I agree with the other poster that you may have a different problem, as mine never lock up like that, but I hate the FTP hangs and other Finder clunkiness. I hope that Finder revs are a top priority for 10.3.
As i posted in answer to a previous thread on Moshe's article, the fact that he used an older version of the OS (10.1.5 vs. 10.2) and couldn't turn off the GUI for server tests seriously damages the credibility of his results.
At the same time, i do agree--OSX is a very young system, and for all the warts has been doing spectactularly out of the gate.
Re:Time is perception relative
on
Is Mac OS X Slow?
·
· Score: 3, Insightful
No, it is not the same. He's saying that the GUI is not inherently slow to him at that processor speed--that is real data, even if you disagree with it. He's not saying, "it's fast if you use the CLI."
Re:Moshe Bar compares OS X to Linux
on
Is Mac OS X Slow?
·
· Score: 4, Insightful
Bah! he uses 10.1.5 instead of 10.2, and he didn't do enough homework to know that you login with >console at the prompt to get rid of Aqua. This makes his benchmarks valueless. He should do some homework.
Everybody does know that this is an enduser agreement for their frequent flier program, and not for their website, right?
It's clearly marked there, and if you click on "I Do Not Agree" you are taken to the main page of their website to place your order--no fuss, no muss.
I'm not arguing that some of their terms aren't ridiculous--but this agreement's length is not to block people from the main site, but probably to keep people from abusing their frequent flier program.
Did everyone just tear into the legalese immediately, w/o reading anything else?
Well, I just stumbled into the test site and suddenly had 25 or so moderator points...such an orgy of excessive, freakish moderation you never did see! People went up! People went down!
Head over there, bang on the system. It's fun to play God for a few minutes.
"Yes, but it discusses a 'smackdown', which I take to mean a straight fight."
I always assume that any fight with Batman is not going to be a straight one, as he is intelligent and crafty--hence, he is definitely going to use kryptonite.
Maybe to us, but to normal folks, especially those who are from 40-70 (and who control most of our culture, even if we'd rather not remember that) it is not at all an open and shut case--I've had to explain and discuss these issues numerous times with parents, uncles, coworkers, etc.
We may know how we feel, but mainstream culture still can be swayed, and the RIAA knows that.
Apple already has made a habit of introducing Macs at non-MacWorld events for the last year and a half, and I suspect that trend is only going to increase.
I see--totally different arguement. I think the tools rock, and it is up to teachers to take them and use them. Flash cards are also tools, and can be used well or poorly, so I do agree that simply having the tools does not equal a great educational experience.
Bitch bitch bitch. You win--it doesn't have a CDRW drive. I was surprised at that.
I'm not terribly interested in continuing this, as I am not actually a "mac fanboy", or whatever language you wish to use. I'm sorry I called you a mornon.
I do think if you try and win your arguements w/o so much bile, you'll get further. But such is life.
Oh, get real. What the hell do I need Karma for, you ignorant dog-faced whore! I'm just trying to keep the damn article from vanishing, you poorly-bred, ill-begotten sh!t-mouthed bastard!
I'm just thrilled that it writes CDRs at 16x...I'm using an 8x notebook burner now, so I was resolved not to take a hit in speed when I get an external DVD writer. At 16x I think a lot of people can finally get one drive for all their burning needs, rather than a seperate CDRW and DVD-R.
There will be exceptions, if you need (or think you need) superfast burning. but this is welcome news.
I would agree with you, but this is a legacy decision that would have saved them crucial months early in the OSX creation process...so I can just as easily see them making the choice then, to get a shipping system out the door, THEN discovering that OSX's biggest problem is that it isn't fast enough, and now trying to retrofit a solution. That matches all the information I've gleaned from mac sites in the past.
It sucks, but if they hadn't gotten X out the door when they did Apple would have been dead in the water--it was already horrendously late for those who started waiting for Copland.
Here I go again, ranting about Mac OS X bowels. This time I want to talk about particular implementation details of Mach-O runtime ABI (Application Binary Interface). Before you get too confused, there are two different things under the 'Mach-O' name:
* Mach-O ABI, which defines how every application in the system executes and calls functions (stack conventions, register usage, and more);
* Mach-O File Format, which defines a way for compiled executables to store different parts of them in the same file (compiled code, data, strings, etc).
The latter is not what I want to talk about today; the first is what puzzles me most. I admit I am just a "small programmer" with no relationship with the powers-that-be at Apple at all (this means, no insider contacts who can explain the reasoning behind the particular important design decisions to me), so my impressions, judgements and guesses expressed in this article may be slightly or totally off the mark. I, however, as many other developers who have dug deep into the implementation of such things, can see obvious drawbacks and oddities about Mach-O ABI, and this is what I am going to talk about.
Mach-O originates from NeXTstep, an operating system created at NeXT for its NeXTstation machines, and later expanded to x86 hardware. NeXTstations were originally based on Motorola 68k CPUs, just like old Macintoshes. Mac OS (classic), on the other hand, used an ABI for PowerPC which followed the ABI principles defined in a document by IBM/Moto for PPC processors. So as you all may already know, m68k and x86 are CISC architectures; PowerPC used in all new Macs is RISC.
To make a long story short, Mac OS X uses an ABI designed for CISC processors, mostly ignoring RISC design principles.
What do I mean by that? Mach-O ABI we see now used in Mac OS X is more or less a direct port of NeXT's Mach-O designed for m68k - it relies on PC (program counter) register to perform various manipulations with data (for the geeks: PC-relative addressing). There's nothing wrong with that, as its an effective and common practice, except for one little thing: there is no PC register in RISC processors (programmatically accessible). That is not a show-stopper though - Mach-O for PowerPC just takes one of 32 general purpose registers and turns it into a program counter-style register, to base all offset calculations off it. That works well, as you can see, as all of Mac OS X applications (except for the ones compiled with Carbon/CFM) use the Mach-O ABI.
That approach works well, except for one small thing: global/static data access adds about 7 cycle overhead per function, and about triple of that for cross-context calls (that is for the G4 class processor) compared to the old, Mac OS Classic ABI (excuse me for the geek talk). Mac OS Classic CFM ABI, in comparison, needed almost 0 cycles for static data access and about 5 for cross-context calls. To rephrase - applications in Mac OS X could be faster, if the Mach-O ABI followed the principles set for the PowerPC chip, and not the ones created over a decade ago for CISC ones.
This brings us the question, "how much faster would the applications be if the ABI was done right?". The answer is, according to some tests done by my friends at #macdev IRC channel, the speed gain would be 10-30%, depending on each particular application (how often does it calls functions). Realistically, the speed gain would be around 10 to 12 per cent (how do I get these numbers, below).
So why did Apple used an outdated ABI for a modern operating system? Frankly, I don't know the reason. About the best one I have heard - it saved Apple a few months in the Mac OS X development time so they didn't have to do massive updates to its NeXT-derived tool chain.
There are signs of change though -- the recent update to GCC, the compiler shipped with OSX, allows it to perform so-called -mdynamic-no-pic optimization, which hard-codes the data addresses in the code, so the result is roughly equivalent to the CFM ABI used in Mac OS Classic -- so the GCC itself, compiled with that optimization, is 10% faster. Applications, to take advantage of that, need to be recompiled, so it doesn't affect 80% of the titles already shipped for Mac OS X. Then again, the optimization above only works for executables and not shared libraries.
Either way, there is no way to change the ABI now, as it would break all of the existing applications - which is obviously not what Apple (or us) would want.
And after all, who cares about a 10% speed loss? You can always get a faster Mac, right?
Further reading: Mach-O Runtime Architecture [developer.apple.com] CFM-Based Runtime Architecture [developer.apple.com]
Thanks to #macdev regulars and an anonymous Apple engineer for helping me with this article.
Update 10/21: fixed a few phrases in the text to make it more clear; I've also been told OPENstep runs on RISC processors (non-PowerPC) - however, I have not investigated how the Mach-O ABI works there - quite possible it obeys the PowerPC guidelines, although I am pretty sure it does the same as on PowerPC. Posted by slava at October 21, 2002 03:40 AM
Second, a USB floppy drive runs $30, and the Compaq POS here has no FireWire, no CDRW, a lower-end version of the OS, no bundled software other than IE and Outlook Express...there's not much comparison. It stinks on ice.
ALSO, you could quote real prices--how much are these stupid rebates? Most are $199 for the computer, so looking at that I'd guess $50 for the monitor, which puts us back up at...a little over the cost of the G3 iMac today.
Your trollish defenses? It has more than one button on the mouse. Whoopie--you can buy a mouse with 100 buttons for your Mac, if it turns your crank.
Other big selling point? This teacher, who has little money and time, can buy and install DVD players, video cards and assorted crap. I know that's what most teachers I know do--they are constantly upgrading their low-end hardware.
If you can't figure out why easy-to-use, effective and free movie and image editing software isn't good for education you're totally pathetic. There are numerous stories at the Apple site, testimonials from ACTUAL teachers detailing how Macs are making a difference in their schools...so STFU.
You ask why the applications should matter to you when you don't use any peripherals? Maybe they don't. But to rant about email servers and forget that students can pick up a hell of a lot from the tools given to them is just lame.
This sort of thing happens all the time: sysadmins are in an interesting position where they feel ethical responsibilities to their network and the privacy of their users because they associate this with their jobs.
Sadly, I think that is leftover from the collegiate atmosphere where the sysadmin culture evolved--corporations have no such rules or regard for privacy. The fact that most corporations track every metric and move their employees make.
If you are allowed to have the illusion of freedom and fairness as a sysadmin, enjoy it but make no mistake: it is an illusion, and if it interferes with real work, higher-ups or the bottom line these "ethics" are going to take a walk.
Businesses only respect ethics that are enforced by government agency and carry real penalties--manipulating internal email is not one of these.
Slashdot Mirror
I agree with the other poster that you may have a different problem, as mine never lock up like that, but I hate the FTP hangs and other Finder clunkiness. I hope that Finder revs are a top priority for 10.3.
As i posted in answer to a previous thread on Moshe's article, the fact that he used an older version of the OS (10.1.5 vs. 10.2) and couldn't turn off the GUI for server tests seriously damages the credibility of his results.
At the same time, i do agree--OSX is a very young system, and for all the warts has been doing spectactularly out of the gate.
No, it is not the same. He's saying that the GUI is not inherently slow to him at that processor speed--that is real data, even if you disagree with it. He's not saying, "it's fast if you use the CLI."
Bah! he uses 10.1.5 instead of 10.2, and he didn't do enough homework to know that you login with >console at the prompt to get rid of Aqua. This makes his benchmarks valueless. He should do some homework.
Everybody does know that this is an enduser agreement for their frequent flier program, and not for their website, right?
It's clearly marked there, and if you click on "I Do Not Agree" you are taken to the main page of their website to place your order--no fuss, no muss.
I'm not arguing that some of their terms aren't ridiculous--but this agreement's length is not to block people from the main site, but probably to keep people from abusing their frequent flier program.
Did everyone just tear into the legalese immediately, w/o reading anything else?
Well, I just stumbled into the test site and suddenly had 25 or so moderator points...such an orgy of excessive, freakish moderation you never did see! People went up! People went down!
Head over there, bang on the system. It's fun to play God for a few minutes.
"Yes, but it discusses a 'smackdown', which I take to mean a straight fight."
I always assume that any fight with Batman is not going to be a straight one, as he is intelligent and crafty--hence, he is definitely going to use kryptonite.
There is only one word, and the word is Kryptonite.
Well, he had his hand at Supes throat and could have killed him, but didn't...so whatever happens after that point is moot.
I bet you are tired of the Linux folks too...yet here you are, trolling at
Huh.
Batman wins through guile, then spares Superman's life. Film at eleven.
Maybe to us, but to normal folks, especially those who are from 40-70 (and who control most of our culture, even if we'd rather not remember that) it is not at all an open and shut case--I've had to explain and discuss these issues numerous times with parents, uncles, coworkers, etc.
We may know how we feel, but mainstream culture still can be swayed, and the RIAA knows that.
Absolutely agreed--I'd love the ability to block overclocking articles.
Apple already has made a habit of introducing Macs at non-MacWorld events for the last year and a half, and I suspect that trend is only going to increase.
Yep, I was expressing regret.
And I called you a mornon, not a moron. Let's not make me look like I actually knew what I was doing.
I see--totally different arguement. I think the tools rock, and it is up to teachers to take them and use them. Flash cards are also tools, and can be used well or poorly, so I do agree that simply having the tools does not equal a great educational experience.
Bitch bitch bitch. You win--it doesn't have a CDRW drive. I was surprised at that.
I'm not terribly interested in continuing this, as I am not actually a "mac fanboy", or whatever language you wish to use. I'm sorry I called you a mornon.
I do think if you try and win your arguements w/o so much bile, you'll get further. But such is life.
Oh, get real. What the hell do I need Karma for, you ignorant dog-faced whore! I'm just trying to keep the damn article from vanishing, you poorly-bred, ill-begotten sh!t-mouthed bastard!
Heh heh heh.
I'm just thrilled that it writes CDRs at 16x...I'm using an 8x notebook burner now, so I was resolved not to take a hit in speed when I get an external DVD writer. At 16x I think a lot of people can finally get one drive for all their burning needs, rather than a seperate CDRW and DVD-R.
There will be exceptions, if you need (or think you need) superfast burning. but this is welcome news.
I would agree with you, but this is a legacy decision that would have saved them crucial months early in the OSX creation process...so I can just as easily see them making the choice then, to get a shipping system out the door, THEN discovering that OSX's biggest problem is that it isn't fast enough, and now trying to retrofit a solution. That matches all the information I've gleaned from mac sites in the past.
It sucks, but if they hadn't gotten X out the door when they did Apple would have been dead in the water--it was already horrendously late for those who started waiting for Copland.
Here is the text:
Unsanity.org
October 21, 2002
Mach-O ABI
Here I go again, ranting about Mac OS X bowels. This time I want to talk about particular implementation details of Mach-O runtime ABI (Application Binary Interface). Before you get too confused, there are two different things under the 'Mach-O' name:
* Mach-O ABI, which defines how every application in the system executes and calls functions (stack conventions, register usage, and more);
* Mach-O File Format, which defines a way for compiled executables to store different parts of them in the same file (compiled code, data, strings, etc).
The latter is not what I want to talk about today; the first is what puzzles me most. I admit I am just a "small programmer" with no relationship with the powers-that-be at Apple at all (this means, no insider contacts who can explain the reasoning behind the particular important design decisions to me), so my impressions, judgements and guesses expressed in this article may be slightly or totally off the mark. I, however, as many other developers who have dug deep into the implementation of such things, can see obvious drawbacks and oddities about Mach-O ABI, and this is what I am going to talk about.
Mach-O originates from NeXTstep, an operating system created at NeXT for its NeXTstation machines, and later expanded to x86 hardware. NeXTstations were originally based on Motorola 68k CPUs, just like old Macintoshes. Mac OS (classic), on the other hand, used an ABI for PowerPC which followed the ABI principles defined in a document by IBM/Moto for PPC processors. So as you all may already know, m68k and x86 are CISC architectures; PowerPC used in all new Macs is RISC.
To make a long story short, Mac OS X uses an ABI designed for CISC processors, mostly ignoring RISC design principles.
What do I mean by that? Mach-O ABI we see now used in Mac OS X is more or less a direct port of NeXT's Mach-O designed for m68k - it relies on PC (program counter) register to perform various manipulations with data (for the geeks: PC-relative addressing). There's nothing wrong with that, as its an effective and common practice, except for one little thing: there is no PC register in RISC processors (programmatically accessible). That is not a show-stopper though - Mach-O for PowerPC just takes one of 32 general purpose registers and turns it into a program counter-style register, to base all offset calculations off it. That works well, as you can see, as all of Mac OS X applications (except for the ones compiled with Carbon/CFM) use the Mach-O ABI.
That approach works well, except for one small thing: global/static data access adds about 7 cycle overhead per function, and about triple of that for cross-context calls (that is for the G4 class processor) compared to the old, Mac OS Classic ABI (excuse me for the geek talk). Mac OS Classic CFM ABI, in comparison, needed almost 0 cycles for static data access and about 5 for cross-context calls. To rephrase - applications in Mac OS X could be faster, if the Mach-O ABI followed the principles set for the PowerPC chip, and not the ones created over a decade ago for CISC ones.
This brings us the question, "how much faster would the applications be if the ABI was done right?". The answer is, according to some tests done by my friends at #macdev IRC channel, the speed gain would be 10-30%, depending on each particular application (how often does it calls functions). Realistically, the speed gain would be around 10 to 12 per cent (how do I get these numbers, below).
So why did Apple used an outdated ABI for a modern operating system? Frankly, I don't know the reason. About the best one I have heard - it saved Apple a few months in the Mac OS X development time so they didn't have to do massive updates to its NeXT-derived tool chain.
There are signs of change though -- the recent update to GCC, the compiler shipped with OSX, allows it to perform so-called -mdynamic-no-pic optimization, which hard-codes the data addresses in the code, so the result is roughly equivalent to the CFM ABI used in Mac OS Classic -- so the GCC itself, compiled with that optimization, is 10% faster. Applications, to take advantage of that, need to be recompiled, so it doesn't affect 80% of the titles already shipped for Mac OS X. Then again, the optimization above only works for executables and not shared libraries.
Either way, there is no way to change the ABI now, as it would break all of the existing applications - which is obviously not what Apple (or us) would want.
And after all, who cares about a 10% speed loss? You can always get a faster Mac, right?
Further reading:
Mach-O Runtime Architecture [developer.apple.com]
CFM-Based Runtime Architecture [developer.apple.com]
Thanks to #macdev regulars and an anonymous Apple engineer for helping me with this article.
Update 10/21: fixed a few phrases in the text to make it more clear; I've also been told OPENstep runs on RISC processors (non-PowerPC) - however, I have not investigated how the Mach-O ABI works there - quite possible it obeys the PowerPC guidelines, although I am pretty sure it does the same as on PowerPC.
Posted by slava at October 21, 2002 03:40 AM
And then I use the word MORNON. Smooth move.
First, the G3 iMac does come with a CDRW.
Second, a USB floppy drive runs $30, and the Compaq POS here has no FireWire, no CDRW, a lower-end version of the OS, no bundled software other than IE and Outlook Express...there's not much comparison. It stinks on ice.
ALSO, you could quote real prices--how much are these stupid rebates? Most are $199 for the computer, so looking at that I'd guess $50 for the monitor, which puts us back up at...a little over the cost of the G3 iMac today.
Your trollish defenses? It has more than one button on the mouse. Whoopie--you can buy a mouse with 100 buttons for your Mac, if it turns your crank.
Other big selling point? This teacher, who has little money and time, can buy and install DVD players, video cards and assorted crap. I know that's what most teachers I know do--they are constantly upgrading their low-end hardware.
If you can't figure out why easy-to-use, effective and free movie and image editing software isn't good for education you're totally pathetic. There are numerous stories at the Apple site, testimonials from ACTUAL teachers detailing how Macs are making a difference in their schools...so STFU.
You ask why the applications should matter to you when you don't use any peripherals? Maybe they don't. But to rant about email servers and forget that students can pick up a hell of a lot from the tools given to them is just lame.
This sort of thing happens all the time: sysadmins are in an interesting position where they feel ethical responsibilities to their network and the privacy of their users because they associate this with their jobs.
Sadly, I think that is leftover from the collegiate atmosphere where the sysadmin culture evolved--corporations have no such rules or regard for privacy. The fact that most corporations track every metric and move their employees make.
If you are allowed to have the illusion of freedom and fairness as a sysadmin, enjoy it but make no mistake: it is an illusion, and if it interferes with real work, higher-ups or the bottom line these "ethics" are going to take a walk.
Businesses only respect ethics that are enforced by government agency and carry real penalties--manipulating internal email is not one of these.