Ubuntu vs. OpenSolaris vs. FreeBSD Benchmarks

[phoronix]

Phoronix: Ubuntu vs. OpenSolaris vs. FreeBSD Benchmarks

Over the past few weeks we have been providing several in-depth articles looking at the performance of Ubuntu Linux. We had begun by providing Ubuntu 7.04 to 8.10 benchmarks and had found the performance of this popular Linux distribution to become slower with time and that article was followed up with Mac OS X 10.5 vs. Ubuntu 8.10 benchmarks and other articles looking at the state of Ubuntu's performance. In this article, we are now comparing the 64-bit performance of Ubuntu 8.10 against the latest test releases of OpenSolaris 2008.11 and FreeBSD 7.1.

http://www.phoronix.com/vr.php?view=13149

[Sacha]

Conclusions:
OpenSolaris
In Java and filesystem related benchmarks, OpenSolaris outperformed the rest. The former due to Java (and Solaris) being owned by Sun and the latter due to OpenSolaris using the ZFS filesystem.

FreeBSD
Interestingly, FreeBSD did well (but not as well) in areas where OpenSolaris performed while Ubuntu did very poorly in these areas. FreeBSD is great for ray tracing!

Ubuntu
Ubuntu was marginally better at everything else (the majority of benchmarks) that was tested.


Question: These are all opensource so why isn't someone working at porting all these goodies over so they all work extra fast! I know people are trying to do ZFS. Licensing issues, yada yada. What about this awesome ray tracing power of FreeBSD?

[ethana2]

Question: These are all opensource so why isn't someone working at porting all these goodies over so they all work extra fast! I know people are trying to do ZFS. Licensing issues, yada yada. What about this awesome ray tracing power of FreeBSD?

FreeBSD doesn't have a built in ray-tracer, it's a matter of scheduling and stuff, and that's a very complex issue; at best we can learn from how BSD works, Linus isn't going to core a scheduler that's been nearing perfection for years just because of a benchmark.


I'd be fascinated to see Snow Leopard thrown in here once it comes out.

[kraftman]

@Sacha

One test won't tell you if system is better to do something then other.

---

@Michael

It looks you are deaf to people suggestions. I can understand that you wanted to make this benchmark compatible with previous one, but why not make one test extra with bonnie++ and larger file? Following to results of your benchmarks it looks like Mac OS beats other systems which are known of their very high performance. You know, it's really funny :> Even more funny are people who take those benchmarks serious.

Probably that is correct use of bonnie++ benchmark:

http://home.comcast.net/~jpiszcz/benchmark/allfs.html

[quintesse]

With Java and OpenSolaris being products of Sun Microsystems, it shouldn't be too surprising that the fastest Java performance was generally witnessed atop this Sun operating system.

Well, that could be the reason, but I suspect the fact that the Solaris system was running update 10 of Java 6 has something to do with this as well. Update 10 introduced a LOT of improvements over previous updates, better performance might be one of them.

[energyman]

it would nice to see a linux that is not cursed with ext3 ;)

btw, if you care about filesystem performance, read this;
http://bulk.fefe.de/lk2006/bench.html

in short, solaris lies, bsd sucks.

[sabriah]

Michael,

Thanks for an exciting roundup!


bonnie++ benchmark:

http://home.comcast.net/~jpiszcz/benchmark/allfs.html


The ZFS in the bonnie++ benchmark here may explain the reason why Solaris shined! It has very low cpu demands in many of the tests. Both Solaris and MacOS use ZFS.

Unfortunately, Linux cannot readily use ZFS bcause of its license, CDDL (http://en.wikipedia.org/wiki/CDDL):


In the words of Danese Cooper, who is no longer with Sun, one of the reasons for basing the CDDL on the Mozilla license was that the Mozilla license is GPL-incompatible. Cooper stated, at the 6th annual Debian conference, that the engineers who had written the Solaris kernel requested that the license of OpenSolaris be GPL-incompatible. "Mozilla was selected partially because it is GPL incompatible. That was part of the design when they released OpenSolaris. [...] the engineers who wrote Solaris [...] had some biases about how it should be released, and you have to respect that".

However, there is the FUSE project http://zfs-on-fuse.blogspot.com/ , which makes Linux run ZFS!

If this would be included in future tests one may see the importance of file system as such.

:)

[kraftman]

Michael,

The ZFS in the bonnie++ benchmark here may explain the reason why Solaris shined! It has very low cpu demands in many of the tests. Both Solaris and MacOS use ZFS.

Leopard doesn't use ZFS. It uses something which is just piece of crap - Drag wonderfully explained that in another thread. As far as I know Apple plans to use ZFS in future versions of Mac OS. There's Linux file system which uses very low CPU too - JFS, but its performance is probably lower than EXT3 etc.

[deanjo]

Leopard doesn't use ZFS. It uses something which is just piece of crap - Drag wonderfully explained that in another thread. As far as I know Apple plans to use ZFS in future versions of Mac OS. There's Linux file system which uses very low CPU too - JFS, but its performance is probably lower than EXT3 etc.

Leopard can use ZFS as a read only option right now. Snow Leopard will introduce R/W capability. Drag's arguments also were extremely outdated (some just plain out wrong). Many of his concerns were addressed in later versions of HFS+.

[mrq1]

Phoronix: Ubuntu vs. OpenSolaris vs. FreeBSD Benchmarks

virtualisation is coming.

it would be great to see a test of this 3
OS on virtualized hardware.

for example via KVM.
of course with the same virtual hardware and
the same amount of ram for every OS.

[sbryant]

Phoronix: Ubuntu vs. OpenSolaris vs. FreeBSD Benchmarks

Over the past few weeks we have been providing several in-depth articles looking at the performance of Ubuntu Linux. We had begun by providing Ubuntu 7.04 to 8.10 benchmarks and had found the performance of this popular Linux distribution to become slower with time and that article was followed up with Mac OS X 10.5 vs. Ubuntu 8.10 benchmarks and other articles looking at the state of Ubuntu's performance. In this article, we are now comparing the 64-bit performance of Ubuntu 8.10 against the latest test releases of OpenSolaris 2008.11 and FreeBSD 7.1.

http://www.phoronix.com/vr.php?view=13149
The introduction said you left things in their default state which might not be the best thing for a beta of FreeBSD. There is a strong possibility that it has debug options on which could impact performance.

I'm installing BETA2 currently (there's an RC2 out as well). So I'll post an update soon with the generic kernel configuration

[rivald]

The introduction said you left things in their default state which might not be the best thing for a beta of FreeBSD. There is a strong possibility that it has debug options on which could impact performance.

I'm installing BETA2 currently (there's an RC2 out as well). So I'll post an update soon with the generic kernel configuration

There's no doubt about it: FreeBSD runs with debugging turned on in all betas, and it's turned off in the RCs. It's certainly not uncommon to have debugging turned on in operating systems during the beta phases. I'm not sure why he chose 7.1beta2 instead of 7.0 release.

[kraftman]

There's no doubt about it: FreeBSD runs with debugging turned on in all betas, and it's turned off in the RCs. It's certainly not uncommon to have debugging turned on in operating systems during the beta phases. I'm not sure why he chose 7.1beta2 instead of 7.0 release.

Maybe because of scheduler? I don't think so if final release will perform noticeable better then beta. Btw. using default settings in all systems is stupid in my opinion. I bet that tweaked Linux kernel can perform ways better.

[sbryant]

Maybe because of scheduler? I don't think so if final release will perform noticeable better then beta. Btw. using default settings in all systems is stupid in my opinion. I bet that tweaked Linux kernel can perform ways better.

There are many things that affect performance, especially if there's more stuff to wade through. Think about it, allocating and setting memory to a certain value takes way from doing other things. Despite the scheduler, all that does is making sure it stays responsive, nothing can be done about the amount of time things require to complete. If it just allocates trash data, that's a lot less time then allocate, write.

On top of that if you have checks in the code for helping debug or generating a sensible core then ofcourse it's going to take up time. You should read up on what these debug options do.


Debug options (the big two are WITNESS and INVARIANTS):
http://www.freebsd.org/doc/en/books/developers-handbook/kerneldebug-options.html

[deanjo]

Should be noted that some distro's also run their Alpha's and Beta's and RC's as well with debugging turned on. It's not limited to BSD.

[ebird]

it would nice to see a linux that is not cursed with ext3 ;)

btw, if you care about filesystem performance, read this;
http://bulk.fefe.de/lk2006/bench.html

in short, solaris lies, bsd sucks.

I don't think so. The Linux kernel has currently a big problem with heavy io. There is an issue which in not really testable with the phoronix test suite. The desktop responsiveness is awful since 2.6.22. And it is not an ext3 issue. I have tried jfs and xfs.

[bugmenot]

it's important to reiterate that all three operating systems were left in their stock configurations and that no additional tweaking had occurred. The performance differences between EXT3, UFS, and ZFS are clear.

uh, yeah. Holy non-sequiturs batman, if you left the hardware configured with random, unknown, and different stock-settings for each system then you are in no way assured to learn *anything* about the performance differences of the filesystems.

you are only learning about how fast they decided to make the stock disk settings configuration.

--
the above link gives a much better picture, linked tester said he enabled the fastest mode available for each.

[pcfxer]

SWEET! FreeBSD beat two OSes with debugging options enabled! Tisk Tisk!

Now, how about Phoronix back off the version and install RELEASE or wait a bit and use 7.1 RELEASE...ORRR even better, recompile the kernel with a stock make.conf and comment out makeoptions DEBUG=-g.

[kraftman]

I don't think so. The Linux kernel has currently a big problem with heavy io. There is an issue which in not really testable with the phoronix test suite. The desktop responsiveness is awful since 2.6.22. And it is not an ext3 issue. I have tried jfs and xfs.

Maybe your hardware is a problem, because I don't notice any responsiveness issue related to Linux kernel. Do you believe that such regression wouldn't be noticed for years?

@pcfxer

Fanboys comming... Are you dumb or something? Benchmark shows that Linux beat your FreeBSD... Idiotic attempt to make a flame war. If you're interested I can show you a benchmark in which Linux kernel 2.6.22 and newer one kick your lovely FreeBSD 7 or 7.1.xx.

And you registered to write such a bullshit? xd

EDIT:

@Bugmenot

I missed your post before. You're completely right!

[energyman]

FreeBSD had to compete with dead slow Ubuntu 8.10 (aka slow edition) and still lost.

What would happen if they had to compete with something fast?
It would be a massacre, that for sure.
And heavy IO? That is freebse's weakest points:
http://bulk.fefe.de/lk2006/bench.html

[pcfxer]

Maybe your hardware is a problem, because I don't notice any responsiveness issue related to Linux kernel. Do you believe that such regression wouldn't be noticed for years?

@pcfxer

Fanboys comming... Are you dumb or something? Benchmark shows that Linux beat your FreeBSD... Idiotic attempt to make a flame war. If you're interested I can show you a benchmark in which Linux kernel 2.6.22 and newer one kick your lovely FreeBSD 7 or 7.1.xx.

And you registered to write such a bullshit? xd

EDIT:

@Bugmenot

I missed your post before. You're completely right!

What? You have no idea who I am and I have no idea who you are. I registered because I've enjoyed the lot of phoronix articles, however, this one just seemed like it had a terrific idea but an inconclusive result.

Also, anyone who knows anything about gcc, knows that -g can affect performance, particularly with data structures like those used in DBs. Run a B-Tree in debug and "release" mode and you'll see what I mean.

Peace,
pcfxer

[curaga]

There's Linux file system which uses very low CPU too - JFS, but its performance is probably lower than EXT3 etc.Actually JFS beats ext3 in almost all tests I've seen. It's a stable performer, unlike ext3 and XFS that are good in one thing but bad in something else.

[energyman]

emm, in a 'fair' test jfs is beaten by everyone. Oh, and xfs? It is well known that its defaults suck. In its standard configuration it is dead slow - but with just a little bit of tweaking it does become A LOT faster. And I am not a xfs fan...

[kraftman]

What? You have no idea who I am and I have no idea who you are. I registered because I've enjoyed the lot of phoronix articles...

Also, anyone who knows anything about gcc, knows that -g can affect performance, particularly with data structures like those used in DBs. Run a B-Tree in debug and "release" mode and you'll see what I mean.

Peace,
pcfxer


I know what you mean. I just replied in such tone, because I thought that your previous post was attempt to make flame (I shouldn't reply at all ;))

this one just seemed like it had a terrific idea but an inconclusive result.

Of course, this and previous one, but what can we do?

[andrnils]

Why not throw in a test with FreeBSD installed on ZFS. There is native support for it since 7.0. I also agree that doing performance tests on betas and release candidates aren't that infomative. So a reiteration on 7.1 RELEASE and 2008.11 when they release that might change things.

I would also love to see a test of how they fair power management-wise.

[kraftman]

Why not throw in a test with FreeBSD installed on ZFS. There is native support for it since 7.0. I also agree that doing performance tests on betas and release candidates aren't that infomative. So a reiteration on 7.1 RELEASE and 2008.11 when they release that might change things.

I would also love to see a test of how they fair power management-wise.

As far as I know ZFS port in FreeBSD is in terrible state (or was). I can't imagine why someone didn't use stable version of FreeBSD in tests? In my opinion benchmarked systems should be tune for the best performance like in professional benchmarks. Default settings can be very different - Ubuntu is desktop distro and FreeBSD is probably tuned for servers etc.

[kebabbert]

it would nice to see a linux that is not cursed with ext3 ;)

btw, if you care about filesystem performance, read this;
http://bulk.fefe.de/lk2006/bench.html

in short, solaris lies, bsd sucks.
If you learned to read an article well, you maybe wouldnt draw wrong conclusions too quick.


In the article, they tried 2 old OpenSolaris distros v0.56 by some random people. They didnt try the real SUN Solaris. So infering that "solaris does lie" is totally wrong. Maybe you could infer that "2 opensolaris distros v0.67 lies" - but, did the people behind the distros promise anything? No. So, wrong conclusion again.


And remember that it is well known that Solaris does not shine with one or 2 CPUs. Solaris shines when you have lots and lots of CPUs in large machines. Then Linux sucks, there are several links about Linux bad scaling when using many CPUs.


Sure, there are Linux clusters with many CPUs, but they are tailored to a specific task and can do nothing else. The clusters suck for ordinary OS usage. They can only crunch numbers and nothing else. Everything is ripped out from the Linuxkernel; drivers for webcams, etc.


Linux uses a naive approach that works good for desktops and small computers. You do know that Linux comes from the desktop and now tries to become a server OS? Solaris comes from the Server halls and now tries to become desktop. To use lots of CPUs efficiently, you must use a complex and heavy design that takes many years to develop - and that machinery does work best in large servers. Linux would suck in one of these, because it scales to bad. Bad threading model, etc. There are lots of links, if you google a bit on that. But for simple tasks in large clusters, Linux is good. Easy to modify. Solaris kernel is difficult to understand, Solaris is from 1982, but was called SunOS then. It is very mature and rock solid. Complex. Mature.

[andrnils]

As far as I know ZFS port in FreeBSD is in terrible state (or was).
I'd say was. There has recently been a big ZFS related commit to -CURRENT. Some more info here (http://ivoras.sharanet.org/blog/tree/2008-11-17.aaaaand-its-there!-the-big-zfs-update!.html)

I can't imagine why someone didn't use stable version of FreeBSD in tests? In my opinion benchmarked systems should be tune for the best performance like in professional benchmarks. Default settings can be very different - Ubuntu is desktop distro and FreeBSD is probably tuned for servers etc.

No, it's a bit strange...

[energyman]

and there are many, many links showing linux scaling very well with lots of CPUs.

Hmm...

SunOS has nothing to do with Solaris. When they changed the name they changed the basis of their kernel too. 'Original' solaris is also known for tons of broken crap. Broken tar, broken find, etc pp.

You could also argue, that Phoronix used the slowest linux out there, instead of something fast.

[rivald]

FreeBSD had to compete with dead slow Ubuntu 8.10 (aka slow edition) and still lost.

What would happen if they had to compete with something fast?
It would be a massacre, that for sure.
And heavy IO? That is freebse's weakest points:
http://bulk.fefe.de/lk2006/bench.html


Nice, a benchmark from 2006. I seem to recall a benchmark from 2000 where windows 2000 blew away a heavily tuned Redhat. Perhaps we can drag that up and make the argument that windows blows linux away? If old benchmarks are okay, maybe we should use them? Perhaps the benchmarks should have included deleting the files, too? Looks like the 2006 benchmarks weren't so favorable to linux.

I think they should rerun it with OpenSolaris, FreeBSD, and Ubuntu, all with debugging turned on. I'm sure the whole point of the benchmark was to show linux as better than everything else, but really... at least take real releases and not betas.

I don't understand why linux fans try so hard.

[energyman]

it was from 2006, yes. But hey, since then nothing really changed. The state of fs in *BSD still sucks. No changes there. The pattern is pretty simple. Over the years the *BSD fanboys are hyping some stuff (like softupdates, or their pretty new scheduler), just to get blown out of the water as soon, as benchmarks by non-*bsd devs/fanboys are coming in.

Some things never change.

[rivald]

heh heh... Yes, nothing has changed.

If we're going to dig up old junk on the web:

http://people.freebsd.org/~murray/bsd_flier.html

That really brings me back... mounting filesystem async in production. Great idea. Performance is king, after all.

If you're unfortunate enough to make a living at systems/network administration, you'll come to realize how much each OS sucks in its own special way. You'll shout curses at 3:00 in the morning at microsoft, linux developers, sun, freebsd developers, openbsd developers, apple, cisco, netgear, hp, dell, sgi, checkpoint, and the rest of them.

[kraftman]

Nice, a benchmark from 2006. I seem to recall a benchmark from 2000 where windows 2000 blew away a heavily tuned Redhat. Perhaps we can drag that up and make the argument that windows blows linux away? If old benchmarks are okay, maybe we should use them? Perhaps the benchmarks should have included deleting the files, too? Looks like the 2006 benchmarks weren't so favorable to linux.

I think they should rerun it with OpenSolaris, FreeBSD, and Ubuntu, all with debugging turned on.

I don't understand why linux fans try so hard.

I don't understand why you can't see that FreeBSD fan started. I can show you that Linux just outperform your favorable system:

http://new.isc.org/proj/dnsperf/OStest.html

Linux 2.6.20(!) kicked ass your FreeBSD-7-CURRENT 200708...

I'm sure the whole point of the benchmark was to show linux as better than everything else, but really... at least take real releases and not betas.

Bulshit... You didn't see previous one. It's something common that freebsd fanboys usually start flames.

EDIT:

Benchmarks made by bsd devs are REALLY objective XD. I fell from my chair when I saw their last revelation - they said that FreeBSD 7 is 15% faster in MySQL (or PostGreSQL), then I searched for some benchmarks and even Linux 2.6.22 was faster.

@energyman

Exactly.

[kebabbert]

and there are many, many links showing linux scaling very well with lots of CPUs.

Hmm...

SunOS has nothing to do with Solaris. When they changed the name they changed the basis of their kernel too. 'Original' solaris is also known for tons of broken crap. Broken tar, broken find, etc pp.

You could also argue, that Phoronix used the slowest linux out there, instead of something fast.
A quick googling showed some examples of bad scaling:

http://blogs.zdnet.com/BTL/?p=8769
"And if I’m not correct, you don’t currently see the level of geometric performance increases on Linux above 16 cores like you do with UNIX. The maturity in the Linux kernel for this level of enterprise performance and stability on this type of hardware just isn’t there yet."


"Gracenote, which provides a media recognition and metadata service for MP3 users (the CDDB database familiar to iTunes users), agrees. "We found the threading model in Linux was problematic. You get to a certain number of concurrent threads and the OS just slows way down," says Matthew Leeds, vice president of operations at Gracenote. Solaris "just works for us.""




But bad scaling is of course to be expected. Linus Torvalds says that Linux evolves just as nature; evolution. Whenever something is broken in Linux he will redesign it into something better. Just as evolution.

To me that is less optimal. How can something be good if you totally redesign it from scratch all the time? v1.0 is never good. You have to polish it for a long time before it is stable and good. Just like Windows, they rewrite everything and first at SP2 windows becomes quite stable. The first iterations suck badly. Dont you agree? And, the constant redesigning is also one of the reasons Linux is never back compatible. There are also lots of links on this. And, also the reason behind the bad coding and all the errors and bugs in the Linux kernel, that Linux kernel dev Andrew Morton speaks of:
http://lwn.net/Articles/285088/
Now Linux is 6.4 million lines of code. It must be impossible to keep all that monolithic Linux kernel with 6.4 million lines of code, bugg free. How can one KERNEL be that big? If you count the new lines, comments etc, Linux kernel is >10 million lines of code. I remember the whole Windows NT was 10 million lines of code. Bloat? Ridicolous. You know, the less code, the better. Right?

Solaris first revision, SunOS, sucked and at the next attempt SUN knew how to do it right -> Solaris. Linux is at it first revision now, and it sucks when stressed enough, because of all the bugs that Andrew talks of. It is a desktop OS, not a Server OS. Here you see some quick googled links what what happens when you stress Linux. Linux is stable at up to 60% or so utilisation, and Solaris stable up to 100% just as mainframes.

http://www.enterprisestorageforum.com/sans/features/article.php/3745996

http://lethargy.org/~jesus/archives/77-Choosing-Solaris-10-over-Linux.html

[rivald]

The funny thing is that this benchmark reminds me why ZFS blows away the other filesystems. What the benchmark doesn't show is that ZFS is more reliable.

If you've used ZFS professionally, you'd realize that was also the case... it's better than LVM, Sun's disksuite and the BSD equivalents (probally gvinum on FreeBSD, and raidframe on OpenBSD and NetBSD.)

I'd say ZFS is the real winner here... it's particularly impressive considering how slow Solaris is at certain operations (if you've administered it professionally, you'll know what I mean) - and this is even an RC. Slowlaris no more!

[kraftman]

The funny thing is that this benchmark reminds me why ZFS blows away the other filesystems. What the benchmark doesn't show is that ZFS is more reliable.

If you've used ZFS professionally, you'd realize that was also the case... it's better than LVM, Sun's disksuite and the BSD equivalents (probally gvinum on FreeBSD, and raidframe on OpenBSD and NetBSD.)

I'd say ZFS is the real winner here... it's particularly impressive considering how slow Solaris is at certain operations (if you've administered it professionally, you'll know what I mean) - and this is even an RC. Slowlaris no more!

The same situation can be with Phoronix benchmarks. If something is slower it can be more reliable etc. but it's not a rule.

[rivald]

True. Benchmarks aren't necessarily relevant, anyway. I'm sure there are MS benchmarks out there showing Windows 2008 as being faster than everything else.

For any professional work, I prefer reliable over fast. That's what I like about ZFS (and it's still fast.) I've used AFS in production environments, and it might be the best of all, in some ways, but it's way more of a hassle to manage.

[kraftman]

@kebabbert

You're repeating some myths introduced by some group of people. There is known problem with "bad scalling" on Linux just, because some idiots test it with broken/bad/not Linux friendly library. If you replace it scaling is great.

...You know, the less code, the better. Right?

Total bullshit. What additional features and drivers have to core Linux kernel parts? And on Linux works probably far more people then on other operating systems.

@rivald

ZFS is in many aspects probably the best file system right now.

I'm sure there are MS benchmarks out there showing Windows 2008 as being faster than everything else.

That's for sure :)

[energyman]

BLABLA

just look at the Top 500 supercomputers. Huge machines with thousands of CPUs.

And now ask yourself 'why are most of them using linux'?
And then ask yourself 'why is nobody using Solaris'?

[energyman]

uh, I was wrong, there is one(!) Supercomputer using Opensolaris (not even solaris... )
http://www.top500.org/stats/list/32/os

Open Solaris 1 0.20 % 18540 20643 2048
compares nicely with the 454 or so Linux using supercomputers...

[jmartin]

> And remember that it is well known that Solaris does not shine with
> one or 2 CPUs.

I don't agree. If you have a specific case where Solaris is not
performing well on one or two CPUs, please file a bug at
http://bugs.opensolaris.org.

It is possible some of the performance differences are due to the
gcc version being used as Solaris bundles gcc 3.4.3 and other distros
may bundle 4.x, but it is much more likely due to the default ABI
used by the bundled gcc. "gcc -O" on Solaris will default to ia32/x87,
whereas on the other "64 bit" distros tested it will default to amd64.
The performance difference can be seen in the two Byte Computational
benchmarks on page 7 where Solaris appears to lag: Dhrystone 2
(./Run dhry2) and Floating-Point Arithmetic (./Run float). These
tests are compiled with "gcc -O" which produces ia32/x87 code.
When adding "-m64" which puts Solaris on par with the other distros,
the performance jumps quite a bit. Measured on a Intel QX6700,
dhry2 goes from 9307771.4 to 13421763.5 and float goes from
707932.5 to 1477185.6.

The ABI used can make a big difference. Solaris allows you to
choose either, but the default for the bundled gcc is still the
slower ia32/x87.

[kebabbert]

KRAFTMAN, ENERGYMAN

As I said earlier, Linux kernel is simple and uses an naive approach. It is easy to modify, whereas the Solaris kernel is complex and mature. You know that an complex construction is more difficult to modify, dont you? And as I said, Linux is found on large clusters because they only do one thing: number crunching and nothing else. It is easy to rip the Linux kernel apart to do that, due to it's naive approach.

For Linux bad scaling or not, there are lots of links on the internet saying that they have problems with Linux bad scaling, and bad code in it's buggy kernel. Or do you disagree with Linux kernel developer Andrew Morton? No matter what you say, these links on bad Linux scaling will be there. They will not disappear. So if Linux scales so well, surely those links about bad scaling would not exist. On the other hand, I have found NO links about Solaris scaling bad. None. The question is if Linux scales badly (according some companies), not if Solaris scales badly, because it does not.

Of course you could rip the Solaris kernel apart to do number crunching, if you only knew it's elaborate and complicated structure. But that is not easy. Linux is good enough for that. But for ordinary OS usage, lots of links says that Linux scales bad.

And, "the less the code the better" - is Bull shit??? Erhm. Well, maybe you dont know that, but if you have much code, then there will be lots of potential bugs. It is easier to find bugs in less code than lots of code. And as Andrew Morton says, the Linux kernel is riddled with bugs.




But the good thing is that Linux and Solaris are quite similar, theyre both Unix-like. I started with Linux, but found back then, that Linux was quite immature, developed by some finnish teenager. And everything I learnt on Linux, I could immediately use on Solaris. Theyre both "Unix". The step between Windows and Plan9 would be huge. But for me, theyre quite similar. And if I get bored on Solaris, I just switch back to Linux - and everything Ive learnt on Solaris, I have with me to Linux. No loss of learning, nor time. Easy to switch back and forth, both OSes has gcc, gnu, vim/emacs, eclipse, KDE/gnome, vlc player, etc. No big difference. And there is also an Solaris distro which is similar to fedora (?) but with the Solaris kernel, everything else is almost the same.

Solaris and Linux share more together, than they differ. Easy to switch between them. No loss of time or learning.

[energyman]

kebabbert, it is ok. We realize it. You are a Solaris fanboy and no matter what, Solaris will be the greatest kernel for everything from your POV.

But your POV and reality don't intersect.
If Linux scales badly, why is it found from embedded controllers (where Solaris does not even run) to 512cpu/node machines?
Must be the bad scaling.
And why are Solaris,hpux,aix installations killed left and right?
Again, must be the bad scaling.

[kraftman]

@kebabbert

For Linux bad scaling or not, there are lots of links on the internet saying that they have problems with Linux bad scaling, and bad code in it's buggy kernel.

Solaris is bugfree? There are lot of links saying that Solaris suck on desktop and on servers when compared to Linux.

Your theories are amazing :). If I find more time I will repeat you more extensively.

@energyman,

Don't even worry about bad scaling, because it's total bullshit.

[kebabbert]

I dont really get it guys. I am trying to say that because Linux is available for large clusters, doesnt mean that Linux scales well. It only means that Linux is simple to tailor to that specific purpose. Those large clusters do not run ordinary Linux kernels. For instance, Ive read that Google are using heavily modified Linux. Do you really think that drivers for web cams are included in Googles Linux cluster, do you think it is commodity Linux? Google has lots of good Kernel developers, and theyve also developed their file system. If you think that those large clusters do ordinary OS usage, then you are wrong. They do specific task. Must I say this again?

For instance, Linux scaling on 64 CPUs:
http://kernelnewbies.org/Linux_2_6_27

Solaris has done that since v2.5.1 on E10k server. Now Solaris is v5.10. Seriously guys, Linux is a young kernel and it can in no way get the maturity as Solaris kernel has. It takes several tries and decades. SunOS was the first try, but SUN redesigned it and renamed it as Solaris later, only when they had the experience to come up with Solaris. A teenager couldnt do this. Dont you understand? Linus is always redesigning everything, a sign of bad design. Everybody knows that SUN has excellent engineers; unique ZFS, unique DTrace, unique Niagara CPU, etc. If they can not match a teenager kernel, then SUN deserves to die. Really.

And also, Linux is not compatible from release to release because of changing ABIs. Bad DESIGN. On some major Linux distros, they live 6 months, and then you have to upgrade or you loose support, and compatibility. That is NOT enterprise. SUN guarantees binary backward compatibility way back to Solaris v2.6. That is Enterprise.

Maybe you missed what the gurus Brian Kernighan, Dennis Ritchie etc said about the Linux code? That is was naive and flawed. Also, Andrew Morton concurs that the Linux kernel deteriotes:
http://lwn.net/Articles/285088/



Linux is buggy but Solaris is stable (same hardware):
http://lethargy.org/~jesus/archives/77-Choosing-Solaris-10-over-Linux.html


Solaris delivers 36% higher performance than Linux says CIO Philadelphia Stock Exchange:
http://www.computerworld.com/hardwaretopics/hardware/story/0,10801,96191p2,00.html


Linux sucks big time as a file server:
http://www.enterprisestorageforum.com/sans/features/article.php/3745996



Linux company hits the boundaries and are forced to switch to Solaris:
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1286507,00.html




As long as I see links similar to these everywhere on the internet, I will continue to be a Solaris fanboy. But when I see links that Linux is better than Solaris I will switch back to Linux. I never see such links though. They always talk about cost, and no vendor Lock in. That is the reason they switch to Linux. Not because of Solaris didnt perform. Ah yes, I remember an article where a company switched to Linux and got higher performance. But, when you study that article, they threw out 800 old solaris 8 servers for 2400 modern x86 Linux servers. I would be seriously surprised if they didnt got higher performance. If they had switched to Solaris, they maybe would have got 36% higher performance than Linux.

I always support the best technology. For me it doesnt matter who wins, both are Unix. I dont have to relearn. My learning time is not wasted. They are similar.

Actually I am becoming interested in Plan9. Seems awesome tech. I am a technology geek. Doesnt matter which OS wins. Us all will reap the fruits! :)

[energyman]

have you even read your links?

Because it does not look like you did.
From the kernelnewbies article:
2.6.27, thanks to some rules on how the page cache can be used and the usage of RCU, the page cache will be able to do lookups (ie., "read" the page cache) without needing to take the mapping lock, and hence improving scalability. But it will only be noticeable on systems with lots of cpus (page fault speedup of 250x on a 64 way system have been measured).

that doesn't mean that linux didn't scale to 64 or beyond. It means that the new code has a 250x speedup on 64way sytems when it comes to page faults.

After that I didn't even bother to read the rest. Because I am pretty sure you didn't either.

[kraftman]

As I said earlier, Linux kernel is simple and uses an naive approach. It is easy to modify, whereas the Solaris kernel is complex and mature. You know that an complex construction is more difficult to modify, dont you? And as I said, Linux is found on large clusters because they only do one thing: number crunching and nothing else. It is easy to rip the Linux kernel apart to do that, due to it's naive approach.

In my opinion naive approach is what you call complex and mature. It's so stupid to keep with old crap then to make new, better design. Some day there will be nothing left then to rewrite some parts of your favorite system (maybe it's just happening, who knows?). You can say that DOS is mature, so why not just polish it then make something better? And simple is better. As you said Linux kernel is more simple.

...there are lots of links on the internet saying that they have problems with Linux bad scaling, and bad code in it's buggy kernel. Or do you disagree with Linux kernel developer Andrew Morton? No matter what you say, these links on bad Linux scaling will be there. They will not disappear. So if Linux scales so well, surely those links about bad scaling would not exist. On the other hand, I have found NO links about Solaris scaling bad. None. The question is if Linux scales badly (according some companies), not if Solaris scales badly, because it does not.

It depends on who is testing. As I mentioned before some idiots don't know how to properly setup Linux system for such benchmarks and that's why those links exist (other ...people are basing on them).

Of course you could rip the Solaris kernel apart to do number crunching, if you only knew it's elaborate and complicated structure. But that is not easy. Linux is good enough for that. But for ordinary OS usage, lots of links says that Linux scales bad.

Stop reading bullshit. I saw great test some time before. Bsd user (that's why it's great benchmark, because it wasn't made by Linux fanboy etc.) benchmarked Linux and FreeBSD performance in MySQL. First time Linux scaled badly, but guy replaced one library and everything was ok. I'll give you link if I find.

And, "the less the code the better" - is Bull shit??? Erhm. Well, maybe you dont know that, but if you have much code, then there will be lots of potential bugs. It is easier to find bugs in less code than lots of code. And as Andrew Morton says, the Linux kernel is riddled with bugs.

Nope. I said that bullshit is what you said in previous post. On Linux works much more people then on Solaris, so they can easily find potential bugs. Btw. you just use some part of Linux kernel don't you? Devs pay great attention to core Linux kernel parts. You don't use many drivers and features which are in the kernel and can be potentially buggy.

I dont really get it guys. I am trying to say that because Linux is available for large clusters, doesnt mean that Linux scales well. It only means that Linux is simple to tailor to that specific purpose. Those large clusters do not run ordinary Linux kernels. For instance, Ive read that Google are using heavily modified Linux. Do you really think that drivers for web cams are included in Googles Linux cluster, do you think it is commodity Linux? Google has lots of good Kernel developers, and theyve also developed their file system. If you think that those large clusters do ordinary OS usage, then you are wrong. They do specific task. Must I say this again?

I said you before about scaling? Must I repeat? :>



Solaris has done that since v2.5.1 on E10k server. Now Solaris is v5.10. Seriously guys, Linux is a young kernel and it can in no way get the maturity as Solaris kernel has. It takes several tries and decades. SunOS was the first try, but SUN redesigned it and renamed it as Solaris later, only when they had the experience to come up with Solaris. A teenager couldnt do this. Dont you understand? Linus is always redesigning everything, a sign of bad design. Everybody knows that SUN has excellent engineers; unique ZFS, unique DTrace, unique Niagara CPU, etc. If they can not match a teenager kernel, then SUN deserves to die. Really.

Energy man already answered you. Everybody knows that Solaris is loosing it's market share. Only ZFS and DTrace keep it still alive.

SunOS was the first try, but SUN redesigned it and renamed it as Solaris later, only when they had the experience to come up with Solaris.

You said that redesigning is bad.

And also, Linux is not compatible from release to release because of changing ABIs. Bad DESIGN. On some major Linux distros, they live 6 months, and then you have to upgrade or you loose support, and compatibility. That is NOT enterprise. SUN guarantees binary backward compatibility way back to Solaris v2.6. That is Enterprise.

There are companies which gave you support for years. Linux is not compatible with what?

Maybe you missed what the gurus Brian Kernighan, Dennis Ritchie etc said about the Linux code? That is was naive and flawed. Also, Andrew Morton concurs that the Linux kernel deteriotes:
http://lwn.net/Articles/285088/

What gurus? Don't base your suggestions on such idiotic opinions. Find out yourself. And Adrew was talking about -mm tree. I'd love to hear objective opinions other system devs.



Linux is buggy but Solaris is stable (same hardware)

Solaris is buggy, every system is buggy and Linux is stable. Guess what system has highest uptime? :>


As long as I see links similar to these everywhere on the internet, I will continue to be a Solaris fanboy. But when I see links that Linux is better than Solaris I will switch back to Linux. I never see such links though. They always talk about cost, and no vendor Lock in. That is the reason they switch to Linux. Not because of Solaris didnt perform. Ah yes, I remember an article where a company switched to Linux and got higher performance. But, when you study that article, they threw out 800 old solaris 8 servers for 2400 modern x86 Linux servers. I would be seriously surprised if they didnt got higher performance. If they had switched to Solaris, they maybe would have got 36% higher performance than Linux.

I always support the best technology. For me it doesnt matter who wins, both are Unix. I dont have to relearn. My learning time is not wasted. They are similar.

Actually I am becoming interested in Plan9. Seems awesome tech. I am a technology geek. Doesnt matter which OS wins. Us all will reap the fruits!

I just suggest you to find some more objective benchmarks and to replace that slow crap to Linux. I never saw Solaris faster then Linux. You can even feel it yourself. Try them on desktop. Look for DNS, MySQL tests etc.

EDIT:

And you're just attacking Linux. What it gives you? Psychical comfort?

[kebabbert]

Kraftman,

You know, it would be nice if you backed up your statements with some links? So far, your statements have been about your opinion with no hard facts. How you wish things would be. To me, opionions doesnt really matter. As long as I see hard links from companies complaining about Linux bad scaling, beeing unstable, etc - your opinions doesnt really matter. Ive presented links.

Seriously, I support the best technology and if you can present evidence that Linux is better I will switch back to Linux. I am a tech geek. This far, everywhere Solaris and Linux is compared, Solaris is always the most stable, has higher performance, etc on the internet.

It doesnt really matter if Solaris is dying or not to me, I only use the best technology. Why use inferior, simpler technology? I could use Windows instead. But it seems that Solaris is gaining more and more ground actually. That is maybe the reason why Linux people always attack Solaris. "Is solaris on it's death bed?", "Solaris should die", etc. I wonder why they do that. Does it give them psychic comfort? But hey, they attack everyone else too; "openbsd developers are masturbating monkeys" etc

In concluding, I would like to say it's been nice to read your opinions. But please present some facts instead.






Energyman,
Nice that youve read at least one of my links. That link you cite, shows that Linux had really bad scaling and now it is catching up. In other words, that link is a testimony that Linux were 250 times slower earlier on 64 cpus. You dont see a contradiction here? You state that Linux scales well, but it was 250 times slower than it should have been. To me, thats a sign of bad design. But I understand if you dont agree with that.

(come on, 250 times slower??? how could Linux be so bad in that aspect???)

[kraftman]

Kraftman,

You know, it would be nice if you backed up your statements with some links? So far, your statements have been about your opinion with no hard facts. How you wish things would be. To me, opionions doesnt really matter. As long as I see hard links from companies complaining about Linux bad scaling, beeing unstable, etc - your opinions doesnt really matter. Ive presented links.

You backed up your statements only on such tales of mystical links? Linux bad scaling and unstable. Do you have personal experience with this? What companies? Sun Microsystems? Oh, maybe Google or Amazon. Wait, hundreds of porn sites. Which of them uses Solaris?

Seriously, I support the best technology and if you can present evidence that Linux is better I will switch back to Linux. I am a tech geek. This far, everywhere Solaris and Linux is compared, Solaris is always the most stable, has higher performance, etc on the internet.

I saw something different, but it doesn't matter. You are always the smartest, the coolest and you know always everything when compared to others. Better stick with Solaris, seriously.

It doesnt really matter if Solaris is dying or not to me, I only use the best technology. Why use inferior, simpler technology? I could use Windows instead. But it seems that Solaris is gaining more and more ground actually. That is maybe the reason why Linux people always attack Solaris. "Is solaris on it's death bed?", "Solaris should die", etc. I wonder why they do that. Does it give them psychic comfort? But hey, they attack everyone else too; "openbsd developers are masturbating monkeys" etc

If you consider that I meant Windows when I said about simplicity I recommend you to use PS3 - it's really simple. Why do you turn everything inside out? You attacked Linux here.

Nice that youve read at least one of my links. That link you cite, shows that Linux had really bad scaling and now it is catching up. In other words, that link is a testimony that Linux were 250 times slower earlier on 64 cpus. You dont see a contradiction here? You state that Linux scales well, but it was 250 times slower than it should have been. To me, thats a sign of bad design. But I understand if you dont agree with that.

(come on, 250 times slower??? how could Linux be so bad in that aspect???)

Maybe someone who did previous tests was 250 times dumber? Or Linux was 250 times slower then new Linux, but still faster then Solaris?

[energyman]

you provided some links you didn't read yourself.
Then you provided some pro-Solaris success stories. But if you look at Redhat's or Novell's sites you will see success stories the other way round en masse.

There are two very simple facts:
a) UNIX (Solaris, HP-UX, AIX) is loosing marketshare to Linux fast.
b) The Top 500 supercomputers are dominated by linux. Second place with 400 installations less, AIX. Solaris. 1. Some years ago, Solaris was the dominator.
c) yes R&K critized Linux. But they critized a lot over the years.

[kebabbert]

KRAFTMAN,

My links are not from SUN website, they are from other independent web sites. Ive shown you several links about bad scaling and bad code Linux has. One such link was from a Linux kernel developer Andrew Morton himself, and another link was from a linux site, stating that Linux was 250 times slower on 64 cpus. But I understand if you think my links are retarded and doesnt count. It is ok if you think I am a Solaris fanatic with no evidence to back up my preference for Solaris.



I think it is interesting that you state that you "I saw something different [about Solaris being faster than Linux], but it doesn't matter." How did you, and when did you compare Solaris to Linux? I myself ran Linux for several years, and have now switched to Solaris. Maybe I have more experience than you have, of both OSes?



Anyway, Linux never let me down.Everything I wanted to do, Linux did. You know, I dont have a massive computing cluster at home to stress Linux with. For a single person Linux will do fine. The problem is that it doesnt cut it for big loads, as you can see from some independent company blogs Ive posted. So what happens if I know Linux, and then my company grows and we have to switch to Solaris? Then I am already familiar to Solaris! :)



But actually, it doesnt really matter. If Solaris dies, I just switch back to Linux. Both are "Unix". And I will be a better Unix admin than you, because Ive had experience from two systems. It's like when you program; if you know one programming language, or if you know two - then you will learn new techniques and methods which gives you a better understanding of programming in general. The gurus says that a good programmer should now several programming languages; C, Java, lisp, etc to broaden the knowledge.




Seriously, if Linux were better I would switch back. I mean it. But as of now, Solaris is simply the best OS out there, in my opinion. But if I see links and articles stating otherwise, I will switch again. Unix or Unix, same-same but different. All my knowledge is not wasted. I have learnt Unix and can use it on Linux or Solaris. gnu is the same on both, so is Vi/emacs, gcc, eclipse, X11, Java, etc. Please provide some links saying that Solaris is unstable and scales badly - in comparison with Linux.



I love the fact that one company migrated 251 Dell 2950 Linux servers each having 2 cpus, that ran 700 instances of MySQL down to... 24 SUN Niagara T5440 Solaris servers! Wow. That's really cool tech! I admire the best tech. Be it Unix or Unix. Doesnt matter.
http://blogs.sun.com/bmseer/entry/mysql_consolidation_on_sun_sparc

I also like that 3 IBM AIX servers with 12 Power6 CPUs at 4.7 GHz got 7000 SIEBEL benchmarks. Whereas one SUN T5440 machine with 4 Niagara 1.4 GHz CPUs gets 14000 SIEBEL benchmarks. IBM had in total 56.4 GHz worth of cpu and got 7000 SIEBEL. SUN had in total 5.6 GHz and got 14000 SIEBEL. Now, THAT is cool! Dont you think that? You dont admire cool ground breaking tech? Here are collected links to Oracle web site with the formal papers with benchmarks:
http://blogs.sun.com/mandalika/entry/siebel_8_0_on_sun






ENERGYMAN,
The links Ive provided earlier are not from SUN site. They are from independent sites. If I need an opinion if Solaris is dying, I will surely not ask some Linux CEO that talks in his own favour.

1. So what? If Solaris dies, I switch back to Linux. But, SUN niagara servers is selling for $1bn USD and it increases 80% each 4 month period. There are lots of smaller Linux companies that get fed up with all the Linux hassle and instability and turns to Solaris. As you can see from my links Ive posted.

2. Cool. But as I said, that is not commodity Linux. It is easy to rip out everything from Linux and tailor it for one purpose. That could also be done with Solaris, but it is more difficult. The Solaris kernel is very elaborate and complicated. And, Solaris scales better. It is not 250 times slower on 64 cpus. (Come on, if that is not bad scaling, then when do you see bad scaling?)

3. Wow. So when someone critize Linux, it is not OK? Linux people can rightly attack Solaris and everyone else, but Linux should not accept any critiscm? Hmm.. What is that called? Cant remember the word...

[energyman]

Niagara.. you mentioned 'numbercrunshing' earlier. Think about it. And think about the fact, that no big iron uses niagara... it is good at doing lots of very simple stuff in parallel. Sadly not everything is simple.

[kraftman]

@kebabbert

What are you trying to proof? You're fanboy in my opinion. You're repeating same bullshit all the time and if you know such revelations as you already said post a new thread and Solaris fanboys will feel there like in Heaven. I don't believe that you used Linux on desktop, switched to Solaris and now you say that Solaris is faster. It's slow as dog on desktop in comparison to Linux. I probably should fill bug report as someone mentioned before, but I'm completely uninterested what's going around this great and very unappreciated system.

I realized that benchmarks in many cases are meaningless so you don't have to use Google, which is based on Linux, too much. It can be very frustrating to you.

Btw. Playing in posts is funny only for short time.

[energyman]

http://bulk.fefe.de/lk2006/bench.html

[kebabbert]

Niagara.. you mentioned 'numbercrunshing' earlier. Think about it. And think about the fact, that no big iron uses niagara... it is good at doing lots of very simple stuff in parallel. Sadly not everything is simple.
Actually, I dont understand your post. So what about number crunching and Niagara? Do you mean that Niagara sucks at nr crunching, or that it is good? So what should I think about it? I dont understand. FYI, The 1.4 GHz Niagara has the world record in both SPECint2006 and SPECfp2006, faster than, for instance, the previous record keeper IBM Power6 4.7 GHz on number crunching:
http://blogs.sun.com/bmseer/tags/specint_rate2006



And "no big iron uses niagara", so what? Niagara is good enough. In fact, Ive heard of some company that migrated their entire IBM mainframe to one T5440 SUN with 4 Niagara cpus. Cant remember where. And STRATA, Europes largest web provider handles up to one billion email/day, migrated their entire Back End to one T5440 with lots of cpu power over. There are lots of similar stories, companies migrate 40 racks with 64 AMD cpus to one SUN T5440 and cut power drastically. And sys admins. And spare parts. etc. And the T5440 is cheap, it costs like 82 000 USD and one similar configured IBM Power6 server costs 412 000 USD. And the T5440 is much faster also.



Yes, Niagara is only good at doing simple stuff, such as running Oracle and SAP (T5440 holds world records in both. Oracle benchmarks, I have linked to. SAP benchmarks: http://blogs.sun.com/bmseer/tags/sap ), MySQL I have linked to, etc etc. And it is the world's fastest cpu at number crunching, which I have shown above. Yes, Niagara is only good at simple stuff, that has no use at companies. Totally worth less CPU, I concur.



The Niagara CPU is unique. Yes, totally unique. Studies from Intel corp show that even under full load a typical x86 server CPU idles 50-60% of the time. This is due to cache misses which all CPU architectures suffer from; they must wait for data to arrive from RAM. That is also why modern CPUs have larger cache, complex prefetch logic, etc. However, CPUs belonging to the T1 family do not suffer from this problem. Instead, as soon a T1 thread stalls due to a cache miss, the T1 switches thread in 1 clock cycle and continues to do work while waiting for the data. Typically on a modern CPU, a thread switch takes a much longer time than 1 clock cycle. This is the reason a T1 can work 95% of the time and only waits for data 5% of the time. Compare this to an x86 CPU at 3 GHz. Because the x86 CPU can only work at half speed due to cache misses, it can be compared to a 1.5 GHz CPU working at full speed. However, one of the T1 threads can compare to an Intel Pentium 3 CPU at 1 GHz in terms of computing power.

Also, in best case scenario, the Niagara can run all 8 threads in one core, simultaneously. That happens when they are in different stage in the cpu pipeline. Not so an Intel x86, a thread occupies the entire core.

You see now, that the Niagara is totally unique? And ZFS. And DTrace. DTrace is pure magic. (DTrace allows the finding of Solaris kernel bugs that are impossible to find otherwise. DTrace only makes Solaris more stable and scalable). And Zones. And Crossbow. etc etc I could go on and on. Seriously. I really really do think SUN has excellent engineers. Maybe you Linux guys dont think so, but that is ok. Maybe you linux guys thinks that ZFS sucks. And DTrace. And Niagara. etc. That is ok. Anyway, all is Unix. If SUN dies, I switch back to Linux. Nothing is lost. Unix is Unix.

[kebabbert]

@kebabbert

What are you trying to proof? You're fanboy in my opinion. You're repeating same bullshit all the time and if you know such revelations as you already said post a new thread and Solaris fanboys will feel there like in Heaven. I don't believe that you used Linux on desktop, switched to Solaris and now you say that Solaris is faster. It's slow as dog on desktop in comparison to Linux. I probably should fill bug report as someone mentioned before, but I'm completely uninterested what's going around this great and very unappreciated system.

I realized that benchmarks in many cases are meaningless so you don't have to use Google, which is based on Linux, too much. It can be very frustrating to you.
I dont say that Solaris is faster than Linux on my hardware. But I can repeat again: I say that Linux did suffice, it did everything for me, and well. I said that Linux doesnt cut it for big loads. Ive personally never had any such load. I told you. Why do I always have to repeat myself?



And, Google is running an modified Linux kernel. Not commodity Linux. Google started as a small company. They use lots of cheap servers with low utilization, because Linux becomes unstable at high utilization. I know that Google has been examining Solaris. If Google could run servers on 100% load with Solaris, than 50% load with Linux - Google would save lots of energy.

[energyman]

no, you came up all the time that linux is only good for numbercrunshing and nothing else. Ignoring the fact that linux kills Solaris off everywhere.
And then you bring up Niagara - which is a chip designed for multi threaded numbercrunshing. It is good at that - and nothing else.

[kebabbert]

http://bulk.fefe.de/lk2006/bench.html
Wow! One benchmark at last! Thanx for that.

The only problem is that they are using some odd home brewn distro of Solaris, v0.51 or so. I think that benchmark is unfair. We could bench Solaris 10 against Ubuntu v0.51 and see who would win?

A better link, please. Remember, if you present good enough evidence that Linux is the best, I will switch. I only use the best tech. Why use something inferior?





NGRGYMAN,
Yes, the CHIP is good for number crunching. But Solaris is something else. The OS and the chip are totally different things. The chip may be good, but the OS suck, or vice versa.

And it is a fact that the best tech doesnt always win. Remember VHS vs Betamax? And Windows has 90% market share, and that tech sucks big time. The best tech doesnt win always.

[energyman]

he took the two leading opensolaris distributions. If you want to, I am sure that Felix v. L. would gladhly accept a big box with Solaris whatever installed on it - as long as he has not to pay for it,

[kraftman]

I dont say that Solaris is faster than Linux on my hardware. But I can repeat again: I say that Linux did suffice, it did everything for me, and well. I said that Linux doesnt cut it for big loads. Ive personally never had any such load. I told you. Why do I always have to repeat myself?



And, Google is running an modified Linux kernel. Not commodity Linux. Google started as a small company. They use lots of cheap servers with low utilization, because Linux becomes unstable at high utilization. I know that Google has been examining Solaris. If Google could run servers on 100% load with Solaris, than 50% load with Linux - Google would save lots of energy.

If Solaris could compare with Linux in big loads Google and many other companies would just use it. They don't base on crap what you gave here. In my opinion your only intention is to make flame. If Solaris isn't faster then Linux on your box why you use it? Because of fanaticism?


If you're interested:

http://www.dbazine.com/olc/olc-articles/ault8

and another one using 2.4.x kernel:

http://www.osnews.com/story/4867/Sun_Versus_Linux_The_x86_Smack-down/page3/

[kebabbert]

ENERGYMAN,
Im sure he would like that Solaris box! :)

Actually, I would prefer that he benchmarked the full blown Linux to the real Solaris 10, instead of benchmarking two home brewn Solaris distros that doesnt work (v0.51 or so), made by some random people. To me, it is like comparing Solaris 10 to a Linux distro v0.51 in Beta. Why do that, when the latest Ubuntu is available? Do we want a fair comparison so everyone can make their own opinions, or do we want to distort things? Is it a fair benchmark? Or not?

If I would benchmark Solaris 10 against Ubuntu v0.51 - would you accept my benchmark?







KRAFTMAN,
I couldnt find the article where they stated that: "Google has been looking for Solaris admins", "there are lots of ex SUN people at Google having vast experience of Solaris", "Google is looking at Solaris".

And I dont think youre argument about Google would just use Solaris if it was better, is valid. Let me rephrase your argument a bit:
"If Linux could compare with Windows, other companies would just use Linux. You are just flaming. Linux is not better than Windows, because Windows has greater market share. If Linux were better, Linux would have the greatest market share. But Windows have the greatest share, which is proving that Windows is best". Do you think this rephrased argument is valid or invalid? If it is invalid, then why is your version valid? As I said earlier, the best tech doesnt always win. Windows has bad tech, and wins. VHS had bad tech, and wun over Betamax. The examples are numerous.



Thanks for backing up your statements with some hard facts. However, I would like other links if you would be so kind. Reason:

1. What would you think if I showed you benchmarks of Linux on 400 MHz machine vs Solaris using dual Xeon 2.8 GHz? You would be totally mad and yell and accuse me of being a cheater? So, it is ok that you show me such links, but I can not show you such links? I would prefer benchmarks, Linux vs Solaris on the same hardware. That would be fair?

2. That is an old benchmark, old Solaris 9 with old filesystem UFS. Do you have any newer benchmarks with Solaris 10 and ZFS instead? Even if Linux v2.4 were faster back then, Im not really convinced that I should install Linux v2.4 on my computer right now. I am interested of the current state. Even if solaris v8 was faster than Linux v2.2 I wouldnt install Solaris v8 right now. To me the history is not important, because that would be disadvantageous to Linux - Linux is a young kernel and Solaris was mature back then. I couldnt compare Linux v0.9 to Solaris v7. That would not be fair. the history is not important to me. I am interested in the current state.

I appreciate you take your time to educate me about Linux performance and stability.

[energyman]

em, you know what schillix is? You know who is behind it? 'random people'? hardly ....

[kraftman]

I appreciate you take your time to educate me about Linux performance and stability.

ROTFL. I won't waste my time anymore. Better educate yourself, there's much you should find out. And you are flaming. MS has monopoly etc. etc. your arguments are just idiotic. Farewell. I posted another benchmark in which Solaris is just terribly slow. You can find it some post before.


Oh, and you're trolling here. As I said before if you want to discuss some things post a new thread.

[kebabbert]

ROTFL. I won't waste my time anymore. Better educate yourself, there's much you should find out. And you are flaming. MS has monopoly etc. etc. your arguments are just idiotic. Farewell. I posted another benchmark in which Solaris is just terribly slow. You can find it some post before.


Oh, and you're trolling here. As I said before if you want to discuss some things post a new thread.
You posted only 2 benchmarks that I discussed, right? And both were invalid, as I pointed out. Ive searched on your nick name, and didnt find other Solaris benchmarking posts.

Thanx for the discussion. If you can find any links showing that Linux is more stable, faster or whatever than Solaris, I would be interested to see them. I mean it. Then please post them here. You know that there are lots of links showing the opposite? It is easy to find them. Just google Solaris vs Linux or something similar.

You see, only hard facts impress upon me. You can state whatever you want, but that doesnt really matter. Only benchmarks and hard facts count. Otherwise it is just opionions and marketing talk. That is why I prefer Solaris right now because there are lots of links showing Solaris being superior, but no links showing Linux being superior. Why is that, if Linux really were superior?

PS. I still would like to know more about your statement that you have tried both Solaris and Linux, and Linux came out on top. How, and when did you do that? In what aspect did Solaris fail? You havent answered. Is it true that you did try both out?

Anyway, farewell for now.







ENERGYMAN,
No, I dont know the people behind Schillix. Should I? There are only two developers doing Schillix. None of them known to me. I would call them two, random guys. I would like to see Solaris 10 against a full version of Linux. Not some crippled versions. I am not interested in comparing S10 against Linux on an old machine. I really want to see, which is the best OS? Then I just install that OS and use it. I know how to use both of them. Theyre both Unix.

If you are trying to get an opionion about something, you want to compare them on equal grounds, right? That is what I want. Equal grounds. I dont think that Solaris on 400 MHz CPU vs Linux dual Xeon 2.8 GHz CPU is equal grounds. That benchmark doesnt say anything about the OSes, it only says that Xeon 2.8GHz is faster than 400MHz CPU. And comparing a Solaris Niagara machine vs a Linux Xeon machine doesnt say anything about the OSes, the Linux machine would loose so hard on every benchmark, but that only proves that Niagara is superior CPU. Which is uninteresting. That benchmark says nothing about the OS.

[energyman]

yes, you really should know Jörg Schilling. If you know anything about Solaris, SCSI, cd burning, you should know that name.

[kraftman]

You posted only 2 benchmarks that I discussed, right? And both were invalid, as I pointed out. Ive searched on your nick name, and didnt find other Solaris benchmarking posts.

Thanx for the discussion. If you can find any links showing that Linux is more stable, faster or whatever than Solaris, I would be interested to see them. I mean it. Then please post them here. You know that there are lots of links showing the opposite? It is easy to find them. Just google Solaris vs Linux or something similar.

Your benchmarks and arguments are invalid and sometimes stupid. I can discuss it, give you some links, but you have to post a new thread, because I don't want you to trash this one.

You see, only hard facts impress upon me. You can state whatever you want, but that doesnt really matter. Only benchmarks and hard facts count. Otherwise it is just opionions and marketing talk. That is why I prefer Solaris right now because there are lots of links showing Solaris being superior, but no links showing Linux being superior. Why is that, if Linux really were superior?

PS. I still would like to know more about your statement that you have tried both Solaris and Linux, and Linux came out on top. How, and when did you do that? In what aspect did Solaris fail? You havent answered. Is it true that you did try both out?

Anyway, farewell for now.


Beginning from end - you didn't answered some of my questions. It seems that you didn't try Linux and Solaris on desktop, otherwise you should notice that responsiveness is better in Linux. Oh, do you know what amount of memory is recommended for Solaris? Imagine, Sun is falling, there are many Solaris fanboys and everyone can do benchmarks. I bet that many of them are made by Sun friends. Phoronix benchmark is more objective in this case (hopefully). You showed me benchmark in which Solaris is better on greater number of CPU's. In my opinion this benchmark is crap, because of problem with one library which breaks scaling on Linux. I bet person who did that test didn't replaced broken library, but ok, it doesn't matter right now. I wonder why you consider that Solaris is better, faster etc. if you only base your opinions on one type of test? Have you anything more to say about Linux stability? How do you test it (in one of my links Solaris just hung)? I'd love to know why Solaris came out on top for you. Because of some Sun friendly links?

I can answer you previous posts and continue discussion , but post a new thread ok?

[kebabbert]

Kraftman,

Thanx for answering. Ok, I will create a new thread in a few days. Right now I have to deliver a project in my job in another country, so I have to fly tomorrow and it is crazy work hours right now. See you soon! :)

[GreatWalrus]

Thank you very much Phoronix. This test was exactly what I was looking for!