DragonFlyBSD 5.0 Released With Initial HAMMER2 Support, Support For 900k+ Processes

[aht0]

I believe you are barking at the wrong tree.
As far as I understood the OP was taking about FreeBSD and not DF-BSD. So was I.

We only ported the software we are using to FBSD, so I cannot compare the performance to any other BSDs.

- Gilboa

No, I am not barking at the wrong tree
Please, look at the title. DragonFlyBSD 5.0 Released With Initial HAMMER2 Support, Support For 900k+ Processeses

You also brought out "5-digit PID's" in your text, thus my natural assumption that you did mix up DragonFly and FBSD like half the other people in here. It's something like people comparing Minix performance in a thread about Linux's, substituting one for other.

By the way, I am not questioning your results. Clang/LLVM does (still) produce slower binaries (compared against GCC), which would affect OSes using Clang/LLVM. When (if ever) they reach parity, I'd be interested in comparing performance between BSD and Linux again.

[gilboa]

I'm well aware of the original subject of this thread.
However, the sub-discussion was - at least far as I understand it - Linux vs. BSD* (FreeBSD including).
Hence I brought up my data point.

BTW, there's a vast difference between supporting 50-100,000 process and threads and actually having them schedule efficiently on a machine with >100 cores/threads.
Even Linux tends to choke at one point or another.

[Guest]

Guest Idle question, if I may. Did you even notice, before storming in to "prove supremacy of the Linux" that this thread is talking about DragonFly, not FreeBSD?

It's pretty fucking funny, watching you panic and posting "proof" ASAP. And start attacking completely different OS. DragonFly is not FreeBSD. I doubt they have much common code left, besides license headers. Dillon rewrote pretty much the whole kernel single-handedly.

Anyway, your activity is complimentary, with a shitty OS, you would not see reason to bother.

Yes, I did, but it seems the person who posted numbers from netflix didn't notice this. DragonflyBSD is my favorite BSD distribution and I like it a lot. Its developers don't have inferiority complexes.

[Guest]

Your link is pointless. Unless I missed something it does not tell in what hardware the test was made.

So, it can be anything, ever a four socket machine.

For the record, the Netflix one was using a single-socket Xeon E5–2697v2, as pointed in the link.

It's as pointless as the first commenter argument about netflix. Overall it shows Linux is capable to achieve at least same performance in this case.

[aht0]

Yes, I did, but it seems the person who posted numbers from netflix didn't notice this. DragonflyBSD is my favorite BSD distribution and I like it a lot. Its developers don't have inferiority complexes.

Don't forget your own mix of superiority/inferiority..

[timofonic]

It depends from the point of view, so I list it regardless. I'd never use it for my work, but I like permissive licenses in work I can use myself.

That's why I said "supposedly". I've seen claims from decent sources, but I never saw that firsthand.

Oh come the fuck on, isn't "as long as you don't need to do anything fancy or modern" caveat obvious enough? Their sound infrastructure is better than plain ALSA, but is frozen in 90's as far as features go, so you don't have 5.1 audio, bluetooth audio, and more advanced stuff.

It seems you can't fucking read, so I wonder why you did even reply?

It's easy to be better than ALSA, even recent Windows versions has better audio performance than Linux. Nothing to new to see. PulseAudio is just a layer to hide the crap behind ALSA.

About Jack: I joke about them, having two similar but separate projects. If Linux wants to become a bit more serious in audio, ALSA must be heavily refactored and thereforce PulseAudio have a extreme diet or finally it's good parts improved and merged to ALSA ecosystem.

But's it's a pipe dream, I know...

matches that of the Linux 4.7.10 DRM state

I'm sorry, but this sounds quite sarcastic to me. BSD world always lags behind in drivers, specially the graphical ones. It's a toy outside certain niches, unfortunately, because Linux needs stronger competitors and stop at this awful stagnation process.

FUSE sucks, ALSA sucks, WiFi needs to be improved, NetworkManager and other network managers are a pain in the ass, Wayland still seems like a never ending goal, it's too bad what happened to KMSCon and related projects, there's lack of more agnostic and robust and efficient subsystems instead making you to be on KDE/GNome wars, Gimp is a mess and isn't sure what it wants to be, Krita seems interesting but I don't see it so much future to it because it's under KDE Umbrella (a disaster as Gnome is these days, I hope things improve over time).

And Coreboot is a toy, no serious investment and funding on RE to EFI BIOS that are full of bugs and specially those related to ACPI. My MSI GE62 2QD Apache Pro needs a total BIOS mod to avoid certain issues, really...

Jabber is practically dead, no serious communication framework. And not, libpurple isn't serious at all as framework too.

And console is outdated too, it needs the Wayland-like treatment but in a more accelerated process.