Which Is Faster: Debian Linux or FreeBSD?

[Shining Arcanine]

How so? I'm still seeing GCC 4.2 vs GCC 4.4 being a factor worth consideration in this benchmark.

I already beat you to that comment:

By the way, here is an interesting question. Are the differences in the *BSD and GNU userland performance because of compiler optimization differences or differences in actual code?

[LinuxID10T]

Has anyone here tested PC-BSD? I know the results should be similar to the FreeBSD it is based off, but still... It would also be great to see some graphics benchmarks.

[energyman]

Could you also give gsched a try (its in 8.1 AFAIK)? It is not specific to CAM-ATA. Try:

# gsched insert ada0

to get the IO scheduler to work on ada0. See man 8 gsched for details.

Thanks for the article.

oh yeas, start tuning. That will help FreeBSE so much.

If tuning FreeBSE is ok, tuning Linux is ok too? Oh wait - linux uses ncq out of the box without tuning and stuff.

[energyman]

This is the first article that I have read on Phoronix in a long time where Phoronix actually did a good job in terms of doing useful benchmarks. I planned to post a very nice comment here as I was reading it until I read the conclusion.

The benchmarks make it clear that a GNU userland is faster than a *BSD userland, which means that the *BSD userland developers need to improve performance. It also shows that the Linux and FreeBSD kernels are roughly equivalent in terms of performance, with Linux being better in file system performance and FreeBSD being better in other areas. Why is it that despite the clarity of these things, Phoronix makes an ambiguous conclusion?

because it is up to the reader to make his own conclusion. You know - really professional tests don't tell you what to think or 'this is the winner'. They show you the number and you are the one who has to introduce them into your own system of needs.

[kraftman]

I am not sure what benchmarks you read, but the ones I read had Debian kFreeBSD consistently outperformed FreeBSD in all compression benchmarks. Perhaps you are confusing the charts where lower is better with the charts where higher is better.

I meant about this: "with Linux being better in file system performance and FreeBSD being better in other areas." I didn't agree Freebsd was better in other areas (in the sense: won more tests or all of them) which aren't disk related: pov ray (on a second machine), dcraw, mafft, gm, byte (significal difference, but on a second machine only), sudokut. himeno. When comes to Debian/kfreebsd vs Freebsd then I agree of course. However, like someone noticed, maybe it's GCC which made a difference here?

[yotambien]

I wanted to see what the results looked like normalised to the best one for each benchmark. Nothing revealing, just easier to visualize the differences.

'1' is the best result obtained by any OS. '0.5' means half of the stuff done compared to the best one.

[Veerappan]

Thanks for the article Michael.

It is nice to see the BSD kernel tested against Linux using the same userspace. Really lets you see how similar in performance the two really are (except when they're not). It also helps to illustrate how much of the difference is in the userspace tools, compiler versions, and the difference in any compilation flags used (as opposed to just kernel differences).

I can tell I'm not the only one who was surprised at the performance delta between BSD Userspace and Debian userspace when running the same kernel.