FreeBSD 8.0 Benchmarked Against Linux, OpenSolaris

[yogi_berra]

Open license incompatibility is totally against the spirit of open-source.

Of course with this logic GPL3 is against the "spirit of open-source" because it is not backwards compatible.

@ kraftman - What makes you think Oracle will change anything?

[kebabbert]

Oracle wants to earn money, which it does by restricting tech to it's products. I hope Oracle keeps everything from SUN open.

Regarding OpenSolaris wins some benchmarks here. That is no big deal, I couldnt care less. OpenSolaris is actually in alpha stage, not beta. Every two weeks the source from the development tree is checked out and released as a OpenSolaris build. Later, when all functionality finally has been added, SUN will release OpenSolaris in beta stage and intensive testing will take place. Then Solaris 11 will be released, rock stable, rock solid and fast. The fun thing is that OpenSolaris is actually quite stable as it is today, right from the development source tree. Wait until beta testing begins, then you will see some REAL stability.

Right now, OpenSolaris is not optimized at all. It is under heavy construction. Later, SUN will optimize OpenSolaris for speed. Then I would like to see OpenSolaris benched on machines with 64 CPUs or more. That is were Solaris strengths are; big scale computers. Not laptops. Solaris comes from server OS, tailored to big iron. Only now it has been directed to desktop and laptops.

For you guys stating that ZFS is the only good thing Solaris has, well you have not heard about DTrace, then. Many developers say that DTrace is THE killer feature of today. Several Firefox developers have switched to OpenSolaris, just because of DTrace. This DTrace will be heavily used for OpenSolaris optimizations, later.

[llama]

Summarizing some of the key packages found in each operating system, ... an eye-crossing amount of versions number

Here's what would be awesome: a version matrix:

                       kernel | filesystem | gcc | x.org | glibc (if applicable) | ...
FreeBSD 8.0
FreeBSD 7.2
OpenSolaris
...

It's pretty common to get to a benchmark result that surprises me, and I want to go check what versions of gcc were involved. Since I haven't memorized the paragraph of version numbers, I have to basically read it all again. If it was in a table, I could scan down just the column of the table I wanted to check.

And I second the suggestion to not say anything about a graph if you don't have anything useful to add. "oh look Fedora won again" is useless. We have to read all the text you write to avoid missing any interesting observations or explanations of why one score is higher, and it just slows us down to read stuff that isn't useful. It especially slows me down when one of those casual comments seems to be wrong (i.e. my intuition as to the root cause of the result differs from yours, for example :P ); it makes me stop and consider replying in the article... But then I don't bother, because it's usually something relatively minor.

High-school science report padding is probably the best description I've seen of the style. Other benchmark sites do this too, writing like it's a play-by-play commentary on a race, with one video card making up for earlier defeats by doing well on this benchmark, and garbage like that.

[avuton]

I know this benchmark and analysis probably takes long enough but I do think it would have been interesting to see win32/win64 in the mix somewhere. Is this a problem with porting the suite to use mingw?? ? Or is it just that performance is known to be so bad in Windows that it just doesn't make sense to from a benchmark POV?

[yotambien]

I know this benchmark and analysis probably takes long enough but I do think it would have been interesting to see win32/win64 in the mix somewhere. Is this a problem with porting the suite to use mingw?? ? Or is it just that performance is known to be so bad in Windows that it just doesn't make sense to from a benchmark POV?

Yes. Performance is so terribly bad in Windows that you would have to leave the benchmark running for weeks before completion. Not worth it, trust me.

[kraftman]

@ kraftman - What makes you think Oracle will change anything?

I saw some interesting article at lwn :>

[kraftman]

Again, can someone explain how to make OpenSolaris kernel run in 32bit mode? Last time, if I remember corectly, Freebsd won more benchmarks against OpenSolaris. If Solaris kernel ran in 64bit mode here it would be fun :>

@Kebbabert

You never give up :P

Btw. You know the answer, don't you?

[Duhorigh73]

The Linux NTFS project seems pretty stable as far as reading NTFS volumes, but write support is very limited You can change data of a file, but arent able to extend files or create new ones. There is some support for dynamic volumes, but again, its not "production" software.

What exactly is your reason for moving to Linux anyway?

[rhavenn]

Another item is that if they do default installs on single partitions on BSD then UFS normally doesn't install with softupdates enabled. Any "sane" admin would install a *nix box with multiple partitions for /, /tmp, /usr, /var, /home and possibly others anyway. Softupdates should speedup the file read/write tests and possibly others as well.

And no, turning softupdates on for the / is not what you want. You want your / to be the most stable in case the other filesystems have issues, so you can still boot to single user mode and recover them.

[kebabbert]

Again, can someone explain how to make OpenSolaris kernel run in 32bit mode? Last time, if I remember corectly, Freebsd won more benchmarks against OpenSolaris. If Solaris kernel ran in 64bit mode here it would be fun :>

@Kebbabert

You never give up :P

Btw. You know the answer, don't you?

I dont know how to make OpenSolaris run in 32bit mode. It chooses the correct version upon boot. If the cpu is 64 bit, then it boots in 64 bit mode. Solaris 32 bit version is not really good, Ive heard. It has been 64bit since ages, a long time ago. If the CPU is 64 bit, then Solaris should have booted in 64bit mode. Remember, there are not different Solaris versions of the kernel, depending on if the machine has many many CPUs, or few, or if it is a supercomputer or a netbook, or if it is 32bit or 64bit. It is the same install CD and the same kernel. This is true scalability. It scales from small netbooks up to whatever you wish, with the same kernel. No need to recompile or redesign or strip out code.



Regarding OpenSolaris winning benchmarks or not. As I told you, OpenSolaris is under heavy development and the focus is not performance, as of now. The focus is functionality, not stability, nor performance. Developers just add all sorts of functionality right now. And very often the functionality is buggy, this is true. Read the OpenSolaris forums, and you will see. It is buggy because it is alfa stage. Not even Beta. Things change pretty fast. In one build, opensolaris performance may suck, in the next build it is very very fast. And the build after that, the functionality is broken and will not work! This has happens all the time, and it is a pain. You have choose which build you want to use. This is true. Read the opensolaris forums and you will see I speak true. Some builds are buggy, others are better. This is because every other week, the source is checked out and a OpenSolaris build is released. Of course such builds are buggy, they are straight from the source development tree! But can compete with other OSes, still. Testament to good code quality. Try to check out code from another OS under construction, and build it, and try to bench it, see how stable/fast it is. And compare that to OpenSolaris builds. OpenSolaris will win hands down.

In my opinion, it is not really fair to compare something under construction to products that have left the beta stage. It is like comparing the FPS of a game under construction vs a fully patched and released game - not really fair? Just before release, the game developers switches focus to performance and raises the FPS a lot. Isn't this true? The same here. No one can expect a product in alfa stage to be optimized for speed.

Therefore, I dont really care of OpenSolaris performance right now. When it is released, I will care. Right now, performance changes from build to build (which all these Phoronix benches show, sometimes OpenSolaris gains performance, sometimes it loose). But OpenSolaris has the ability to become very fast when it is released later, and left this alfa stage.