, the developer tools, etc. (This is cheaper than a full Visual Studio package alone!)
How many hours have you spent getting your Linux box up and running the way you want? How much do you figure your time is worth? I suspect that if you add it up, you'll find it in excess of $500. Net loss, it seems to me.
I like Linux. I love the idea of open source.
I still have both my feet on the ground though, and can see a cost benefit when I see it, *beyond* the initial short term outlay... which in this case is peanuts anyway.
And those expensive hardware costs? Check again. $1600 will get you a kick-butt little machine for serving up a small business. You could even go down to an iMac at $1100 for an unsupported (but working) alternative. For a *small* business, that's just fine. How much did your Linux box cost? Support? Warrantee? Time you spent putting it together, keeping it running?
You have to think long term, not like an accountant who can't see past the next week's budget.
Err...
GNOME?
Afterstep?
Enlightenment?
FVWM?
Lesstif?
'kay, so these aren't all Desktop Environments. Point is, the world is bigger than KDE. KDE just happens to be the best one right now.
Please note that the flamers are not a good representation of the mentality of the Linux community as a whole...
I suspect they are, unfortunately. I have an older Mac with a G3 card and a Pentium II, both with Rhapsody DR2 and BeOS installed. I was considering trying out Linux on both platforms, but reading slashdot.org is enough to convince me it won't be worth it. If this is typical of the famed "Linux Community", will I have to stand hundreds of flames pouring in for every helpful comment, every time I need some "community support"? Bleargh. Grow up and I'll reconsider.
>Well, LinuxPPC works on some PPC, right? Or else
>we wouldn't be talking about it? How about firing
>up OSX on that same machine and running your
>benchmarks?
Apple can't do that. They don't support them both on any single machine. Why doesn't anybody try a 9500 or 9600 with a G3 card? That should be compatible with both X and LinuxPPC... I'll do it as soon as my X CD arrives.
I'd say you are tied with him for the eloquence award.
Heh. I was reading all this and it reminded me of a post I read a while back. Some poor soul mistakenly called this web site a "Linux site"... I wonder what threw him off...
A microkernel is a small kernel that provides very basic OS functions (multitasking, VM, message-passing) to servers which run in user mode. These servers do all the higher-level operating system functions, with the advantage that they are protected from each other and the microkernel is protected from them. Theoretically, you can have servers for different components of the OS, but most implementations to date are single servers (i.e. a single user-mode server running on a microkernel -- which almost defeats the purpose of a microkernel).
The Apple promotional information indicates Darwin/Mac OS X is based on Mach 2.5. Mach 2.5 was a monolithic (no user-mode servers) BSD derivative, not a microkernel. Mach 3.0 was the first one with the BSD layer moved from the kernel to a user-mode server.
If Darwin/Mac OS X does use a monolithic Mach 2.5/BSD kernel (which is what OSF/1 uses), it will not face the sort of performance problems faced by MkLinux and other microkernel operating systems.
That said, the Apple material also mentions a `Mach microkernel', so it may be something very different from Mach 2.5, although I can't imagine why Apple would mutate Mach 2.5 into a Mach-3-like microkernel for a production OS and not offer multiple OS servers. It would basically be a performance hit without adding anything.
Incidentally, the best-performing server OS for the x86 PC (FreeBSD) is also based on BSD and Mach (4.4BSD folded the Mach VM system back into the main BSD tree, but is still entirely monolithic).
Apple makes nice boxes. They may now have a nice OS. However they feel the need to lie (OK, spin, twist, whatever you want) through their publicity to make it sound like more then it is. If it's a server that is so damn good then why do they have to lie to make it look good? Why does apple never admit "we're slower for the price, and we crash a lot, but you love us anyway, and we love you[r money]" ???
If they were so stupid as to say that, and held a press conference with no bake-off, and published benchmarks that said they were slower than comparable competition's products, I as a stockholder would sue those incompetents IMMEDIATELY!
...but no, they did everything right.
No, Apple compared a 400MHz PowerPC G3 running Mac OS X to a 450MHz Pentium II running Linux (Red Hat, I think?).
A 450MHz Pentium II is actually a bit faster than a 400MHz PowerPC G3 (based on SPEC CPU performance), so the allegedly superior performance of Mac OS X, if true, is rather impressive.
I'd like to wait for proof before passing judgement, but the fact is optimised BSD systems (such as FreeBSD) have always tended to outperform Linux (and everything else) in the server market, so I find Apple's claims about its BSD OS credible.
Mac OS X Server is just shipping. It can't be verified if Apple's claims are "hype" or "vapour" as you put it.. people won't have it in their hot little hands for another week I believe.
Unless of course, you have a crystal ball which would be a neat little trick. Can I have one too?
Wait until people have practical experience with the OS for a period of time and we will see if Apple's claims stand.
Sheesh!
My remark about not trusting the benchmarks offerred by Apple or any company was made in passing --and nothing you said (because basically you said nothing) changes my scepticism. The thrust of my comment was that the current Mac is not a "No-headache" purchase. That stands. Maybe that's what really pisses you off? You can't deny the truth in my statement so you decided to grab it by a small corner and pretend you collapsed it in the center? Answer please do --and give us some more of your outraged indignation, Mr. Famous!
People, people people. Awrgight, so MSX beats the present distro of Linux. So what can be made to make Apache on Linux even faster? That is the only point worth discussing.
What changes has apple made to the kernel/Apache to optimize it? We should be discussing technical details rather than burying our heads in the sand or screaming like children because of some Marketing stats.
> here is the cost of a 600MHz Alpha running
> Red Hat Linux, this machine would blow the
> doors of the Mac G3.
I just spec'ed and purchased an Alpha for a Windows NT server (there just isn't much choice when it comes to accounting software). So I'm not particularly biased against Alpha when I say this. You're wrong.
For web/file serving, the way superior floating point performance of the 21164 doesn't come into play. The SPECint95 rating for a 600Mhz 21164 with 2mb L3 cache is 17.9 (from DCG Inc.'s web site). The 400Mhz G3 is estimated by IBM and Motorola at 19.1. Even with some play in the benchmarks, a 600Mhz 21164 does not "blow the doors off" the a 400Mhz G3. The only advantage you have in your configuration is the second SCSI channel for a slightly slower CPU. One could also buy a 400Mhz G3 setup from say, ClubMac for $2800. Add a _64_ bit PCI ATTO U2 dual channel SCSI controller, the same two IBM drives and another 128mb RAM for roughly $1900 + $500 for MacOS X Server. That's $5200 and we've got a spare 9gb 7200rpm U2 drive.
To blow away the 400Mhz G3 in integer you've got to move to a 667Mhz 21164 or a 500Mhz 21264. Then we're talking $$$.
I agree...!! Simple explanation, they cannot except the fact of diversity. Face it people.....!!
All of the marketing bulletpoints really don't matter. PC's (and Alphas) are considerably more tunable. So instead of merely deciding to include all of the 'bulletpoints' one can build a machine optimized for the task quite possibly leaving out some 'bulletpoints' in favor of spending that money on more relevant components.
Apple's latest Mac being able to outrun one particular example of a canned PC, amongst hundreds, really doesn't prove much.
Hardly. Just hand pick the hardware, like Apple can, and Linux is no more difficult to deal with than MacOS, NT or OS 10.
You have a point about benchmarks. The use of the Byte benchmark suite has been controversial for comparing the performance of the x86 and PPC processors.
;-)
However, I've seen benchmarks done in Photoshop where the G3 beats a 500mhz PIII. Then again, I've seen benchmarks done in MS Office where x86 wins but I'll never accuse Microsoft of optimizing their code for PPC.
Lest we also forget other companies (Intel, MS, etc) have marketing departments as well?
Pentium II is as much RISC as PPC. Alpha is RISC, more than PPC is and more than Pentium II is. RISC is a buzzword :)
You really have a fetish for false strawmen don't you?
IBM makes nice hardware, I agree...harddisk...and PowerPC? Tease with bogomips? Why not lmbench?
Then click on over to a vast array of web based PC and Alpha vendors that will gladly do it for you. Hell, these noises just might encourage someone like Cobalt to show up Apple.
I can just see it in Cobalt's and Corel's adds now...
Webservers that are even faster than OS 10 G3's... '-p
> You can get a 667MHz Alpha, fully loaded with
> top-of-the-notch components and loads of RAM
> for under $5k. That surely beats MacOS X.
First, what exactly are you comparing? A machine vs. an operating system? Huh? Assuming you mean that a 667Mhz 21164 running Linux will beat a 400Mhz G3 running MacOS X Server, you're probably right. However, the $$$ figure doesn't match up.
I've been pricing 21164's lately and just put in a purchase request for one. For example, DCG Inc. lists a 667Mhz 21164 with 4mb L3 cache with a Samsung UX motherboard (warning... stay away... the LX is more $$$), 64mb SDRAM, 53c875 SCSI controller, 10/100 ethernet, 4gb 7200rpm SCSI drive, CD-ROM, case, etc. for $4200. Move to an LX motherboard, add the RAM, upgrade the 10krpm 9gb SCSI drive, add another SCSI drive and you're near $6000. Conversely, you can bump up a 400Mhz G3 to a 466Mhz G3 ZIF zocket upgrade from PowerLogix. Plus the $5k G3 price is full retail. It's cheaper to add in your own components and just buy a bare box (300Mhz tower and pop in a 466Mhz upgrade).
Most people tend to have more time than they have money. That is why Apple is on the bottom and cheap mediocrity like Microsoft and McDonald's rode to the top.
You can't buy anything with a little spare time.
...not that Linux is the horror to deal with that you make it out to be anyways...
This isn't 1994 anymore and it's not Slackware that is the state of the art in 'ease of use' distributions. Apple's 'its easy so it will cost you less time' argument grows less relevant by the day.
BTW, one does not 'spend time keeping Unix running'. It tends to do that all by itself. Afterall, that is what it was designed for.
THAT is why linux server marketshare is growing so explosively.
For those that don't want to learn at all, there are even the cheap(er) OEM linux servers like the Netwinder and the Cobalt Cube.
LinuxPPC is a helluva lot faster than MkLinux.
PowerMac G3 boots NetBSD/macppc. There is also NetBSD/i386 for a cheapy intel box. And OpenBSD/i386 if you care for cvs access...
One thing I've noticed while reading these post day in and day out - Linux geeks are just as biased and fascist about thier beloved OS as Mac users are about thiers. Both groups will deny 'till they're blue in the face anything negative about thier favorite OS. You're all the same.
get GGI Berlin...
>hey took code from FreeBSD, NetBSD, and OpenBSD.
any other details?
claim superior performance by offering a comparison between a version of a product that has been tuned for performce and a version that has not.
thanks Apple -- once again you're living up to those standards that we've all come to expect from you.
Read the full text from the Apache Web site about Performance
here's a quick quote from the paper:
===================================
Apache Performance Notes
Author: Dean Gaudet Introduction
Apache is a general webserver, which is designed to be correct first, and fast second. Even so, it's performance is quite satisfactory. Most sites have less than 10Mbits of outgoing bandwidth, which Apache can fill using only a low end Pentium-based webserver. In practice sites with more bandwidth require more than one machine to fill the bandwidth due to other constraints (such as CGI or database transaction overhead). For these reasons the development focus has been mostly on correctness and configurability.
Unfortunately many folks overlook these facts and cite raw performance numbers as if they are some indication of the quality of a web server product. There is a bare minimum performance that is acceptable, beyond that extra speed only caters to a much smaller segment of the market. But in order to avoid this hurdle to the acceptance of Apache in some markets, effort was put into Apache 1.3 to bring performance up to a point where the difference with other high-end webservers is minimal.
Finally there are the folks who just plain want to see how fast something can go. The author falls into this category. The rest of this document is dedicated to these folks who want to squeeze every last bit of performance out of Apache's current model, and want to understand why it does some things which slow it down.
Note that this is tailored towards Apache 1.3 on Unix. Some of it applies to Apache on NT. Apache on NT has not been tuned for performance yet, in fact it probably performs very poorly because NT performance requires a different programming model.
all of userland?
I wonder if PowerPC is good value? Why IBM doesn't use them in Think Pads, workstations and $900 machines? Doesn't IBM manufacture and research?
There is no way to compare the "speed" of different OSes. Those that try are invariably lame or are marketing drones (or both).
Linux may be a challange to NT; seeing as how there are Enterprise level app's on the table (well on the horizon at least).
but as for OS X -- a CD-ROM full of OS software and a single CPU platform to run it on is hardly my idea of an Enterprise ready operating system (no SMP and they call it a server OS! what a joke.)
And as everyone knows, a web server needs a good gui. I mean, without a gui, what would it do with the memory the GUI would be using?
I suppose that they could use it to run more web server processes, and thus increasing the speed of the server.
And on another note, the tests were performed by different groups, so for all we know the linux box could have been running with its default config, while apple had tweaked apache as far as it could.
er, could it be that MS has never seen fit to sell windows for PPC and that IBM just doesn't want to/cannot do it for them and then have to beg ISV's to produce the binaries for the win32/PPC platform. In short, did you have reason for posting or do you just like hearing stupid questions get abrupt replies?
that's why I said it was actually a good thing
Yeah apple has a nice 'nix out with a nice GUI and decent server performance. For certain applications, it will be a good tool. 'nuff said.
/. Unfortunately, there seem to be a lot of adolescent types who are just fanatical. Linux fundamentalists! If a brand new OS dropped out of the sky, clearly superior to Linux in every way, these people probably wouldn't even consider trying it. Maybe we need parallel discussion groups, one for intellegent rational debate, another for people who just want to spout off things like fuck Steve Jobs or fuck Apple. To all of you hot heads out there just flaming away and spouting off "fucks", NOBODY IS IMPRESSED, nothing is gained by it, and it just doesn't speak well for the Linux community. I really believe that these flamers will continue to taint the image of Linux, and that is truely a shame because Linux is a nice OS.
Nobody ever said that OSX is supposed to be the end all of operating systems.
So what if you can build a $1000 486 domain server running Linux. Linux is a good tool too (I run it on my PII450, next to my Mac).
Can't we coexist with other OS's, realizing that they may all have their place. Do we have carpentry discussion forums where people rant and rave about how their hammer is better than so and so's saw - "lets see those saw people try to drive a nail into solid oak!".
I really like using Linux, and there are a lot a really smart people on
depends on what you call small. I wouldn't call Aberdeen small, but they'll sell you freaking 450 dual Xeon servers for what Dell wants for the PII Poweredge. Aberdeen is smaller than Dell, but if I were buying for a school I would trust an outfit their size. Maybe I'd get a second vendor involved, so there'd be some insurance and leverage for me, but I would avoid paying the name brand premium --definitely. That's all a side issue to the "benchmarking" thing here. As to that I'll just say: we'll see. OSX will prolly be good --real good. However, Apple has this teensy exaggeration problem as many companies do, so I'll wait to see some other test results before forming an opinion.
IF you specify the components, you can easily BEAT the realiability of Dell and the others. For instnace, AOpen parts are ISO 9002 certified, Dell ain't got that yet that I know of.
Well, being a PC and Apple tech for 4 years, I can show you where Apple hardware has never matched the speed of the IA32 hardware that it was intended to compete with. Yeah, a G3 cpu by itself is fast, but you stick it on the old gen mobo's that Apple is using, and you just pissed away it's speed advantage.
Oh yeah, and I bet they ran a default config of linux on that Dell, if you sat down and recompiled the kernel and everything else for Pent Pro/][ then you would be seeing a 20 to 40% boost in performance. Linux distro's ship compiled for 386's, meaning the code isn't intended for superscalar cpu's, and thus take no advantage of them.
My barebones 21164-533LX cost me about $1200 for case, cpu, mobo, and powersupply.
It's painfull, but you've got to show some repsect for NT, as bloated as it is, to be able to operate at full functionality on a 486sx-16 with 6MB of ram. (I've done it, it takes 8 to do the install, then you can drop it to 6 and run it, hope you've got a decent HD to swap to though!)
duh.
Buy a mac because it's 'headache free'?! Hah, mind coming over to IT Repair at UMaine sometime, we'll be glad to show you just how 'headache free' Mac's are. Hopefully they'll improve with the new OS, but as they are now... your comment makes me laugh.
I like the part in the Byte docs about not using the benchmark to compare different cpus, epecially differnt architectures, but just to use it to see the results of different settings on one system.
WinNT 2000, hell, there is basic plug and play in NT 4. (Not that plug and play is really usefull)
NT's based on a posix complint unix style core.
Would you say linux is faster than Win NT?
NT has been ported to PPC, there were only a few systems that could run it (None made by Apple could, it was relased for specific boxes only), but support for it, as well as the MIPS port, which used to rock, have been dropped, leaving IA32 and AXP the only active ports of NT.
The docs on how to optimize Apache state in the first sentence of the first paragraph that Apache is NOT the fastest httpd in terms of raw performance, and that the focus of the development team has been *correct* and *reliable* http serving rather than "how fast can we move these bits" and that Apache will NOT perform as well as some other servers on raw performance benchmarks.
That being said, in my experience, IIS on NT4 beat the fscking pants off Apache at transfering a 128-byte file over and over. By an order of 10. On identical hardware.
Does that mean IIS is the better server? Certianly not. Does it mean i didn't do enough to optimize Apache? Maybe i could have gotten it down to an order of 5 or maybe even 3. Does it mean that Apache wasn't written to transfer html docs that are smaller than the http header itself? Bingo.
I've helped design benchmarks. They're pure journalism, and their numbers carry little meaning. Just as a benchmark can be designed to give unrealistic numbers, an application can be taylored to get the best benchmark numbers possible. And these numbers will rarely, if ever, have any relationship with reality.
Hey Erik, So you have a SCSI card and you run an IDE drive...Would get better performance if you get a IDE CD -ROM and SCSI hard drive..Don't Ya..
Hey guys..Dell 2300 beat all the servers in that range in PCWEEK test..including Micron and Compaq..How do we know if Apple ran this test on the dell using Single ended drives..setting it to 10Mb transmission..Numbers look way suspicious
Hey Hey..6100 is the Pentium Pro system..going on like three years..6300 is the Xeon ..try it ..may be u will be singing a different tune...
Wrong..They have been designing there own boards ..extreamly fast..Poweedge 2300 beat all the others in PCweek testing..also DELL designed board...I am wondering if Apple used Single Ended SCSI in that system setting it to 10Mb transmission..The numbers look way way suspicious..even Solaris.numbers too
for a long time...Poweredge 6300 is a Dell system
very fast
But granted, 4 way pentium Pro systems (Three years ago) by all the first tier vendors had intel motherboards..I think compaq, IBM, HP and DELL..
But after the intial product launch..they go their own way
"First Tier" vendor means different things DIFFERENT THINGS..In hardware DELL, COMPAQ, IBM and HP are first tier..(ie Alpha) vendors for Intel. (They work with Intel to fix bugs on the processors..they really do that..trust me)
In OS, those 4 are first tier vendors for NT and Netware and VA is one of them for LINUX..so is RED HAT!!!!
: and nearly every mac user that I know who
: isn't a secretary or grade school teacher could hold their own on a
: unix workstation.
Um, obviosly you're dealing with a *completely* different mac user community than I've ever seen.
Apple, if we are to believe your fudge...list the configuration..everything in all the three systems.
Hard drives, Nics, SCSI cards, RAID level's..what test ran...how it was run..What libs were used.
Numbers look real suspicious..SPARC doing so low..c'mon..give me a break
Come on, be serious. My home machine has 32mb and runs Linux without a problem. And yes, I am running X, and doing a lot of development on that machine. My previous machine had 16mb RAM and a 250mb Linux partition, and even that was workable (yes, with X). You might want to use fvwm instead of Enlightenment/Gnome/KWM/KDE though.
I imagine it is to support those folk who don't own G3's, but who would like more stability/speed/etc from their PPC systems.
I also imagine that MacOS X clients are going to be somewhat more heavy duty than 8.6.... Have you noticed that many people don't install NT Workstation on their PC, but choose to use Win95/98?
Strikes me as a sensible strategy
Oh... you forgot to mention its wonderful Network Server line running a modified version of AIX.
:-))
Others will have pointed out tho, that most of these unix products did actually have fairly short shelf lives. The Network servers are a case in point. They are very nice hardware - rebadged + slightly modified Motorola servers. They have quite a lot of grunt for their time, had all those neat facilities that one would want from a server -
* optional twin power supplies,
* I think that the 700 series was dual CPU
* lots of bays for hot swappable drives
* good industrial design, meaning that most
parts of a system can be replaced very quickly
* even tho AIX is an abomination, it is stable
and secure. (But hey, you can boot LinuxPPC on
them today
They didn't last very long tho... which is a damn shame.
I think/hope that they understand that they really won't be given another chance if the fsck around with their server line. I also think/hope that they do not want to stay caught in the educational/consumer/desktop market.
Why don't you use OpenStep. ObjC is compiled but
is dynamic. It is fast and portable.
OpenStep API are great and there is the GNUSTEP
project, a free implementation of OpenStep.
You may be right for DR2 PPC (that's what I heard ... I don't think that an
too, and I also heard that DR1 PPC was
slower even).
But DR2 PC (aka NeXTSTEP 5.1) runs as fast as
NeXTSTEP 4.2 PC
hypothetical CR1 PC (NS 5.2) would run faster.
Why don't you try with NeXTSTEP 4.2 PC,
or Rhapsody DR2 PC (NS5.1).
NeXTSTEP/MacOSX is not SMP yet, so the test
you be made on mono proc hardware.
Hey Annonymous..You said AOPEN is ISO 9002 complient..and Dell is not..You might et sued for that..Dell is ISO complient on every part.
Acer reliability (which is what AOpen is) is worse than Dell. What bugs me is we have a bucnch of armchair experts who never ran a server with 200 to 300 clients hooked up and with 100 up time. Nt might not stay up everyday, but netware does.
Dell is first in reliability in all the fortune 500 companies..not compaq, not HP not even Intel OEM systems. BTW, what did apple have on the poweredge 2300, sigle ended SCSI running at 10M???
IA32 ?? what is that ? I suspect it is vapor ware
like the merced. HPPA are far better, and NeXTSTEP
runs on HPPA (i've tested it on a 712).
Let's make the test with an HPPA 8200, or
if your using vapor ware, HPPA 8500.
Wrong..They have been designing there own boards
for a long time...Poweredge 6300 is a Dell system
very fast
But granted, 4 way pentium Pro systems (Three years ago) by all the first tier vendors had intelmotherboards..I think compaq, IBM, HP and DELL..
But after the intial product launch..they go their own way
Wrong..They have been designing there own boards
for a long time...Poweredge 6300 is a Dell system
very fast
But granted, 4 way pentium Pro systems (Three years ago) by all the first tier vendors had intel motherboards..I think compaq, IBM, HP and DELL.. But after the intial product launch..they go their own way
Linux rules what? ... .... Arf ... :-) ... just because one said that OSX may be
This is such a meaningless statement
The goal a free world is not power.
But without knowing what you meant I can say
you are wrong (you stupid mindless idiot)
VINDO ROOLZ
I am so amaized to see free OS users making
war
faster on one point than your beloved OS.
Do you have any wisdom ?
NeXTSTEP runs on PC since 1993
OS X CR1 is NeXTSTEP 5.2
NeXTSTEP 4.2 also runs on sparc and hppa
OS X aka NeXTSTEP can be remotly admined because
of NetInfo. That was a key feature of NeXTSTEP.
under OS X, you can either remotly admin ...
1- either graphicaly with NetInfoManager
2- textually using telnet/rlogin
OS X is NeXTSTEP 5.2. NeXT STEP exists since ....
1988 and was a BSD4.3
So NeXT hence Apple has a lot of history of
running and supporting unix apps.
Those guys are NeXTSTEP users who were there
far before Linux existed.
NeXTSTEP 4.2 runs fine with a 486/16Mo, I've
developed on this for 3 years. You can even
have 8Mo but it begins to be hard for the
graphical server + emacs + gcc + gdb + tcsh + ProjectBuilder + InterfaceBuilder +
Sorry.
So does NeXTSTEP(== MacOS X). ... ...) :-(
Oddly the graphical server uses postscript.
We may think this would make things really worse
for speed (not for ease of dev) but no
it works great on a 486 with 32Mo, or even 16Mo
(prepare to swap if you are a developer
I've developed on this config for serveral years.
I've even tried with 486/4Mo but its unusable
Mac OS X is based on the Mach 2.5 kernel, so it shouldn't suffer from the microkernel performance hit which affects MkLinux and other systems implemented on top of Mach 3.0.
How can you say such a thing. I've used WebObjects ...).
and it's great. I'm sure you didn't even saw it
once. It's expensive but its great.
I don't know the product your talking about, and
it may surely be a great product too, but why
should WebObjects be screwed ?
Do you know OPENSTEP ? then you must know about
GNUSTEP, and know about GNU Web (objects
If gnu considers OPENSTEP and Web Objects, those
products mustn't stink that bad.
If you want to participate in the development and growth of an OS (or kernel in the Linux case), the user community seems to me to be very important.
I very much like the *BSD community, which seems to be very open, democratic and egalitarian, with no reliance on a `dictator' (however benevolent) to manage things, as is the case with Linux.
The Linux developers may be nice people as well, but what I have seen of the user community (plus the apparent reliance on a single `dictator' to ultimately commit everything) scares me off.
you are right, you can't compare the benchmarks. the Sun Ultra 10 has an IDE harddisk.
At least I can breath some fresh air.
... lots of apps.
How good to read such a news.
The only way I can explain this user's
attitude is they are
1 - teenagers (or almost)
2 - neither developers nor administrators
but as the Linux's reputation increase, median
users come, and some of them don't have much
philosophy.
I don't think this attitude is representative of
the core Linux attitude but as users are more
numerous than developers and admins, we may see
more and more Linux integrists.
We can't do anything about this, because every
community has its integrists, especially when
it gets bigger.
I use quite a lot of different OSes,
I don't use those OSes for the same purpose,
and I don't think they are exclusive.
NeXTSTEP (since 1993) to develop (because of
OpenStep)
Linux (with GNUSTEP) because there are so much
great apps on it.
Windows (9x) sometimes I play
And I'm about to install GNU HURD because it
sounds really great(its architecture).
I have a PC, a NeXT, a SUN, a Silicon, and
an Amiga.
variety is the spice of life - Dai ju yume
A recent comparison of thin web server platforms published by the Gartner Group showed significantly better performance on FreeBSD 2.2.7, as compared to Linux 2.0.34. Admittedly, both versions are somewhat old, but this performance difference seems to be the same story there has been for years, and I imagine current versions of both Linux and FreeBSD offer improvements.
2 121999_3.html
http://advisor.gartner.com/n_inbox/hotcontent/hc_
More broadly, I have also been very impressed with the smoothness of the FreeBSD VM system, especially under a heavy load. Linux feels noticably less responsive than FreeBSD, though not as bad as NetBSD/OpenBSD or NT. I haven't, however, used NetBSD (or OpenBSD?) since the switch to UVM, which was a very substantial change, so my experience with it may be out of date. Of course, this is just my impression, but that's what drives my decision as to which OS to use at the primary one (currently that is FreeBSD).
Just bought a 21164a (not the cheaper 21164PC!) 500mhz on a AlphaPC 164 mobo w/ 1MB L3 cache NEW for $450. Add the ATX case and power supply and your up to about $600 for a barebones. Not bad. Add your video, RAM and SCSI components and you are up to about $1500. I already had 8 matching SIMMs totaling 256MB (gives me a 256-bit memory bus :) and a lot of other high-end gear so all I had to do was dump my dual P6 mobo (sold it for $300) and move my components over. Best $150 upgrade I ever did!
Alpha is very good at both integer and floating point; the high clock speeds and relatively low performance per cycle reflect design decisions.
PA-RISC, at the other end of the performance-per-cycle spectrum, is almost as fast as Alpha, but only runs HP-UX (for now). Its relatively low clock speeds also reflect design decisions.
SPARC is still a contender, but PowerPC and x86 lag severely behind Alpha and PA-RISC.
My opinion: unless the Alpha port of Linux is utter crap, current Alpha systems running it will outperform anything based on PowerPC.
> The combination of BSD net code and mach has so
> far shown no evidence of any credible
> performance at all.
OSF/1 does rather well on the Alpha platform. Like Mac OS X, it is based on a a monolithic Mach 2.5 kernel and 4BSD.
You don't get it. The point is not weither OS X ....
is faster or not than Linux/*BSD.The key technology of MacOS X (aka NeXTSTEP 5) is
OPENSTEP, the portable developement environment, not the OS. MacOS X is attractive because of it.
Linux/*BSD won't be as attractive unless integrated dev env exists (GNUSTEP is on the way
and is GPL - happy ?)
NeXTSTEP lives since 1988. It may not be the most
powerfull OS, but it has been widly used for
critical mission apps, hence it is very stable
(like linux and *BSD).
I don't understand how you dare comparing NT and
NeXTSTEP. This only shows you've never heard
about NeXT's history , who used it(Fortune 500),
and what for (critical mission applications).
NeXTSTEP is great, trust me. And we will make
even better in GPL (GNUSTEP). But we must
construct, not destruct and criticize especially
with out knowing what things worth.
You like GPL? write GPL apps and shut up
I use Rhapsody DR2 (aka NeXTSTEP 5.1)
and I have SMTP, DNS and Samba.
Have you ever installed NeXTSTEP?
NeXTSTEP is far more proven than linux or *BSD
Get informed, this is history. NeXTSTEP is
a critical mission OS used by the Fortune500
which is not the case with Linux or *BSD
NeXTSTEP 4.2 is great so is 5.2 (MacOSX)
> Everyone knows FreeBSD always has been and
> always will be architecture-bound (it only runs
> on Intel).
FreeBSD is a flavour of BSD, which is not and has never been tied to the x86. NetBSD, based on the same BSD source code, has been ported to a huge number of platforms. This alone (and the history of BSD in the CSRG at Berkeley) shows BSD is not in any way bound the the x86 architecture. Linux, on the other hand, was originally designed as a clone of the BSD kernel for the x86 PC, and, from an architectural standpoint, is much more heavily tied to the x86 than FreeBSD. This is evident in, among other things, the Linux VM system.
FreeBSD has historically been x86-only because of the FreeBSD project's primary goal: to create the stablest, best-performing operating system for commodity hardware (if you ask me, it's done that). This has traditionally meant x86, but FreeBSD has recently been ported to Alpha, and a PowerPC port has been discussed. That may happen, but FreeBSD is not likely to be ported to some of the more obscure hardware that runs NetBSD and Linux.
The NetBSD project focusses primarily on portability, hence its flavour of BSD has been very widely ported, but hasn't incorporated improvements in FreeBSD which don't translate well to all of its supported architectures. The difference is one of goals, not of architecture (in fact, the Alpha port of FreeBSD is based on NetBSD/Alpha).
I can't say whether the creation of separate branches of BSD to pursue various goals (performance, portability, security) is a good idea or not, it's just different from Linux model, where everything is merged into a single tree, and certain goals have to give way to others on an individual basis.
The only possible future for the consumer PPC line including the 603 - 604- 750 and so on, is with Apple, and maybe Linux I hope. Though IBM-Linux-on-PPC for consumers would likewise face a forbiddingly steep hill to climb in the consumer space.
> NT's based on a posix complint unix style core.
NT does include a POSIX subsystem, but it runs on top of the executive and the Win32 subsystem, not at the core. Moreover, it was designed to be useless for anything other than meeting POSIX.1 compliance (which is the reason it's there).
The core of NT is a modified microkernel, which is similar in some respects to the Mach microkernel, but neither is inherently UNIX-like. Mach is, however, an offshoot of 4.3BSD, and so is used primarily in UNIX-like operating systems. NT's microkernel could theoretically be used in a similar fashion, but its only real subsystem, Win32 (portions of which now run in kernel mode), in not at all like UNIX.
say a complete sentence, will you?
faster in WHAT???
Now that you've set up my box, are you going to give me support for when it goes down? or if a part goes bad? hmmmmm that $800 just doesn't sound as cheap anymore...
Refering back to those first-tier companies, this is why people don't get fired for buying Microsoft, Compaq, Dell or any of these name-brands. Even if they are a bit more expensive, the hassle and the service is worth it to any small or large business.
ps. Do you mind if I call you every hour on the hour because my server has gone bezerk? 2 am sound ok?
I wonder sometimes...
shad
hmmm did you say on most??? If I was "BOSS", I'd be weary of that most...People get fired for sentances that use most.
"It works MOST of the time."
"It installs on MOST systems."
Again remember who is going to use the web servers. Probably mostly small to mid-sized companies. Why should my web flower delivery business take a chance on a server that I may not get full support for and that may not work on my machine. The problem with linux is that the support is not as advertised as others. If Linux or BeOS or any non-MS operating system wants to go mainstrem, you must have great support and none of this "MOST" stuff. hmmm what about my web FedEx type business, or Distribution. If my server goes down, for even an hour, I may lose my shirt that day. Have a few days like that and I may have to ask Red Hat, or whom ever I bought my copy from for a shirt. Maybe some pants too.
I'm still wondering
shad
heh, too funny. like that cat the other day, telling us how PII is now a risc chip because it emulates risc.....
Sorry, I misread it. I understood IA64 ...
Nevertheless this is not a stupid statement.
What is really stupid is the apparent linux
community reaction face to "Apple says OS X
runs faster than linux on a specific point"
Nobody here seem to have used NeXTSTEP
or Rhapsody. All this is nothing but speculation
about who's got the biggest dick. I don't
think my statement is stupier than the average
statements in this thread.
Lastly, I don't think MacOS X would be really
faster than Linux. Can't do anything against
free-dev except open sourcing.
MacOs X must first be stable and easily usable,
then be fast (may be not as fast as FreeBSD, but
faster than NT is sufficient)
Sorry again for misunderstanding your statement
MacOS X is not at the present time SMP
But Mach is, so this should not be so
problematic to add SMP to OS X.
I've heard rumors that said Apple was
testing MacOSX SMP on SPARC SMP hardware
(remember NeXTSTEP runs on PC, HP, SUN)
I've using NeXTSTEP for 5 or 6 years, I think
it has the pontential to chalenge NT.
The funnier is when NeXTSTEP 1.0 came out
(Mach+BSD4.3+Pre-OpenSTEP) windows3 didn't even
exits (1988)
I use NT, Linux and FreeBSD. My experience has been that the problem you've mentioned (a few user processes eating all resources) is very severe in NT, less so in Linux (very mild) and least of all in FreeBSD (virtually nonexistent).
So did I. In fact, I work as a developer so I can write code 50+ hours/week instead of having to do something boring. What the suits decide to buy does matter, because we have to put up with it and make it work.
Oh, gimme a break. Linux people say Linux is faster than NT in *everything*. Fucking hypocrites.
Pricing is pretty flakey. If you're a large school with an experienced network administrator, you can get a Poweredge 2300 for $3500, with NT. That's what I'm using because our network admin buys lots and lots of computers, so he got us a deal.
Fact is, while you guys might be able to shave off five hundred bucks or even fifteen hundred, the average SOHO or teacher can't pull those kinds of deals because they lack connections and expertise. For them, this is a damn good deal.
The Apple OS X stuff looks VERY hot. I would love to hack linux all day, however my burn rate is amazing and I have to get to get fuel ($$$) to keep that flame happy! The Mac gui stuff has always been light years out there. I work with an NT and G3 side by side, and for sure the Mac screens just LOOK better. May save me a hell of a lot of configurations hours.
Okay, I'm an AC, never posted before and am throughly caught in the reality distortion field and loving every second of it. Now that that's off my chest, I just want to make one point about the fact that macs don't ship with multibutton mice. There's a good reason for it. Macs don't need multibutton mice. In fact, studies show that multibutton mice are actually less efficient than single button mice. If I can find them again, I'll post links. In the meanwhile, while that second button on PC mice is being used for pop-up menus. My mac brings up pop-up menus using a timed delay mechanism. I just hold down the mouse button and up it comes. The same studies showed that this is the best way to implement pop-up menus.
Personally, I prefer a three button mouse myself, but I would never let my mom use a multibutton mouse. She's still learning to use the computer and more options will just confuse her. In the end, macs are not targetted at slashdot readers. In my case, I expect to install LinuxPPC or Yellow Dog as soon as one runs on Yosemitie, whichever is finished first. I'm really sick though of the one-button mouse complaint. It's so frustrating, especially when one considers that, unlike Windows, a lot of thought went into the design of the mac user experience to make it easy and consistent.
>Right now FreeBSD and Linux are basically neck
>and neck on network benches
Really? How do you explain this then?
http://www.anzen.com/products/nfr/testing/
*Linux is not ready yet...
Besides, what's worse- a small "community" (for some reason that word has really begun to grate on me in the last few months...) a la *BSD, BeOS, etc., or a community which has mutated to the point of being detrimental to the platform, as is the case with Linux? Sometimes I wonder if the comments people make on Slashdot have turned more people away from Linux than Slashdot itself has turned people on to Linux. That would imply that Slashdot has done more harm than good to Linux.
yeah, right...and like MacOS 8.5 is stable heh, if it IS faster well that give the open source community (i mean the real open source not the pseudo-semi-opened-liscence) something to do over the weekend right? :-)
---
If you can pick the terms of the benchmark, you can make anything outperform anything else. According to the article:
Mac OS X Server, when coupled with a new Macintosh Server G3, is the fastest platform for running Apache for under U.S. $5,000 -- outperforming Linux, Solaris and Windows NT Server...Based on WebBench benchmark testing performed by ZD Labs on a Dell PowerEdge 2300 Pentium II 450 MHz running Red Hat Linux, and a Sun Microsystems Enterprise Ultra 10S Server 333 MHz running Solaris; and NetBench benchmark testing performed by Apple on a Dell PowerEdge 2300 Pentium II 450 MHz running Windows NT Server, and a 400 MHz Macintosh Server G3 running Mac OS X Server.
Correct me if I'm wrong, but it looks like they are comparing the WebBench benchmark on RedHat on a Pentium II to the NetBench becnchmark on MacOS X Server on a G3. Not only aren't they running on the same processor, but they aren't even the same benchmark!!!
MacOS X may or may not be faster than Linux in some sense, but this test proves nothing.
----
Open mind, insert foot.
OS X doesn't run FreeBSD, it runs hacked-up version of BSD/OS Lite from BSDI, a commercial Unix vendor.
--
The world is neither black nor white nor good nor evil, only many shades of CowboyNeal.
But Linux was standing there in a nice Red :)
--
People using html in email should be shot.
Being the happy owner of 604e/200, IBM 2.1g HDs (fast/wide but on a narrow bus with adapters) and 64M ram, I have to say this: wheeeeeee :) ;) [1]
:)
Even previous gen stuff is a kick done this way- and it came in at under $1000 not counting monitor, and kicks PII/300s in bogomips
[1] yes, I know bogomips are not an accurate benchmark. Pentium advocates have always been happy to throw around benchmarks like Office, why shouldn't I tease them with bogomips? It's a linux benchmark, too
It's basically BSD. If you don't like that, run a Linux on it. QED. If the linux isn't out for the next-gen PPC chips yet, wait two weeks ;)
...because of this, MacOS recognizes and coexists with Unix partitions- including Linux. Forget the tendency of Windows boxes to consider Unix partitions raw and format them- _all_ the Apple stuff that linux will run on, uses MacOSes which are aware of what Unix partitions are, and will leave the Unix partitions alone and not mess with them. That's a big installed base of software which is unix-coexistence-friendly... no booby traps there. It thinks the linux partitions are A/UX.
Running GNOME or KDE is not to be done w/o gobs of RAM, no.
On the other hand, I've used WindowMaker for a long time on a machine w/ 32MB RAM (and lots of background processes).
Before it had 32MB RAM, the machine had 16MB and I used the Lesstif WM. I had no speed problems there either. Then again, there was less background load too...
Posted by Geocrawler:
What did you think of this line at the bottom of the press release?
>>Open Source is a trademark of Apple Computer, Inc
That's pretty bizarre, isn't it?
Posted by bafoon:
Quick and Dirty? Boy...
The future is about cross platform portability, hardware agnostic tools.
Have you considered Java? You think on that.
Posted by Robert Sixkiller:
Ok first of all this is about OS X Server, not consumer. Mac OS X will be out by the end of the year. So yeah, installing OS X Server on a box, running Apache then ignoring it wouldn't even be such a bad idea.
As for requirements, Apple says you need a G3 with 64 Meg RAM etcetera, but this really isn't the case. This is the minimum "Supported" config.
Mac OS X Server actually runs on any real PCI Mac, which is: 7300/7500/7600/8500/8600/9500/9600 and a bunch of clones.
I'm running it on a 9500/233 160/2GB myself (And it ran when I had 64Mb as well), and I think it's a kickass OS. It will never outperform Linux though. What will ?
Let's just watch and see (and try!) before we "guess Apple's OS sucks" (Couldn't find an appropriate American expression for it)
Posted by bafoon:
What if you didn't need yer virtual machine? Makes it look a bit different now, doesn't it?
OK, OK, this post is funny. It does raise some serious points, though.
:(
Apple makes nice boxes. They may now have a nice OS. However they feel the need to lie (OK, spin, twist, whatever you want) through their publicity to make it sound like more then it is. If it's a server that is so damn good then why do they have to lie to make it look good? Why does apple never admit "we're slower for the price, and we crash a lot, but you love us anyway, and we love you[r money]" ???
I suspect a lot of us have been disgusted with this kind of bullshit benchmarking in the past, and don't like seeing even a somewhat nice vendor lying to people like this. It also raises big customer problems. Am I going to have to deal with clients saying "we should use macosX because apple says it's faster." Well, now I have to dash their hopes and explain that apple published bogus publicity, not benchmarks, and then fight their resistance to the fact that that cute apple would ever lie to them. *sigh*.
I hated when apple used to do this, and hoped they'd stop this bullshit now that they've had a makeover. I gues not
-Peter
== Just my opinion(s)
"Based on WebBench benchmark testing performed by ZD Labs...."
Ok, once I got to that, I knew the rest was bullshit. I don't think ZDNet has ever had a fair bench in their existence.
-Erik-
To give you an example the current box I am running at home is a system w/asus mb, 64mb sdram, 233 pentium +mmx, 4gig western digital drive, 24x toshiba, sb 64awe and a diamond viper which cost me about $830 or so and it's been up over 190 days.
.26 relisys monitor, logi mouseman+, keyboard, awe32, and ASUS V3400TNT (Nvidia Riva TNT) for about $1100.
:)
Ditto, I go through a wholesaler and I got a PII-350, 128mb, 8gig IDE WD, Adaptech 2940AU SCSI card, SCSI Zip, SCSI 32x Teac CD, 17"
I had to return the ram because it was DOA, but I got a replacement the next day and I was up and running. That's what I call support, not "please hold, all of our lines are busy".
And I never paid a bloody windows tax either.
-Erik-
and then maybe I'll pay attention.
Until then, it's just more Apple hype. And Apple is the true great as far as corporate hype is concerned. They'll die off, though, just like all the rest of the proprietary low-end competitors to Microsoft.
Hey, that reminds me -- how about an Apple SMP box? Oh wait, that's not fair. Only LinuxPPC runs on those.
(if there was an HTML tag for "enormous middle finger wagging in the face of Apple" I'd put that here)
Remember that what's inside of you doesn't matter because nobody can see it.
Linux is just the next hot trend for the technology groupies to infest.
Took about 30 seconds to find one. I wonder how it would do against a Microway PowerMax: (ad copy from Microway's site):
- Microway Screamer-LX Motherboard (21164A CPU)
- 4 PCI/2 ISA, 2 Serial/1Parallel Port
- 4 MB 9ns SRAM Cache
- Full-Size Tower (10 bays) with DIMM Cooling Unit & PS/2 400 Watt Power Supply
- 256 MB SDRAM (2 each 16x72-10ns DIMMs expandable to 1 GB)
- ITI3140U Ultra Wide SCSI-3 Controller
- 10/100Mbps Ethernet RJ45
- 9.1 GB UW SCSI Hard Drive 7,200 RPM (Seagate Barracuda)
- 8MB PCI Video Card
- 32X Toshiba SCSI CD-ROM Drive
- 3.5" Floppy, DEC PS/2-style Keyboard, Logitech 3-Button Mouse
- Either NT Workstation (CD) v4.0 or Red Hat LINUX (CD) v5.2
- Digital's FX!32 Software Emulator
System Prices:$4,695 with 533 MHz Alpha Processor
$5,295 with 600 MHz Alpha Processor
$5,795 with 667 MHz Alpha Processor
Let's see, the 533 MHz option at $4695 meets the $5000 limit nicely.
From Apple's site, The G3 was about 20% faster than Linux on a PII 450. I suspect this machine running Linux would blow it away.
RISC, fast SCSI drives and lotsa RAM running UNIX is the stuff dreams are made of. :)
cause LinuxPPC doesnt work on the same machine. NEXT!
It's far easier to forgive your enemy after you get even with him.
It's far easier to forgive your enemy after you get even with him.
Ad hominem. Last resort of the weak minded.
So its not OK to point out this was a bogus marketing test? It was. Its not OK to point that this is Junk Science? It is. The Hardware is not equivalent, and the test itself is a bit unrealistic. 32 clients? What did they do regress the test until they found a client connection rate that produced the results they liked? Where is all the data to back up their claims? Do their conclusions follow from all the data, or did they hunt for some data that validated their conclusion and discarded any that didn't? I'd love to see the real numbers, then I could make an informed decision based on this - but this press release is nothing to make any sort of informed decision on - regardless of who wrote it.
This is not science, this is junk science. You have to publish your methodology, your numbers, be rigorous in your methods (double blind the test) and everything has to be equal. Linux runs on PPCs, so why not run the test on the same hardware? Some people probably had knee jerk reactions to this test, but you would be the first to bash a test when someone said "A 667 Mhz Alpha running Linux out performed a PII450 running Windows NT!" They're not valid comparisions, the hardware is not the same. Maybe the PII is a dog compared to the G3. Apple certainly claims this. So if we take Apple at their own word, the test is invalid. The G3 is always going to win (or so Apple claims).
Why would this be whining to point out their junk science? I'll be the first to point out bad reasoning and bogus results anywhere I see them - including within the Linux community. I do this as part of my research all the time. I'm a pretty big skeptic of my own work. It keeps us honest, because we want our products/research to be the best and human beings sometimes look past results that don't conform to what we already believe. Its a classic problem with all sciences. Thats why we have to use riguous controls and methods to prevent this from happening.
So don't you know how these things are done in a commercial software and hardware company? These tests are always carefully done, and redone internally until the company gets results they like. And if they get results they don't like, they never publish those results and they don't ask third parties to do those same "tests".
After the company has come up with a testing criteria that gives them the results they want, they pay a third party to perform the exact same test and even then, the company only publishes the results when they are favorable. The third party testing company does not have the rights to publish the results - and this is a condition of getting paid! This is called junk science. Look hard enough and you can find some data to support your conclusions, and then you just discard all the data that runs counter to your pet hypothesis. Thats called junk science.
I'm sure OS X is a fast OS, its a UNIX variant - so what do you expect? Its a real OS, like Linux, Solaris, BSD, DU, and others. It better be fast. The G3 is supposed to be a fast as hell chip, and apple claims that its faster than the PII450 - os what do you expect? The G3 should out perform the PII450 - by Apples own admission! So this test is bogus on that count alone, the equipment (Apple said it first!) is not equivalent, and the test criteria are questionable at best (32 clients? I smell something fishy here).
--
Python
Python
Perhaps if you needed to pick your nose during the install...
And I prefer Mountain Dew to set up my Mac server, thankyew very much.
SoupIsGood Food
More importantly, why didn't they run LinuxPPC on the same hardware? The price would have effectively been cheaper!
sigs are a waste of space
Before we see that someone has gone and ported Darwin over to Intel hardware? All the pieces (I think) are already out there.
That should make for some interesting benchmarks, DarwinPC vs. MkLinux!
Y'know, when flames are on a purely technical level, I can tolerate them, but this is just plain silly. How old are you, twelve?
On the bright side: you're so far inside your bubble that you're not going to make one lick of a difference in this world compared to someone who's clued into reality, not their own distorted utopia.
Have a nice day.
-Stu
As you say, press-release "science" is "junk science". While there is some schred of truth to them, they're obviously not objective.
....Which makes me wonder what all the insane huff here is about. So Apple posted a benchmark, big deal. It's a "good sign" for Apple, but of course not conclusive, nor should it ment to be taken as conclusive. The flamers here sure seem intent on proving the obvious.
Almost all statistics that don't come from a neutral body are pretty much junk. Note that I include the statistics from Gartner & GIGA and Dataguess here too, as they're far from neutral in this industry.
I figured that most people knew that benchmarks like this are flawed, but fun to speculate on
-Stu
if you're a student and join apple dev connection, you can get it for $99.
That's fscking cheap.
-Stu
I was about 14 when Windows 3.x came out, and I can assure you, most people I knew were *NOT* saying how neat it was, they were busy deleting it off their drives....
BBS SysOp's especially in that era will understand. DesQView was usable for multi-node BBS', Windows was not. OS/2 was better still, but then the Internet caused many people to just forget about BBS' altogether (and OS/2...)
-Stu
oh really? most of the mac users i know are arrogant tossers who somehow think that using a mac makes them "creative" while we techies are just boring geeks to them.
oracle 8 (especially 8i) *is* a big deal.
macos x is too little, too late.
oooh, i high school kiddie! and he has an elite warez d00d name! and look, some k-rad buddies!
loser.
The problem is, Apple and its user base has no history AT ALL of running and supporting *nix type applications.
Sure, a bunch of Mac fans are going to get really into it, but I can't see old-style *nix people getting very excited.
Oh, and:
" Mac OS X Server requires 64MB of RAM, 1GB hard drive and a CD-ROM drive. "
This is conisderably greater than the published min Spec of NT4.0 (Let alone Linux)
I've played with OS X on an G3. It's not exciting.
-----
It might very well be faster. I haven't seen what setup they used to test, though, so I assume that it's bogus marketing drivel. For US$5K I could put together a pretty damn nasty machine. Regardless, w/o the details their words mean exactly squat. Also, even on the same machine, how would LinuxPPC compare?
--
"First they ignore you.
Then they laugh at you.
Then they fight you.
Well, no.
ZD Labs ran WebBench on the Dell Red Hat system and on the Ultra 10 Solaris system.
Apple ran NetBench on the Dell NT system and on the Mac OS X system.
Perhaps you might want to consider an English class or two. Perhaps you might want to consider reading more carefully before making an ass of yourself. Perhaps not.
At the bottom of their press release, we find again:
Open Source is a trademark of Apple Computer, Inc.
They appear to have added the Open Source thing to their templates... What can we do about it? Do they actually own a trademark on the term Open Source somehow?
Hm.. I disable everything but Apache on my Linux box. Now, bring it down.
Thank you, drive through.
Please note that the flamers are not a good representation of the mentality of the Linux community as a whole...
A single PII 450/512k for 5k doesnt seem like much of a deal. I just priced a Dual PIII Xeon/512k with 512megs ram, LVD drives, 10/100 ethernet. costs alittle under 5k. Me thinks the numbers look diffrent when you throw in a 2nd cpu and a big chunk of ram.
Why the heck does it come with a RAGE 128? So you can play Unreal deathmatches with the server? Seems like overkill. They should stick a stupid RAGE II in it and shave some cost.
You aren't paying $500 for the BSD layer... [it has been opensourced] you are paying for things like the GUI, WebObjects, etc. TIMES FIVE [the CD allows you to put OSXServer on up to 5 different machines.
I'd pay $500 for WO alone [if you haven't used it... check it out... it really is *quite* robust/modular/reusable/scalable/fast very cool]
Blocklevel: Practical Information Architecture
What is this talk about the "BSD Kernel" and the "Mach microkernel"? From what I can infer from the context, is the Mach a layer of software between the hardware and the BSD kernel? If that's the case, doesn't that mean it will be slower than a native BSD, and that Apple took a quick & dirty way out? I confess complete ignorance on this, and ask for excessive corrections/suppliments/answers to my assumptions and questions.
I've done more than consider Java...I've coded about 10,000 lines in it. I know my way around, and I also know how sluggish Java can be. Far better to code in C or C++ and port the code, compiling it on the native system. That Java Virtual Machine's a beast. I like Java, but lets not sacrifice performance on the alter of portablitiy.
Well, I'm assuming that they're running that on a high-end Blue G3. They can't compare LinuxPPC on a Blue G3 to MOSX on a Blue G3 because LinuxPPC can't *run* on the Blue G3s.
Steve specifically ignored LinuxPPC, in fact. Not surprising, since I know he knows we exist.
And if they ever announce specs of LinuxPPC on Blue G3s before we get them running, I'm gonna have to hurt people.
-- haaz.
Actually, Apple has released one UNIX package and shipped a second. A/UX was Apple's UNIX for 68k Macs, which was around from the late eighties to the early 90s. Apple also shipped IBM's AIX on their Apple Network Server machines, which were big beautiful boxes. Unfortunately, they didn't sell well, and Apple cancelled them.
:)
LinuxPPC made a lot of ANS owners happy when it started running on them.
So, Apple does have a past with UNIX -- one that always ended in cancellation...
-- haaz.
Regarding the minimum spec for OS X Server:
This is conisderably greater than the published min Spec of NT4.0
If you don't have more than 64MB of RAM in an NT Server, you're crazy.
To get an equivalent NT box with an unlimited user license for under $5K is impossible. And you can forget about USB and FireWire.
granted.. apple is more insane than any other computer company i know.. though.. they are putting some sort of effort in.. can you say the same for microsloth?
sum fine
Thankfully, I've never worked on a MAC, but doesn't it suffer the same problems as NT (ok, ONE of the problems)? You can only admin the thing from the console? What good is that?
Thank you. That's what I was going to ask.
Agreed those are all good things to have. But for $500 and the bucks I have to shell out for a G3, I'd also like things I can usually get with the above list (NT excluded) like:
SMTP
DNS
SMB Connectivity
C'mon. OSX server is a nice first step. It's unproven at this point and will remain in Apple's line of "niche" products. I think it's a good first step, but there's still a long road ahead for them to be a player for the rest of the non-Mac world...(read 90% of us).
There's a reason why one of the Mac's alert sounds is called 'sosumi'
-Simon
Why does apple never admit "we're slower for the price, and we crash a lot, but you love us anyway, and we love you[r money]" ???
Gee, what do you think, slicko?
You're right that there's no SMP for supported macs, although you can still SMP with a 4-processor 9600. Yes, I know that Apple says OS X Server needs a G3, but it WILL run on older boxes.
In addition, I'd wager a pair of socks, that in a few months, Apple will release a multi-core G4 version of their computers. That means, that there will be 4 processors in the same piece of silicon.
Oi!
Let's talk about speed!
One thing that no one has talked about yet is the security that OS X Server provides. In fact, the normal Mac OS is one of the most secure servers you can find! (Yeah, I know, it sux as a server, though).
Just imagine, if you have an OS with one of the highest levels of security in the world--that actually is worth using as a server. Damn, that would be OS X Server.
Amen. Were it not for a really _NASTY_ power outage (and the failure of the primary backup generator) my email box would be at an uptime of 275 days right now... And it's a noname 486 that got hit by lightning. (I kid you not, IRQ 4 dosn't work but the system still runs)
My higher end boxes have similar reliability, if smaller uptimes. (I tend to swap their hardware more often) The trick is to not buy noname-boards from a first tier company, but to buy all the name-brand hardware yourself. Granted you lose the support from Dell or HP or Compaq, but you save enough to have more clued people around. It's all a tradeoff.
--Dan
A better comparison would be between LinuxPPC and Rhapsody^H^H^H^H^H^H^H^Hmacos X server.
MkLinux and mXs both run on the Mach microkernal, whereas LinuxPPC runs directly on the PPC chip. It is documentably 20% faster than either. So, no need to go out and test, it's already been tested.
I've run all three OSes (okay, fine, I used Rhapsody DR2, but they didn't change the Mach part between then and release) on my PPC 7500/150, and LinuxPPC is visibly the fastest. It's in use right now. As soon as NetBSD/macppc works reliably, it will (probably) beat LinuxPPC (in my esteem, anyway).
Do you have a
That Java Virtual Machine's a beast.
While this is certainly true, it is not inconceivable that the JVM could be made much faster, if it were taught to more intelligently optimize code. (Right now, it hardly does any optimization.)
That said, interpretted compilation will forever be slower. Nothing to do about that. It might be made workable, though (which Java really isn't, currently).
Do you have a
I think Dell only very recently started building there own board level components. Previously, I understood they pretty much took whatever Intel made for them, tested it, and assembled it. I thought this was there entire business model, and the primary reason that IBM, Compaq, and others have problems with Intel dictating server architectures because then they can't differentiate.
Fine, then you go out and buy XYZ and test it against the $5000 Mac OS X Server G3/400. Until then, jeez louise, keep quiet! As annoying and pointless as "PR benchmarks" may be, at least they tested something.
;-)
Sorry, but "the idle speculation of a Linux user" holds less weight with me than "a stacked benchmark cited in a press release." I suspect most people agree. Go test. Then come back, and we can all have fun picking apart your benchmarking setup
Apple has had and sold AUX then AIX on it's hardware. You can still buy liscense upgrades for them. Years of experience no less. And they produced software that ran in unix and allowed Macs to access X Windows from the Mac OS.
On top of that, the people in charge of the OS are from NeXT. Think about it.
oh yeah and there was that MkLinux thing as well. It ran okay on PCI and NuBus based Macs and was the only Linux choice for PPC macs for a while.
the people at Apple working on that ar apparently involved in the OS X Server/Darwin project due to thier experince.
People are people no matter what OS they use, and because of that they will act the way they will on whatever OS they use. The real problem lies in the "my penis is bigger" syndrome. Where everyone wants everyone to think they got the best OS. Now, that is not really a bad thing, the bad thing comes from when you start to bring others down for using another OS. I just tend to ignore the idiots who spout "linux everywhere." There is a saying that no one tool can do everything, because by trying to become the "ONE" tool, is impossible, that is why folks who are specialist cary around very large tool boxes, and have tons of smaller toolboxes to do different jobs.
anyway, i guess i started to go off on a tangent.
To get back to the point, the folks who shout the loudest in here are just folks who have installed the OS cause its "cool", and "hip" and have not really done anything with it. If you look at the programmers and the network administrators in here, you would realise that these guys usually know what they are about because they have been exposed to multiple platforms and multiple operating systems. Most of the regular linux folks i have meet are very friendly, in fact, most are willing to go out of there way to help new users as long as you are actually willing to learn some of the basics for yourself and do not want to be handfed.
so, i don't think that the AC of Slashdot are an indication of the the so called "linux community." and anyway, why would you use or not use an OS because of who else is using it? My belief is that you should use either what you can afford, or the best OS/Platform for the job.
Its spelt "L-I-N-U-X", but pronunced as "Free Beer"
what?!?
where?
oh god, noooooooooooo!!!!!!!
when did this start to happen?
i can't believe that i did not notice that there has been a big reduction in the amount of sunshine. Damn, what will i do now?
oh the humanity............
why doesn't someone do something!!!!!
help me, help me please!
Its spelt "L-I-N-U-X", but pronunced as "Free Beer"
shouldn't a benchmark for a webserver "not" be running on the server that is being benchedmarked?
I should think that you should have a workstation that contains the benchmark software that is connected to the server, and then it loads the hell out of the server, better yet, get multiple workstations running the benchmark software on the network to strain and bring the server to its knees. Now that is how a server should be tested. And in that case, the platform the benchmark software is running on will be irrelavant, as tcp is tcp.
Its spelt "L-I-N-U-X", but pronunced as "Free Beer"
Read the fine print on the benchmark.
The test was with static html, not cgi. I'll wager linux AND solaris would kick MacOS' ass on cgi performance. Linux/Apache's static html performance isn't all that great at all anyway - WHO CARES about static html performance on, what, 32 clients? This benchmark is a joke.
let's see cgi performace test on 300 clients or more, Apple.
Fuck Apple. Fuck Steve Jobs. Another proprietary garbage vendor.
support gun control: take guns from cops
And the configuration for that price is....?
I just price dout a Dell PowerEdge 2300 with dual 450 Mhz Pentium III, 256 MB RAM, and dual 9.1 GB Ultra2 drives, dual NIC, 17" monitor, and WinNT 4.0. (Smae config as the G3, minus the extra CPU) Price? $6,127.
So, no, a dual PIII is not even close to being less...
Sure it's faster when comparing it on different
hardware.
But where's the comparison between OS X and
MKLinux running on the same system?
It's FSF that's the church and RMS is the savior-not Linus.
---
This may make a great alternative to NT. Now what will they say? Here's an easy to use, high performance server that's open source-but not hackerish, supported by a famous brand name. It has a great dev environment. 2 catches: no SMP (please correct me if I'm wrong) and only for macs. Linux can challenge NT on many fronts but this seems to attack the other fronts.
---
I can get a G3 400 for $1500 too, but it is not a complete server system. Use your brain, that is what its there for.
Dude, this is getting pretty bad, you should make some sort of Hitler Steve Jobs, your slant is becomming very transparent.
So OS X can saturate a T1 a few milliseconds faster than Linux. Big deal. Anyway, I'd like to see exactly which WebBench stats they're using.
'Sall I had to say.
It's a bit odd that they didn't compare it with *BSD. Could it be because they OS X *is* *BSD, and they don't want it to get out that there's no need to pay $499 for it?
Also odd that they used different benchmark programs on different servers.
Why didn't they run the benchmark agains LinuxPPC on the same box?
Beware the Reality Distortion Field.
-- Out of cheese error! Redo from start.
The day OS X can touch a hard-core distro (like Debian) is the day a Voodoo3 outperforms a TNT2. This is just like the whole G3 vs. PII deal--tweaking one benchmark and beating statistics into a form that Apple likes.
"Even genius needs a competent technique."--Robert Fripp
CGW's 3D GameGauge, which is used for testing 3D accelerators, is pretty accurate.
"Even genius needs a competent technique."--Robert Fripp
True.
Ah, well...has anyone ever done any benchmark tests pitting the various Linux-supported architectures against each other, with systems identical other than CPU architecture?
"Even genius needs a competent technique."--Robert Fripp
Apple says a G3 400 beats a Dell P2 450 measured by connections per second over 10bT.
See the official hype from Apple.
Personally, I believe that benchmark. Unfortunately eveyone knows you can get el-cheapo PC for $1000 to do almost as much. Heck, upgrade to the good el-cheapo for $2000 and yer pretty well loaded. But Apple won't stand for such comparisons, and will insist on being compared only to quality vendors such as Dell, Compaq, IBM and Sun. If it were my small business to run, I'd buy a quality machine over el-cheapo, and I'd buy the Mac because it comes headache-free.
Start Running Better Polls
SELECT cid,date_format(date,"W M d, @h:ip") as time, name,email,url,subject,comment, nickname,homepage,fakeemail,realname, users.uid as uid,sig, comments.points as points,pid,sid,pid
FROM comments
WHERE sid='99/03/17/098200' AND comments.points >= '0' AND comments.uid=users.uid ORDER BY cid ASC
i jusr wonder how it did appear on the page.
--
Memory fault -- brain fried
Balls on. 32 clients and under 100 connections per seccond is a weak test. Novell Netware (probably one of the least loved server OSs in the internet comunity) does a good 3000 CPS on MUCH crappier hardware with more clients with static HTML. I suspect that hardware being equal (MKLinux or equivalent hardware) linux would either dead tie (both running the same apache, yes?) or linux whup it's ass if the MAC machine is spinning cycles maintaining the GUI (hopefully it boots to text console, nice poetic justice). I would like to see how the load is distributed on the systems. NT has this habbit of letting a few user procesess eat all system resources, I know this is not so in Linux, but I don't have any experience with BSD.
Anyone else think this peculiar?
NOTE: Apple, the Apple logo, Macintosh, Mac OS, Power Macintosh and WebObjects are registered
trademarks of Apple Computer, Inc. Open Source is a trademark of Apple Computer, Inc.
Duh, didn't pick that one out. I meant: Open Source is Trademarked by Apple? Nice typo of mine. This was copied from the link supplied by /.
Do you notice a pattern here?
If it isn't pro-linux, it's FUD.
Apart from the hardware disparity, it is not clear if they are comparing the same version of Apache either. I would like to see some details on the benchmark.
(a) VA research are a first tier vendor of linux machines. Dell aren't. They offer no support for linux. (b) You can get a dual CPU poweredge for less than $5000- (c) Does this really prove anything besides the fact that the G3 CPU is better for a web server ?
I just read the threads and what people are saying is not religious fanatiscm but for more control on the benchmark test. Run the test on the same hardware and then run LinuxPPC against Mac OS X and lets see the numbers.
- 24x cdrom
- ATI rage 128/16
- Built in 10/100 ether
- 256 mb ram
- ultra2 scsi
- 2 9gb ultra2 scsi HD's(10000rpm)
- OS10 server
_____- unlimited clients
_____- 5 server licenses
_____- WebObjects(50 transaction/min)
_____- Apple File Services
_____- NetBoot
- USB
- FireWire(IEEE 1394)
- Spanky looking box
What does a comparable Linux Box Cost?(add in the cost of WebObjects, or something comparable)
How about a comparable NT box?
"Stuff... In my home!? NEVER!" - Zim on Invader Zim
"I want the toilet seat!" - Little Dog on Two Stupid Dogs
- 4 PORT 10/100 NIC(giving a total of 5 10/100 ports) :P
- 24x cdrom
- ATI rage 128/16
- Built in 10/100 ether
- 256 mb ram
- ultra2 scsi
- 2 9gb ultra2 scsi HD's(10000rpm)
- OS10 server
_____- a good UI
_____- unlimited clients
_____- 5 server licenses
_____- WebObjects(50 transaction/min)
_____- Apple File Services
_____- NetBoot
- USB
- FireWire(IEEE 1394)
- Spanky looking box
- Setup in 15 minutes or less(dont take this out of box experience for granted)
What does a comparable Linux Box Cost?(add in the cost of WebObjects, or something comparable)
How about a comparable NT box?
"Stuff... In my home!? NEVER!" - Zim on Invader Zim
"I want the toilet seat!" - Little Dog on Two Stupid Dogs
bottom line is, its a web server with apple's name on it. Mac OS's have always been innovative, and is recognized for simplicity, something that is rarely associated with "server".
Also, its fast, RISC, powerful, challenges microsoft, and new. A web server is a web server. Who cares about "old style nix people", MOSXS is not a hobby, its a new business solution.
----------
"They misunderestimated me." --George W Bush, Nov. 6, 2000
I would have agree. Sadly, the majority of those who dont share your opinions fail to remove brand-name bias or back up their vague arguments.
It's nice to see people devoted to Linux, but most of you need to expand your horizons.
-f
----------
"They misunderestimated me." --George W Bush, Nov. 6, 2000
Because I have to buy it.
For the first time I connected my one windows box through my linux server with ip_masq, over a single ppp connection.
I did it for free.
As a small businessman, linux will remain my tool of choice, not because it is open source. Since I don't program, I benefit from this only indirectly (I still believe it is the best way to go), but it is not my primary motivation for using linux.
My primary motivation is cost/benefit. When I introduced myself to linux there was NT and commercial Unices. All where way too expensive. I needed a solution I could afford. I was amazed that the twist of human fate had occured. Imagine a radical new development paradigm had occurred in my lifetime, and it was given away for free! Was I dreaming?!
Thank God for Linux!
MacOSX on the other hand, (while it may be good or superior), cannot compete with linux on a cost/performance scale. The fact that MacOSX only runs on expensive hardware is the nail in the coffin.
MacOSX my be excellent, superior, wonderful, whatever. It's expensive, and I can't afford it. Therefore, I will never use it, not even to pique my curiosity. I might try FreeBSD, though.
Well, by that token, Apple's pricing is inflated too. I can get a G3/400 from Apple for $1999 custom-configured. Add some RAM from the Chip Merchant, get OS X Server for $499, pick up a couple of fast SCSI drives third party, and a cheat F&W Ultra SCSI card. For under $4k, you can have the same performance apple touts in these specs.
What people don't get is that this is a press release. Nothing more. Press releases are always slanted. I'm going to install OS/X today on my old 604e/233 and to some tests. I am using LinuxPPC on the same box right now, and I will benchmark the two and compare.
- Vincit qui patitur.
I wonder what sort speed Apache and LinuxPPC would give. Running on the same hardware as MacOs X
Server of course.
Does this mean MkLinux and LinuxPPC are now
competitors to the future of MacOs?
Will Apple kill off MkLinx?
>Check your facts jack
In my experience.
PowerBook 1400 - PowerPC 603ev 166MHz - 548Kkeys/s
IBM PC Pentium MMX 200 MHz - 420 KKeys/s
We have one PC in our office here that's
managed 556 KKeys/s Pentium II, not sure
of the clock speed.
PowerPC G3 550MHz (466 overclocked) - 1736K keys/sec [1]
[1] from http://www.macintouch.com/g3zif466.html
Hope this helps
I think everyone agrees that benchmarks published by the vendor (whomever that may be) are often times misrepresentative of the facts...
Let's do our own benchmarks with OS X Server. I ordered my copy and would be more than willing to test it out vs LinuxPPC on my G3/266. What benchmarks should I be using though??
I am going to venture a guess that MacOS X Server will be pretty darn fast with Apache (a different press release that I read said that all the machines were running Apache 1.3.4) but I want numbers to prove it.
RateVegas.com - Vegas Reviews
This is the key point... I think it's a typo... Jobs/Apple know how religious the Linux/Open Source community is (come on, the Macintosh community is the same way... funny how so few are religious about wintel...)...
RateVegas.com - Vegas Reviews
Being a RISC fan, I'll believe that a PPC 400 Mhz chip is faster than a Pentium II 450; plus, we don't know about hard drives, memory, etc. And which Linux? Kernel 1.0? =)
I feel need to email Apple and ask them to publish the complete results for the benchmarking - including complete hardware specs, Linux kernel version (if they are using RedHat then they are probably using the 2.0.x which is now ~2 years old), etc. If Mac X truely is faster than Linux (on comparable hardware) then fine, but I doubt the conclusions they've made will hold under closer examination. I know Apple has been eyeing the OSS commuity and they would love to tap into that "mindshare" (in MS speak) as they are trying to do by open sourcing some the the Mac X drivers, but hijacking the Linux momentum is very short sighted of them and it will only drive the OSS community away.
\forall code \in C, \frac{\Delta readability(code)}{\Delta t} < 0
hahahah...who's ignorant? Since when has the computer industry been based on proprietary software? Realize this, most of what we use today is bases on non-proprietary (ie OSS, IEEE, ANSI, etc) software. Take for example UNIX, UNIX started out as freeware from Bell Labs, it basically killed all the proprietary mainframes of the 70's. Today most of the internet is powered with UNIX and its derivatives. Sure, IBM, HP, Sun and others have made thier own proprietary version on UNIX, but they are all based on the original, free UNIX from Bell and BSD. Further, most of the services that you will find on the internet (and in most organizations) are actually OSS (ie apache, sendmail, etc). So actually, I think you ment to say that it is in the best intrest of big business to say that the computer industry is lead by proprietary software (wouldn't MS like you to beleive that most of the internet uses NT and IIS). You may want to consider this:
"Even a fool is thought wise
if he keeps silent,
and dicerning if he holds his tongue"
-Proverbs 17:28
\forall code \in C, \frac{\Delta readability(code)}{\Delta t} < 0
If Apple was smart, they'd bring back the server chassis that they sold AIX on - with a hot swap array, duel power supplys and 2 (or 4?) 604s, it was the closest thing to enterprise class hardware Apple ever made. (Maybe with the G4s...)
Adding a fast SCSI card and mirrored drives to a desktop box does not make a server in the real world, where uptime is more important than money.
--
Business. Numbers. Money. People. Computer World.
Well, I have to agree with you partly. I'm a high schooler, and we just got a yosemite to replace the old server (yeah, the IT department at school is a bunch of Mac guys, but I'm now a Die Hard Linux guy).
I'm pretty hyped about Apple releasing OSX server, we are getting a copy of it free to play with. Alas, I have to say I don't like seeing crap like this benchmark. I could have built a better computer for $5k, and probably configured Linux better for the benchmark. Anyways, every big company twists benchmarks around to put them in favor of their product, so it is a load like most of us have been saying (I know I'm going to be arguing with Schism and Cracker tomorrow over this).
Between this and their open source efforts (I hope they fix the liscence, that would be really cool, and release the rest of their stuff), I think Apple is going in the right direction. I just wish companies would cut out the crap about benchmarks, or at least put something up that isn't a load of bull for the techs...
ph43drus
I was wondering if anyone can clear up a question I have on this very topic.
Can anyone claim a trademark on any term or phrase even if there is a registered trademark holder for the same term or phrase?
I noticed in an article/release about the new Dell dual Pentium III/Xeon's that Microsoft is claiming a trademark on "NT" (not Windows NT, just NT). I think everyone knows that Nortel owns the registered trademark for NT, it's on every Windows NT box! So, can I claim a trademark for NT, or Open Source, or whatever, also - even if it conflicts with a registered trademark owned by another entity?
For the uneducated, 1000% is 10 times the speed, not 1000 times. Also, 1000% as fast is not the same as 1000% faster.
NewsAlert quoted an official Apple press release. They didn't claim that Open Source was a trademark of Apple, Apple did.
I received a nice reply from Russell Brady at Apple stating that it was an honest mistake and:
Open Source is
a trade mark of the Open Source Initiative. He also stated that it has been corrected on their web site, so that's probably why people don't see it if they go there now.
Your wrong, Apple made a mistake in their original news release but corrected it. See my above message.
No no no. News organizations DO NOT modify official press releases from companies. They could get into a LOT of trouble doing so. It's quoted verbatim from Apple. Apple made a mistake and changed their web site to reflect that. See my above message.
Face it, Linux is now a religion, not just a software. And I think a world like this is worst than "Windows everywhere"
Then check out of this world. What do you think Gates and Co. have been doing for the past 19 years. They have more "religion" in their "movement" than the Linux crowd does. We just back it up with facts.
Screw the hype. Apples suck
That's probably because NetBSD was ported to the i386. Heck, it's probably just from the standard 4.4BSD/386 code.
--jon. Postel is dead. May we all mourn his, and our, loss.
No, no, no, it goes like this: Do you pray to Saint IGNUcius every night? Do you thank Erica S. Raymond for food? Do you go to the nearest chapter of the Church of Emacs (xemacs is fine) on Wednesday nights? If you want religion, you need to head on over to the Church of the Subgenius. Cheers, Joshua (not yet a YC30)
--jon. Postel is dead. May we all mourn his, and our, loss.
Whoops. I mispelled ESR's name there. I was even using the Preview button! I really should mount /dev/brain more often.
--jon. Postel is dead. May we all mourn his, and our, loss.
I don't believe you children. Apple finally delivers the full-blown modern microkernel-based, multiuser, preemptive multitasking, protected memory, command-line capable, Unix OS with the friendly GUI on it, just what you've spent years flaming them for not delivering.
So what do you do? You flame it just because it's from Apple! Why can't you grow up and admit Apple is capable of making something really good (and then overcharging for it)? Are you really so insecure that you have to believe your chosen OS or kerner or GUI or CPU is the only good one?
Also, for the naysayers who doubt Apple's commitment to Unix: A/UX; NeXTSTEP; AIX; MAE; MkLinux; OS X. 'nuff said.
Gawd, am I ever sick of people whining about the price difference between a first-tier maker and a noname box builder. You really do get what you pay for. Name me ONE bargain-basement vendor with out-of-the-box failure rates of under 10%. That designs any board-level component themselves. That can effectively support 100 corporate accounts with 25,000 desktops each.
Welcome to the fray. I can't be rejecting you, because I'm responding to you.
Sorry, I do have my hot buttons, and one of them is people describing how much less a given level of computer from a first-tier maker would cost if you only would buy it from Joe's Beige Box Assembly of Black Duck, Minnesota (JBBAoBDMN.com).
There's a reason cheap boxes are cheap: because their makers have no R&D, no marketing (okay, that's a plus), no QA, no support, and no infrastructure. They often have little or no knowledge, too. Big companies and schools couldn't buy from them if they wanted to, because the little guys can't scale to those numbers.
A native kernel will run faster than one built on top of Mach. The advantage of Mach is modularity, not speed.
You don't need to tell me what's in a modern OS. Just because these features are old doesn't mean they aren't considered essential for a modern OS. I was just mentioning the features that Unix and NT bigots usually kvetch about.
I'm still waiting for those systems to adopt modern features like aliases that follow their target file when it gets moved; windows that can display across multiple screens run by different video cards at different color depths; knowing when a floppy disk is in the drive; and knowing where applications are without being told.
Please refer to my comment in response to the immediately previous article about insults and name-calling. Not that you exactly come across as an Apple booster yourself. Pot, meet Kettle.
The Mac had sound from the very beginning. Good sound, even. I recall Apple Records having kept their peace until Apple Computer tried to have Apple Records' trademark nullified.
No, it isn't. NT is based on its own microkernel, which is more like VMS than anything else. It has a POSIX-compliant Unix layer that runs on top of the kernel, but it is nearly useless, as you can't use it to write graphical applications. At least, that was the case last time I looked.
That's what they said about every MacOS release since 7.0, which is more than 15 over the last 8 years, counting the interim releases.
you mindless cretin...
LINUX ROOOLZ!
I just priced a Dell Powedge 2300 with dual PIII 450 and it came out to $5129. Pretty close to $5k. Why are you adding a monitor? Why are you adding Windows NT? Why does Dell not offer a 450 PII? PIII seems a bit overkill for a server, isn't it just a PII with MMX2?
Yes with NT it is $800 more, so the NT one will have to be slower, oh well.
Q.
Oh yeah these aren't even Xeons... :)
Q.
OT *is* fast, but MacOS X and MacOS X server only have BSD Sockets support in the kernel. Everything above goes thru the heavy compatibility layer.
Matt Slot / Bitwise Operator / Ambrosia Software, Inc.
Can anyone claim a trademark on any term or phrase even if there is a registered trademark holder for the same term or phrase?
See http://www.bitlaw.com/trademark/index.ht ml .
Sexier... BAH! I don't keep the cases on my computers long enough to worry about sexy. Besides, as far as I'm concerned, a good computer is a hidden computer. Keyboard, monitor, (maybe) mouse should be readily visible. Sexier... Creepy little things look like coolers. Blech
Chris
So Buddha walks into a pizza parlor and says: "Hey, make me one with everything."
This AC is absolutely right... the sheer number of posts whining about a PR dept. doing what a PR dept. does is sickening... Apple is a company out to make a buck, sure they're gonna put some fishy numbers based on vauge comparisons. I'd really have thought there'd be a more supportive response for a major OS vendor testing the open source waters. MSX seems like a pretty nice piece of work, and I look forward to examining it personally. I would much rather discuss details than waste my time reading lame "hmmm... those marketing numbers look susupicious" posts.
didnt the article say that it would be released
free?
"All that glitters is not gold"
did you see the hardware they were running??
400 mhz risc with 1 mb L2 cache and ultra 2
10,000 rpm hdd's.
and its surprising that it spanked a pentium II ??
I'm all for building nice intel systems, but when
you need performance and have the money to burn,
i have to agree--- BUY RISC and run *nix
"All that glitters is not gold"
The Apple people need to be straight forward. Every time they come out with a new OS or new anything they claim it's faster that Windows or Intel Platforms in General, and now Linux? I just don't buy it. I've heard it before, sure maybe in their lab, but within a week after every release they have they are disproved by every magazine on the planet. I like that Apple has made somewhat of a comeback, but they should realize that the underdogs need to work together, ie linux & Mac & BeOS (although I'm not so sure about BeOS, couldn't get the demo CD to run on any of about 6 machines, all with supported hardware). Anyhow, the Be people have promoted Linux along with their OS, Mac should do the same.
You miss the point. They compared with normal, Red Hat Linux running on a PII-450. There is no way to compare the OSes on the _same_ hardware, because they aren't releasing MacOS X Server for Intel-based hardware, just PowerPC processors (G3 PowerMacs to be specific). They were comparing "comparably priced" hardware, and their numbers are probably right. A 400 MHz G3 running MacOS X Server and Apache probably does outperform a PII-450 running Red Hat Linux and Apache. However, that is not all there is in the PC world, either. For example, you can run the Red Hat Linux on a _dual_ PII-450, and almost assuredly beat MacOS X Server hands down, because MacOS X Server and G3s don't run with SMP (yet, that comes this Fall). If you ran a quad-Xeon with 1024K caches, Linux, and Apache, you would probably run rings around the G3 400 and MacOS X Server. The point isn't that the fastest possible PowerMac and MacOS X Server beats the fastest possible PC running Red Hat Linux, because this is not true. The point is that MacOS X Server is very fast, and at least very competitive with Intel hardware for the money. Plus, the MacOS X Server machine is probably much easier to set up and run, and administer. MacOS X Server is one hell of an OS, and I am excited as I can be about it. It is a great time to be an Apple customer. Microsoft is technically outclassed by MacOS X Server in a very serious way, and that will be made even more severe later this year when MacOS X (consumer) is shipped. The Unix that underpins MacOS X Server is free, in source-code form, to anyone who wants it, and Microsoft will _never_ do anything like that. They would be too ashamed to let anyone see their code.
People, you have to remember also that for $499 you get a 5-server license for MacOS X Server. That means you can install the OS on five separate MACHINES with that one license. That works out to around $100 per machine, for one HELL of a system. I would say a $100 system compares favorably with LinuxPPC or any other free OS, especially to businesses. As far as performance goes, I wouldn't be surprised if we found out that MacOS X performs about the same as LinuxPPC on the same hardware, give or take a little. There may be some reasons I would want to run LinuxPPC on a machine, but there are a lot more reasons I would go with MacOS X at $100 per machine. And remember, there is _no_ user limit to how many users can be simultaneously connected to that machine for that $100 per machine license, unlike NT with its stupid 5 or 10 user limit or whatever it is for the $900 license for NT. Microsoft, look out!!
How much does a comparable Alpha system go for these days? Just out of curiousity...
NO PII is not RISC, never was. i am not sure about alpha vs ppc RISC wise.
no, you really don't understand. Bogomips aren't just an inaccurate benchmark, but they only have ANY meaning with the same type of CPUs, for example, you can't compare PIIs bogomips to a Pentium. Whole different architecures such as PPC and Intel is absolutely meaningless. At least office benchmarks, while very bad, aren't completly meaningless.
Its really funny when someone flames someone else for being stupid, and makes an equally (if not more) stupid mistake in their own post. Go check out the in progress Alpha port of FreeBSD. Good day.
... because it has already gone through the grubby hands of the evil marketroids.
It's as simple as that. It's called propaganda, and every (non-Open Sourceish) company does it. Do you really think that the Pentium III's are really that cool? Do you think that Oracle 8 is that big a deal? Shit happens.
Nonetheless, MacOS X _is_ really bloody cool.
Post scriptum: Steve Jobs used to be a phreak. That should say something about his ethics...
Peace,
Kaufmann
To the editors: your English is as bad as your Perl. Please go back to grade school.
I'm a unix user, but I admit...the Apple hardware is faster than intel hardware. OS X server is *probably* just as fast as any unix machine (minus overhead for the gui),
Which can be turned off.
and I guarantee it's faster than NT. However, Steve's quote: "Mac OS X server is a powerful web server..." is ludicrous...Mac OS X server is running on powerful hardware, which is running a powerful *3rd PARTY* web server.
I think Steve meant Web server in the context of 'system providing Web content', not the standard meaning of the software itself (i.e., Apache).
Furthermore, if you're comparing the performance of $5000 machines...you should be sure that all the machines are $5000. You don't need a $4000 copy of Back Office to run an Apache web server on NT.
No, but you need a brand machine with a Xeon processor in order to get anything like G3-400/OSX performance out of NT.
Peace,
--
Rafael Kaufmann
[rnedal@olimpo.com.br]
To the editors: your English is as bad as your Perl. Please go back to grade school.
BSD/BSDi used to be faster. Not in 2.2. :-)
I used to recommend BSDi for the best commercial web server implementation. Fastest and most stable stack. Best price/performance.
Not anymore.
---
"Eternal vigilance is the price of Freedom."
This has already been addressed.. look at the previous submission about this.
---
"Eternal vigilance is the price of Freedom."
Checkout ByteMark documentation at http://www.byte.com/bmark/bdoc.htm, which is the benchmark Apple used for their G3 vs. P-II comparison. BTW this link used to be on Apple's G3 benchmark pages, but not any more. A careful and informed reading of the ByteMARK doc reveals that even the integer results are twisted.
Choosing CodeWarrior for the Mac vs. Watcom 10.0 for the PC is totally laughable.
Another note: it appears that there are no results on www.spec.org for Apple systems. SPECint95 is a relatively fair crossplatform test. I wonder why Apple has not posted results there.
BTW 1st post
Modern? Come on. It's 1999, and Apple is just now adding features that are fifteen years old. They tout NetBoot like it's the America's Cup, but I bet a quarter of the slashdot readers already know how to do that with their linux/*BSD boxes.
And in a perfect world, you wouldn't have to have an HFS+ partition to do it. What's that all about?
Yes, it's nice to see Apple pull its head out of the sand. Yes, I'll probably be running MacOS X on a server around here, but let's also get real: it isn't revolutionary, it's evolutionary.
Hell, I'd even take NeXTstep over MacOS X...
We're just saying Apple should be realistic (instead of marketing mavens). Look at Corel and the Netwinders. They didn't say,"It'll blow a PC out of the water!" They said,"It's small, fairly cheap, it rips compiling the kernel, but don't do any floating point..." Those of us who are enlightened consumers can understand that, and appreciate the cander.
As opposed to you, who probably still thinks Chicago is a cool font.
Alan, you're a god. I even did the requisite bows in my office before reaching for the keyboard. And I agree with you on all counts EXCEPT the last: in networking, FreeBSD may hold it's own with Linux.
I used to believe otherwise, until I saw the info on the CIDER/SHADOW Project and FreeBSD's implementation of the Berkeley Packet Filter. When the NSA recommends FreeBSD, you have to look twice.
Open Source is a trademark of Apple Computer, Inc.
s erver.html, and this doen't mention "Open Source" being a trademark.
My initial guess was that this must've been copied straight from Apple's press release...
It is traditional for corporations to attempt to "protect" phrases they like by claiming to own them. (Was it $5 million that Microsoft had to pay for "Internet Explorer"?)
One company in the UK recently applied to register Y2K as a trademark! (This was refused, of course).
However, the original Apple press release for this story is at http://www.apple.com/pr/library/1999/mar/16macosx
Also, at http://www.publicsource.apple.com/ps-faq.html Apple states...
Q. What is open source licensing?
Open source is a new term for the historical development model used by the UNIX and Internet community to facilitate distributed development of complex, high-quality software...
So, the question is why on earth did NewsAlert claim that Open Source is a trademark of Apple Computer, Inc.?
(p.s. of course, "copyright" is not the same thing as "trade mark"...)
--
Can anyone claim a trademark on any term or phrase even if there is a registered trademark holder for the same term or phrase?
:-)
Very broadly...
Trademarks are registered in different "classes" of goods and services - e.g. there are distinct trademarks for "Apple" for computers and "Apple" for music.
If someone thinks you are using a similar name to them for a different product, and that this is affecting their business, they can try and sue you for "passing off". (McDonalds resteraunts threaten this quite frequently).
Also, as you American's can sometimes forget, it's a big world out there... It is possible for the same trademark to be registered for similar products in two different countries by two competing producers.
I think the statement you quote that "NT is a trademark of Windows" is probably over-zealous subediting, rather than a faux pas by Microsoft... Can anyone confirm this?
Cheers
--
There is a big difference between a "trademark" and a "registered trademark".
Saying "XXX is a trademark" is a statement that XXX is being used by someone for some business purpose. It is not a criminal offense for nyone to use the mark "XXX" (unless this is fraudulent). The remedy for infringment of a non-registered trademark is an action for "passing off".
Saying "XXX is a registred trademark" is much more serious. It is a criminal offense (in the UK anyway) to: -
(1) falsely use a registered trademark
(2) claim a mark is registered when it isn't
(3) wrongfully threaten someone with enforcement proceedings
People often claim that "XXX is a trademark" with the hope that it will give them some sort of legitimacy to a word or mark, and scare off other people from using it.
As we've seen in this thread, sub-editors for some reason seem to love to add it in to press releases for no apparent reason too.
If in doubt, always seek proper legal advice
[Which this isn't, by the way...]
--
...you get the idea
IIRC it was the arrival of sound in the Mac that caused Apple Records to freak out - although I can't seem to a nice link on the net to the whole story. Again, IIRC, the tale is told in The Macintosh Bathroom Reader... (or was it theM Macintosh Bible?)
My point is, if you've been selling double glazing for 10 years under the trade name "Windows 2000", Microsoft couldn't (or shouldn't be able) to stop you using that name, even if they "obtain" a registered trademark for computer software. You'd have a good shot at registering your trademark for whatever class of goods double glazing comes in... You'd also be liable to be sued to hell if you tried to claim some soft of affiliation with Microsoft!
--
I had Rhapsody DR2 running on a Powerbook 3400 - there was no support for the PCMCIA slots or Zip drive in the bay, but it ran.
IIRC Mac OS X Server is supposed to have an option to install to "unsupported" hardware.
--
"If you can read this you are too close."
for the naysayers who doubt Apple's commitment to Unix: A/UX; NeXTSTEP; AIX; MAE; MkLinux; OS X.
Where are A/UX, NextStep, AIX, MAE, and MkLinux now? Apple can never seem to stay committed to anything (or anyone) very long. Yes, they are now clearly betting the farm on OS X.
I am confused by Apple's client OS strategy, though. If OS X Client is due out in late 1999, why is Apple wasting time and money developing Mac OS 8.6 (Veronica)?
cpeterso
Oh, wait, sorry, that's not until 2008... forget I said that
Al, help me out here!
--
Beef
"Raging Moderate" of the
I've heard there are night and day differences in speed from DR2 and the final release. I could be wrong though.
--
InstantCool
Right now they seem to have dropped plans to support a PC version. Some rumors say there might still be one, but not for awhile.
--
InstantCool
This is a point Apple has ALWAYS skirted around. They put out boxes which, while admittedly faster, will cost you 2 arms, a leg and some genitalia to buy. Then there's the cost of OS X server.
So of course, you'll see these benchmarks compared on 'equally priced hardware'. Well of course this has to be the case, it takes most of that 5k just to reach the minimal OS X Server's requirements. Why not compare the numbers on a $1,000 machine? I can find any number of current generation x86 boxes that only cost that much. Or last generation Alpha's or Sparc's or anything. But will I find an G3 capable of running OS X Server for that cost? Fraid not.
And even these 1k boxes can hold their own. Hell we've all heard the stories of 486's running DNS servers. Linux will install on a 386 for pete's sake. You'll find boxes that have uptimes long enough to just about advertise the local power company's reliability moreso then the Linux box itself. I love Linux because the price is right. And that's ALL the price, from the hardware you need on up.
Tarnar
P.S. If I could afford a G3 450 or whatever the heck they used, I'd be a farily content guy. OS X would definitely have a place on the harddrive. Next to Linux.
And wasn't the iMac supposed to be 1000% faster than a PII 450 too? Able to jump tall buildings in a single bound, more powerful than a locomotive, etc etc....
Apple seems to be one of the best at trumping up they hardware/software - and turning a deaf ear when people actually start doing real world tests on it (like in the iMac's case - turning it on).
Companies are starting to compare their produts with
;-) ?
Linux! "...outperforming Linux, Solaris and Windows NT Server...."
Linux was the first of the list. So, even if it is
a twisted PR, it proves one thing: Linux is mainstream.
Time to try *BSD
The real big deal is not whether or not MkLinux is a bit faster than Mac OS X on the same hardware. The real deal is that OS X seems to give Unix-like stability and Unix-like performance, but you don't have to be a /.er to set it up. Any Joe Idiot can now setup and run a near-GNU quality web server. If you want to talk price/performane, letting Joe Idiot take 4 hours to install the server and having him maintain it in his spare time is a LOT cheaper than hiring Mr.Guru to set up and run a Linux+Apache box. The cost of the OS and server hardware is totally miniscule compared to the relative salaries of these two. OS X could cost $10,000 and it would still pay for itself twice over in a year for most small to medium sized businesses.
...witness the linuxppc and mklinux communities. Also, most of the universities in this country are teeming with Mac Heads that are also heavily exposed to unix, and nearly every mac user that I know who isn't a secretary or grade school teacher could hold their own on a unix workstation.
I, for one will put OS X server on a multiboot box and ignore it most of the time, as I can't think of a compelling reason to run it instead of linuxppc
$5k optimized mac vs $800 generic PC? sure il will go faster. Let me build a $5k PC optimized for web serving and I bet anything it will be faster than any MacOS X box at the same price.
PR stuff.
The guy complaining about the interpretation is clearly an ass!
The ONLY interpretation is that the comparison is for 2 different benchmarks.
i.e. a screwed comparison
Correct me if I'm wrong, but I'm fairly certain Open Transport is not used in Mac OS X Server...which sucks, but i think they're using BSD networking...
Jeff Croft
----------
Jeff Croft
http://jeffcroft.com
On background of some of the prior released materials on the OS, I knew it would be competent. But it looks like we have a new monster on our hands.
I would really like to get hold of a G3 with this OS on..................I like the PowerPC G3.....
Live long and prosper...
Don't get your panties in a bunch. Performance
:) and give them 2 hours to configure and optimize the environment. Then run the benchmarks. I bet each will perform about 10 times higher than the numbers found for each in Apple's tests.
numbers mean very little, except that under some
theoretical load (and they at least superficially
attempted to equalize variables between the systems) the system should be able to perform
"well enough" to be considered a server OS, on par with other servers below $10K. That's all they needed to prove, but of course for the press to report it it has to be "the fastest".
A fair test is to start with these roughly comparable systems, as Apple did, and then give each out-of-the-box fresh system to a team of platform experts (e.g., give the Sun box to two Sun employees, the NT box to MS employees, the Linux box to Dean Gaudet, etc
My point is that sometimes the choice of platform for a project should factor in the expertise in a group - if your co-workers are Solaris weenies, well by all means go with Solaris.
The real debate should be, given out-of-the-box configurations, which platform & server are easiest to speed-tune for the non-expert? Of course, that's a hard number to give 5 degrees of precision to.
Brian
Compare this with Apple's ads about a G3 toasting
a Pentium II. In that case, they measured core speed using special instructions, and with the basis of those results, stated that the G3 is more than twice as fast.
Computer architects do not like these benchmark; they are more biased towards SPECint and SPECfp, since those compares system performance using real applications and not core speed using a toy program.
In the same way, the Mac OS Server vs. Linux test should be run on the same hardware, and configured in a correct way - equivalence down to compile options of the web server, if necessary.
Given Apple's tendency to 'twist' the numbers, I wouldn't take those benchmarks too seriously, although I find Mac OS Server quite exciting.
regards,
Graduate Student, book/computer/engingeering geek.
When Apple upgraded the BSD layer to 4.4, they took code from FreeBSD, NetBSD, and OpenBSD. So you are right when you say it isn't running FreeBSD (just parts of it), but you are wrong when you say it is based on BSDI.
"Dude, this is getting pretty bad, you should make some sort of Hitler Steve Jobs, your slant is becomming very transparent."n sLaw.html
----
http://www.wins.uva.nl/~mes/jarg320.old/g/Godwi
------
Godwin's Law prov. [Usenet] "As a Usenet discussion grows longer, the probability of a comparison involving Nazis or Hitler approaches one." There is a tradition
in many groups that, once this occurs, that thread is over, and whoever mentioned the Nazis has automatically lost whatever argument was in progress. Godwin's
Law thus guarantees the existence of an upper bound on thread length in those groups.
----
(sure, sure, its a usenet reference, but it applies elsewhere).
ia32 hasn't been vapor where since 1985
I'm sorry, but that was a *really* stupid comment
if you don't know what somthing is, you should
*Keep your mouth shut!*
ReadThe ReflectionEngine, a cyberpunk style n
please, "knowing when a floppy disk is in the drive" if that's all you mac heads can come up with, it's pretty sad.
and before OS X (read: about the last 5 years) mac OS has been wofully inept, no multithreading, no *protected memory*!
but I've had to sit and listen to mac users talk about how great there systems where beacuse the disk drive didn't have a button (witch bugged the hell out of me, "look it only takes 10 seconds to get your disk out!").
in the mean time, the system's need to reboot about every hour.
And don't say that I never use the things, they are the *only* computers at my school, and I've been forced to use them just about every day... I know what I'm talking about
ReadThe ReflectionEngine, a cyberpunk style n
Hi,
maybe that's because there are a lot of Linux/Unix only Users out there that read Slashdot and have never used or seen a Mac for real.
Say anything against Linux (or even OSS) and they count it as personal insult. (why these people still stick with intel is another question...)
they regard apple as toy or mickey mouse computer and thus it has no chance against mighty linux...
it's a shame to see that the once open minded linux community is becoming proud of itself like most stupid nt users are, who often regard linux as hacker/kids operating system...
just to let you know: i use linux on my peecee and on my m68k mac...
Robert
OSx is crippled by Mach. Lmbench alone shows how
dire mach is. If they had used FreeBSD and it
was equivalent to Linux on the same box I'd be
prepared to believe it. Right now FreeBSD and Linux are basically neck and neck on network benches (and you'll need HIPPI to saturate either
meaningfully).
A mach system call on a high end x86 box is the same sort of speed as a syscall on an old sun4c
box without mach..
So NFR is optimised to a specifc magic BSD API.
Thats even less relevant than apples little bit
of bent benchmarking.
Why are apple using 2 benches, why are they using
10baseT not gigabit ether. Think about it
The combination of BSD net code and mach has so far shown no evidence of any credible performance at all. BSD networking without Mach is fast and its nice to see FreeBSD are stil trying to keep up with Linux
Apple has already killed off Mklinux, its only one active developer at apple who is working on it now.
:)
LinuxPPC is the only working linux for macs until Debian realeases its version. MKlinux is outdated and slow, its been practicly dead a loong time
/don't falme my spelling
De lyckliga slavarna är frihetens bittraste fiender, legalisera!!!
Exactly, No DR4 and just the kernel is being developed, Anybody can use the real linux kernel as of 2.2.x, so why should anybody need mach to host it (maybe some 6200 people but nobody else). MkLinux is as good as dead. The mach version used ain't even GPL...
De lyckliga slavarna är frihetens bittraste fiender, legalisera!!!
>Will Apple kill off MkLinx?
(notice the word APPLE in the question?)
I still really doesn't think apple care a bit about MkLinux, just leaving one developer to the project.
please note that I have only said MKLINUX is as good as dead, NOT mach or mac linux or anything.
Ive said that MkLinux (as an apple project) is as good as killed off. Of cource the sources are free and will be free but apple doesn't care about it any more.
The main purpose of MkLinux was as I see it to start the linux development for mac, and it did, now we have LinuxPPC and don't need mklinux anymore. It is slower and it is older so why care. Apple doesn't
Of cource a lot of people have downloaded and bought it, it was the only linux for mac when it was released, but as soon as you've tried the real kernel instead of mach you see how much faster it is and will never go back to mach.
Probably apple will use some parts of the mach kernel in OS X but thats something totally different than MK LINUX
Please tell my a good reason why MkLinux is better than the "real thing"?
/my opinion
De lyckliga slavarna är frihetens bittraste fiender, legalisera!!!
It's not a deal, it's a Dell. If they'd gone to the bother of finding the fastest PC under $5k and putting Linux/Apache on it they might not have been able to prove their point.
--
E_NOSIG
Gosh, you people are touchy. I make an innocent little comment about how if you really wanted to find the fastest web server under $5k you wouldn't be buying Dells and I get flamed.
/. post. Now I feel all rejected. Sniff.
We use Dells at work, and I really like them. The 2300 is a bit widgy for what I do (currently using 6100s, going to 6300s), and if you buy them by the thousand they get really cheap, but for a one-off competition they are not a low cost option.
BTW that was my first
--
E_NOSIG
Gee .. I wish you would consider stating facts
...(mostly because no one really knows.)
... is simple .. there are NO plans .. it doesn't meant that there won't be a DR4 just that neither Apple nor anyone else involved wants to discuss products that don't have solid release plans...
.. not practice.
rather than opinions. The Mach version is a BSD style license (it is the CMU license to be precise).
Its hard to imagine that over 20K purchasers of the MkLinux CD-ROM are just going to disappear. Not to mention the number of downloads
The issue of "No DR4"
Obvious to anyone with a recent computer science background, a microkernel (such as Mach) allows multiple OS personalities to run on the same hardware at the same time. This is called theory at this time
David Fickes ADVICE Marketing (650) 321-2198
And we all trust ZDnet for "honest" and "objective" statistics... I'm sorry but this article gets filed right along with good 'ole Bill Gates' book...
Yes, one day I may actually learn to spell...
Vaporized? Why? The NT box you're using gonna crash again?
Vaprized? Why? The NT box you're using gonna crash again?
Don't you people have anything better to do than focus on the business side of computing? Frankly, it's rather vulgar. I don't know about you, but I went into computing BECAUSE I LIKE COMPUTERS, not because I wanted to see how big, rich fat-cats could benefit from technology. Sickening.
What on EARTH does it matter how cheap PCs are when you buy them by the thousands? How many of you can buy PCs by the thousands for your own PERSONAL use? None, unless one of you out there happens to be Bill Gates. And how much does it matter if PCs don't come with support? If you don't know how to do your own rack-a-fratchin' support for ordinary desktop PCs, what the fsck are you doing running Linux?
It's time to re-think our priorities, people...
With spending like this, exactly what are "conservatives" conserving?
Uh, no. NeXT is a company that has been operating and providing Unix support for well over ten years. Apple's support of AIX on PowerPC machines and AUX on 68k machines alone establish them as a UNIX vendor with deeper roots than most people are willing to believe.
It amazes me that much of the Open Source community is so hostile towards Apple. Much of the flameage is exactly the same as one would hear from some dumbass M$ apologist. While Apple PR is clearly trying to cash in quick on some of this open source hype, their OS is based on OSS and they (as NeXT) have been active in the open source community long before most slashdot readers (average age: 20). Just look at Avie's work on mach for one.
Then again, if you want to be ignorant and angry, that's your problem. You're probably running code written and paid for by NeXT right now if you're running an open source OS.
X may be bloated, but Linux is not X. If you use a lightweight window manager it's not that bad at all.