Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

60x speed-up of Linux “perf”

eighty-twenty.org

Post reply on HN
Print view View original

211–220 of 224 posts

Re: 60x speed-up of Linux “perf”

#211

Post by glandium »

a-dub wrote: post #145

is it the fork/exec overhead or the overhead of re-parsing the dwarf data that is responsible for the slowdown? process spawn thrash is obviously bad, but i'm curious how much it contributes to the issue here? forks are pretty cheap these days as i understand, and i think an exec may also be pretty cheap since the program image is already going to be sitting in the buffer cache. reading/parsing dwarf data, on the oth…

Parsing the dwarf data has orders of magnitude more overhead than fork/exec. (source: I'm the one who opened the linked Debian bug)

Re: 60x speed-up of Linux “perf”

#212

Post by account42 »

bombcar wrote: post #181
tyree731 wrote: post #143

Earlier quoted context omitted.

> FWIW, this issue is essentially entirely caused by Linus, who refuses to use or accept GPL3. That's a bit disingenuous. Linus has said no to the GPLv3, yes, but his reasons for doing so have merit.

The very fact that the GPL v3 is incompatible with v2 indicates that v2 has something the v3 takes away, no matter how well-meaning that was.

What the GPL3 takes a way is a loophole to violate the spirit of the GPL without violating the letter of the GPL2.

Re: 60x speed-up of Linux “perf”

#213

Post by account42 »

marcthe12 wrote: post #199
thayne wrote: post #63

Earlier quoted context omitted.

Maybe it depends on gcc so it can use gcc's assebler for inline assembly?

no its for linking. basically clang unless configured in the source it does not know what link options to give. Actually even rust uses gcc or clang to do same thing.

Clang will also use libgcc by default under Linux to allow e.g. stack unwinding to work in mixed Clang + GCC applications.

Re: 60x speed-up of Linux “perf”

#214

Post by account42 »

pphysch wrote: post #72
captainmuon wrote: post #26

Earlier quoted context omitted.

If we are nitpicking, they can , there is nothing material stopping them. It is "just" at odds with copyright law. In a society with different laws, there would be no problem. I wonder what would be greater - the productivity gain when we would not have to make workarounds due to licensing, and when we could just legally access the source code of everything. Or the loss, because people might have less incentive to in…

If only we were permitted to view the digital IP rights tyranny as another disruptable industry with latent energy that could be unlocked by a savvy founder... The economic activity & value directly suppressed by IPR is unbelievable. Hard to even mentally scratch the surface. It's extremely economical (for society) to digitally copy and distribute useful information. Most Western IP laws are draconic in the purest se…

> Most Western IP laws are draconic in the purest sense of the word.

IP laws in most countries are also not decided by a democratic process but rather pushed in by trade deals, which also make it almost impossible to change those laws.

Re: 60x speed-up of Linux “perf”

#215

Post by Someone »

monocasa wrote: post #177
Someone wrote: post #172

Earlier quoted context omitted.

Calling that a fault shows bias. You could just as well call it a choice.

A choice that results in consequences is normally how you assign fault for those consequences.

For those consciously omitting “and later”, the effect of not allowing that probably isn’t a fault, but a desired outcome.

“You can do A, B, and C with the software I wrote, or whatever X may at some future date decide you can do with it” isn’t something everybody is happy with. It certainly requires some long-term trust in what X will or will not do.

Re: 60x speed-up of Linux “perf”

#216

Post by andrepd »

mistrial9 wrote: post #104
saurik wrote: post #96

FINALLY AN ACTUAL ANSWER!! :D I had done a bunch of research into this a while ago and filed an issue with the Ubuntu bug tracker, but was told it was due to ABI stability (which did not make any sense). https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1894407 Understanding that there is actually an underlying license problem is like finally being told all of the reasons for everything that happened on LOST ;P.

> This bug affects 3 people (!)

I'm absolutely positively sure that the amount of people using perf on Debian and derivatives (Ubuntu, Mint) is >>3

Re: 60x speed-up of Linux “perf”

#217

Post by roelschroeven »

faho wrote: post #3

> Michał Sidor suggests building against libbfd, something that the Debian maintainers don’t want to do. "don't want to" isn't quite correct - they can't . Perf is licensed under the GPLv2, libbfd under the GPLv3. The licenses are incompatible, which makes the combination unredistributable - which is what Debian would be doing with it. Debian is legally not allowed to do this.

How do other distributions handle this? Do they also have a slow perf? Or do they just link perf with libbfd regardless of the incompatible licenses?

Re: 60x speed-up of Linux “perf”

#218

Post by matheusmoreira »

olliej wrote: post #151
matheusmoreira wrote: post #71

Earlier quoted context omitted.

The root cause is copyright. If it were to be abolished, no one would ever have to think about licensing ever again. None of this pain would exist. Think about all the time that would be saved when people no longer need to think about all this lawyer bullshit.

In the absence of copyright things like the GPL would have no power - a company could take your work and bundle it into their product and never contribute anything back ever.

In the abscence of copyright, copying some company's work would not be a crime either.

Re: 60x speed-up of Linux “perf”

#219

Post by matheusmoreira »

junon wrote: post #76
matheusmoreira wrote: post #71

Earlier quoted context omitted.

The root cause is copyright. If it were to be abolished, no one would ever have to think about licensing ever again. None of this pain would exist. Think about all the time that would be saved when people no longer need to think about all this lawyer bullshit.

Not sure if this is a pisstake on my argument, but a world without copyright (or something similar) would be a world of endless exploitation and stifled innovation.

> a world without copyright (or something similar) would be a world of endless exploitation and stifled innovation

Says who? The copyright monopolists?

There's plenty of historical evidence to the contrary:

https://news.ycombinator.com/item?id=28330810

It seems obvious in hindsight. Less monopolies lead to more competition and better products. Even the US engaged in such infringement.

Re: 60x speed-up of Linux “perf”

#220

Post by matheusmoreira »

junon wrote: post #84
wizzwizz4 wrote: post #80

Earlier quoted context omitted.

Copyright as it exists today does an awful lot of exploitation-enabling and innovation-stifling in itself. (And that's ignoring the rest of the IP suite.)

This is like saying "cops today do a lot of nasty stuff, let's get rid of all cops". The result is pure, unmitigated anarchy, looting, murder, and lawlessness. I don't find either to be useful lines of thinking.

Not really. Things would be pretty simple. You see something? You can copy it. Not a single legalese document in sight.

Don't compare this stuff to police brutality, looting, murder. They're not even in the same realm. Intellectual property is just ideas and absurd notions of ownership. It's like trying to own numbers. The real brutality is sending people to jail over this.

Post reply on HN