It's really quite disingenuous to label the other side "complex and unreliable" when both sides are complex (and, as far as we can tell, reliable). In the end it's the performance that counts, and here we have an argument that the zero copy approach either "isn't faster in the real world, only benchmarks" -- ok then create a better benchmark OR "is only a little bit faster". Well, a little bit faster is still faster.
Actually, I think you're being a bit disingenuous here. For COW in this context, t's not bad benchmark OR only a bit faster - it's bad benchmark AND (I would guess) easilly an order of magnitude slower.
This sort of thing matters almost exclusively to people doing really deep performance tuning, and for them it's better to present a simple API with large rewards for tuning, instead of transparently doing something weird to an existing API that will break in the field without you noticing and requires really weird usage to get the best performance.
That sort of depends on what you mean by "deep performance tuning"
I'm a typical programmer.... lazy as hell.
Right now, I'm in the middle of developing a network application - think of it as an on-line jukebox. I have streming audio out (multiple destinations), chat messages that have to be distributed to other users in the system, etc.
It's not a particularly high-performace type system... but because of the VOLUMNE of data I have to push out, a "little tweak" like this could make the difference between me being able to host it on my current server (Athelon 2800+, 2 gig memory) and having to shell out a few K for a multi-cpu, shit-load-of-memory system.
It's a hobby system right now, and will *probably* wind up staying that way - with a few tends of users, who cares?
But that one simple API notification, and the potential performance improvements, could mean the differnece between me being able to host 10/20/25 people on my system and being able to host 100/200/250 people on my system. With the amount of I/O I'm doing (and the application is 90% I/O driven), that's significant when you try to scale up.
ANd all I'd have to do to take advantage of it is put a simple wrapper around the malloc() calls where I allocate my network buffers, and my read/write routines.
Not exactly what I'd call deep performance tuning.
If the app is using a suitably large ring-buffer, the kernel will usually be done transmitting before it gets reused. A copy won't happen unless the NIC can't keep up, or the remote machine isn't ACKing fast enough. In that case you need to back off your transmit rate anyway, so the bottleneck isn't the extra page faults. Think of it as a self-adjusting algorithm.
I want to know what the hell kind of network hardware & link YOU have, that it can keep up with the speed of memory writes inside of an applicaton.
"Suitably large" is a crock, in any case. Simple math. If I can write to buffers faster than you can send it (and I guarentee that I can), then all a larger buffer will do is delay the inevitable.
I don't think it's a tricky issue at all - I tend to side with Linus on this one.
As far as the insults are concerned...... who amongst us techies has not at somepoint said something like "Anybody who is still using plain b-trees when rbl trees are so OBVIOUSLY superiour SHOULD BE SHOT ON SIGHT?"
I'ts a hot technical debate, and I seriously doubt that any *BSD developer who *isn't* an idiot would be too badly insulted by what Linus said.
Now - if the technical discussion devolves into just simple name-calling, then they're *all* idiots.
"Remember, saying you don't want all software to be Free Software is like saying you don't want all humans to have freedom (I'm excluding criminals doing time for obvious reasons)."
Isn't THAT kind of like somebody from PETA saying "Well - ANIMALS are people too, yanno"
I have been, actually - the point I was trying to make is that when somebody can't find a job, it's not necessarily because they're an idiot, have no skills, or are lazy.
I've been a programmer since 1980..... I started as a batch terminal operator with Control Data, worked my way up to mainframe operator, started messing about with the fortran manuals, and eventually became a programmer
I've had a few articles published (security related, years ago). I was in a position where I held up the liscensing of a nuclear reactor because I was unwilling to sign off on the reliability of the reactor's emergency shutdown system (and was fortunatly backed all the way by my bosses).
I've done a lot of good work over the years, and then, 16 years ago, I decided to stay at home when I got sole custody of my daughter. I've been raising her myself ever since, and don't regret it one bit.
BUT....... here's the catch
For the last 2-3 years, I HAVE been activly looking for work, and can't get hired.
I have no interest in management, or project planning. I'm a programmer - I want to code. I have no desire to do anything else.
I can't get work at a 7-11 because they won't waste their time on me, because they know I'll leave as soon as I get a better offer.
I can't get *any* programming position because I have on HELLOVA good looking resume, and they know I'll leave as soon as I get a better offer.
My choise is to either leave a profession I've done and loved my entire adult life, or go eenie-meenie-minie-moe and pick something else to do, and pretend to like it.
There's a really, really big hole in those definitions.... and I've seen it in action
Many, many moons ago, here in Canada (we have had similar laws here), I remember one case that went to the supreme court. In this case, the complaintant was claiming relegious discrimination on the basis of the fact that he was jewish.
The Supremes told him to get stuffed, because his relegion WAS a factor in his ability to do the job
The job in question?
He was applying to be a sales representative for a heavy equipment manufacturer. The position was in Saudi Arabia.
Yes, 99.999% of the time descriminating on the basis of relgeion, sex, race etc is a bad thing, and should be stomped out.
But sometimes, it's just reality. These things *can* affect someobody's ability to do the job.
Actually, Marx's style of communism was never even *approached* in the Soviet Union.
Marx himself said repeatedly that communisim was impossible in Russia, because it was still a feudal society. In order to become a communist state, you first had to become industrial, than capitalistic, then socialistic, and THEN communist.
Soviet-style "communism" was at best, highly socialistic, and at worse, nothing more than an idological justification for the olicarchy in power.
No, the TOS does *not* say that you can't use "ad blocking software". It says that if you have ads on your live journal page, you're not allowed to mess with the layout so that the ads can't be seen by people LOOKING at your page. Not quite the same thing.
Wow..... and all this time, regardless of how imperfect any political system is, I was under the apparently mistaken impression that *some* people actually ran for elected office because they were GOOD people.
New flash.... everything isn't an evil plot. Sometimes, people really *are* trying to do something good for somebody.
I just did a quick count on my music database. I have somewhere around 11,300 CDs/albums. I have just over 100,000 songs in total.
My largest colletions are Blues, Classical, and Jazz, in that order.
How/where do I get my music?
Newsgroups. I pay $19 US/month for my subscription. I have a 5 mbit DSL connection, and can download an album in about 2 minites.
Then, I listen..... if I like, I keep the downloaded copy, and order the CD from whereever. If I *don't* like, I trash it, and don't bother
If DRM were "standard", I'd be hosed.... my collection is housed on a linux server, tucked away neatly inside a database, and I've written programmes that allow me to manage my collection easilly.
Oh - and the CDs that I've bought? I stick them in storage, usually without even opening them.
Now - let's talk DRM.
With DRM, I wouldn't have 90% of my collection, simply because most DRM protected music isn't acessable in Linux. I wouldn't have been exposed to 3/4 of the groups that I now like.
How has my collection affected music sales, or the revenues for the artists?
POSITIVLY - VERY MUCH SO
Most of what I play is blues.... and there is a very large number of "regional" artists & groups out there that play in their local area, or maybe one or two states/provinces, and never go any further afield than that. I've heard them, thanks to the newsgroups.... and I've bought their CDs.
I also run a music room on-line, as a hobby.... people come into my room, and via a web page, they can browse thorugh my music collection, see what i have, and request a song. That song is then placed into a queue and played automatically. They cannot download - they can only request. Think of it as an automated, 24/7 all-request radio station
THEY hear music they've never been exposed to before, because somebody else has picked it, or it's on my playlist. At least a half-dozen times a day, somebody will ask me who sang that last song, and where they can get it.... so I point them to the artists website if I have it, or at least give them the artist name and album.
I'm not costing the RIAA, Sony, or the artists a damned thing - I'm MAKING them money. And if anything, they should be paying ME money for the exposure I'm giving their acts. I'm indulging in my hobby/passion/obcession, whatever you call it, I'm not ripping anybody off, and I'm thoroughly enjoying myself.
I know that I've "sold" at least 20 CDs for Georgette Fry, a local blues singer, who's absolutly awesome - some of them to people in Australia who would never have heard of her.
I know that I've "sold" at least the same amount for Hans Theessink, a Dutch singer, to people in the United States.
And I've probably "sold" 50 copies of albums for the Bondi Cigars, an aussie blues group, to people in Canada and the USA.
RIAA - can the crap about DRM "protecting" the artists - it's bullshit. You're costing yourselves AND the artists involved money.
From the article: RFID chips are already going to appear in U.S. passports starting in October 2006, the Bush administration ruled last October.
a) That's gonna seriously screw up some american tourist's habit of wearing maple leaf emblems on their clothing/backpacks so they can claim to be Canadian.
b) Congrats - you just enabled every wanna-be terrorist to be able to track down and find an american in any crowd. Gonna make it much easier to figure out which foreign tourists you want to kidnap, don't you think?
If you are referring to XP solutions that make the uptime claim that you say is impossible, consider this. It's entirely possible to have 100% uptime running WinXP if you use either clusters and/or employ load balancing.
No. The *cluster* may have an uptime of %100, but a single XP machine does not.
Still, I don't see grandmaw getting a cluster installed so she can keep Messenger running for 3 days while she' waiting to hear about the birth of her latest grandchild.
I find it endlessly fascinating that as soon as something differs from how it's done int he USA, it's automatically inferiour.
No, the EU trial system isn't the same as it is in the USA
No, defendants don't have the same rights they do in the USA
They have different rights, because in Europe (or anywhere else other than the USA), people have different ideas about what is fair, what is right, and how best achieve the balance between them all.
"Not Fair!" doesn't really apply. It's a different system, with different rules, that suites the sensibilities and ideals of the people it serves - just as yours serves you.
Re:Not to worry, true believers! They'll be back
on
CRIA Falling Apart?
·
· Score: 5, Insightful
The current situation is just that they want to distance themselves from the bad press of the moment, eh. In a year or so they'll be back and better than ever, the hosers.
Probably not, actually. The labels that left, although they do have a few well-known acts, generally have small, relativly unknown artists in their stables... and those artists tend to be in *favour* of downloads as it increases their exposure.
They're simply doing what's best for their business, not what's best for Sony.
Actually, you're an idiot, while the previous poster was right on target.
Actually, I am a lot of things, but an idiot is definatly not one of them.
One of the things I am, though, is somebody who's not afraid to admit that he's wrong if he is
And one of the things I'm not is someobdy who ignorant, rude, or arrogant, or egotistical enough to personally insult somebody who is wrong.
I guess your particular form of idiocy will have to wait until the next time you bring your car to a machanic to be fixed because you're too much of an idiot to know how to rebuild an engine.
If you are, in fact a lawyer, it might have been nice if you had added your two cents to inform, and not to belittle.
Slashdot Mirror
It's really quite disingenuous to label the other side "complex and unreliable" when both sides are complex (and, as far as we can tell, reliable). In the end it's the performance that counts, and here we have an argument that the zero copy approach either "isn't faster in the real world, only benchmarks" -- ok then create a better benchmark OR "is only a little bit faster". Well, a little bit faster is still faster.
Actually, I think you're being a bit disingenuous here. For COW in this context, t's not bad benchmark OR only a bit faster - it's bad benchmark AND (I would guess) easilly an order of magnitude slower.
Not quite the same thing.
carefull .... if the COWs with guns don't get you, the chickens in choppers will CERTAINLY dust your arse
This sort of thing matters almost exclusively to people doing really deep performance tuning, and for them it's better to present a simple API with large rewards for tuning, instead of transparently doing something weird to an existing API that will break in the field without you noticing and requires really weird usage to get the best performance.
.... lazy as hell.
... but because of the VOLUMNE of data I have to push out, a "little tweak" like this could make the difference between me being able to host it on my current server (Athelon 2800+, 2 gig memory) and having to shell out a few K for a multi-cpu, shit-load-of-memory system.
That sort of depends on what you mean by "deep performance tuning"
I'm a typical programmer
Right now, I'm in the middle of developing a network application - think of it as an on-line jukebox. I have streming audio out (multiple destinations), chat messages that have to be distributed to other users in the system, etc.
It's not a particularly high-performace type system
It's a hobby system right now, and will *probably* wind up staying that way - with a few tends of users, who cares?
But that one simple API notification, and the potential performance improvements, could mean the differnece between me being able to host 10/20/25 people on my system and being able to host 100/200/250 people on my system. With the amount of I/O I'm doing (and the application is 90% I/O driven), that's significant when you try to scale up.
ANd all I'd have to do to take advantage of it is put a simple wrapper around the malloc() calls where I allocate my network buffers, and my read/write routines.
Not exactly what I'd call deep performance tuning.
If the app is using a suitably large ring-buffer, the kernel will usually be done transmitting before it gets reused. A copy won't happen unless the NIC can't keep up, or the remote machine isn't ACKing fast enough. In that case you need to back off your transmit rate anyway, so the bottleneck isn't the extra page faults. Think of it as a self-adjusting algorithm.
I want to know what the hell kind of network hardware & link YOU have, that it can keep up with the speed of memory writes inside of an applicaton.
"Suitably large" is a crock, in any case. Simple math. If I can write to buffers faster than you can send it (and I guarentee that I can), then all a larger buffer will do is delay the inevitable.
I don't think it's a tricky issue at all - I tend to side with Linus on this one.
...... who amongst us techies has not at somepoint said something like "Anybody who is still using plain b-trees when rbl trees are so OBVIOUSLY superiour SHOULD BE SHOT ON SIGHT?"
As far as the insults are concerned
I'ts a hot technical debate, and I seriously doubt that any *BSD developer who *isn't* an idiot would be too badly insulted by what Linus said.
Now - if the technical discussion devolves into just simple name-calling, then they're *all* idiots.
or, I *could* have just meant dropped someTHING
.........
friggin preview button
"Remember, saying you don't want all software to be Free Software is like saying you don't want all humans to have freedom (I'm excluding criminals doing time for obvious reasons)."
Isn't THAT kind of like somebody from PETA saying "Well - ANIMALS are people too, yanno"
That's ridiculous! If you keep spreading rumors like that, I'm going to find out where you live, and pay a visit, along with Mr. Smith and Mr Wesson.
Freaking l00z3r.
A *real* geek would just hack into NSA or SAC and arrange for somebody to be accidently dropped on his head.
Not that I'd ever think about something like that - that's bad.......
I have been, actually - the point I was trying to make is that when somebody can't find a job, it's not necessarily because they're an idiot, have no skills, or are lazy.
Q: Why did the scots invent scotch?
A: Because they'd already invented golf and curling
A lot of that can depend on your situation, too.
..... I started as a batch terminal operator with Control Data, worked my way up to mainframe operator, started messing about with the fortran manuals, and eventually became a programmer
....... here's the catch
I've been a programmer since 1980
I've had a few articles published (security related, years ago). I was in a position where I held up the liscensing of a nuclear reactor because I was unwilling to sign off on the reliability of the reactor's emergency shutdown system (and was fortunatly backed all the way by my bosses).
I've done a lot of good work over the years, and then, 16 years ago, I decided to stay at home when I got sole custody of my daughter. I've been raising her myself ever since, and don't regret it one bit.
BUT
For the last 2-3 years, I HAVE been activly looking for work, and can't get hired.
I have no interest in management, or project planning. I'm a programmer - I want to code. I have no desire to do anything else.
I can't get work at a 7-11 because they won't waste their time on me, because they know I'll leave as soon as I get a better offer.
I can't get *any* programming position because I have on HELLOVA good looking resume, and they know I'll leave as soon as I get a better offer.
My choise is to either leave a profession I've done and loved my entire adult life, or go eenie-meenie-minie-moe and pick something else to do, and pretend to like it.
There's a really, really big hole in those definitions .... and I've seen it in action
Many, many moons ago, here in Canada (we have had similar laws here), I remember one case that went to the supreme court. In this case, the complaintant was claiming relegious discrimination on the basis of the fact that he was jewish.
The Supremes told him to get stuffed, because his relegion WAS a factor in his ability to do the job
The job in question?
He was applying to be a sales representative for a heavy equipment manufacturer. The position was in Saudi Arabia.
Yes, 99.999% of the time descriminating on the basis of relgeion, sex, race etc is a bad thing, and should be stomped out.
But sometimes, it's just reality. These things *can* affect someobody's ability to do the job.
Actually, Marx's style of communism was never even *approached* in the Soviet Union.
Marx himself said repeatedly that communisim was impossible in Russia, because it was still a feudal society. In order to become a communist state, you first had to become industrial, than capitalistic, then socialistic, and THEN communist.
Soviet-style "communism" was at best, highly socialistic, and at worse, nothing more than an idological justification for the olicarchy in power.
In this case, more the worst than the best.
That's why most immigrants come here. They want the challenge!
They do? I'd love to see some numbers on that.......
Somebody - PLEASE - mod parent up to a 10 or 15 or something
No, the TOS does *not* say that you can't use "ad blocking software". It says that if you have ads on your live journal page, you're not allowed to mess with the layout so that the ads can't be seen by people LOOKING at your page. Not quite the same thing.
........ this is a story?
Geeze
Wow ..... and all this time, regardless of how imperfect any political system is, I was under the apparently mistaken impression that *some* people actually ran for elected office because they were GOOD people.
.... everything isn't an evil plot. Sometimes, people really *are* trying to do something good for somebody.
New flash
Hey awesome - the Bondi Cigars are one of my favourite bands here in Oz! Have you checked out their website?http://www.bondicigars.com.au/
:-)
:-)
Yes - that's where I send people that want to purchace
I presume you know what a Bondi Cigar is?
Do you have any idea how many aussies have come into my room, asked me the same question, and taken so much delight in telling me?
Ok - let's talk music fan.
..... if I like, I keep the downloaded copy, and order the CD from whereever. If I *don't* like, I trash it, and don't bother
.... my collection is housed on a linux server, tucked away neatly inside a database, and I've written programmes that allow me to manage my collection easilly.
.... and there is a very large number of "regional" artists & groups out there that play in their local area, or maybe one or two states/provinces, and never go any further afield than that. I've heard them, thanks to the newsgroups .... and I've bought their CDs.
.... people come into my room, and via a web page, they can browse thorugh my music collection, see what i have, and request a song. That song is then placed into a queue and played automatically. They cannot download - they can only request. Think of it as an automated, 24/7 all-request radio station
.... so I point them to the artists website if I have it, or at least give them the artist name and album.
I just did a quick count on my music database. I have somewhere around 11,300 CDs/albums. I have just over 100,000 songs in total.
My largest colletions are Blues, Classical, and Jazz, in that order.
How/where do I get my music?
Newsgroups. I pay $19 US/month for my subscription. I have a 5 mbit DSL connection, and can download an album in about 2 minites.
Then, I listen
If DRM were "standard", I'd be hosed
Oh - and the CDs that I've bought? I stick them in storage, usually without even opening them.
Now - let's talk DRM.
With DRM, I wouldn't have 90% of my collection, simply because most DRM protected music isn't acessable in Linux. I wouldn't have been exposed to 3/4 of the groups that I now like.
How has my collection affected music sales, or the revenues for the artists?
POSITIVLY - VERY MUCH SO
Most of what I play is blues
I also run a music room on-line, as a hobby
THEY hear music they've never been exposed to before, because somebody else has picked it, or it's on my playlist. At least a half-dozen times a day, somebody will ask me who sang that last song, and where they can get it
I'm not costing the RIAA, Sony, or the artists a damned thing - I'm MAKING them money. And if anything, they should be paying ME money for the exposure I'm giving their acts. I'm indulging in my hobby/passion/obcession, whatever you call it, I'm not ripping anybody off, and I'm thoroughly enjoying myself.
I know that I've "sold" at least 20 CDs for Georgette Fry, a local blues singer, who's absolutly awesome - some of them to people in Australia who would never have heard of her.
I know that I've "sold" at least the same amount for Hans Theessink, a Dutch singer, to people in the United States.
And I've probably "sold" 50 copies of albums for the Bondi Cigars, an aussie blues group, to people in Canada and the USA.
RIAA - can the crap about DRM "protecting" the artists - it's bullshit. You're costing yourselves AND the artists involved money.
From the article:
RFID chips are already going to appear in U.S. passports starting in October 2006, the Bush administration ruled last October.
a) That's gonna seriously screw up some american tourist's habit of wearing maple leaf emblems on their clothing/backpacks so they can claim to be Canadian.
b) Congrats - you just enabled every wanna-be terrorist to be able to track down and find an american in any crowd. Gonna make it much easier to figure out which foreign tourists you want to kidnap, don't you think?
Two Words: Stockholm Syndrome
http://en.wikipedia.org/wiki/Stockholm_syndrome
If you are referring to XP solutions that make the uptime claim that you say is impossible, consider this. It's entirely possible to have 100% uptime running WinXP if you use either clusters and/or employ load balancing.
No. The *cluster* may have an uptime of %100, but a single XP machine does not.
Still, I don't see grandmaw getting a cluster installed so she can keep Messenger running for 3 days while she' waiting to hear about the birth of her latest grandchild.
I find it endlessly fascinating that as soon as something differs from how it's done int he USA, it's automatically inferiour.
No, the EU trial system isn't the same as it is in the USA
No, defendants don't have the same rights they do in the USA
They have different rights, because in Europe (or anywhere else other than the USA), people have different ideas about what is fair, what is right, and how best achieve the balance between them all.
"Not Fair!" doesn't really apply. It's a different system, with different rules, that suites the sensibilities and ideals of the people it serves - just as yours serves you.
The current situation is just that they want to distance themselves from the bad press of the moment, eh. In a year or so they'll be back and better than ever, the hosers.
... and those artists tend to be in *favour* of downloads as it increases their exposure.
Probably not, actually. The labels that left, although they do have a few well-known acts, generally have small, relativly unknown artists in their stables
They're simply doing what's best for their business, not what's best for Sony.
Actually, you're an idiot, while the previous poster was right on target.
Actually, I am a lot of things, but an idiot is definatly not one of them.
One of the things I am, though, is somebody who's not afraid to admit that he's wrong if he is
And one of the things I'm not is someobdy who ignorant, rude, or arrogant, or egotistical enough to personally insult somebody who is wrong.
I guess your particular form of idiocy will have to wait until the next time you bring your car to a machanic to be fixed because you're too much of an idiot to know how to rebuild an engine.
If you are, in fact a lawyer, it might have been nice if you had added your two cents to inform, and not to belittle.