Netbook Performance: Ubuntu vs. OpenSolaris [Archive]

jollyd

07-17-2009, 02:06 PM

JollyD, you are interesting me. What are, on your opinion, the advantages of Solaris against linux or even Windows or MacOS ?
It's not for joking you, it's really to learn. I don't know Solaris. It's seems however to be a nice OS, but I really don't know it. You say I still could install one release and see by myself. However, a install process is always a long thing (and my second hard drive is gone at western digital for exchange, it was dead-out-of-the-box).

Hi, thanks for your comment.
Coming from Debian my main concerns were about the Linux kernel and the documentation.

I think it's not honest when something (driver, app) is reported as "working" and it's true in a "perpetual-beta" sense.
In Solaris or BSD when something is reported as "functional" it's true.
Sometimes you discover peripherals working with Solaris which are not listed... the guy from sun was surprised when I reported the successful use of 5.1 audio soundcard and USB scanner plugged on a USB/Firewire PCI card on my Ultra SPARC 60 few years ago.

Features apart, under OpenSolaris I enjoy the quality of the documentation and manpages which are substantial and structured in a more logical way. Moreover ergonomy of CLI commands is overall far better than GNU and Linux: see zpool, zfs, zoneadm, svcadm, svccfg, svcs, prioconctl. They seem more polished, more logical and well-documented.

From a developer viewpoint, I like the design concern behind Solaris which is lacking in Linux. As a by-product backward compatibility is a great advantage over Linux for "stability in time" and avoid wasting time rewriting things or breaking drivers every minor version like I experienced with Debian.
That's maybe why OpenSolaris evolves quickly: I think it's ahead of Linux in term of design but I admit used to lack sometimes some facilities for a GNU newcomer and hardware support (some USB peripherals,Radeon chips). But overall driver quality seems better than Linux (Wifi, Ethernet, USB framework, audio => I dislike PulseAudio and ALSA).

This come with the respect of standards under Solaris which are well documented, unlike GNU which is a standard per se but not very well defined. In Solaris you can compile your apps with a given "standard" profile. The POSIXness of GNU is something variable but I'm not an expert.

I like the fact that everything can be monitored through DTrace scripts, the set of tools and SMF service management. Monitoring/auditing the kernel and service is easy and way better than Linux. No comparison. The modular kernel debugger is wonderful.
When you hit a bug you know where it's hidden...

From a user viewpoint, the system is as responsive as under Linux and support swapping better than my Debian GNU/Linux which dies everytime I solve a too big linear system (reboot needed even with recent kernels == pure crap).
Some may say the system may have a little overhead but that's the price for decent statistics, virtualization etc... I use OpenSolaris on two Pentium-M laptops with 1.5-2GB ram and 4200rpm HDD and it's great ! I see no sensible difference w.r.t Debian.

Some software is lacking in the repository but I have multimedia support with Mplayer (no issue) and no major problem to compile almost every software which is POSIX compliant. Everytime I have problem it's a matter of disrespect of POSIX or GCCism or Linuxism (bash as default shell, thanks guys...).
Some programs in the repository are not up to date which is sad.

Install is as easy as Ubuntu, 3D is ok, sound is perfect (thanks Boomer!), suspend/resume ok, sound with WINE will be supported in a near future but I already run some programs, I run MATLAB in a Linux zone which I can't run anymore on recent Debian,

ZFS is wonderful, even with old CPU like 32bits Pentium-M it's fine !
It did save my life several times with the snapshot functionality and is well integrated in gnome.
My external drives are now formated with ZFS.

When someone says Solaris is slow or heavy, it's pure bullshit.
Considering features it does run incredibly well !
FAT support is not optimal and advertized as not complete (it's honest).

Of course Linux may perform better in some area but you can't ask Solaris to do all the monitoring, checksumingand virtualization without a little overhead. To be short, CPU are mostly idle and RAM is inexpensive then the price is worth it (2GB RAM is recommended but I used my laptop with 1GB and Eclipse during 6months).

Conclusion: from a user and developer viewpoint, Solaris has nice features and provides the strength of a UNIX systems as Linux and *BSD do with a polished, standard-concerned, well-documented userland.
Overall the OpenSolaris community is very skilled and eager to share its knowledge (guys on #opensolaris and sun developers are very kind).

So my comments is positive and possibly biased but I think this system has the potential to take a place along Linux distributions. It's a matter of personal taste. Let us respect everyone's taste.
Criticism about Solaris is sometimes obviously biased or misguided which is sad. For the time being my experience with OpenSolaris is better than with Ubuntu or Debian.

Kind regards,

a.

jollyd

07-17-2009, 02:15 PM

If solaris were to get more traction I'd be worried about it pulling back to bing full proprietary again.

That being said, I have a customer who is getting slaughtered by window's utterly poor network & IO and theres a chance solaris may be more palatable than linux as an alternative. However these benchmarks dont show good IO throughput and I've seen enterprise users complain about ZFS integrety issues,

I think the comparison is not quite right since ZFS was designed for taking advantage of the CPU.
The CPU used in this comparison suffers maybe from its "in order" architecture and the complex machinery behind ZFS+IO stack maybe be a bottleneck.
I think you won't have this issues on server grade systems.
I'm not an expert, just my 0.02...

Kind regards,

a.

kraftman

07-17-2009, 02:26 PM

In Solaris or BSD when something is reported as "functional" it's true.

No, it's not, but you have to digg in another thread here. Some people even call stable Freebsd 7.1 unfinished beta - data corruption with SATA or SATA/RAID. In Solaris as far as I remember are broken some wifi drivers marked as stable.

Sometimes you discover peripherals working with Solaris which are not listed... the guy from sun was surprised when I reported the successful use of 5.1 audio soundcard and USB scanner plugged on a USB/Firewire PCI card on my Ultra SPARC 60 few years ago.Nice surprise, but I prefer to have working hardware listed.

Features apart, under OpenSolaris I enjoy the quality of the documentation and manpages which are substantial and structured in a more logical way. Moreover ergonomy of CLI commands is overall far better than GNU and Linux: see zpool, zfs, zoneadm, svcadm, svccfg, svcs, prioconctl. They seem more polished, more logical and well-documented.First and fundamental question:

documentation is for who? And if it's such meaningful why Solaris almost died?

Sorry, when comes to ergonomy I can't stand Solaris CLI commands.

From a developer viewpoint, I like the design concern behind Solaris which is lacking in Linux. As a by-product backward compatibility is a great advantage over Linux for "stability in time" and avoid wasting time rewriting things or breaking drivers every minor version like I experienced with Debian.
That's maybe why OpenSolaris evolves quickly: I think it's ahead of Linux in term of design but I admit used to lack sometimes some facilities for a GNU newcomer and hardware support (some USB peripherals,Radeon chips). But overall driver quality seems better than Linux (Wifi, Ethernet, USB framework, audio => I dislike PulseAudio and ALSA)."stable" API/ABI usually buggy and crappy :> When comes to design Linux devs learned on Solaris mistakes. Threads creation is much faster and simpler on Linux. Stop writing bullshit about drivers quality, because you can't proof anything. I can say it's opposite, but it will be childish flame. "stability in time" = stay in the same place for years.

From a user viewpoint, the system is as responsive as under Linux and support swapping better than my Debian GNU/Linux which dies everytime I solve a too big linear system (reboot needed even with recent kernels == pure crap).Swapping is way faster on Linux, but I have to dig to give you proof. Why reboot needed? It's needed rather when comes to Solaris. Linux has even patches which prevent from memory fragmentation.
Some may say the system may have a little overhead but that's the price for decent statistics, virtualization etc... I use OpenSolaris on two Pentium-M laptops with 1.5-2GB ram and 4200rpm HDD and it's great ! I see no sensible difference w.r.t Debian.What's better in Solaris virtualization? :confused:

Some software is lacking in the repository but I have multimedia support with Mplayer (no issue) and no major problem to compile almost every software which is POSIX compliant. Everytime I have problem it's a matter of disrespect of POSIX or GCCism or Linuxism (bash as default shell, thanks guys...).
Some programs in the repository are not up to date which is sad.Linux is POSIX compliant. Bash, yeah thanks for this.

Install is as easy as Ubuntu, 3D is ok, sound is perfect (thanks Boomer!), suspend/resume ok, sound with WINE will be supported in a near future but I already run some programs, I run MATLAB in a Linux zone which I can't run anymore on recent Debian, When comes to drivers and successful suspend/resume Solaris doesn't have a chance. It's Matlab fault.

cruiseoveride

07-17-2009, 02:49 PM

What makes you think that?

Because no one except SUN, Phoronix and a few eccentrics give 2 shits about Solaris

hdas

07-17-2009, 03:07 PM

jollyd

07-17-2009, 03:07 PM

No, it's not, but you have to digg in another thread here. Some people even call stable Freebsd 7.1 unfinished beta - data corruption with SATA or SATA/RAID. In Solaris as far as I remember are broken some wifi drivers marked as stable.

As in every OS. Data corruption even occured with Linux and any other OS from time to time when a driver is broken. Issue is when you can't take another version and compile it against you kernel because from a minor to another interfaces had changed.

Never got 2 wifi cards (Linksys to be exact) working under Debian GNU/Linux although they were advertized as working for the same major version.
Maybe it was patched and working under distribution X but Y won't.
Sure it always work 90% of the time but what is the potential issue for the 10%, in particular when you can't trace changes in interfaces without being an expert (which I'm not) ?

Sorry, when comes to ergonomy I can't stand Solaris CLI commands.

As I said it's a matter of taste.

"stable" API/ABI usually buggy and crappy :> When comes to design Linux devs learned on Solaris mistakes. Threads creation is much faster and simpler on Linux.

I think it's matter of granularity of the developement model. Truth stands in the middle. ;)

Swapping is way faster on Linux, but I have to dig to give you proof. Stop writing bullshit about drivers quality, because you can't proof anything.

I don't write bullshit, just figure that I didn't expressed my thought correctly. I dislike when parallel port driver is broken.. then I upgrade and wifi stops working, then upgrade and USB freeze with my USB key (and so on)...
I spend many hours on such problems. I prefer losing few microseconds on thread creation and avoiding spending 2 hours figuring which combination of kernel version /driver version is optimal. Moreover I had in mind that exporting statistics with kstat is nice.

As for swapping issues: with friends we were stunned... we tested on 5 kernel versions and compared with MacOSX, FreeBSD and Solaris. Debian couldn't stand the test and even ssh was unavailable. @ work on the cluster some nodes had the same issue and we had network connectivity issues that administrators couldn't diagnose. An update solved the network problem but not the swapping issue.
I admit maybe it's a Debian specific problem.

On my laptop and desktop under Debian I have problems with USB mass storage: couldn't handle more than on device without freezing.

I gave few example of the drivers that did cause some issues under Linux and no problem under BSD and Solaris.
Didn't meant to judge the quality of the code, but the fact that I fear the uncertainty of a driver working correctly at time $t$ and not at time $t + \delta t$;)
I'm writing about my experience, which may be different from yours.

What's better in Solaris virtualization? :confused:

I was thinking of zones and crossbow.

Linux is POSIX compliant. Bash, yeah thanks for this.

Seems to me that Linux and GNU use a superset of POSIX.
It's not clear to me whether default behaviour is the correct one.
I think linking /bin/sh to /bin/bash was not a lucky choice.

It's Matlab fault.

Agreed, don't take it as criticism (which isn't) but I express the fact that I'm satisfied with brandz.
A positive for one, is not a negative for the other.

Best regards,

a.

jollyd

07-17-2009, 03:14 PM

Solaris on netbooks? Looks like the next big thing is going to be a cluster of atoms (lattice?) running solaris or bsd. <sarcasm> Mmm, I so much want to run opensolaris (or freebsd) on my netbook/nettop with zfs and dtrace - so that I can browse, chat and watch streaming videos reliably :D. </sarcasm>

ha ha ha !

We can think of it as a sequence:

Windows user: Linux on a netbook ???
Linux user: Solaris on a netbook ???
Solaris user: OpenBSD on a netbook ???
OpenBSD user: Haiku on a netbook ???
Haiku user: Hurd on a netbook ???
Hurd user: Minix on a netbook ???
Minix user: Plan9 on a netbook ???

Please, any idea for the next iteration ? ;)

kraftman

07-17-2009, 04:45 PM

As in every OS. Data corruption even occured with Linux and any other OS from time to time when a driver is broken. Issue is when you can't take another version and compile it against you kernel because from a minor to another interfaces had changed.

The point is Linux is released every 3 months, so fixes come usually very quickly and patches are backported to previous releases (no matter if distros do this or kernel devs).

Never got 2 wifi cards (Linksys to be exact) working under Debian GNU/Linux although they were advertized as working for the same major version.
Maybe it was patched and working under distribution X but Y won't.
Sure it always work 90% of the time but what is the potential issue for the 10%, in particular when you can't trace changes in interfaces without being an expert (which I'm not) ? I just wanted to say a single driver marked as stable can be broken on every OS.

You can always ask at lkml. ;) I have no knowledge about tracing etc. so I can't argue here.

I think it's matter of granularity of the developement model. Truth stands in the middle. ;)Yes, well said, but this one is even mentioned in faq ;) However, it can be different in current Solaris releases.

I don't write bullshit, just figure that I didn't expressed my thought correctly. I dislike when parallel port driver is broken.. then I upgrade and wifi stops working, then upgrade and USB freeze with my USB key (and so on)...
I spend many hours on such problems. I prefer losing few microseconds on thread creation and avoiding spending 2 hours figuring which combination of kernel version /driver version is optimal. Moreover I had in mind that exporting statistics with kstat is nice.The same happens on others. It depends on distros, because they have last word which kernel should be used (if there are known regressions they should choose a good one). The another point is I never had such problems (as far as I remember I never had a single problem due to regression on Linux).
As for swapping issues: with friends we were stunned... we tested on 5 kernel versions and compared with MacOSX, FreeBSD and Solaris. Debian couldn't stand the test and even ssh was unavailable. @ work on the cluster some nodes had the same issue and we had network connectivity issues that administrators couldn't diagnose. An update solved the network problem but not the swapping issue.
I admit maybe it's a Debian specific problem.It depends what Debian release was tested. It won't be fair to compare current BSD or Solaris release against old Debian Stable. :)

On my laptop and desktop under Debian I have problems with USB mass storage: couldn't handle more than on device without freezing.

I gave few example of the drivers that did cause some issues under Linux and no problem under BSD and Solaris.
Didn't meant to judge the quality of the code, but the fact that I fear the uncertainty of a driver working correctly at time $t$ and not at time $t + \delta t$;)
I'm writing about my experience, which may be different from yours.Yeah, I already said I never had such problems, so those are different experiences.

Seems to me that Linux and GNU use a superset of POSIX.
It's not clear to me whether default behaviour is the correct one.
I think linking /bin/sh to /bin/bash was not a lucky choice.It's probably a distro choice, but I don't know about details and I am happy with bash, so it's just a personal feeling.

Agreed, don't take it as criticism (which isn't) but I express the fact that I'm satisfied with brandz.
A positive for one, is not a negative for the other.

Best regards,

a.Thanks for good explanation. I should take your previous post like distro to distro comparison rather then Solaris to Linux. I also didn't clear many things in previous post, but it seems you already done this. :) Sorry for many, many spelling mistakes.

Please, any idea for the next iteration ? ;)

You forgot Macs ;)

kebabbert

07-20-2009, 09:48 AM

I know several people switched from Linux to OpenSolaris, mainly because of ZFS. With other solutions, your data is at risk because of silent corruption. The problem is when your hardware silently corrupts the bits, without telling you, without noticing it themselves. Then you need ECC functionality. ECC scans and corrects flipped bits in RAM. ZFS does the same thing on disk. And hardware raid doesnt help against problem of flipped bits, because HWraid wont even notice if a bit has been flipped. You need ECC to detect that. No filesystem utilizes ECC, except ZFS. The larger the discs, the more probable of some bits gets corrupted. Also, ZFS doesnt need fsck, and Linux fsck does only check the metadata, the data is not checked.

One of the best textst on why to use ZFS, on future filesystems and the new problems hyper modern filesystems face. A new disc has 20% of the surface dedicated to error correcting codes, and still there are errors!
http://queue.acm.org/detail.cfm?id=1317400

CERN investigates silent corruption and presents very interesting conclusions:
http://storagemojo.com/2007/09/19/cerns-data-corruption-research/

It is time to abandon RAID-5, because the discs are so big now that very often bits will be silently flipped. The larger the raid, the more flipped bits, eventually you will always see flipped bits. Only ZFS fixes this problem:
http://blogs.zdnet.com/storage/?p=162

ECC RAM
http://en.wikipedia.org/wiki/Dynamic_random_access_memory#Errors_and_error_corr ection
"Electrical or magnetic interference inside a computer system can cause a single bit of DRAM to spontaneously flip to the opposite state."

Other things I like with OpenSolaris is that it is more robust than Linux, it scales better, etc. Solaris is an OS for big computers and big loads. On the desktop it doesnt shine.

For instance, you dont face code of varying quality in Solaris, as Linux kernel developer Andrew Morton says about Linux:
http://lwn.net/Articles/285088/
Q:Is it your opinion that the quality of the kernel is in decline? Most developers seem to be pretty sanguine about the overall quality problem. Assuming there's a difference of opinion here, where do you think it comes from? How can we resolve it?

A:I used to think it was in decline, and I think that I might think that it still is. I see so many regressions which we never fix."

That is why see people switching from Linux to Solaris:
http://lethargy.org/~jesus/archives/77-Choosing-Solaris-10-over-Linux.html

http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1286507,00.html

Linux RAM overcommit it not a good strategy:
http://opsmonkey.blogspot.com/2007/01/linux-memory-overcommit.html

Linux doesnt scale well, when used as a file server:
http://www.enterprisestorageforum.com/sans/features/article.php/3745996

And the lack of stable API/ABI is a bit of a pain. Linux is a moving target, your old drivers will not necessarily work. With Solaris is a different thing, the API and ABI has been frozen since way back. SUN guarantees binary compatibility back to Solaris v2.6, now Solaris is v5.10.

kraftman

07-20-2009, 01:45 PM

Other things I like with OpenSolaris is that it is more robust than Linux, it scales better, etc. Solaris is an OS for big computers and big loads. On the desktop it doesnt shine.You mean File Systems right? That's why BTRFS is developed and in MySQL Solaris sucks a lot. When comes to strict e CPU scaling and big loads anything doesn't have a chance. Read about RCU or better about hierarchical RCU which is patented technology :> Linux is robust and probably that's why you see higher memory usage here:

http://opsmonkey.blogspot.com/2007/0...vercommit.html (http://opsmonkey.blogspot.com/2007/01/linux-memory-overcommit.html) *

Life actually verified everything and there's no Sun's propaganda anymore :)

For instance, you dont face code of varying quality in Solaris, as Linux kernel developer Andrew Morton says about Linux:Wrong :) Many Solaris features are/were just for advertisements (read about 'new' features which cause unstability and performance penalties - it's not following KISS like Linux; some of the reasons why commercial Unixes died). Its code is a big pile of legacy bull :>

Linux RAM overcommit it not a good strategy:Why? Maybe thanks to this Linux creates threads much faster (*) and that's why it scales better then Solaris? I'm sure I read about this not so long ago and it was explained. I will try to find it. P.S. It's even mentioned in this link you provided - forking processes and threads are threaten like processes - creation is incredibly fast :)

Linux doesnt scale well, when used as a file server:First paragraph.

A:I used to think it was in decline, and I think that I might think that it still is. I see so many regressions which we never fix."Meaningless :) We don't know how it's in Solaris and what/where are those regressions? Old drivers etc.? And situation changes :)

And the lack of stable API/ABI is a bit of a pain. Linux is a moving target, your old drivers will not necessarily work. With Solaris is a different thing, the API and ABI has been frozen since way back. SUN guarantees binary compatibility back to Solaris v2.6, now Solaris is v5.10.I think there's nothing to argue :) Linux "guaranties" compatibility with binaries from...'91 :>

Linus talked about how nice it is to know that we can still run binaries from 1991http://lwn.net/Articles/298510/

kebabbert

07-20-2009, 05:03 PM

You mean File Systems right? That's why BTRFS is developed and in MySQL Solaris sucks a lot. When comes to strict e CPU scaling and big loads anything doesn't have a chance. Read about RCU or better about hierarchical RCU which is patented technology :> Linux is robust and probably that's why you see higher memory usage here:

http://opsmonkey.blogspot.com/2007/0...vercommit.html (http://opsmonkey.blogspot.com/2007/01/linux-memory-overcommit.html) *

Life actually verified everything and there's no Suns propaganda anymore :)

Wrong :) Many Solaris features are/were just for advertisements (read about 'new' features which cause unstability and performance penalties - it's not following KISS like Linux). Its code is a big pile of legacy bull :>

Why? Maybe thanks to this Linux creates threads much faster (*) and that's why it scales better then Solaris? I'm sure I read about this not so long ago and it was explained. I will try to find it. P.S. It's even mentioned it this link you provided - forking processes and threads are threaten like processes - creation is incredibly fast :)

First paragraph.

Meaningless :) We don't know how it's in Solaris and what/where are those regressions? Old drivers etc.? And situation changes :)

I think there's nothing to argue :) Linux "guaranties" compatibility with binaries from...'91 :>

http://lwn.net/Articles/298510/
I dont really agree with you. You should read the comments in your last link at the bottom. People complain that Linux has bad compatibility, they dont agree with Linus saying '91. And there are also lots of articles talking about Linux' problem with not defined and unstable ABI. I understand that you believe that Linux has defined and frozen ABIs, but there are people not agreeing with you. Just google a bit on unstable abi Linux. For instance
http://linuxdevcenter.com/pub/a/linux/2004/09/02/driver_ease.html

"the incompatibility between different stable point versions of the kernel hampers the Driver on Demand concept. You could compile a driver for 2.6.5 and it would probably not work on 2.6.10 if you simply loaded the precompiled binary module; you would need to recompile the driver for each kernel version."

We talk about unstable ABI here. Maybe Linux have "stable" APIs, I dont know that. But if Linux have stable APIs, then they allow Linux to run old programs. But device drivers require stable ABI. The prefered state is both stable APIs and ABIs.

Regarding Sun propaganda about bad Linux scaling, maybe you have read this link? Linux scaling experts talk about Linux scaling bad is only FUD from evil Unix vendors. Linux scales very well, they say.
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci929755,00.html
They talk about Linux scaling to 10.000 intel processors and yadda yadda. But 10.000 intel CPUs is just a cluster, a bunch of PCs. That is called horizontal scaling and you add a PC to the cluster and Linux scales (with a stripped down tailored kernel). For Big Iron, one machine with several CPUs, Linux scales bad - this is vertical scaling. The experts admit that in Linux v2.6 Linux will scale vertically up to... 16CPUs. Whereas Solaris scales vertically to hundreds of CPUs today on Big Iron. You know, there is no Big Iron with 10.000 cpus. When you talk about that many CPUs, you always talk about clusters. Which the scaling experts admits:
"With the 2.6 kernel, the vertical scaling will improve to 16-way. However, the true Linux value is horizontal scaling."

Just recently, in Linux v2.6.27 the kernel is no longer 250 times slower on some tasks on 64CPU machines. Earlier, the kernel was 250 times slower. I dont know how much problems there are still, that havent been fixed.
http://kernelnewbies.org/Linux_2_6_27
"page fault speedup of 250x on a 64 way system have been measured"

You know it takes decades to scale well. Linux has just recently started with that. Solaris has been doing that for decades.

Regarding my link where Andrew Morton complains about bad quality, and you just refuse to accept that link as "Meaningless" where Andrew talks about people need to submit better code and test it. Well, maybe you know better than Andrew Morton, maybe he is wrong. And maybe you know better than these Linux kernel developers too:
http://kerneltrap.org/Linux/Active_Merge_Windows

"the source tree breaks every day, and it's becoming an extremely non-fun environment to work in. We need to slow down the merging, we need to review things more, we need people to test their [...] changes!"

Regarding you dont know whats in Solaris code, well why dont you take a look? It is OpenSource, and available online. The guru Kernighan and Richie and those, had studied the Linux code and said it was not that good, in fact.

Then you write:
"Many Solaris features are/were just for advertisements (read about 'new' features which cause unstability and performance penalties - it's not following KISS like Linux). Its code is a big pile of legacy bull" So the Solaris code is apparently bad, you say. At the same time you write:
"We don't know how [the code is] it's in Solaris"
You know the code is bad, but you dont know how the code is? It seems that I have misunderstood you.

About Linux creating fast threads, that is not the same thing as scaling well. There are several Unix companies switching to Linux, and then they have to switch back to Solaris, because Linux doesnt cut it under high loads. For instance this article:
http://www.enterprisestorageforum.com/sans/features/article.php/3749926

Regarding my link about Linux RAM overcommit, and you state it is a good thing, because it allows Linux to create threads quickly. You are surely joking. No sane person would prefer to have random processes killed on a Linux server, when memory runs out. What happens if a Linux process is very important and has run for a few weeks with a calculation? On Solaris random processes are not killed as on Linux, instead Solaris refuses to allocate more memory. All Solaris processes are allowed to finish. Linux over allocates more memory than available and when memory is finally needed, random Linux processes are killed. That is hardly optimal. You are joking.

Regarding
"Many Solaris features are/were just for advertisements (read about 'new' features which cause unstability and performance penalties - it's not following KISS like Linux)"

You sure know that ZFS has been called "rampant layering violation" by Linux devs because ZFS simplified the file system architecture? And you do have heard about ZFS advantages? And DTrace advantages? And Zones? And SMF? UltraSparc Niagara etc etc? For instance, DTrace:
http://www.theregister.co.uk/2004/07/08/dtrace_user_take/

Bootnote
-----------
"Using DTrace, I instrumented every single assembly instruction in the function. What we found is that 5492 times to 1, there was a short circuit code path that was taken. We created a version of the function that had the short circuit case and then called the "real" function for other cases. This was completely inlinable and resulted in a 47 per cent performance gain.

Certainly, one could argue that if you used a debugger or analyzer you may have been able to come to the same conclusion in time. But who would want to sit and step through a function instruction by inctruction 5493 times? With DTrace, this took literally a ten second DTrace invocation, 2 minutes to craft the test case function, and 3 minutes to test. So in slightly over 5 minutes we had a 47 percent increase in performance."

Or PHP + DTrace. If you are a developer you MUST read this.
http://blogs.sun.com/bmc/entry/dtrace_and_php_demonstrated

Do you really call these technologies "just advertisements" and "new features which cause unstability"??

But anyway. I understand that you believe Linux has stable ABIs and all my links where companies tell that Linux becomes unstable during high loads - you dont accept. And also you dont accept the links where Linux kernel devs discuss the declining quality. And I understand that when I post such links, you think they are only SUN propaganda. Those links dont exist, or are made by SUN. It is ok if you believe all this stuff is SUN propaganda. Let us stop there.

kraftman

07-21-2009, 04:58 AM

I dont really agree with you. You should read the comments in your last link at the bottom. People complain that Linux has bad compatibility, they dont agree with Linus saying '91. And there are also lots of articles talking about Linux' problem with not defined and unstable ABI. I understand that you believe that Linux has defined and frozen ABIs, but there are people not agreeing with you. Just google a bit on unstable abi Linux. For instance
http://linuxdevcenter.com/pub/a/linux/2004/09/02/driver_ease.html

"the incompatibility between different stable point versions of the kernel hampers the Driver on Demand concept. You could compile a driver for 2.6.5 and it would probably not work on 2.6.10 if you simply loaded the precompiled binary module; you would need to recompile the driver for each kernel version."

We talk about unstable ABI here. Maybe Linux have "stable" APIs, I dont know that. But if Linux have stable APIs, then they allow Linux to run old programs. But device drivers require stable ABI. The prefered state is both stable APIs and ABIs.

That's why I quoted - guarantees. Linux doesn't have stable API/ABI. I think, stable means old and crappy in this case :). However, you can still run such old binaries, but don't ask me how, because I'm not interested in doing this.

Regarding Sun propaganda about bad Linux scaling, maybe you have read this link? Linux scaling experts talk about Linux scaling bad is only FUD from evil Unix vendors. Linux scales very well, they say.
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci929755,00.html
They talk about Linux scaling to 10.000 intel processors and yadda yadda. But 10.000 intel CPUs is just a cluster, a bunch of PCs. That is called horizontal scaling and you add a PC to the cluster and Linux scales (with a stripped down tailored kernel). For Big Iron, one machine with several CPUs, Linux scales bad - this is vertical scaling. The experts admit that in Linux v2.6 Linux will scale vertically up to... 16CPUs. Whereas Solaris scales vertically to hundreds of CPUs today on Big Iron. You know, there is no Big Iron with 10.000 cpus. When you talk about that many CPUs, you always talk about clusters. Which the scaling experts admits:
"With the 2.6 kernel, the vertical scaling will improve to 16-way. However, the true Linux value is horizontal scaling."When comes to RCU it's good when comes to clusters, but there are some other things which affects scalability like my favorite threads creation. I like when someone kills its own arguments ;) - in this link it's about first 2.6 (so 2.6.0?) kernel which allows to scale up to 16 CPUs and this kernel is very old, don't you think? Some older kernels weren't even preemptible, but everything changed.

Just recently, in Linux v2.6.27 the kernel is no longer 250 times slower on some tasks on 64CPU machines. Earlier, the kernel was 250 times slower. I dont know how much problems there are still, that havent been fixed.
http://kernelnewbies.org/Linux_2_6_27
"page fault speedup of 250x on a 64 way system have been measured"Page fault is 'faster' in this LINUX kernel 250x (maybe thanks to RCU :>) then on previous Linux's one. However, it just improved scalability and didn't make it 250 times better. Little difference ;)

You know it takes decades to scale well. Linux has just recently started with that. Solaris has been doing that for decades.Nope, Linux started with this quite long ago and they base on other systems as I mentioned before.

Regarding my link where Andrew Morton complains about bad quality, and you just refuse to accept that link as "Meaningless" where Andrew talks about people need to submit better code and test it. Well, maybe you know better than Andrew Morton, maybe he is wrong. And maybe you know better than these Linux kernel developers too:
http://kerneltrap.org/Linux/Active_Merge_WindowsWe still don't know how it looks in others. Quality is something much more important for Linux devs then for Solaris guys (that's why they did some stupid advertisements), so it's meaningless and out of the context.

"the source tree breaks every day, and it's becoming an extremely non-fun environment to work in. We need to slow down the merging, we need to review things more, we need people to test their [...] changes!"Isn't this about rc's? And I think it's no longer actual. Linus is usually satisfied ;)

Regarding you dont know whats in Solaris code, well why dont you take a look? It is OpenSource, and available online. The guru Kernighan and Richie and those, had studied the Linux code and said it was not that good, in fact.I'm not a dev and I'm not interested in such opinions :) Sun gave me some reasons to not believe in such things. 'Guru's are corruptible :> Like this one from GPL camp who betrayed it ;p

Then you write:
"Many Solaris features are/were just for advertisements (read about 'new' features which cause unstability and performance penalties - it's not following KISS like Linux). Its code is a big pile of legacy bull" So the Solaris code is apparently bad, you say. At the same time you write:
"We don't know how [the code is] it's in Solaris"
You know the code is bad, but you dont know how the code is? It seems that I have misunderstood you.Yes, I think Solaris isn't so good. We don't know how [the regressions are] it's in Solaris.

About Linux creating fast threads, that is not the same thing as scaling well. There are several Unix companies switching to Linux, and then they have to switch back to Solaris, because Linux doesnt cut it under high loads. For instance this article:
http://www.enterprisestorageforum.com/sans/features/article.php/3749926It's about file systems. I completely agree ZFS is better, but if you say scalling here think about FS not about scheduler or locking mechanism. However, we don't know if this guy is right and he may be unaware of gnu's malloc ;)

Regarding my link about Linux RAM overcommit, and you state it is a good thing, because it allows Linux to create threads quickly. You are surely joking. No sane person would prefer to have random processes killed on a Linux server, when memory runs out. What happens if a Linux process is very important and has run for a few weeks with a calculation? On Solaris random processes are not killed as on Linux, instead Solaris refuses to allocate more memory. All Solaris processes are allowed to finish. Linux over allocates more memory than available and when memory is finally needed, random Linux processes are killed. That is hardly optimal. You are joking.I'm really not sure about this one, so when I find link I mentioned before I will paste it here. It looks like gnu malloc problem :> They usually make crap. Some exploits are gcc related and this crappy malloc... GNU/Linux? You've got to be kidding xd

Regarding
"Many Solaris features are/were just for advertisements (read about 'new' features which cause unstability and performance penalties - it's not following KISS like Linux)"

You sure know that ZFS has been called "rampant layering violation" by Linux devs because ZFS simplified the file system architecture? And you do have heard about ZFS advantages? And DTrace advantages? And Zones? And SMF? UltraSparc Niagara etc etc? For instance, DTrace:
http://www.theregister.co.uk/2004/07/08/dtrace_user_take/Yeah, ZFS, but when comes to KISS there are other things. I mentioned before about threads creation which implementation is (or was, because maybe Solaris guys changed it) much simpler on Linux. Zones, as far as I know Linux's Xen provides zones, but I'm not interested in such features, dtrace is another nice thing, about those CPU's people say Linux runs better :> SMF it's hard to name some features the same, so there's maybe something like this under different name or it's not exciting.

Do you really call these technologies "just advertisements" and "new features which cause unstability"??I thought mainly about other 'features' like those related to virtualization and others.

But anyway. I understand that you believe Linux has stable ABIs and all my links where companies tell that Linux becomes unstable during high loads - you dont accept. And also you dont accept the links where Linux kernel devs discuss the declining quality. And I understand that when I post such links, you think they are only SUN propaganda. Those links dont exist, or are made by SUN. It is ok if you believe all this stuff is SUN propaganda. Let us stop there.I said before Linux doesn't have stable ABI (as far as I know ;)). There were many Sun's friendly companies, so it's propaganda for me :) I wrote what I thing about scaling. We can give much more 'proofs' etc. but it will usually reduce to believe or not ;) OS'es are too complicated to gave good picture about them. I also said before stable API/ABI can be crappy etc. but it's probably not a rule. You don't have to agree with anything I wrote, so I believe we can stop here.

mespina

07-29-2009, 08:19 PM

wow noce inf thx

frantaylor

07-29-2009, 08:56 PM

kraftman

07-30-2009, 07:17 AM

With Solaris you can set up a machine and it will run for years with no manual intervention.

Every Linux distribution I've ever seen comes with one daemon or another that will run out of control and chew up all the RAM or CPU after a few months of uptime.

I have seen big CPU loads render a Linux machine completely unusable. It takes ages to get a prompt, if ever, and even more ages before it starts to act on what you type. I have had Solaris boxes loaded down in a similar manner, but I was able to get a responsive prompt and kill the offending process.

Bullshit :> There's a Linux machine which runs more then 12 years (I hope it still runs, because I checked some time ago, year or two maybe). There are many more which runs for years. About this unresponsiveness it maybe known bug I/O related (and not sure if not hardware related, because only some configurations are affected; it may also be your messed config). If it takes more then 120s. I can say it's opposite and give no proofs, but why play in such childish games? The facts are Linux replaced Solaris in many, many environments. Solaris lives, because of ZFS.

Solaris runs forever? XD

kebabbert

07-30-2009, 07:51 AM

kraftman

07-30-2009, 08:20 AM

Kraftman,
You know, the problem is not to run for 12 years. MS-DOS machines could also run for 12 years. The problem is to run under high load with multiple users and programs running for long periods. That is the problem. Any OS could run for 20 years, just dont run any programs on it. Under high load, Linux crumbles and gets unstable. Whereas Solaris does not.

I know what you mean and I can realize this. However, I think opposite: under high load Solaris crumbles and gets unstable. Whereas Linux does not. :>

As Ive said, Solaris has been doing this stuff for decades, whereas Linux has not. The first version of Solaris 30 years ago, was called SunOS. It was not that good, had not good code, did only scale well to 8-16 cpus, just like Linux today. Todays Linux kernel is 2.6.30 not 2.6.0 like in your "proff" man ;)

Then SUN scrapped SunOS and did it anew, i.e. Solaris. Solaris is version 2.0 and it takes decades to scale well. To scale well is nothing you do in a few years. It takes decades. Look at Windows, MS has tried to make Windows scale well for 20 years. Still it doesnt succeed. Linux scaled to 4-8 CPUs recently in v2.4. Now it is v2.6.30 or so. Iit is impossible to go from bad scaling to good scaling, in a few years. You have rewrite all lock mechanisms etc. Solaris scales now to several hundreds of CPUs in one big machine. Linux scales to thousands nodes in a cluster, but not on one big machine. As I showed, Linux suffered when trying to scale to 64 cpus recently on 2.6.27 where it was 250 times slower on a certain thing. I bet there are other things which hasnt been fixed yet. Seriously, it takes decades to scale well. It isnt nothing you do on a coffee break. Maybe you should learn some programming?Proof this is impossible. You still don't understand what I already wrote about scalability (250 times faster, but what? :>.). If Linux is much younger then Solaris why it scales far better on clusters while Solaris not (why not to use the same argument when comes to one big machine?)? You're still killing your own arguments. It took decades and Linux isn't reinventing a wheel. Linux takes what's the best from others and adds some things on it's own (Linus said this, didn't he?).

And about your weird remark:
"Yes, I think Solaris isn't so good. We don't know how [the regressions are] it's in Solaris."

How can you say that Solaris is not good, when you now nothing about the code? You say, we dont know which regressions are there. Maybe there are no regressions at all (not likely)? But still you say things.I don't need to know the code to say this. In opposite how can you say that Solaris is good, when you know nothing about the code? And maybe there are many regressions? (don't know).

It is like, "I dont like that restaurant's food, but I dont know how the food is"Nope, it's like: I don't like that restaurant's food, but I don't know how the kitchen is.

And your other statement:
"Quality is something much more important for Linux devs then for Solaris guys"

That is weird. You know that Solaris is restrictive with accepting code from anyone.I don't know this (but if you mean accepting code from some users...). They already lost, so it can't have such quality like Linux.

Whereas Linux accepts code from anyone. And Ive posted links showing that the Linux kernel devs complain about the bad code, the source tree breaks, etc. And how do you react to those links proving I am right, and you are wrong??? I have given you proof. Proofs not from SUN, but from Linux devs.Not true. Xen isn't merged (KISS philosophy? at least in current Xens form...), Ksplice isn't merged, grsecurity isn't merged (however, I'm not sure if they wanted this, but as far as I remember...). I'm sure there are other examples. I said what I think about those links (or rather those guys ;)).

P.S. I take everything about scalability with grace of salt, because it's possible you're scenario is real, mine or we're both wrong.

kebabbert

07-31-2009, 08:53 AM

I know what you mean and I can realize this. However, I think opposite: under high load Solaris crumbles and gets unstable. Whereas Linux does not. :>
I have posted several stories showing that Linux becomes unstable. If you think opposite, then you surely must have some reason to believe so. Can you post some of your links proving that Solaris gets unstable? I would like to hear more on this. Ive never seen links on Solaris being unstable. Please post them. Or are you making things up? Talking about a restaurant without knowing anything about it?

Todays Linux kernel is 2.6.30 not 2.6.0 like in your "proff" man ;)
Que? I dont understand. I say that the first version of Solaris, was called SunOS 30 years ago. The first iteration scaled bad, just to a few CPUs, just like Linux today. Then SUN's engineers scrapped SunOS and did it anew and called it Solaris, with all the lessons taken from SunOS. Linux, OTOH was created by a teenager who just recently had read Tanenbaums book on Operating Systems. They say that SUN has got the largest concentration of PhD's outside a university. I somehow doubt that a single teenager outcodes SUNs engineers producing innovations such as ZFS, DTrace, Niagara CPU, etc. If SUNs first iteration called SunOS, were crap, then what makes you believe that a teenager and coders on their spare time succeeds better than SUN? Especially when Linux devs complain on the quality of the Linux code?

Proof this is impossible. You still don't understand what I already wrote about scalability (250 times faster, but what? :>.)
No I dont understand. Could please try to explain again?

I am claiming that, just recently Linux was 250 times slower on 64 cpu machines on a certain thing than now. I am implying that this may also indicate that there are other things that are not fixed in Linux, regarding 64 CPU machines. I suspect most Linux devs have access to dual CPU machines at most. If they dont have access to 64 cpu machines for million of USD, then how can they improve the 64 cpu code? They can not. They have no hands on experience of 64 CPU machines. SUN engineers have had experience since many years. I really find it doubtful that a bunch of spare time coders produce well scaling without access to Big Iron? That would be a miracle.

If Linux is much younger then Solaris why it scales far better on clusters while Solaris not (why not to use the same argument when comes to one big machine?)? You're still killing your own arguments. It took decades and Linux isn't reinventing a wheel. Linux takes what's the best from others and adds some things on it's own (Linus said this, didn't he?).
There is a reason Linux scales well on clusters: The Linux devs has access to clusters, which is basically a network with a bunch of PCs. They can experiment with it and correct the anomalies they observe. The Linux kernel is simple in it's structure and easy to modify for whatever reason. Whereas the Solaris kernel is complex and mature. It is non trivial to rip out things from a complex kernel such as Solaris.

As Solaris scales well vertically, which is difficult to do - it can of course be used for large clusters also. But it is easier to take a simple kernel and rip out everything and just use it for clusters. The Linux kernel for clusters is modified, it is non standard Linux kernel. Whereas Solaris kernel for huge Big Iron is the same kernel, down to EePC laptops. It is exactly the same DVD. THAT is scalability. You dont use std Linux kernels for clusters. You modify it.

A cluster just does one thing: calculates. A cluster is no replacement for Big Iron where many users log in at the same time and do all kind of work, where many different processes interact.

I can argue that MS-DOS is scalable as Linux (I just have to modify it first). Or C64 is as scalable as Linux. But that is not a true statement. MS-dos is not scalable, even though I modify it.

Linux scales well on a network, which is easy. This is horizontal scaling. Vertical scaling on one Big Iron - is difficult to do. Linux is not as good as Solaris on this.

I don't need to know the code to say this. In opposite how can you say that Solaris is good, when you know nothing about the code? And maybe there are many regressions? (don't know)
Please explain again why think that the Solaris code is bad - without knowing anything about the code?

Myself has only looked at parts of the Solaris code, but it didnt tell me much. I have no idea about the Solaris code quality. But I KNOW that there are lots of testimonies of companies that try Linux for small loads, and when load increases they switch to Solaris because Linux doesnt cut it anymore. For instance this link about a die hard Linux company is forced to switch to a Unix:
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1286507,00.html
"The problems we encountered were because Linux doesn't scale all that well," Rand said."

Or this one:
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1313798,00.html
"As a small company with 15 employees and contractors, Real Time Matrix was a die-hard Linux shop. But the company's computing processing needs quickly surpassed its size."

What I am trying to say is, based on articles and testimonies, etc Solaris doesnt have the problems that Linux has. Therefore I draw the conclusion that Solaris code is better. At least Solaris doesnt kill processes randomly or sucks at file serving, as Linux does. It also has stable API and ABIs - which means that SUN has designed the Solaris kernel well from the beginning. Linux breaks everything all the time, which means it is not well designed. Why not design Linux APIs and ABIs well instead of trying different approaches all the time?

Nope, it's like: I don't like that restaurant's food, but I don't know how the kitchen is.
Nope. It is more like "everyone says that restaurant performs good, and there are articles proving that - but that restaurant must be bad. I know nothing about it, I dont know how to cook food (you can not program) but I know that the food is bad. How I know it? I dont know. And regarding that other restaurant called Linux, the chefs themselves say the kitchen is bad, but they lie. I know the kitchen is good. How do I know that? I dont know. I am not a chef. But I know it".

I don't know this (but if you mean accepting code from some users...). They already lost, so it can't have such quality like Linux.
I am glad that Solaris has not such quality as Linux. I wouldnt want Solaris to kill my processes randomly. I wouldnt want Solaris to have unstable and changing ABIs. What happens if you upgrade the Linux kernel and it breaks the device drivers you have? You wont notice that, but only under big stress it will be noticed. And Linux begins to show problems under large stress. (Cut your crap on "I have never had problems with Linux, you must be lying" - because it is one thing to run Linux with light load on the desktop, and another with large load and many processes requesting RAM which kills processes etc.)

Linux crumbles and they switch to Solaris:
http://lethargy.org/~jesus/archives/77-Choosing-Solaris-10-over-Linux.html
"Yes. Same exact hardware. We reinstalled Linux twice even to make sure there wasn't something wrong with the install. I've had lots of other people chime in reporting very similar problems."

Not true. Xen isn't merged (KISS philosophy? at least in current Xens form...), Ksplice isn't merged, grsecurity isn't merged (however, I'm not sure if they wanted this, but as far as I remember...). I'm sure there are other examples. I said what I think about those links (or rather those guys ;)).
My links from linux devs such as Andrew Morton et. al are not true? I have made up those links, where Linux devs complain on the quality?

Ok. Fine.

P.S. I take everything about scalability with grace of salt, because it's possible you're scenario is real, mine or we're both wrong.
You admit that maybe I am right, and you admit that maybe you are wrong - and still you insist that Solaris code is bad, and that Linux code is good and the Linux devs are lying. How can you insist if you dont know? How can you insist that a restaurant is bad, when you dont know anything? "I PROMISE that restaurant is bad - but I am not sure. Maybe you are right, or maybe I am right. But I promise you. It is as I say. But I dont know"

Look, it is one thing to use Linux on a desktop for personal use. It is another thing to run Linux with large loads on a machine with many CPUs, with many concurrent users. I work at a large company where we use Solaris for some of our big systems. We are now switching some systems to Linux, but that is because of politics. Not because Solaris doesnt cut it anymore.

frantaylor

07-31-2009, 09:19 PM

Bullshit :> There's a Linux machine which runs more then 12 years (I hope it still runs, because I checked some time ago, year or two maybe). There are many more which runs for years. About this unresponsiveness it maybe known bug I/O related (and not sure if not hardware related, because only some configurations are affected; it may also be your messed config). If it takes more then 120s. I can say it's opposite and give no proofs, but why play in such childish games? The facts are Linux replaced Solaris in many, many environments. Solaris lives, because of ZFS.

Solaris runs forever? XD

Solaris 10 in a production environment is more robust than RHEL. You can argue blah blah blah about features and release cycles, but the only thing that really matters is: are our customers getting the necessary performance levels? This is based on our testing and our customers' experience. They keep asking for the Solaris version. They want very much to move to Linux for the cost savings, but they get frustrated with the instability. We hear all the stories about the experiments, they call us for help with them. Many of our customers are running Solaris or Tru64 in clusters, which you can imagine is terribly expensive in this day and age. And yet they keep them running because they are more robust than the Linux solutions.

Linux is untouchable as a web server and on the desktop, but it is not yet ready for high-performance, high-availability database servers. Go to your hospital or your state's lottery commission and ask them what they use for a database server. Chances are it will be Solaris or Tru64 or even VMS. Rarely do you see Linux machines used for this.
The cost savings are SO compelling, you know that they would choose Linux if it would work for them, but they do NOT.

kraftman

08-01-2009, 09:38 AM

@Kebbabert,

I'm really not interested in this and that's why:

I am claiming that, just recently Linux was 250 times slower on 64 cpu machines on a certain thing than now. I am implying that this may also indicate that there are other things that are not fixed in Linux, regarding 64 CPU machines.If you don't understand such obvious thing. I tried to explain this before. Linux wasn't 250 times slower on 64 cpu machine. Page fault was 'slower' (then on previous Linux kernel), but it may have almost no impact in overall scalability (or not so big impact etc. etc.). I'm tired to repeating some thing all time and I don't care what you think, because I use my own brain and I'm not very interested in discussions where you can 'proof' some things, but they may have nothing to do with reality.

Solaris 10 in a production environment is more robust than RHEL. You can argue blah blah blah about features and release cycles, but the only thing that really matters is: are our customers getting the necessary performance levels?

Blah, blah, I'm not the one who started mentioning features. I still consider RHEL is much more robust (or the newest kernel, I don't know what you use there).

This is based on our testing and our customers' experience. They keep asking for the Solaris version. They want very much to move to Linux for the cost savings, but they get frustrated with the instability. We hear all the stories about the experiments, they call us for help with them. Many of our customers are running Solaris or Tru64 in clusters, which you can imagine is terribly expensive in this day and age. And yet they keep them running because they are more robust than the Linux solutions.No, it's opposite when comes to being robust. You see... I don't see any proofs, neither do you (at least here...).

Linux is untouchable as a web server and on the desktop, but it is not yet ready for high-performance, high-availability database servers. Go to your hospital or your state's lottery commission and ask them what they use for a database server. Chances are it will be Solaris or Tru64 or even VMS. Rarely do you see Linux machines used for this.
The cost savings are SO compelling, you know that they would choose Linux if it would work for them, but they do NOT.People still use Solaris, because migration to Linux can be too expensive in their cases. Is this ZFS which gives it (in your opinion) such advantage on database servers? Is MySQL used on those servers?

@Kebabbert

As you can see here even such old kernel like 2.6.8 scales wonderfully on up to 64 CPU's machine (vertical scaling which you tried to proof is very bad on Linux; imagine how fast is 2.6.27 now - 250 times faster? ;)):

www.hp.com/techservers/hpccn/downloads/HPCAST_Bigtux.pdf (http://www.hp.com/techservers/hpccn/downloads/HPCAST_Bigtux.pdf)

frantaylor

08-01-2009, 06:05 PM

Sorry I am a newbie here with the quoting stuff.

---
No, it's opposite when comes to being robust. You see... I don't see any proofs, neither do you (at least here...).

---
People still use Solaris, because migration to Linux can be too expensive in their cases. Is this ZFS which gives it (in your opinion) such advantage on database servers? Is MySQL used on those servers?
---

I wonder what kind of "proof" one can insert into a web form that would satisfy you. I can't exactly paste a 32-CPU SPARC machine into a text box.

If you want "proof", go over to sun.com. Look and see that you can still purchase these fantastically expensive SPARC machines. Please explain to me how they could still be in business doing this, if Linux is everything you say it is. And then you can surf over to hp.com and see how their Tru64 and VMS systems are very much alive and well, and you can purchase the big expensive hardware for these OS's too. Again, these people would have been out of this business years ago if Linux were able to handle the workloads that these machines do.

MySQL!!!! Hahaha!!!! I am talking about REAL databases, with REAL performance. Stuff like Oracle, DB2, Intersystems Cache. Try doing SELECT with a join on two tables with 100,000,000 rows in mySQL and see how far you get. mySQL is a toy database for toy applications where you don't care if your data gets corrupted. Go ahead and find me a hospital that keeps patient records in mySQL.

If you read the threads in LKML about Linus and Con Kolivas and the scheduler nightmare, you realize how amazing it is that Linux works as well as it does. At a real software company, people like Linus get put in their place by the boss when they lash out emotionally at other developers. But King Linus feels free to rip people a new one when he is having a bad day. This is NOT the development model I want to see for a production kernel.

Your statistics are meaningless, the only way to see for yourself is to boot up a big workload on a big machine and check it out. I have access to these machines on my job. If you had access to machines like this then you could see for yourself too. Apparently you do not, and so your opinion remains an opinion.

kraftman

08-02-2009, 05:27 AM

Sorry I am a newbie here with the quoting stuff.

[ quote ] text [ /quote ]

I wonder what kind of "proof" one can insert into a web form that would satisfy you. I can't exactly paste a 32-CPU SPARC machine into a text box.Real one. Correctly configured Linux kernel, Googles malloc library.

If you want "proof", go over to sun.com. Look and see that you can still purchase these fantastically expensive SPARC machines.I don't want a 'proof', but a proof. There are no proofs at sun.com.

Please explain to me how they could still be in business doing this, if Linux is everything you say it is.Very easily. If their servers are cheaper then concurrent ones, they may have some agreements, Solaris can be enough for such workloads (or there's no difference here between Solaris and Linux). Why sun offers Linux servers?

And then you can surf over to hp.com and see how their Tru64 and VMS systems are very much alive and well, and you can purchase the big expensive hardware for these OS's too. Again, these people would have been out of this business years ago if Linux were able to handle the workloads that these machines do.Nope, as you can read in pdf I gave old 2.6.8 scales almost perfect (there's a law which explains this). Many people just don't need to migrate to Linux if Solaris is enough for them and if those systems scale the same on their hardware.

MySQL!!!! Hahaha!!!! I am talking about REAL databases, with REAL performance. Stuff like Oracle, DB2, Intersystems Cache. Try doing SELECT with a join on two tables with 100,000,000 rows in mySQL and see how far you get. mySQL is a toy database for toy applications where you don't care if your data gets corrupted. Go ahead and find me a hospital that keeps patient records in mySQL.I mentioned MySQL, because Solaris suck there.

If you read the threads in LKML about Linus and Con Kolivas and the scheduler nightmare, you realize how amazing it is that Linux works as well as it does. At a real software company, people like Linus get put in their place by the boss when they lash out emotionally at other developers. But King Linus feels free to rip people a new one when he is having a bad day. This is NOT the development model I want to see for a production kernel.You have no idea about this. It's not only related to SD vs CFS (and it seems CFS ended this nightmare you're trying to persuade; Ingo also replaced other things and 2.6 brought big changes; your thoughts are somewhere around 2.2 - 2.4; 2.6 < real time approach), but locking mechanism, thread creation and RCU gives Linux's big advantage. I don't care what you want to see, because I don't consider you're some kind of guru if you gave such idiotic examples.

Your statistics are meaningless, the only way to see for yourself is to boot up a big workload on a big machine and check it out. I have access to these machines on my job. If you had access to machines like this then you could see for yourself too. Apparently you do not, and so your opinion remains an opinion.This is real machine which actually works (if comet didn't hit it...). It's far more then idiotic talk. You're talk remains your talk man :> Reality remains reality.

MartjeB

08-02-2009, 05:56 AM

Don't feed the trolls..

yotambien

08-02-2009, 06:21 AM

kraftman

08-02-2009, 10:20 AM

1. Linux is the holiest operative system, especially on the server, but especially on the desktop.
2. Linux gives me strength, it lights my path and it keeps me warm; in Linux I trust.
3. Linux has no problems, it only tests your faith.
4. I shall spread the freedom of choosing what I chose, all I chose, and only what I chose.
5. I shall not let logic, facts or experience cloud my vision.
6. In moments of weakness, if the enemy presses hard or my path is not clear, the answer is NO.
7. The number of irrational explanations for a given fact is clearly greater than the number of rational ones.
8. Listening to others, humility and self-criticism are weaknesses not to fall into.
9. Purposely missing the point, repetition and insults are well established trolling techniques I shall have no qualms to use.
10. No post is one too many to reaffirm my bigotism and impaired comprehension skills as long as I have THE LAST WORD (http://en.wikipedia.org/wiki/Wikipedia:The_Last_Word).

Nice try, but you missed the point. Solaris guys wants to prove Linux doesn't scale. However, I can realize you want to stand up, but again... you should really replace Linux to Solaris in your points. Funny thing is I don't know which nick is real one :>

Yotambien. remember. Say this pray every time before going to bed. Arguments are not needed.

http://communities.vmware.com/thread/115302
http://forums.sun.com/thread.jspa?threadID=5371569
http://osdir.com/ml/db.mysql.bugs/2006-04/msg00000.html
http://www.computing.net/answers/solaris/hangs-at-boot-after-mutlicast-mssg/3015.html

If someone wants 'profffs' :P

Don't feed the trolls..And known Yotambien came XD

kebabbert

08-02-2009, 02:39 PM

@Kebbabert,
If you don't understand such obvious thing. I tried to explain this before. Linux wasn't 250 times slower on 64 cpu machine. Page fault was 'slower' (then on previous Linux kernel), but it may have almost no impact in overall scalability (or not so big impact etc. etc.). I'm tired to repeating some thing all time and I don't care what you think, because I use my own brain and I'm not very interested in discussions where you can 'proof' some things, but they may have nothing to do with reality.
You dont understand what I am trying to say. I am not saying that Linux is 250 times slower than Solaris. I am not trying to say that Linux page fault is 250 times slower than Solaris. You dont understand.

I am trying to say that just recently, Linux had some great scalability problems on 64 cpu machines. Linux is still inmature on Big Iron. I bet there are lots of other areas where Linux still has scalability problems. Solaris has been doing this on Big Iron for decades. I doubt Solaris performance can be 250 times increased.

This is not true, but I am trying to say something like: If it is impossible to improve Solaris performance 250 times, but you can still improve Linux 250 times - which is most mature? I bet there are still large optimizations to be done on Linux. Linux is not mature, it has not scaled on Big Iron for decades yet.

Now, do you understand? I am not saying that Linux is 250 times slower than Solaris. I say that Linux can still be improved much more on other areas, whereas Solaris can not be improved. And this is indicium that Linux is not mature. Do you understand?

Blah, blah, I'm not the one who started mentioning features. I still consider RHEL is much more robust (or the newest kernel, I don't know what you use there).
Jesus. You NEVER use the latest kernel or latest version in production! Are you mad?? You use stable and well tested software, where most of the bugs have been ironed out! Jesus.

People still use Solaris, because migration to Linux can be too expensive in their cases. Is this ZFS which gives it (in your opinion) such advantage on database servers? Is MySQL used on those servers?
Look, he tries to say that under high load and very demanding setups, Linux doesnt cut it. Neither does MySQL. MySQL is a toy database and can not handle the largest databases. You need e.g. Oracle to handle the largest databases. Jesus.

As you can see here even such old kernel like 2.6.8 scales wonderfully on up to 64 CPU's machine (vertical scaling which you tried to proof is very bad on Linux; imagine how fast is 2.6.27 now - 250 times faster? ;)):
Of course Linux functions on large servers. There are developers trying to submit patches for those. But as we see, there are still room for lots of improvements in Linux kernel for large servers. I wouldnt be surprised if soon another patch told that "Linux is not anymore 1000 times slower on ....".

http://communities.vmware.com/thread/115302
What does this link prove? That Solaris under VMware gets unstable? What does it say about Solaris on real SPARC hardware? Nothing. You know, I have Ubuntu on VirtualBox and Ubuntu is slow and lags and shows problems. Does this prove that Ubuntu is slow and lags? Or is it maybe VirtualBox that has some problems? How can you believe that if Solaris shows problems under VMware, then it is Solaris fault? Are you mad?

http://forums.sun.com/thread.jspa?threadID=5371569
Great. The guy can not install Solaris on a machine because of some missing device drivers or whatever. Does this prove that large Enterprise systems are unstable on Solaris? Are you nuts? It is one thing to setup a large system and run it under high load and keep it stable - and another thing to install Solaris. If Solaris doesnt install, it doesnt prove anything. Shit man. How do you reason?

http://osdir.com/ml/db.mysql.bugs/2006-04/msg00000.html
Another great "proof". This is a problem with Solaris 8. Not Solaris 9 or Solaris 10. This link has nothing to do with large enterprise systems. Show links about them instead. Not about an ancient Solaris version. I can show you link about someone having problem using toy database MySQL on Linux v2.2. Does that prove that Linux doesnt scale well? Jesus.

http://www.computing.net/answers/sol...mssg/3015.html
Another link about some ancient Solaris 8. Jesus. Look, if you want to prove something, post links about Enterprise people complaining that Solaris is unstable under high load on large systems. I think you will not find any such links, but there are lots of such links on Linux.

We are discussing large Enterprise systems. Stock Exchanges. etc. Prove your points using that domain. Please do not show links about someone having problems with installing Solaris. Or someone having problems with an ancient Solaris version that is hardly supported anymore. As of now, you only make yourself an idiot, that knows nothing about large Enterprise systems.

If someone wants 'profffs' :P
Proofs of what? Exactly what have you proved? That Solaris sometimes exhibit installation problems? That ancient Solaris v8 shows some problems? How do you reason? Seriously? We are talking about large Enterprise systems. Jesus. It is totally differnt to discuss large Enterprise systems and desktop usage with toy database MySQL. Shit man. You are lost. I work in large enterprise systems, and your questions are so strange and weird I just wonder. It is like you ask me "when driving a car, where do I insert my coin?" - what coin? Why should you insert money into a car? What are you talking about? Money? Are you completely lost?? Jesus.

Rip-Rip

08-02-2009, 03:22 PM

[...]
Now, do you understand? I am not saying that Linux is 250 times slower than Solaris. I say that Linux can still be improved much more on other areas, whereas Solaris can not be improved. And this is indicium that Linux is not mature. Do you understand?
[...]

Hi,

I didn't read the whole topic so maybe you've already answer to my questions. Did you compare, I mean on same hardware, with real charts, Solaris against Linux on those "Big Iron"? Also, how can you be sure that Solaris can not be improved?

Thanks for your response

kraftman

08-02-2009, 05:34 PM

You dont understand what I am trying to say. I am not saying that Linux is 250 times slower than Solaris. I am not trying to say that Linux page fault is 250 times slower than Solaris. You dont understand.

You're according to my comment about pdf (where - ;) is and this means, 250 times faster was a joke there :>), but I already answered this before.

I am trying to say that just recently, Linux had some great scalability problems on 64 cpu machines. Linux is still inmature on Big Iron. I bet there are lots of other areas where Linux still has scalability problems. Solaris has been doing this on Big Iron for decades. I doubt Solaris performance can be 250 times increased.If you read this pdf and looked at those tests 2.6.8 scales very, very well. I'm trying to say those tests you saw was fake - gnu malloc, improper kernel config etc. I now wonder what you mean. You said you don't consider Linux is 250 times slower then Solaris, but you're saying now you doubt Solaris performance can be 250 times increased. This is like Linux performance was increased 250 times, but only page fault is faster and we don't if this have big impacts on performance/scalability. Again, 2.6.8 (it will be my favorite now ;)).

This is not true, but I am trying to say something like: If it is impossible to improve Solaris performance 250 times, but you can still improve Linux 250 times - which is most mature? I bet there are still large optimizations to be done on Linux. Linux is not mature, it has not scaled on Big Iron for decades yet.
Answer Rip-Rip question please.

About profffs. It was a joke to show this discussion is idiotic... You see - profffs. I make grammar mistakes, but not like this ;) The problem is there's too much FUD about Linux scaling. It's even mentioned in one of the articles you gave. Sorry I ignored you're reply before. I should response to you...

frantaylor

08-03-2009, 12:29 AM

You're according to my comment about pdf (where - ;) is and this means, 250 times faster was a joke there :>), but I already answered this before.

If you read this pdf and looked at those tests 2.6.8 scales very, very well. I'm trying to say those tests you saw was fake - gnu malloc, improper kernel config etc. I now wonder what you mean. You said you don't consider Linux is 250 times slower then Solaris, but you're saying now you doubt Solaris performance can be 250 times increased. This is like Linux performance was increased 250 times, but only page fault is faster and we don't if this have big impacts on performance/scalability. Again, 2.6.8 (it will be my favorite now ;)).

Answer Rip-Rip question please.

About profffs. It was a joke to show this discussion is idiotic... You see - profffs. I make grammar mistakes, but not like this ;) The problem is there's too much FUD about Linux scaling. It's even mentioned in one of the articles you gave. Sorry I ignored you're reply before. I should response to you...

2.6.8 kernel is NOT supported by RedHat or SUSE. Customers will not run kernels that are not supported. Period. End of sentence. It could be 1000 times better than the installed kernel and it would still not matter.

If 2.6.8 kernel is so wonderful, then why is it not available on a commercially-supported distribution?

Here is a typical Linux FAIL scenario:

Customer has hard limit for transaction completion, say 5 seconds with 10000 users. Linux may complete 99.9% of transactions in 1.5 seconds, but 0.01% come back in 6 seconds, FAILING the test.

On same hardware, Solaris completes 100% of transactions within 5 seconds and PASSES the test. Even if the average response time is twice Linux, Solaris WINS and Linux LOSES.

frantaylor

08-03-2009, 01:15 AM

In case you were wondering, here are customer scenarios that require hard transaction time limits:

- Customer is automobile manufacturer, and cannot afford to stop assembly line to wait for query results

- Customer is stock trader and has upstream performance promises to their customers.

- Customer is bioengineering firm and cannot wait for samples to spoil before receiving test results.

- Customer is Turnpike Authority and must process SpeedPass accounts to avoid traffic jams at toll booth.

- Customer is Lottery Commission and cannot tolerate hundreds of thousands of unsatisfied customers 10 minutes before drawing.

- Customer is package shipping company that cannot stop conveyor belts to wait for package routing information.

- Customer is commercial airline and cannot hold flights to wait for passenger manifest generation.

- Customer is NOT junior in long underwear playing with daddy's computer.

kraftman

08-03-2009, 04:58 AM

2.6.8 kernel is NOT supported by RedHat or SUSE. Customers will not run kernels that are not supported. Period. End of sentence. It could be 1000 times better than the installed kernel and it would still not matter.

If 2.6.8 kernel is so wonderful, then why is it not available on a commercially-supported distribution?

Here is a typical Linux FAIL scenario:

Customer has hard limit for transaction completion, say 5 seconds with 10000 users. Linux may complete 99.9% of transactions in 1.5 seconds, but 0.01% come back in 6 seconds, FAILING the test.

On same hardware, Solaris completes 100% of transactions within 5 seconds and PASSES the test. Even if the average response time is twice Linux, Solaris WINS and Linux LOSES.

You're so f*cking troll XD. 2.6.8 is very old kernel. You're a moron XD Point was this if such old kernel scales wonderfully at least up to 64 CPUs on "Big Iron" machine, newer kernels scales even better. You're talk about transactions is bullshit and it's opposite to what you said before. Thanks a lot. I wouldn't be surprised if Yotambien is hidden under those 'new registered' nicks. Similar style XD I have no doubt, 2.6.8 is my favorite one XD

MartjeB

08-03-2009, 05:04 AM

Here is a typical Linux FAIL scenario:

[..trolling..]

Solaris WINS and Linux LOSES.
What are you talking about? Really, if I should say the same thing replacing Solaris with Linux and the other way around in that sentence, would it make *any* sense?

You're just making something up and then you say Linux sucks? What the heck?

Look:
Here is a typical Solaris FAIL scenario:

Customer has hard limit for transaction completion, say 5 seconds with 10000 users. Solaris may complete 99.9% of transactions in 1.5 seconds, but 0.01% come back in 6 seconds, FAILING the test.

On same hardware, Linux completes 100% of transactions within 5 seconds and PASSES the test. Even if the average response time is twice Solaris, Linux WINS and Solaris LOSES.

kraftman

08-03-2009, 05:11 AM

@MartjeB

I think they/he is already full. No more feeding from my side ;).

kebabbert

08-03-2009, 05:11 AM

Rip-Rip
"I didn't read the whole topic so maybe you've already answer to my questions. Did you compare, I mean on same hardware, with real charts, Solaris against Linux on those "Big Iron"? Also, how can you be sure that Solaris can not be improved?"

I am not saying that Solaris can not be improved. I am saying that I doubt Solaris can be improved 250 times, just as Linux. Maybe Solaris can be improved 100% or so. But I doubt Solaris can be improved 25000% just as Linux.

I am trying to say that Linux can be improved much 250 times, while Solaris can not maybe 2 times. I have no proof of this, but I suspect this. Because Solaris has run on Big Iron for decades, whereas Linux has not. During these decades, Solaris has corrected all those obvious slow downs, that Linux suffers from.

As I said, I have no proof of this. But I suspect this. And it sounds reasonable, that a Operating System that has run for decades on Big Iron has ironed out the most obvious slow downs, and now only smaller optimizations is left to do? While a fresh Operating system still has lot of large improvements to do? Is it reasonable?

The problem is that not all Linux kernel devs have access to Big Iron, only a few has. Whereas all Solaris kernel devs have always access to Big Iron. The majority of Linux patches will not be about Big Iron, only about 2-4 CPUs and clusters.

Kraftman,
Regarding your pdf showing that "Linux scales very well" - fine. But I doubt that Linux scales very well in general. It seems that Linux scales well on one benchmark. Linux DOES scale well, on large clusters. That is well known fact. Everyone agrees on this. But on Big Iron, Linux sucks. Here are some Linux experts on scalability. They say Linux sucks on big Iron, but is very good on clusters:
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci929755,00.html
You hear that Linux is good on 10.000 cpus, no Big Iron has 10.000 cpus. They have only 100 or so CPUs. If they talk about scaling on 10.000 cpus, they always mean clusters, which basically is a network.

frantaylor

08-03-2009, 07:42 AM

kebabbert

08-03-2009, 04:04 PM

frantaylor

08-03-2009, 05:44 PM

frantaylor,
Interesting post. You state that Solaris is slower than Linux from your experience. That is interesting.

I wonder, have you tried both OS on large machines with lots of CPUs and large load? From reading articles I get the impression that Linux is good on few CPUs but jerks and stutters when having to use many CPUs, whereas Solaris runs evenly on many CPUs. Maybe Solaris flows slower than Linux on few CPUs, but I suspect Solaris flows better on many many CPUs, it doesnt hickup. Whereas Linux runs fast on few CPUs and hickups and stutters on many CPUs, it doesnt flow smooth and even.

Linux is like a small car, it is fast but as soon it has to climb a height or carry large load, the car looses speed. Solaris is like a big loader, it maybe is slower on light load but doesnt slow down when climbing big heights or carrying large loads. The big loader with the strong motor just runs and runs, not matter what work to do.

Kind of. What does your experience say about this analogy?

That sounds right to me. Although even with all of that stuttering, Linux does manage to give more of the CPU to the threads and consume less in the kernel. It's just that it's not even. Some threads get lots of CPU and some get very little. It's the threads that are starved of CPU that are the problem. Like I said, it doesn't matter if Linux gets the job done faster on average. What matters is that ALL the threads finish in a timely manner.

Thanks for your response. There are lot of people on this board who take any Linux criticism way too personally. For goodness sake, it's just software. I get the feeling that most of these foul-mouthed people are just bored trust-fund babies with too much money to spend on their watercooled gaming rigs.

And who knows, maybe someday Linus will start paying attention to people who know something about process scheduling. There's always hope.

kebabbert

08-04-2009, 03:47 AM

In other words, Linux does not scale well on big machines with many CPUs. Because Linux doesnt treat the CPUs evenly. If some threads gets lots of CPU, and others starves, then Linux is not suitable to run on many CPUs. Then Linux will be better on few CPUs.

Or more suited to large clusters, where each node has few CPUs. You do not want Linux to run on many CPUs. Better to divide-and-conquer: split all 10.000 CPUs down to many nodes, where each node has few CPUs. And run Linux on each node. Because Linux can not handle 10.000 CPUs as a whole. (I doubt Solaris can handle that many CPUs well).

kraftman

08-04-2009, 05:08 AM

Okay, my point is subtle so please read carefully. I do not dispute that Linux scales well. I do not dispute that Linux will handle a workload faster than Solaris.

What I am saying is that with Linux, all threads do not receive equal CPU access. Some get more than others. There is a lot of variation. I can see this myself on my 8-core box. I can start up 8 "tar czf" commands on a big directory and watch them all run. They do not all get the same amount of CPU. They do not all finish at the same time. Some of them take much longer. Solaris is less efficient, but the kernel is better at making sure that all the threads are getting CPU equally.

You've got to have properly configured kernel. You should know this if you're an expert shouldn't you? CFS is here (however, reagrding to what you wrote later it can be related to something else).

No you do not know me. I am not who you think I am.It's hard to say - And who knows, maybe someday Linus will start paying attention to people who know something about process scheduling. There's always hope.So trollish...

I have been writing code for Unix since BSD 4.2 on a PDP-11. I still have an SLS CD-ROM with 0.99pl3 kernel that I ran on my '486. I have used many kinds of UNIX boxes from Data General to SGI workstations to huge AIX machines. I love Linux, it runs on all my computers. I run Fedora on my machines and I submit bug reports and patches.You can even be Santa Claus, but your previous talk was just a bull. You said before Linux doesn't scale well, now you said something different. What's wrong? SGI you say, so you should know:

http://www.prnewswire.com/cgi-bin/stories.pl?ACCT=104&STORY=/www/story/09-09-2002/0001796550&EDATE=

"Demonstrating linear scalability from 2 to 64 processors..." 2002... don't ask me which kernel...

All I am saying is that Solaris is better if you need your CPU threads to be distributed evenly. Otherwise it sucks. I don't want it on my desktop and I would not run a web server on it. But I will run a big SQL database on it if my users need their SQL queries to complete in a timely manner every time.Again, you need to properly configure kernel to receive fairness (in your case I suppose, distro or rhel...).

One thing that does bug me about Linux is the regressions. I go to a lot of trouble to set up a box in a certain way. Then I run a software update and now something does not work. For instance my laptop used to run Google Earth just fine. I did a software update and now it does not work. Once I could not even log in after a software update because of a change to a gnome config file, it took far too much of my time to figure that out.Distros/gnome problem? You're amazing me...

There is also a lot of unfinished stuff in Linux. I have to work with IPv6 and the kernel support is perfect. But userland has not caught up. Stuff that just works in IPv4 needs to be tweaked for IPv6. The DHCPv6 client sometimes gets stuck and I have to kill it. I also had to patch SELinux to get the DHCPv6 client to work. I don't have these problems with IPv6 in Solaris or even Windows, everything works great as is.Some userspace problems? Not Linux kernel - it's IPv6 compliant. However, it seems FUD about scalability is just FUD now you're trying to make a flame?

Can we please put a lid on the swearing and name calling?Sure, but why you didn't post smarter comments before?

I am here because I want to learn how to make my Linux machines run better. I thrash on them hard for my job and I spend too much time waiting for them. I have learned a lot over the years about performance and sysadmin and I would like very much to share. Unfortunately it seems that this site has many spiteful people who get their kicks by insulting and swearing and name-calling. I don't have time for this either.It's because you're not right and/or your arguments are too weak.

In other words, Linux does not scale well on big machines with many CPUs. Because Linux doesnt treat the CPUs evenly. If some threads gets lots of CPU, and others starves, then Linux is not suitable to run on many CPUs. Then Linux will be better on few CPUsYou base on what? If years ago it scaled without problems up to 64 CPUs on big iron? RCU can be something what Frantaylor is missing, but he started posting little smarter comments, so maybe he will explain.

It's the threads that are starved of CPU that are the problem.I'd love to hear more about this. It can be true, but can you explain this better?

frantaylor

08-04-2009, 07:13 AM

frantaylor

08-04-2009, 07:38 AM

At my company we have big SMP systems that were set up by RedHat and SuSE engineers for our testing. We told them to do their best because we use these systems to sell our product. They want to sell their product too, so they worked hard to do a good job. We also invite Sun and HP and IBM to do the same, and we have machines from them too. We demo our product to our customers on all the machines, and we show them the price tags. Of course the Linux solution is a small fraction of the price of the big vendor solutions, but they buy the big expensive ones anyway.

kraftman, please explain to me how RedHat and SuSE can fail to sell systems in this environment, where we give them the opportunity to showcase their product. They take us very seriously and they send their best engineers.

kraftman, I know a lot of really smart people, and none of them show the arrogance and lack of tact that you do. Many of my coworkers have advanced degrees from MIT and Stanford. They are genuinely interested in sharing their knowledge and they do not slight the works of others. They do not engage in name-calling and swearing. If someone is misinformed, they find a polite and casual way to explain the situation instead of heading straight into insult mode. Perhaps your technical skills are very good, but your people skills are very poor. These technical skills are useless unless you have the ability to work well with others and share your insights.

kebabbert

08-04-2009, 07:53 AM

Kraftman,
I dont buy that "there is nothing wrong with Linux, the problem is somewhere else". If the computer crashes, then it crashes. It doesnt matter who did it. It crashed. End of story.

If the computer lags, then it lags. It doesnt matter which kernel you used, or how you configured it. It lags.

Solaris uses the same install DVD from small desktops (laptops) up to Big Iron. It is the SAME kernel. That is scalability. For Linux you have to tailor and configure and change and recompile the kernel. That is hardly scalability. Linux is configurable, not scalable.

People says that they want to see more OpenSolaris features. Then the solaris kernel developers says that they accept patches if they are good. And always people shun away and think that ZFS is an incredible complex piece of software, and they are not able to patch it. Neither is Solaris kernel easy to patch, it is that complex. There is a one week course on ZFS, the architecture and the source code. And that is not enough. It is that complex. Whereas Linux has a more simple structure.

Anyway, kraftman, maybe you should work in large enterprise systems and see yourself? Maybe then you will realise that it is different thing to run Linux on desktop and on large systems. For desktop Linux is good, yes. For large systems, it is not so good, it doesnt scale, etc. You seem to have little experience of large systems. Get some experience, then we can continue this discussion. Meanwhile, listen to people with experience of large systems.

You know desktop Linux. Not large systems. They are totally different animals. It is a mistake to think that Linux will behave the same on both.

kraftman

08-04-2009, 07:59 AM

This whole thread is just getting boring.

kraftman should get a job at RedHat, provisioning systems. If he is as good as he says he is, he can make a lot of sales for them. Apparently he can do things that the RedHat and SuSE engineers cannot.

Again I made mistake... It seems you can't explain anything I asked for. You failed to give a reliable arguments, proofs. I showed you Linux scales great on big irons since 2002. Another examples:

http://linux.sys-con.com/node/45704
http://www.thefreelibrary.com/NEC+Solutions+America+Offers+First+TPC-C+Benchmark+on+Intel+Itanium...-a0115026313

You should also know RedHat established record when comes to high power servers.

This whole thread is just getting boring.

It's boring till begining. Typical trollish scenario.

@Kebbabert

If the computer crashes, then it crashes. It doesnt matter who did it. It crashed. End of story.

Same about Solaris. But in this case you should take into consideration Franteylor is a troll.

Anyway, kraftman, maybe you should work in large enterprise systems and see yourself?

You wrote similar thing using previous nick man :> Anyway, maybe you should work in large enterprise systems and see yourself? However, such dumb people who can't answer simple things and who don't know what 2.6.8 means when comes to kernel...

That is hardly scalability. Linux is configurable, not scalable...

Best luck running unmodified Solaris on desktop, server and HPC using same config. Yeah, this is one of the most idiotic things I ever read.

frantaylor

08-04-2009, 09:05 AM

kraftman

08-04-2009, 09:45 AM

"Franteylor is a troll."

From Wikipedia:

"In Internet slang, a troll is someone who posts controversial, inflammatory, irrelevant or off-topic messages in an online community, such as an online discussion forum, chat room or blog, with the primary intent of provoking other users into an emotional or disciplinary response or of otherwise disrupting normal on-topic discussion."

I believe this describes kraftman quite well...

It seems your knowledge ends here. You, your friend (or just you?) tried to proof Linux doesn't scale on big irons. I even pm'ed you (Kebbabert and another new registered guy) to give some different look, but you ignored this. You're the one who's provocating others, because if I want to drill some topic further you're just hidding. I shouldn't reply (to not make Yotambien happy), but this is my weakness :>

Best luck running unmodified Solaris on desktop, server and HPC using same config. Yeah, this is one of the most idiotic things I ever read.

...with full performance.

The point is you don't point anything, but just talk. For your information 2.6.27 allows Linux to scale up to 4096 CPUs without providing overhead when much less CPUs are used.

...this includes performance and stack footprint optimizations for crazy
SGI systems with 4096 CPUs

P.S. I know and it's more then believe :>

P.S. 2 Thanks you very much! Your post is last. What you wrote in next post can be related to Solaris benchmarks etc. etc.

This is the difference between reading a bunch of stuff on the web, and having to deal with real applications.

You can't proof this and this is why such discussion is meaningless. It can be opposite, but can we proof? You're not trustworthy to me, so I don't buy it.

Oracle has pretty crummy performance anyway, compared to their competitors. It is a nightmare to set up and configure correctly, and it falls down if there is the slightest problem. Their client drivers are the very definition of bloatware. It doesn't even matter if the server is fast, if the clients are dragged down by crummy drivers.

Yeah, Sun's servers are the best. We all know this...

@Kebbabert

Yes, but the difference is that Solaris doesnt becomes unstable, when Linux does. If Solaris crashes, then it crashes. I dont buy "it was because of the ...., it was not the kernel".

Nope, difference is Linux doesn't becomes unstable, when Solaris does.

Regarding your profffffs that Linux scales well, that is good that you try to provvvvve things, instead of making things up. But you know, 32 cpus are not many cpus. That is chicken shit. And also, your link admits that Linux doesnt scale well. Have you read your link?

There are also machines up to 64 CPU's and it is 2002 and 2004 year, so as I mentioned few times old kernels were able to scale very well on big irons.

Do you really believe that any OS can go from small servers up to Big Iron in a few years? It takes decades and is very complex. Windows hasnt succeed despite many years of optimization.

No, I just know this and this is a big difference. Windows aims mainly for desktops. I'll try to stop here, because if you don't accept normal arguments/proofs it's just waste of my time. I already answered many times to what you're repeating in your last comment.

@Frantailor

What about Wallstreet?

I'm really patience XD

Kebbabert you're on my ignore list now :>

frantaylor

08-04-2009, 09:54 AM

The TPC-C benchmark does not measure the worst-case performance, it measures the best-case performance. These benchmarks are interesting, but they do not reflect actual performance in the field, and they do not take into account the fact that some applications require hard deadlines for completion of transactions.

We all know that these benchmark programs are rigged to show good performance. In some cases, companies are known to put in code that detects that the benchmark is running, and fakes out the benchmark program, inflating the results. They are also known to put a lot of work into optimizing the code so that the benchmark runs well, at the expense of ordinary applications that do not use the same types of queries and table layouts as those used for the benchmarks.

Again as I said, Linux can crunch very well on average, but customers do not care about that. They need to know that their queries will complete within a set timeframe. These benchmarks do not measure this.

This is the difference between reading a bunch of stuff on the web, and having to deal with real applications.

Oracle has pretty crummy performance anyway, compared to their competitors. It is a nightmare to set up and configure correctly, and it falls down if there is the slightest problem. Their client drivers are the very definition of bloatware. It doesn't even matter if the server is fast, if the clients are dragged down by crummy drivers.

kebabbert

08-04-2009, 10:13 AM

Same about Solaris. But in this case you should take into consideration Franteylor is a troll.
Yes, but the difference is that Solaris doesnt becomes unstable, when Linux does. If Solaris crashes, then it crashes. I dont buy "it was because of the ...., it was not the kernel".

You wrote similar thing using previous nick man :> Anyway, maybe you should work in large enterprise systems and see yourself? However, such dumb people who can't answer simple things and who don't know what 2.6.8 means when comes to kernel...
I dont have any other nicks here. Why do you believe that? Have other people told you to get some experience of large systems, than me and frantaylor? Why am I not surprised?

Best luck running unmodified Solaris on desktop, server and HPC using same config. Yeah, this is one of the most idiotic things I ever read.
The Solaris kernel is the same on all machines. It is the same install DVD. There are no other Solaris distros with different kernels. It is one and only kernel used on Big Iron with many many CPUs, down to laptops.

Regarding your profffffs that Linux scales well, that is good that you try to provvvvve things, instead of making things up. But you know, 32 cpus are not many cpus. That is chicken shit. And also, your link admits that Linux doesnt scale well. Have you read your link?

"Linux had a hard time running on servers larger than 16GB due to the way in which large memory management was implemented on Linux and in hardware (IA32). Because it was hard to stabilize a large memory system, scalability beyond eight CPUs on Linux was difficult; large memory and a larger number of CPUs tended to go hand-in-hand.

For example, some applications are built to run on large CPU systems and some data warehouse environments still require an SMP box. Until now, it wasn't possible to consider moving them to Linux. However, with Linux 2.6 coming up in enterprise distributions soon (SUSE/Novell SLES9 will be the first), it looks like the top end of the server market is within the reach of Linux."

Do you really believe that any OS can go from small servers up to Big Iron in a few years? It takes decades and is very complex. Windows hasnt succeed despite many years of optimization.

And last thing; TPC-C is useless and is not representative of real work loads. Every database admin says this. Ask them. For instance, IBM hold the TPC-C record recently. It was a $17 million machine with 2TB RAM! No admin has access to such TPC-C machines. They dont exist in companies, but are pathological machines built only for TPC-C then taken down. TPC-C is not representative of a real load.

Post instead links of Linux doing large work loads on real stuff. Not some benchmarks. You know, Linux performs very well number crunching, calculation mathematical things on large clusters. But that Linux kernel is stripped down and can not do anything else than calculate. It can not handle many users logged in doing lots of work. Why dont you post Linux number crunching benchmarks as well? Linux excels in doing one thing and can show high numbers.

But doing one highly specialized thing and doing general work, are two different things. You still dont understand this? You think that 32 cpus is great? You think Linux on desktop is great, and therefore it can handle any work load with many CPUs? Do you know that there are lots of histories of Linux companies have to switch to Solaris, because their work load increases beyond what Linux can handle? Do you want me to post some of them links?

I dont post links showing Solaris runs fast on one CPU, or Linux can not install on a machine, those links you post. I post links about large systems, Enterprise things - where Linux doesnt cut it. I challenge you to post such links about Solaris. (You will not find any links about Solaris underperforming. But there are lots of links about Linux underperforming). Post links about Solaris failing on large systems, if you can. You can not. Whereas I can easily find and post several on Linux failing on large systems.

frantaylor

08-04-2009, 10:48 AM

Windows aims mainly for desktops.

The original Windows NT developers were poached from Digital's VMS team by Microsoft. They were specifically tasked with creating a server operating system that would scale to many processors. The only reason it went to the desktop is because Microsoft's desktop OS (Windows 95) was a disaster and they had nothing else to offer.

frantaylor

08-04-2009, 11:11 AM

The TPC-C benchmark results touted in the linked article were run on Itanium, a very different architecture from the Intel architecture that the vast majority of Linux applications run on. Itanium was designed from the ground up for server performance, the results you get on it will not translate well to Intel or AMD systems.

The vast majority of the Itanium systems sold are HP boxes running HPUX or VMS or Tru64. Dell was selling Itanium Linux and Windows systems but they only sold a very few, so they gave up. SGI was selling them too, and we all know what happened to them.

Again, if these benchmark numbers meant anything, everyone would have rushed out and bought a nifty new Itanium machine. The only ones I ever see are in our lab.

kebabbert

08-04-2009, 12:35 PM

kraftman,
"Nope, difference is Linux doesn't becomes unstable, when Solaris does."

Ok, I challenge you to show at least ONE link that backs up your statement. Just one. Not two. But one. Go ahead. You will not find any such links.

Meanwhile you search, here are some links showing that Linux just doesnt cut it on large systems (not desktop, but large systems):

Here is a Linux company forced to switch to Solaris.
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1286507,00.html#

"The company's CEO, Joshua Rand, started the company with the free Fedora Linux distribution. That worked well enough for a small startup, but as business scaled, Fedora's effectiveness declined. So in 2005, Sapotek moved to a commercial version of Linux: Red Hat Enterprise Linux (RHEL).

After two years of trying to make RHEL work, Rand had to move on. He looked closely at Solaris 10 and, after speaking with Sun engineers about a possible migration, decided to give Sun's Startup Essentials program a try.

"Being Linux people, we were hesitant to switch," he said. "We didn't even consider [Microsoft] Windows, because we are open source," said Rand. "Sun set up some virtual servers for us to run tests, and we ported all of our apps onto those virtual servers. We did load testing, saw that it worked well and decided to go ahead with the migration."

Sapotek now runs Solaris 10 OS on Sun 4200 servers with 64-bit Advanced Micro Devices Inc. Opteron quad-core processors, along with Sun's x4500 storage unit.

The improvement is significant; with four compute nodes instead of five, Rand has more computing power and 99.99% uptime, compared with 97% uptime with RHEL, he said.

"With this switch, we've gone from playing in the sandbox to getting our doctoral degree. You can't even compare Red Hat GFS to Solaris ZFS," Rand said. "We no longer need to do all those chores we had to do with Linux. I can't even quantify the number of man-hours we freed by moving to Solaris. We have so much more time to develop our software now."

Another one:
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1313798,00.html

You want more links? Just ask. Now, can you find ONE LINK showing Linux is more stable than Solaris on large systems? No you can not. Why can you not find such links? Is it because such links doesnt exist?

You claim lots of things but prove none. When you "prove" something, your links are just weird. One guy can not install ancient Solaris 8 on a PC - which shows that he had a missing device driver or something. That link doesnt show Solaris performance on large systems. Another link of yours showed a shitty 32 CPU machine with an artificial BENCHMARK. Not real work.

Come on, mr big mouth. Prove your claims. Show ONE link about Solaris on large systems. Do not show links on installation ancient Solaris 8. I really really wonder how you reason. Your arguments are flawed and your logic just strange. Not correct logic. Your links are strange, and doesnt prove any one of your points. You dont know how to prove things. "My cycle is stolen and I want to prove it by eating dinner up side down" - really really strange logic and reasoning.

frantaylor

08-04-2009, 01:23 PM

97% uptime with RHEL

I've never ever seen an uptime percentage so low. The guys I know at the UPS datacenter (they use IBM mainframes) claim 99.9999% uptime.

The IT people at the NYSE lose their entire yearly bonus if their uptime drops to less than 99.99%. They use Linux, but it took a 15 year migration project to get off of HPUX. Even so they use way too much hardware and alarms go off if any machines have a load average of more than 0.1. They do not believe in putting any kind of a load on their machines, they are afraid of performance slowdowns. They know full well that Linux does not behave well under load.

kebabbert

08-05-2009, 05:13 AM

kraftman,
If you can not show any links about Solaris becomes unstable on large systems under large load, then you are a liar and FUDer just like that Matt Bryant thingie. You are just spreading FUD about Solaris. You dont know shit, and still you claim various things and "proves" them with irrelevant links.

You want to prove that Solaris becomes unstable on large systems under high load, and shows a link on a guy has problems installing ancient Solaris 8 on a desktop? What? Are you just weird or strange or a liar? Whenever I state something about Linux on large loads, I have shown several links. In fact there are many links on Linux not coping large load, including the one you posted. I dont make things up, nor do I FUD or lie. There are numerous testimonies about Linux having problems. I have showed several links where Linux kernel devs complain about the low Linux code quality - and you just refuse to consider those links. What? Are the Linux kernel devs lying?

Until you can prove any claim you have made, I will call you a FUDer and liar. You are spreading FUD about Solaris. There is no proof backing your claims up. There are no links showing that Solaris becomes unstable on large systems under high load - just as you claim.

kraftman, you are spreading FUD. And spreading lies, too.

But of course, if you can show ONE link, then you are not lying. Then you are telling the truth. Then I will apologize. But until then, you are a FUDer and liar.

frantaylor

08-05-2009, 10:16 AM

kraftman

08-05-2009, 10:58 AM

If you look at his other posts you can see where he links to a devastating kernel bug that causes terrible performance issues. He knows full well that Linux has major issues and he just ignores them when he wants to make his argument. He is even worse than all the things you accuse him of.

You're still amazing me XD It seems you don't believe such bug exists:

Did you read the comments in the bug report?

"this bug has long past the point where it is useful.
There are far too many people posting with different issues.
There is too much noise to filter through to find a single bug.
There aren't any interested kernel developers following the bug."

It is not even a bug report, it is just a random flame festbecause it ruins your entire theory :>

About this bug. Only some system configurations are affected (probably not so many, because I saw only one report at lkml about this issue). There's also workaround and some tuning helps some people.

@Kebbabert

Still, I already said everything about what you're babbling here :>

@Frantaylor

Will you be so kind to not quote his text next time please?

kebabbert

08-05-2009, 06:48 PM

"Still, I already said everything about what you're babbling here :>"

Still Ive asked you to show one link, and you can not. Then please stop spreading FUD about Solaris or you are a liar. You do not consider yourself as a liar, I hope. So please stop FUDing about Solaris.

mudd1

08-07-2009, 09:32 AM

I'm really too lazy to read the whole thread so excuse me if I just don't know what you're flaming about. But it seems to me as if an example of someone switching from Solaris to Linux was searched for. Well, our department is currently doing this. Solaris had major issues with performance on very full disks, unbootable servers due to a zfs partition corrupted by Solaris, the Sun hardware itself also corrupted many files and the Sun support was more than lousy as far as I heard (of course Sun themselves called it "Platinum", not "lousy"). Maybe Sun isn't what it used to be.

frantaylor

08-07-2009, 10:41 AM

mudd1

08-07-2009, 11:20 AM

In all my years of computing I have never seen a system that exhibited robust behavior with full disks. Even with systems that are otherwise quite bulletproof, all bets are off when the disks fill. It's like expecting robust behavior from an airplane when it runs out of fuel in the middle of the sky.

Sure, but I wasn't talking about full disks as in "no space left on device". I was talking about 80-90% full disks that lead to an I/O speed dropping to a few kilobytes per second. Not a very good thing to happen with hundreds of users doing stuff simultaniously on that disk.

kraftman

08-07-2009, 05:20 PM

I'm really too lazy to read the whole thread so excuse me if I just don't know what you're flaming about. But it seems to me as if an example of someone switching from Solaris to Linux was searched for.

'Discussion' if I can say this, was at extremaly low level. It's not hard to guess where such talk usually leads, so there's no motivation to proof anything (cause anyone knows its version...). If you want to have fun read it from begining, but I'm not sure if you'll find there something interesting.

What's easy to realize Kebbabert is some kind of troll or he's just incredibly dumb (however, he ignored my private message, so it looks like he's rather a troll or a dumb troll, whatever...). There's always possibility he just wanted to make me laugh. If yes, thank you very much :)

kebabbert

08-09-2009, 05:28 PM

mudd1
There are lots of people switching from Solaris and from IBM AIX to Linux. This is because of cost issues or politics (as Solaris entry level support is cheaper than e.g. RedHat).

What I asked for, is links showing people switching from Solaris to Linux because of stability issues. I have never seen such testimonies.

Regarding your problems. It is well known that ZFS has some bugs and performance issues. It takes many years to get a file system stable, maybe decades. BTRFS will need many years before even reaching beta phase.

It seems your problems are filesystem related due to ZFS. And not because of stability issues. Solaris has also a mature filesystem, UFS. Maybe you didnt knew that. Anyway, it seems that your problems are about file system and not stability. Hence, I am not really interested in your story. ZFS has bugs and is not perfect. It takes decades to get such stuff good. As Operating System scaling, which also takes decades. Impossible to achieve in a few years. It takes decades.

Kraftman,
regarding your PM. I didnt notice them until now, why fork the discussion from the forum over to PM? Anyway, Ive read your PMs, and your links now. I must say your "profffffs" are strange. You reason weird. You show me links from Linux v2.2
http://www.astahost.com/info.php/Linux-Unix-Kernels_t961.html
vs ancient Solaris. That doesnt prove anything about current status. And also, your link doesnt talk about stability or anything.

You may have heard about current Solaris 10. It is version 5.10. Years earlier we had Solaris 9, which is Solaris v5.9. And Solaris 8 which is Solaris v5.8. Your link talks about Solaris v2.2!! Jesus, it is old. Your link doesnt prove anything.

Regarding your comment to why Linux is successfull, and Solaris is not - and point to the link. I dont agree. Linux is successfull not because of technical merits - because Linux has no technical merits. Linux has no new tech, Linux just copies. Linux copies ZFS and call it BTRFS. Same with DTrace and other techniques. Linux follows and copies. Linux doesnt invents. And it is unstable with unstable API/ABI. No technical merits.

The reason Linux is successfull is because it is possible to big large companies around Linux. Some analyst explained this. You can found a Linux company and be dollar billionare. Nobody "owns" Linux. But you can not found a large company around Solaris or FreeBSD - as someone owns them Operating Systems. You can be rich on founding a Linux company. Someone else develops Linux, you just package and sell it. You do no work, it is like selling air. And you become a dollar billionare. That is the reason Linux is successfull. If Linus would release his own Linux distro, saying that "this is the official Linux distro" then everyone would abandon Linux. Linux would be as Freebsd - owned by some one. RedHat would die. Everyone would use Linux own distro. No more dollar Billionare. No more Linux.

KDesk

08-09-2009, 09:27 PM

The reason Linux is successfull is because it is possible to big large companies around Linux. Some analyst explained this. You can found a Linux company and be dollar billionare. Nobody "owns" Linux. But you can not found a large company around Solaris or FreeBSD - as someone owns them Operating Systems. You can be rich on founding a Linux company. Someone else develops Linux, you just package and sell it. You do no work, it is like selling air. And you become a dollar billionare. That is the reason Linux is successfull. If Linus would release his own Linux distro, saying that "this is the official Linux distro" then everyone would abandon Linux. Linux would be as Freebsd - owned by some one. RedHat would die. Everyone would use Linux own distro. No more dollar Billionare. No more Linux.

You are confused...

Self made operation systems based on Linux can be distributed as a Linux-based distribution because the license (mostly GPL) of the individual parts which conform the distribution allow to do this.

FreeBSD uses mostly (and prefer) the BSD license, which is less restrictive that the GPL. This gives everybody the chance to create their own FreeBSD-based distribution.
This is way distributions like PC-BSD, DesktopBSD and also Debian GNU/kFreeBSD exists.

This is one of the advantages of the FOSS, which FreeBSD, Linux, and many Open Solaris components are part of.

So, what you say is not a valid argument.

Did you know that Linux has almost 90% of the Top500 OS share? http://www.top500.org/stats/list/33/os Ah, and Open Solaris has 0.2%, congratulations!

Apopas

08-10-2009, 04:40 AM

Regarding your comment to why Linux is successfull, and Solaris is not - and point to the link. I dont agree. Linux is successfull because of technical merits - because Linux has no technical merits. Linux has no new tech, Linux just copies. Linux copies ZFS and call it BTRFS. Same with DTrace and other techniques. Linux follows and copies. Linux doesnt invents. And it is unstable with unstable API/ABI. No technical merits.
Well, by the way you say Linux has unstable API you make it sound negative as if the Linux's devs can not make one. Actually, unstable API means that it constantly changes because the developers choosed that way. If you agree or not with their ways doesn't matter. The matter is that it's by choice. Only Linux works in that way, well that's an innovation and while that strategy is bad for the mainstream, Linux is succesful. Now, your commnet about the copies of Linux is very vague, a matter of personal opinion mainly rather than justification or even common sense. I even have heard that KDE and Gnome copied Windows because they both use windows and folders...

kebabbert

08-10-2009, 08:44 AM

You are confused...

Self made operation systems based on Linux can be distributed as a Linux-based distribution because the license (mostly GPL) of the individual parts which conform the distribution allow to do this.

FreeBSD uses mostly (and prefer) the BSD license, which is less restrictive that the GPL. This gives everybody the chance to create their own FreeBSD-based distribution.
This is way distributions like PC-BSD, DesktopBSD and also Debian GNU/kFreeBSD exists.

This is one of the advantages of the FOSS, which FreeBSD, Linux, and many Open Solaris components are part of.

So, what you say is not a valid argument.
Maybe I wasnt clear enough. FreeBSD has an official distro. No one can come and make another FreeBSD distro and found a large company around it. Why should anyone pay for the non-official FreeBSD distro? Anyone serious on using FreeBSD, will use the official FreeBSD distro. Not RedHat FreeBSD distro, or whatever. There is ONE official FreeBSD distro.

Linux has no official distro. Linus dabbles with the sucky kernel. Anyone can come and create a Linux distro and found a large company around it and become $ billionaire. Look at RedHat founders. Anyone can take Linux and make lots of money from it. That is not possible to do with FreeBSD. But if there was one official Linux distro by Linus Torvalds, then everyone would abandon RedHat, SuSE, etc. Every serious customer would stick to the official Linux distro, supported by Linus himself.

What do you think serious customers prefer? A windows clone as ReactOS or true Windows by Microsoft? You can not profit large from FreeBSD, no customer will choose your FreeBSD distro variant. They will all use the original.

Did you know that Linux has almost 90% of the Top500 OS share? http://www.top500.org/stats/list/33/os Ah, and Open Solaris has 0.2%, congratulations!
Jesus. We have been through this before just recently. The point is, the Top500 says nothing. On rank nr 5, we find IBM Blue Gene with 700MHz PowerPC CPU. Does this mean that the 700MHz PowerPC is faster than most CPUs?

Linux is easy to tailor to do number crunching, but such a kernel does nothing else. It can only do one thing. Linux scales good on clusters, but sucks on big iron.

Apopas,
Of course it is a bad thing to have unstable API and ABIs! The only reason Linux has unstable is because Linus does not know how to do it right. That is BAD DESIGN. A good design doesnt need to change API/ABIs all the time. Well designed interface is better than badly designed interface.

If you upgrade your Linux kernel, then maybe your drivers will not work correctly. They will crash during certain circumstances. This makes Linux unstable under high load. How in earth can you consider this as a good thing? Have you ever programmed professionally yourself?? I doubt that.

Here we see an example of the unstable Linux kernel. On the Linux kernel mail list, the Linux gurus are fighting again. Alan Cox thinks that the Linux kernel bugs should be corrected, instead of working around the bugs in the applications. When a Kernel bug is corrected, it may break applications, but that is ok. The applications have to be recompiled. Linus T says that he should not blame Kernel bugs, but instead code around the bugs. As a result, developer Alan Cox has quit. Just as Kernel developer Con Kolivas.
http://lkml.org/lkml/2009/7/28/375

All these regressions and bugs in the Linux kernel makes it hard to create a stable environment. Yes, I know Kraftman will consider this lkml thread as FUD and lies, made by me. But you others can read the thread and see all the complaints on the Kernel bugs making it hard to do stable apps and device drivers. The main point being unstable API and ABI. That is the culprit. Unstable API/ABI makes the whole kernel unstable. Which is a BAD THING. Better to design correct from the beginning.

http://lkml.org/lkml/2009/7/24/182
Rafael:
Well, I thought we were expected to avoid breaking existing user space, even if that were buggy etc.

Alan Cox:
I don't know where you got that idea from. Avoiding breaking user space unneccessarily is good but if its buggy you often can't do anything about it.

Linus:
Alan, he got that idea from me. We don't do regressions. If user space depended on old behavior, we don't change behavior.

Apopas

08-10-2009, 09:26 AM

Linux has no official distro. Linus dabbles with the sucky kernel. Anyone can come and create a Linux distro and found a large company around it and become $ billionaire. Look at RedHat founders. Anyone can take Linux and make lots of money from it. That is not possible to do with FreeBSD.
That's exactly the reason Linux rocks. Freedom in every aspect of it!

Apopas,
Of course it is a bad thing to have unstable API and ABIs! The only reason Linux has unstable is because Linus does not know how to do it right. That is BAD DESIGN. A good design doesnt need to change API/ABIs all the time. Well designed interface is better than badly designed interface.

If you upgrade your Linux kernel, then maybe your drivers will not work correctly. They will crash during certain circumstances. This makes Linux unstable under high load. How in earth can you consider this as a good thing? Have you ever programmed professionally yourself?? I doubt that.
Why on earth we have always to repeat again and again old debates?
Plz read this, I have posted it over and over. That's the reason Linux is like that and makes it better than any other operating system. Purely by choice!
http://www.kroah.com/log/linux/ols_2006_keynote.html

kebabbert

08-10-2009, 11:00 AM

That's exactly the reason Linux rocks. Freedom in every aspect of it!
And that is the reason Linux is successfull, whereas FreeBSD is not. You can make lots and lots of money on Linux. Where the money is, everyone goes there. If Linus T said that all Linux distros are obsolete and people should use his official Linux distro, then RedHat would die. Everyone would abandon Linux. No more multi billionaires = no more attention from companies. It is all driven by money. If Linus T somehow forbade people to make money on Linux, it would die. FreeBSD will never produce any dollar billionaires. Neither will OpenSolaris. Because someone "owns" those OS, there is one and only official distro.

I am not confused.

Why on earth we have always to repeat again and again old debates?
Plz read this, I have posted it over and over. That's the reason Linux is like that and makes it better than any other operating system. Purely by choice!
http://www.kroah.com/log/linux/ols_2006_keynote.html
What a bunch of horse shit that article is. Do you really believe that propaganda? Have you read it?

"Last year Dave Jones told everyone that the kernel was going to pieces, with loads of bugs being found and no end in sight."

Also linux dev Andrew Morton complains on this. And Alan Cox. etc etc. So how can the article state that Linux is the most stable OS when the article states the kernel is full of bugs? Did IQ dropped while I was gone?

And the linux design principle ("there is no design, only evolution") that just plainly sucks big time. Why? Because it is hard to make the Linux environment stable. Because there is no stable API/ABI. Linus T says it helps him to make the Kernel more stable and clean. There are no old APIs that have to be maintained, all old things gets removed. The kernel is always up-to-date with current API. No old stuff left. This helps Linus to make a less complex, simple kernel and stable. He says.

That is bull shit. Solaris kernel has frozen the API and ABI since many many years back and old drivers and applications on small desktops work in multi million Big Iron today. Solaris kernel evolves constantly. If you design it right, there are is contradiction between stable API and clean kernel. ZFS, DTrace, etc etc all those tech rocks AND having a stable API/ABI at the same time. It CAN be done. It just Linus that doesnt know how to do that. The SUN company has the largest concentration of PhD in a company, Ive heard. That may be true. The Solaris kernel is complex and intricate, with lots of new high tech all the time; ZFS, Zones, SMF, DTrace, etc. SUN's engineers are top notch. Linux is simple and easily modified as M.Sc Linus rewrites big parts all the time. Then the kernel must be simple to modify - which suits Top500 well.

If I were to start with kernel development, I would surely start with Linux. Because it is friendly and easy. There are lots of links and help to get, starting with kernel development. Solaris kernel has not equally much documentation, and it is the product of many PhDs. I wouldnt dare touch it until Ive become a kernel guru.

You are confused.

kraftman

08-10-2009, 12:41 PM

Well, by the way you say Linux has unstable API you make it sound negative as if the Linux's devs can not make one. Actually, unstable API means that it constantly changes because the developers choosed that way. If you agree or not with their ways doesn't matter. The matter is that it's by choice. Only Linux works in that way, well that's an innovation and while that strategy is bad for the mainstream, Linux is succesful. Now, your commnet about the copies of Linux is very vague, a matter of personal opinion mainly rather than justification or even common sense. I even have heard that KDE and Gnome copied Windows because they both use windows and folders...

That's it :) As far as I know kernel devs prefer 'unstable' API, because there's always better way to do things. Now I know, thanks to you :)

That's exactly the reason Linux rocks. Freedom in every aspect of it!Fanboys don't get it ;)

P.S. Great link from the great source if you know what I mean :>

@KDesk

Yeah TOP-500 where Linux killed Solaris (incredibly quick IMO). The same situation is probably when comes to 'big irons', but it looks we can have endless discussion here... If XEN will be merged it's possible other systems will loose it, because it must satisfy Linux's kernel standards and thus it has to be modified (maybe there's another possibility, but this one is what I read). If this happen we'll probably have similar situation like when comes to TOP-500.

@Kebbabert

Regarding your comment to why Linux is successfull, and Solaris is not - and point to the link. I dont agree. Linux is successfull because of technical merits - because Linux has no technical merits. Linux has no new tech, Linux just copies. Linux copies ZFS and call it BTRFS. Same with DTrace and other techniques. Linux follows and copies. Linux doesnt invents. And it is unstable with unstable API/ABI. No technical merits.Hahaha, i.e. Linux's RCU (and then hierarchical RCU) is something you can dream about as Solaris or *BSD, or whatever user (if you have a lot of CPUs). Linux follows in some ways, because like I mentioned before they aren't reinventing the wheel and they make new stuff also. You're saying something opposite to what you were claiming before. The most important Linux's merits are performance, scalability and flexibility (and license). However, can you backup your statement? You don't expect someone will give you counterarguments if you didn't give any, right? DTrace? I say Systemtap.

Anyone can come and create a Linux distro and found a large company around it and become $ billionaire. Look at RedHat founders. Anyone can take Linux and make lots of money from it. That is not possible to do with FreeBSD.You can do the same with *BSD code and you can even close it, but question is why almost nobody's interested? :> And no anyone, it must be good.

If nobody will quote your text I won't reply (;)). You already proved you don't understand obvious things.

Apopas

08-10-2009, 04:17 PM

And that is the reason Linux is successfull, whereas FreeBSD is not. You can make lots and lots of money on Linux. Where the money is, everyone goes there. If Linus T said that all Linux distros are obsolete and people should use his official Linux distro, then RedHat would die. Everyone would abandon Linux. No more multi billionaires = no more attention from companies. It is all driven by money. If Linus T somehow forbade people to make money on Linux, it would die. FreeBSD will never produce any dollar billionaires. Neither will OpenSolaris. Because someone "owns" those OS, there is one and only official distro.
Well, that "owns" thing is curse no good...
The only reason the users will abandon every other distro for the one Torvalds recommends, will be that the Torvalds-dist will meet their needs while the rest won't. But if ever Torvalds says something like that then the only thing he will succeed will be to divide the community in two parts. 1% will use his Linux till it totally dies along with his reputation and 99% will use Linux2 which will just be the fork and continuation of Linux as we know it now. That's the power of GPL!

I am not confused.
I didn't say such a thing, maybe you are, maybe not, I don't know. But for sure you are biased.

What a bunch of horse shit that article is. Do you really believe that propaganda? Have you read it?
Propaganda? Hahaha. That's propaganda and your's is not? At least he is a kernel developer and doesn't own it.
And yes I've read it many years ago and many times since then. Linux design has not changed since the time this article has been written, but Linux's success has for the better.

And the linux design principle ("there is no design, only evolution") that just plainly sucks big time. Why? Because it is hard to make the Linux environment stable. Because there is no stable API/ABI.
So you say here Linux has not stable API and that sucks because there is not stable API...

That is bull shit. Solaris kernel has frozen the API and ABI since many many years back and old drivers and applications on small desktops work in multi million Big Iron today.
Huh? What small desktops are you talking about? Are there one hundred around the world? As RealNC said once "Solaris for desktop is like mustard for ice-cream"

Solaris kernel evolves constantly.
Yeah, that's obvious, only Solaris evolves...

You are confused.
Again I didn't say such a thing but anyway I'm not either confused or biased :rolleyes:

Apopas

08-10-2009, 04:29 PM

That's it :) As far as I know kernel devs prefer 'unstable' API, because there's always better way to do things. Now I know, thanks to you :)
Always eager to share :)

Fanboys don't get it ;)

P.S. Great link from the great source if you know what I mean :>
Hush, it's propaganda as they say around ;)

You can do the same with *BSD code and you can even close it, but question is why almost nobody's interested? :> And no anyone, it must be good.
Well it's good, but not the best ;)

You already proved you don't understand obvious things.
Hehe he could but he's just biased as I mentioned above (I hope there is such a verb) :rolleyes:

kebabbert

08-11-2009, 04:51 PM

Yeah TOP-500 where Linux killed Solaris (incredibly quick IMO). The same situation is probably when comes to 'big irons', but it looks we can have endless discussion here... If XEN will be merged it's possible other systems will loose it, because it must satisfy Linux's kernel standards and thus it has to be modified (maybe there's another possibility, but this one is what I read). If this happen we'll probably have similar situation like when comes to TOP-500.
Maybe you have a hard time understanding, but I can explain again, those supercomputers on Top500 can only do one thing; run a stripped down specialized Linux kernel that only does number crunching. You dont login to those supercomputers and do office work, they have problems doing that, as they are not built for that.

Linux on those supercomputers are stripped down. Try to strip down the Solaris kernel. It will be difficult, because it is so complex. Of course SUN could strip down Solaris kernel to do simple number crunching on top500, but that is pointless. You dont need a complex kernel to do number crunching. You need a stripped down kernel with no luggage, where everything is thrown out. Which kernel is easiest to tailor to do one task? A simple Linux kernel or a highly complex Solaris kernel?

Nr5 on Top500 uses 700MHz PowerPC cpus - does that mean that the CPU is fast? No, it is logically wrong to generalize from top500 observations. I suggest you study logic, as you have numerous times showed flawed logic. For instance, you want to prove that Solaris becomes unstable on large systems, and you show links to someone having problem with installing Solaris 8?? You need logic studies, then your posts would be more relevant. As of now they are weird.

Hahaha, i.e. Linux's RCU (and then hierarchical RCU) is something you can dream about as Solaris or *BSD, or whatever user (if you have a lot of CPUs).
Wow! RCU!!! OMG!!!

But... but... if RCU is so good, why does Linux scale bad, then? Why does Linux become unstable under high load, then? Linux can use any technique, but it wont help. Linux is still unstable and scales bad on big iron. But Linux scales well on large clusters.

Linux follows in some ways, because like I mentioned before they aren't reinventing the wheel and they make new stuff also.
New stuff like what? Exactly what new tech has Linux? Linux just follows. Linux has never invented something new. It only copies, but the copies sucks big time.

You're saying something opposite to what you were claiming before.
I dont understand, explain again and dont be so fuzzy. Your logic is hard to follow.

The most important Linux's merits are performance, scalability and flexibility (and license).
Performance: Yes, it looks like Linux is faster on desktop. But Linux scales bad on large computers.

Scalability: Yes, Linux scales very well on clusters. But sucks on large computers.

Flexibility: Agreed. Linux exists on far more platforms than Solaris. But is it easy to port? Maybe there are lots of ugly hacks you have to do to port Linux, as the Linux kernel code is messy (the Linux kernel devs say).

The Solaris kernel code is very well structured and not a mess. The hardware dependent code is isolated, this makes it easy to port to new CPUs. But the code was closed earlier, and SUN were not interested in porting the code. Does that mean that Solaris is not flexible? No.

However, can you backup your statement?
Which statements do you want me to back up? Try to be clearer!

BTW, have you backed up ANY of your statements? You ask me to back up, but have you? No. Great.

You don't expect someone will give you counterarguments if you didn't give any, right? DTrace? I say Systemtap.
Systemtap. Geez. You clearly dont know anything about it. See this picture below. On a conference, Linux people wrote down requests for new functionality:
-DTrace for Linux
-Like Systemtap?
-No, like DTrace.
-Like Systemtap, but not crap.
http://blogs.sun.com/ahl/entry/dtrace_knockoffs

If Systemtap were so good, why are there no stories when Systemtap were used successfully? There are no such stories, or? OTOH, there are lots of stories where DTrace saved the day:
http://uadmin.blogspot.com/2006/05/what-is-dtrace.html

Here are some things that DTrace can do, and Systemtap can not:
http://uadmin.blogspot.com/2005/10/what-dtrace-can-do-that-systemtap-cant.html
Invoking Systemtap can crash the system that is being investigated. DTrace can only read, and can not crash the system. Hence, no one will invoke Systemtap on a production machine. But there are no problems with DTrace:
http://www.sun.com/bigadmin/content/dtrace/blogs/jarod/

Linux just follows and copies. It doesnt do anything new cool stuff like DTrace, Zones, or ZFS.

You can do the same with *BSD code and you can even close it, but question is why almost nobody's interested? :> And no anyone, it must be good.
I can try to explain again. No one can create a new BSD distro and sell it big time, because there is one official BSD distro. If you want to sell something, you want control of it. Did you understand? There are many people that consider FreeBSD as a better server OS than Linux.

You already proved you don't understand obvious things.
Anyone has a hard time to follow your weird logic and reasoning. Not just me. I have a double Masters, one in comp sci and one in math. I understand more things than you do. You should study some logic. Seriously. You are hard to understand.

The only reason the users will abandon every other distro for the one Torvalds recommends, will be that the Torvalds-dist will meet their needs while the rest won't. But if ever Torvalds says something like that then the only thing he will succeed will be to divide the community in two parts. 1% will use his Linux till it totally dies along with his reputation and 99% will use Linux2 which will just be the fork and continuation of Linux as we know it now. That's the power of GPL!
No, it doesnt work that way. Linus has control over the kernel. He might as well introduce some code that makes the kernel have problem with the non official distro. If he does that all the time, then there will be to much trouble and everyone will change to his distro.

SUN has the same position. There are lots of Solaris distros now: OpenSolaris, Belenix (which is Ubuntu environment but with the Solaris kernel + ZFS + DTrace + etc), Milax, Korona, Aurorax, Schillix, etc etc etc. If someone needs Solaris distro, which distro do they choose, you think? SUN's distro or some random person's distro? There are lots of forks, and all companies will choose the official distro: OpenSolaris. No other company can come and fork OpenSolaris and make a fortune, because SUN owns Solaris.

But Linux is ok. There is no official Linux distro. Anyone can make a distro, and companies can buy which Linux distro they want. There is no THE one and only Linux distro. This is the reason Linux is successfull. Money drives it all.

So you say here Linux has not stable API and that sucks because there is not stable API...
No, I didnt say that. Read my post again, but slowly.

Huh? What small desktops are you talking about? Are there one hundred around the world? As RealNC said once "Solaris for desktop is like mustard for ice-cream"

Jesus. I am trying to say that if you have an old desktop using an old device driver, you can just copy it to the newest Big Iron Solaris machine. No recompile needed, as Linux almost surely would need.

Yeah, that's obvious, only Solaris evolves...

No, I didnt say that. Read my post again, but slowly.

I am claiming that it IS possible to have good backwards compatibility and also invent new hot technology at the same time. Good compatibility and new tech are not opposite. You can have them both at the same time. Which Solaris proves.

Again I didn't say such a thing but anyway I'm not either confused or biased
Of course you are biased. I am biased. Everyone is biased. As soon as you state some opinion, you take a bias. Only ignorant people say they are not biased.

bridgman

08-11-2009, 04:55 PM

http://www.xkcd.org/619/

yotambien

08-11-2009, 06:18 PM

Oh, my, this opens a whole new can of worms...

WARNING: may not be suitable for the humour impaired.

http://http://www.adequacy.org/stories/2002.1.2.14159.23968.html (http://www.adequacy.org/stories/2002.1.2.14159.23968.html)

kraftman

08-12-2009, 06:28 AM

http://www.xkcd.org/619/

Yeah and who writes such crappy graphic card drivers? :P

@Yotambien

Easy, this is sometimes true, but not suitable for this topic :> Here's rather Solaris fanboys parade :P

@Kebbabert

It seems you still don't understand a thing. I actually showed you Linux scales great on big irons, so what's the problem?

If Systemtap were so good, why are there no stories when Systemtap were used successfully? There are no such stories...Stories are only at sun.com or freebsd.org. It's sometimes very funny to read such things. However, many *BSD devs are very friendly and just smart. They're conscious of things you don't understand and that's why I don't even want to talk with you, but if you
write such bull all the time... About such stories, benchmarks against other systems, it's a little unprofessional IMHO.

http://sourceware.org/systemtap/wiki/SystemtapDtraceComparison

http://sourceware.org/systemtap/wiki/Myths

As I mentioned before I'm not interested in debugging, so think what you want about this. There's also another utility, but like I mentioned...

No, it doesnt work that way. Linus has control over the kernel. He might as well introduce some code that makes the kernel have problem with the non official distro. If he does that all the time, then there will be to much trouble and everyone will change to his distro.Ask yourself who controls Solaris or *BSD then... Very big difference. What's the official Kernel distro?

Anyone has a hard time to follow your weird logic and reasoning. Not just me. I have a double Masters, one in comp sci and one in math. I understand more things than you do. You should study some logic. Seriously. You are hard to understand.You can even have a black cat, but it looks you're dumb like hell. You know what the sarcasm means? Maybe that's why I'm hard to understand to you sometimes. Btw. mentioning you've got some Masters is even more childlish then your arguments. Do you consider it will make you look smarter? Btw. can you name those people who had troubles? Yotambien, Frantaylor and you? What logic should I study? To realize you're just giving more fuel into the fire? I know this, but you're doing this in such funny way, so I can't resist to not reply sometimes :P

Btw. can you explain why you ignored very friendly pm (second time, you probably forgot, but long ago I also sent you one which you ignored too and if I'll drill a little we'll probably see a trolls face, am I right? :>)? You see, it's good to look at some things from bigger perspective and then drill into the details. What model do you prefer Master (you really should understand this one)?

P.S. Tannenbaum probably also had some Masters, but mentality is what counts.

P.S. 2

Linux is evolution, not intelligent designBut isn't there someone intelligent who directs evolution into proper direction and eventually corrects its mistakes? :>

kebabbert

08-13-2009, 09:20 AM

Easy, this is sometimes true, but not suitable for this topic :> Here's rather Solaris fanboys parade :P
Maybe it is a Linux fanboy parade here? Ive posted several different links from Linux kernel devs showing that Linux kernel code quality is not good, and what is your response to those links? You just dismiss the statements from the Linux kernel devs! Now what is that? Fanboyism or what? Even if Linus Torvalds himself said that the Linux kernel is buggy (which he has said) then you would still claim that Linux kernel is NOT buggy. Even if God himself said something about the Linux kernel you would reject that. If you dont call that fanboyism, I dont what it is.

If you post links about Solaris becoming unstable under high loads on large Enterprise systems, I have to reconsider. I have told you this several times and asked you to post such links. How many times have I said that? Many times. You have claimed that several times, but never showed any evidence to your claims.

I show critical thinking, asking for evidence, willing to reconsider if I see evidence. You are not willing to reconsider no matter what evidence. Nothing I can say, or Linus T can say, or all Linux kernel devs say, can make you change your mind. And you call ME the fanboy? You know, some people would consider YOU as the fanboy here.

It seems you still don't understand a thing. I actually showed you Linux scales great on big irons, so what's the problem?
Did you show that? I missed that. You only showed one benchmark on a small 32 CPU system. Please post those links again, where you show that Linux scales well on Big Iron.

Stories are only at sun.com or freebsd.org. It's sometimes very funny to read such things. However, many *BSD devs are very friendly and just smart. They're conscious of things you don't understand and that's why I don't even want to talk with you, but if you write such bull all the time... About such stories, benchmarks against other systems, it's a little unprofessional IMHO.
Maybe you missed that Linux people tend to brag about when Linux achieved a milestone or done something cool. So if there were lots of stories about Systemtap, then we would have seen those. But where are they?

http://sourceware.org/systemtap/wiki/SystemtapDtraceComparison

http://sourceware.org/systemtap/wiki/Myths

As I mentioned before I'm not interested in debugging, so think what you want about this. There's also another utility, but like I mentioned...
I dont get this. Why do you post these links? What is your purpose? What are you trying to prove? Are you trying to prove that Systemtap is superioer to DTrace? If you want to say something, say it clear. And why do you mention this other utility? Do you want to prove that there are better utilities than DTrace?

I dont understand anything. What are you trying to say? Why do you always have to be so fuzzy?

Ask yourself who controls Solaris or *BSD then... Very big difference. What's the official Kernel distro?
I dont understand. SUN controls Solaris, and big difference to what? What do you mean with "official kernel distro"? What is your point here? Are you trying to say that Linux is successfull because of it has a official kernel distro? I dont understand. What is your point with this paragraph? What are you trying to prove?

You can even have a black cat, but it looks you're dumb like hell. You know what the sarcasm means? Maybe that's why I'm hard to understand to you sometimes.
Great. Dont you know that it is hard to distinguish sarcasm from sheer stupidity merely by reading a post? Have you not read that you must be very clear on email and such, because the small nuances disappear? Didnt you know this? Great. Look, you must be clearer with your sarcasm. Insert sarcasm tags.

BTW, I have problem following your logic. Not anything with your sarcasm. For instance, you want to prove that Solaris becomes unstable under high load, and you prove that by showing links to someone having trouble installing Solaris v8! And the discussion about DTrace, you posted a comparison list on DTrace and Systemtap. What were you trying to say with that list? That Systemtap has more features and therefore is better? No, you can not be that dumb. Because the number of features doesnt make a product great. And that list was tailored to Systemtap's features. A DTrace list would look different because that list would focus on different things. And you can use DTrace on production. Maybe I am wrong on this, but as I have heard, Systemtap requires you to recompile that program you want to examine. You need not to do that with DTrace. And Systemtap can crash the system, DTrace can not.

So showing a biased list of features doesnt show that Systemtap is better than DTrace. Maybe you knew that. Or maybe your logic is weird.

Btw. mentioning you've got some Masters is even more childlish then your arguments. Do you consider it will make you look smarter?
No, but it will make your statements about me being dumb, childish.

Btw. can you name those people who had troubles? Yotambien, Frantaylor and you?
Problems with that? What are talking about? Shit man, you are just totally off the road. You are in the forest with your car right now. No one follows you. No one understands you.

What logic should I study? To realize you're just giving more fuel into the fire? I know this, but you're doing this in such funny way, so I can't resist to not reply sometimes :P
You should study mathematical logic. Is there any other logic, maybe? Maybe then your replies would make sense. Right now, you write weird things as "yes I agree on that but disagree on this" - without explaining what "this" is or what "that" is. You are very hard to understand and your logic is just plain wrong.

Btw. can you explain why you ignored very friendly pm (second time, you probably forgot, but long ago I also sent you one which you ignored too and if I'll drill a little we'll probably see a trolls face, am I right? :>)?
Maybe you should read my posts? I wrote that I didnt notice any PMs to me, until just recently when you wrote that I ignored your PMs. I did not ignore your PM. I didnt notice. There is no popup or anything. I told you that I read your PMs now. Why dont you read my posts?

You see, it's good to look at some things from bigger perspective and then drill into the details. What model do you prefer Master (you really should understand this one)?
What are you talking about? Which models can I choose from? You have only described one model. Why do you have so much trouble making sense?

P.S. Tannenbaum probably also had some Masters, but mentality is what counts.
What mentality? What are you talking about? "Mentality counts" regarding what? Regarding programming? Or just in general? What do you mean? Shit man, you are lost. Totally utterly lost.

But isn't there someone intelligent who directs evolution into proper direction and eventually corrects its mistakes? :>
Eh, no. Are you kidding me? Dont you know that according to one of the greatest scientists ever, it is pure chance that directs evolution. Pure probability. Nothing intelligent. Havent you heard about Darwin? Have you missed school?

kraftman

08-13-2009, 02:54 PM

At first, read a new pm please :> It may change your point of view by 180 degrees. I didn't suppose Sun is such bunch of maggots, but you should realize this now. Oh, if someone's interested:

http://vger.kernel.org/~davem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability (http://vger.kernel.org/%7Edavem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability)

Burn Sun, burn...

And yes, RCU :>

Maybe it is a Linux fanboy parade here? Ive posted several different links from Linux kernel devs showing that Linux kernel code quality is not good, and what is your response to those links? You just dismiss the statements from the Linux kernel devs! Now what is that? Fanboyism or what? Even if Linus Torvalds himself said that the Linux kernel is buggy (which he has said) then you would still claim that Linux kernel is NOT buggy. Even if God himself said something about the Linux kernel you would reject that. If you dont call that fanboyism, I dont what it is.

This is one of the things which make me just sick when comes to your logic and one of the things why I don't take your posts seriously. Imagine, there are two people. One says he's the smartest and another one says he's not so smart. The truth is the first guy is really dumb, but his ego is very big and the second guy is just humble. The similar situation can be when comes to Solaris and Linux. There's also a lot of marketing involved. Solaris is Sun's product and it's in their interest to present it from the best side and sell it. It's little different when comes to Linux, because as someone said (maybe even in one of the links you provided) Linux isn't drove by marketing rights. Of course, some people and companies can (and probably do) advertise it, because it's in their interests to sell servers with Linux preinstalled, but devs are just humble and aware of some things.

If you post links about Solaris becoming unstable under high loads on large Enterprise systems, I have to reconsider. I have told you this several times and asked you to post such links. How many times have I said that? Many times. You have claimed that several times, but never showed any evidence to your claims.I'm not interested in providing you such links. I'm more interested in showing you Linux scales great. Someone else said there are problems with Solaris when comes to big loads, but like I mentioned before (I hope, because this thread is quite long) there can be a lot of reasons why it's that. However, when there's migration there must be reasons.

I show critical thinking, asking for evidence, willing to reconsider if I see evidence. You are not willing to reconsider no matter what evidence. Nothing I can say, or Linus T can say, or all Linux kernel devs say, can make you change your mind. And you call ME the fanboy? You know, some people would consider YOU as the fanboy here.Those aren't evidences, but just words and they can be out of the context in some parts. Still, different mentality and laws (marketing vs. reality, egos?). However, it depends :)

Did you show that? I missed that. You only showed one benchmark on a small 32 CPU system. Please post those links again, where you show that Linux scales well on Big Iron.No, I gave more benchmarks - Big Tux up to 64 CPUs and running old Linux kernel - 2.6.8 and another one is with up to 32 CPUs. Maybe I gave some more, but you can easily check (I don't keep them :)). Those are evidences which fully satisfy me and like I said there's always known point of such discussion - you'll stick to your version I'll stick to mine and that's why I don't see too much sense in such flames. It's usually just waste of time.

Maybe you missed that Linux people tend to brag about when Linux achieved a milestone or done something cool. So if there were lots of stories about Systemtap, then we would have seen those. But where are they?Probably at lwn.net. However, I don't consider Systemtap being milestone in anyway. New features and optimizations are just natural. Radeon KMS will probably be something which should bring a lot of interest of desktop users.

I dont get this. Why do you post these links? What is your purpose? What are you trying to prove? Are you trying to prove that Systemtap is superioer to DTrace? If you want to say something, say it clear. And why do you mention this other utility? Do you want to prove that there are better utilities than DTrace? No, you said: "If Systemtap were so good, why are there no stories when Systemtap were used successfully?"

and I wanted to show how it compares when comes to DTrace. I'm not interested in debbuging, so I left judging for you.

I dont understand anything. What are you trying to say? Why do you always have to be so fuzzy?Because there were already many flames like this one and when comes to proving something "you" can usually undermine any proof (or profff) and you'll just realize more patient or more endure person wins. Imagine, some genius will come here and he'll proof with help of Miltons model Hurd is the best. You know it's not, but what if you won't be able to show him he's wrong? The truth is what counts (don't take this offensive please. It's just better to no theorize too much, because it's easy to jump into conclusions).

I dont understand. SUN controls Solaris, and big difference to what? What do you mean with "official kernel distro"? What is your point here? Are you trying to say that Linux is successfull because of it has a official kernel distro? I dont understand. What is your point with this paragraph? What are you trying to prove?You said: "No, it doesnt work that way. Linus has control over the kernel. He might as well introduce some code that makes the kernel have problem with the non official distro. If he does that all the time, then there will be to much trouble and everyone will change to his distro."

What problems do you mean, because I'm little confused here?

Great. Dont you know that it is hard to distinguish sarcasm from sheer stupidity merely by reading a post? Have you not read that you must be very clear on email and such, because the small nuances disappear? Didnt you know this? Great. Look, you must be clearer with your sarcasm. Insert sarcasm tags.I don't have big troubles with distinguishing it, but if you want I can limit this.

BTW, I have problem following your logic. Not anything with your sarcasm. For instance, you want to prove that Solaris becomes unstable under high load, and you prove that by showing links to someone having trouble installing Solaris v8! And the discussion about DTrace, you posted a comparison list on DTrace and Systemtap. What were you trying to say with that list?...I don't know why you have problems with my logic. I already explained why I gave such links you're according to (I even said those are profffs). It was to show what your proofs means to me.

So showing a biased list of features doesnt show that Systemtap is better than DTrace. Maybe you knew that. Or maybe your logic is weird.I answered before.

No, but it will make your statements about me being dumb, childish.That's the point :) I stick with my opinions and you stick with yours. However, opinions change.

You should study mathematical logic. Is there any other logic, maybe? Maybe then your replies would make sense. Right now, you write weird things as "yes I agree on that but disagree on this" - without explaining what "this" is or what "that" is. You are very hard to understand and your logic is just plain wrong.I probably don't have any problems with logic, but when I don't take something seriously I don't care too much :>

Maybe you should read my posts? I wrote that I didnt notice any PMs to me, until just recently when you wrote that I ignored your PMs. I did not ignore your PM. I didnt notice. There is no popup or anything. I told you that I read your PMs now. Why dont you read my posts?Sorry, but you were on my ignore list, so I didn't notice. I said before why I didn't read your posts, but maybe I was wrong?

What are you talking about? Which models can I choose from? You have only described one model. Why do you have so much trouble making sense?I just supposed you can be aware of micro and macro scale models, because you've got some Masters. However, you don't have to be aware of this. You can look at some things with bigger perspective and base your opinions and you can also look at some details. However, it will be just too much theorize.

What mentality? What are you talking about? "Mentality counts" regarding what? Regarding programming? Or just in general? What do you mean? Shit man, you are lost. Totally utterly lost.If Linus would just bought what Tannenbaum said Linux would probably be just dog slow turtle now. Mentality, not titles counts. That's why I'm not interested in your Masters. No offense. It can be this way your mentality is all right.

Eh, no. Are you kidding me? Dont you know that according to one of the greatest scientists ever, it is pure chance that directs evolution. Pure probability. Nothing intelligent. Havent you heard about Darwin? Have you missed school?I'm according to what Linus said :> It was in Linux context, so probability? ;) Btw. ask yourself about probability of this chance. Of course, there are some theories which can help, but I don't buy it. I don't consider Darwin being great scientist, but it's just my humble opinion.

kebabbert

08-14-2009, 05:05 AM

At first, read a new pm please
Ive read it now. I dont get it. Why are you forking this same discussion to PM? And then you also post it here? What is the purpose with this forking? To confuse us? To make me miss your arguments, so you can call me dumb for not noticing your PM? I think you should keep all your arguments in this thread, so I can reply to them without making people confused ("which argument is he replying to? is it PM? or is he just drunk?"). Please dont make us confused. It is hard to follow your logic as it is.

:> It may change your point of view by 180 degrees. I didn't suppose Sun is such bunch of maggots, but you should realize this now. Oh, if someone's interested:

http://vger.kernel.org/~davem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability (http://vger.kernel.org/%7Edavem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability)

Burn Sun, burn...

And yes, RCU :>

I dont change my point at all. There are links showing that Linux has scalability problems on a SGI 1024 CPU machine, via a discussion on mail list by Linux kernel devs. So what? Everyone knows that Linux has scalability problems.

Sure, Linux seems to run on a 1024 cpu machine, which doesnt prove anything. It only proves that Linux runs on 1024 cpu machine. But how well does it run? Is it stable? Maybe it crashes every other month? Maybe that machine is only used for number crunching and can not act as a Big Iron with lots of users at the same time? How many companies has migrated all their users to a SGI machine doing office work? I suspect noone. I strongly suspect that machine is only used for number crunching. Because if you need Big Iron serving many users, then 64 CPUs will do fine. There is no need to build a Big Iron with 1000.000 CPUs to serve some users. Nor to big a specialized expensive machine with 1024 CPUs. There are lots of 64 CPUs machines to buy, that are much cheaper.

As everyone agrees, Linux is good for number crunching because you need a stripped down simple kernel with no luggage. No one denies that. But number crunching is a simple task, and any kernel will do for that, any CPU will do for that (in fact IBM on nr5 top500 uses PowerPC 700MHz). Just stripp down the kernel a lot. Remove all bloat (you know that Linux kernel is 10 millions line of code today - that is lots of bloat. The entire Windows NT with GUI and everything were 10 millions line of code. The more bloat, the more bugs and unstable). Also you could easily strip down Solaris. I suspect Solaris would yield better performance for number crunching.

If you want to convince me that Linux is more stable than Solaris on large systems under high load, then you have to take these steps:
1. Explain why all Linux kernel devs complain on the bad code. Come up with a good explanation. You can not just dismiss all complaints from the Linux kernel devs. Maybe the code is just bad. You have to prove that the code is not bad. For instance, by showing that all such links are jokes. Or the Linux kernel devs complaining got fired because they couldnt program at all. etc.
2. Show links that Solaris becomes unstable under high load.

Whereas I have to take these steps:
1. Show links that people and companies says that Solaris is more stable than Linux, and scales better.
2. ???

I have done step 1) which is easy. There are lots of testimonies. What step should I take in 2) you think, to convince you? Or is it impossible to convince you?

Regarding "burn Sun burn", that is fine. You can think that if you wish. That is your OPINION. And everyone has right to have an opinion. Opinions can never be wrong and I can not complain on an opinion. But claims can be wrong. Do not claim that Solaris is unstable, if you can not prove that - because that is just plain wrong. Claims/facts can be wrong, opinions can not. My opinion is that SUN has released more open source than anyone else (according to studies) and that is a good thing.

I hope you agree with me on the difference between opinions and claims.

This is one of the things which make me just sick when comes to your logic and one of the things why I don't take your posts seriously. Imagine, there are two people. One says he's the smartest and another one says he's not so smart. The truth is the first guy is really dumb, but his ego is very big and the second guy is just humble. The similar situation can be when comes to Solaris and Linux. There's also a lot of marketing involved. Solaris is Sun's product and it's in their interest to present it from the best side and sell it. It's little different when comes to Linux, because as someone said (maybe even in one of the links you provided) Linux isn't drove by marketing rights. Of course, some people and companies can (and probably do) advertise it, because it's in their interests to sell servers with Linux preinstalled, but devs are just humble and aware of some things.
Yes that is a valid remark. This is the only interesting and sane thing you have ever written here. The rest is just weird stuff about you "proving" things, which are no "proffffffs".

Let us discuss this point. You believe that the Linux kernel devs doesnt try to hide problems, whereas SUN tries to hide problems, right? And this is the reason there are several testimonies showing that Linux is unstable whereas there are no testimonies showing that Solaris is unstable? And this is the reason there are no links showing Solaris is unstable? And that is why you can not show me links about Solaris unstable, that I ask of?

Well, again, I dont agree with your conclusion. The thing is that SUN maybe tries to hide problems. That may be true. But the thing is that the companies that run Solaris does not try to hide problems! The sysadmin people at those companies, will complain anonymously on different forums if Solaris were crappy. And also there will be links and interviews with an "unamed" company that complains on Solaris. But still, there are no such links or testimonies or interviews showing that Solaris becomes unstable under big load! Nowhere. No anonymous postings on forums, no nothing. But there are lots showing that Linux becomes unstable.

So mr Genius, how do you explain this total lack of Solaris complaints? Is SUN threatening everone to shut up? SUN has hired some brutes that beat up everyone complaining? Why are there NO complaints on Solaris stability nowhere on earth? Is it because there are no complaints, or is it because SUN is threatening everyone?

So please post some links. There should be some links if it were true that Solaris shows problems under high load, right? There are lots of links showing people having problems with Solaris; installation, problems with ZFS, etc. But no complaints of becoming unstable under high load. Has SUN deleted all links on stability problems on large systems on the entire web, but left the minor installation problems links?

Granted, there are companies switching from Solaris to Linux, but it is because of Solaris is being more expensive (which is not true anymore), and because of politics. There are NO companies switching because Solaris doesnt cut it anymore, because Solaris becomes unstable. No such companies. My Fortune500 company is switching some systems to Linux, but it is because of politics. Solaris has run well earlier. No problems. (I suspect there will be more problems with Linux, because of changing API/ABI, upgrades can not be done easily, etc).

Mr Genius, how do you explain this? Are "Linux devs humble and Solaris devs tries to hide things"? In fact, have you read the open source Solaris mail lists? There are lots of bugs and problems there too, in fact, the last 2 OpenSolaris builds were skipped because of bugs (OpenSolaris builds come every other week). No one is saying that Solaris is bug free, because it is not. But we say that the Solaris code and design is better, and there are less bugs than in Linux. That is all we are saying. We dont say Solaris is the best OS there is.

I'm not interested in providing you such links. I'm more interested in showing you Linux scales great. Someone else said there are problems with Solaris when comes to big loads,
I must have missed that. Someone complained on ZFS bugs. Could you repost the links showing that Solaris becomes unstable under big loads?

However, when there's migration there must be reasons.
Yes, cost is a very good reason. And also politics. We have large customers that REFUSE to buy our Linux system, because we are competitors and they hate us.

No, I gave more benchmarks - Big Tux up to 64 CPUs and running old Linux kernel - 2.6.8 and another one is with up to 32 CPUs. Maybe I gave some more, but you can easily check (I don't keep them :)). Those are evidences which fully satisfy me
Are you serious? You make one/few observations and then you draw the conclusion that it is always true?? Are you for real? That is not logically correct to do that!

Ok, I show you one link on Solaris being better on something, then you must draw the conclusion that Solaris is always better on everything? Would you accept that? No, you wouldnt. Why do you accept a few benchmarks and believe Linux scales well, then? Scaling well on one/few benchmarks is one thing - but it does not prove anything! Didnt you know that?

kebabbert

08-14-2009, 05:06 AM

and like I said there's always known point of such discussion - you'll stick to your version I'll stick to mine and that's why I don't see too much sense in such flames. It's usually just waste of time.
Yeah. I stick to what all people and sysadmins say. And testimonies say. Me, myself has never run Linux nor Solaris on big large systems. I have no experience of that. Ive talked to our sysadmins that do that, and read articles on the net - everyone says that Linux becomes unstable. I would be dumb to dismiss ALL testimonies. And Ive searched the web, but there are NO testimonies showing Solaris becomes unstable. I would like read such testimonies to learn more about Solaris stability. So if someone has links, please show them.

No, you said: "If Systemtap were so good, why are there no stories when Systemtap were used successfully?"

and I wanted to show how it compares when comes to DTrace. I'm not interested in debbuging, so I left judging for you.
Aha. Ok now I understand your point. Please be clearer in the future. I can not read your mind.

The thing is, I can show a totally different list that benefits DTrace where Systemtap has "no" on every feature. The point is: Such a list does not prove anything! I want testimonies. Articles. Real life stories. About Systemtap being superior, or even successfull. Ive posted such links about Solaris.

You know, you read the advertisement and everything seems fine. Then you try it and it sucks big time. Im mostly interested in real life testimonies. Reviews. etc. Dont you agree that real life stories are more interesting than a list?

Because there were already many flames like this one and when comes to proving something "you" can usually undermine any proof (or profff) and you'll just realize more patient or more endure person wins. Imagine, some genius will come here and he'll proof with help of Miltons model Hurd is the best. You know it's not, but what if you won't be able to show him he's wrong?
Then maybe he is right? You know, in science, if you can not prove him wrong, then he could be right and YOU be wrong. Havent you studied science?

And how do you know that Hurd is not best? Maybe it is?

The truth is what counts (don't take this offensive please. It's just better to no theorize too much, because it's easy to jump into conclusions).

You said: "No, it doesnt work that way. Linus has control over the kernel. He might as well introduce some code that makes the kernel have problem with the non official distro. If he does that all the time, then there will be to much trouble and everyone will change to his distro."

What problems do you mean, because I'm little confused here?
I dont understand. I dont talk about "problems". What "problems" have I talked about? Could be clearer? Write things as "what problems regarding scaliblity do you mean?" Instead of "what problems?". Jesus. You ARE hard to follow.

I don't know why you have problems with my logic. I already explained why I gave such links you're according to (I even said those are profffs). It was to show what your proofs means to me.
I have severe problems with your logic. It is not correct logic. Ive studied lots of logic. You reason strange. To me, you dont say things as:
1) I am hungry, therefore I must eat to stop being hungry.
2) It is raining, therefore I will get wet if I go out.

Instead, you say things as:
1) I am hungry, therefore I must paint my house to stop being hungry.
2) It is raining, therefore I will cry to not get wet
The things you say doesnt make sense. It is hard to follow. Logically, they are wrong. Look at this:
3) Someone can not install Solaris v8, therefore Solaris is unstable under high load.
Now this is just weird to me. I dont understand your logic or your reasoning. Because in step 3) you start to reason and argue and talking about Solaris is unstable. But 3) is not true! You have not proved anything!

I have problems with your logic, because you havent studied logic, whereas I have. If you tried study logic, you would understand why you reason strange.

That's the point :) I stick with my opinions and you stick with yours. However, opinions change.
Yes, but facts/claims doesnt not change.

I probably don't have any problems with logic, but when I don't take something seriously I don't care too much :>
You have severe problems.

Sorry, but you were on my ignore list, so I didn't notice. I said before why I didn't read your posts, but maybe I was wrong?
Ok, but dont call me dumb and a troll then, for not noticing your PMs. I dont understand the necessity to fork off this discussion to PM. People that follows our debate will not understand, unless they see all arguments. "what is he talking about? I am confused. What did he wrote in PM???"

I just supposed you can be aware of micro and macro scale models, because you've got some Masters. However, you don't have to be aware of this. You can look at some things with bigger perspective and base your opinions and you can also look at some details.
Aha, do you speak about macro and micro? Yes, of course I know those. Why dont you say that, then? You are so unclear. You think something, and write half of what you think and expect me to read your mind. It doesnt work that way.

In computer science you have think at macro and micro at the same time. Also in math. Therefore you must be used to both. I am a macro guy, but learned to focus on micro also. I had a hard time when studying math and comp sci.

If Linus would just bought what Tannenbaum said Linux would probably be just dog slow turtle now.
Maybe Linux would have much better code and less bugs? Linux is a mess right now, kernel dev says so. Tanenbaum had different, cleaner design which is important to keep the bugs down. Linus has no design, he rewrites everything all the time when he sees what he thinks is a better solution. This new code introduces new bugs all the time. You know, it takes long time before the bugs get fewer. People say that Windows requires Service Pack 1 to get useable. Because then MS has killed most bugs. What would happen if MS rewrote entire Windows all the time? Then there would be new bugs all the time. You must keep the same code and kill the bugs in that code. Then that code will get almost bug free. You can not get new code bug free. It takes long time to get it bug free. Solaris code is mature now.

I'm according to what Linus said :> It was in Linux context, so probability? ;) Btw. ask yourself about probability of this chance. Of course, there are some theories which can help, but I don't buy it. I don't consider Darwin being great scientist, but it's just my humble opinion.
Look, you shouldnt listen to much to Linus. He is not God. Clearly, he has taken some bad decisions earlier. That is why Linux is in such terrible mess. And also he is rude and flames people. What would you consider of your manager if he told you that your recent work was crap and you are an incompetent idiot? Would you like that? No. Linus does say so, and he has attitude problems. You dont need to insult people.

kraftman

08-14-2009, 08:28 AM

Look, you shouldnt listen to much to Linus. He is not God. Clearly, he has taken some bad decisions earlier. That is why Linux is in such terrible mess. And also he is rude and flames people. What would you consider of your manager if he told you that your recent work was crap and you are an incompetent idiot? Would you like that? No. Linus does say so, and he has attitude problems. You dont need to insult people.

Now I see, I don't have to say a single word more. You didn't understand even this :) I didn't agree to what Linus said, so why your logic told you something opposite? If it works this way it's just enough to deny what you were talking about to see how it is in real. You ignored proof which unmask your, Frantaylor's and Sun's lies. There's also explanation:

And let it not be missed how much Sun enjoys attacking it's competition via blogs, so they don't have to make any official statements in this area or stand behind what they say in any official capacity. And that, my friends, makes for one big coward of a company.

http://vger.kernel.org/~davem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability (http://vger.kernel.org/%7Edavem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability)

You know, you read the advertisement and everything seems fine. Then you try it and it sucks big time. Im mostly interested in real life testimonies.I only saw Solaris advertisements when comes to such things and it seems it's just propaganda.

I have problems with your logic, because you havent studied logic, whereas I have. If you tried study logic, you would understand why you reason strange.The reason why you have problems with my logic is very clear - you're just dumb. I cleared some thing few times, but you don't get it. Person with average intelligence shouldn't have a single problem with understanding me.

I dont understand. I dont talk about "problems". What "problems" have I talked about? Could be clearer? Write things as "what problems regarding scaliblity do you mean?" Instead of "what problems?". Jesus. You ARE hard to follow.I'm talking about this: Linus has control over the kernel. He might as well introduce some code that makes the kernel have problem with the non official distro.

How that's possible you're so dumb? You started talking about some problems and now you're asking? Do you expect I'll explain you a single word, because it seems you've got problems with obvious things and if you're talking nonsenses it's ok? This what problem.

Yes, but facts/claims doesnt not change.So, you should worry...

Ok, but dont call me dumb and a troll then, for not noticing your PMs. I dont understand the necessity to fork off this discussion to PM. People that follows our debate will not understand, unless they see all arguments. "what is he talking about? I am confused. What did he wrote in PM???"I just did you a favor, because I noticed you started trolling and I wanted to tell you you're wrong. I believed you don't want to be shamed, but it seems you don't care :) I called you dumb and troll not because you didn't notice my pm... I'm actually fully satisfied, because you've got serious problems with some obvious things and that's funny.

Maybe Linux would have much better code and less bugs? Linux is a mess right now, kernel dev says so.Nope, Solaris is a mess, but dead one.

Solaris code is mature now.It's not bug free and it's old pile of crap right now. Call it mature if you want.

You ignored the most important thing in my response:

http://vger.kernel.org/~davem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability (http://vger.kernel.org/%7Edavem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability)

I'll repeat. It unmasks Sun's propaganda and it shows this company is just bunch of cowards and maggots. Die as "sun" as possible :>

I assure you and some other idiots I won't let such FUD to be spread :>

Btw. my responses are VERY clear when compared to yours. Only chaos and bullshit.

Sure, Linux seems to run on a 1024 cpu machine, which doesnt prove anything. It only proves that Linux runs on 1024 cpu machine. But how well does it run? Is it stable?You didn't read. Few years. Linux has RCU and that's why performance and scalling is much better then on Solaris. Performance and stability is something why they run Linux instead of such crap.

If you want to convince me that Linux is more stable than Solaris on large systems under high load, then you have to take these steps:
1. Explain why all Linux kernel devs complain on the bad code. Come up with a good explanation. You can not just dismiss all complaints from the Linux kernel devs. Maybe the code is just bad. You have to prove that the code is not bad. For instance, by showing that all such links are jokes. Or the Linux kernel devs complaining got fired because they couldnt program at all. etc.
2. Show links that Solaris becomes unstable under high load.I explained this very clear and I said very clear what I think about this. I don't care what you think I just won't let you spred FUD. If someone's and idiot why should I care what he thinks? Your links are jokes and link which I gave eliminates them as "proofs". I gave you some very valuable links.

P.S. Don't fool yourself by talking about Tannenbaum.

nanonyme

08-14-2009, 08:36 AM

I'm talking about this: Linus has control over the kernel. He might as well introduce some code that makes the kernel have problem with the non official distro.Technically only so far. Distros are known to remove and change stuff in kernels they use. (Sometimes causing more issues, sometimes fixing something. It's not like they'd be perfect anyway but my point was, it happens. The code is opensourced, it's not like there's Linus' Gestapo guarding you use it like he wants to. As long as you abide GPL, you can do pretty much anything you want with it)

kraftman

08-14-2009, 08:41 AM

Technically only so far. Distros are known to remove and change stuff in kernels they use. (Sometimes causing more issues, sometimes fixing something. It's not like they'd be perfect anyway but my point was, it happens. The code is opensourced, it's not like there's Linus' Gestapo guarding you use it like he wants to. As long as you abide GPL, you can do pretty much anything you want with it)

I perfectly understand this :) I just replied some maggot who doesn't understand a thing. Oh, this bold text is his sentence :D.

Apopas

08-14-2009, 01:43 PM

I have a double Masters, one in comp sci and one in math. I understand more things than you do.
...

No, it doesnt work that way. Linus has control over the kernel. He might as well introduce some code that makes the kernel have problem with the non official distro. If he does that all the time, then there will be to much trouble and everyone will change to his distro.

SUN has the same position. There are lots of Solaris distros now: OpenSolaris, Belenix (which is Ubuntu environment but with the Solaris kernel + ZFS + DTrace + etc), Milax, Korona, Aurorax, Schillix, etc etc etc. If someone needs Solaris distro, which distro do they choose, you think? SUN's distro or some random person's distro? There are lots of forks, and all companies will choose the official distro: OpenSolaris. No other company can come and fork OpenSolaris and make a fortune, because SUN owns Solaris.

But Linux is ok. There is no official Linux distro. Anyone can make a distro, and companies can buy which Linux distro they want. There is no THE one and only Linux distro. This is the reason Linux is successfull. Money drives it all.
Well, if for some reason something goes wrong with the official kernel, then each distro will remove or fix the parts they don't like. Also, even now 99% of the distros use their patched/fixed kernels and not the official one that Torvalds releases. They have freedom fortunately. And as long as they keep giving the services they used to do to their customers, then the users will stay to their distro till they find something that meets their needs better of course. Because for the users the names Torvalds or Cox means nothing. They found Linux with the names Slackware, Redhat, SUSE, Mandriva, Ubuntu etc and their communities, in the same way the users of Solaris met it only with the names Sun and Solaris. You see, Linux was created from the begining from the users instead of Solaris which was developed by a company and then was given to the community. If that sucks for you or not, doesn't matter. It is a fact and the difference is enormous, but usually you can only feel it rather than understand it. The freedom of Linux made it able to give money and money made it succesful. Freedom drives it all.

Of course you are biased. I am biased. Everyone is biased. As soon as you state some opinion, you take a bias. Only ignorant people say they are not biased.
Speak for yourself sir, if you feel biased then you know very well that you are not able to make a conversation, so everything we say here is pointless.

kebabbert

08-17-2009, 07:50 AM

Now I see, I don't have to say a single word more. You didn't understand even this :) I didn't agree to what Linus said, so why your logic told you something opposite? If it works this way it's just enough to deny what you were talking about to see how it is in real. You ignored proof which unmask your, Frantaylor's and Sun's lies. There's also explanation:
Forgive me for saying this, but your english is not the best. I admit my english is not perfect either, but I have a hard time understanding your text.

I write: "... according to one of the greatest scientists ever, it is pure chance that directs evolution. Pure probability..."

And you:
"I'm according to what Linus said. It was in Linux context, so probability? Btw. ask yourself about probability of this chance. Of course, there are some theories which can help, but I don't buy it..."

Which I dont really understand. "I'm according to what Linux said"? What do you mean? And then you write "It was in Linux context, so probability? ask yourself about probability of this chance" - which chance? I can not read your mind. I actually dont understand what you are trying to say here. Do you mean that there is a low probability that Linux would have evolved to this stage if it were only by random choice? I dont understand. Let me repeat that again: I can not read your mind. Be clearer.

I only saw Solaris advertisements when comes to such things and it seems it's just propaganda.
Is this SUN advertisement? It is SUN that has written this?
http://lethargy.org/~jesus/writes/choosing-solaris-10-over-linux

Is this SUN advertisement?
http://www.enterprisestorageforum.com/sans/features/article.php/3745996

Has SUN written this?
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1313798,00.html

And this?
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1286507,00.html

Do you want more links? Where did you see "only" Solaris advertisements and propaganda, in my links? You know, most people would say that these links are real life stories. Not SUN advertisements.

I have a question. A) Where did you see "only" SUN advertisements?

The reason why you have problems with my logic is very clear - you're just dumb. I cleared some thing few times, but you don't get it. Person with average intelligence shouldn't have a single problem with understanding me.
Have you ever considered the possibility that it is you that is dumb? I have intelligence far above average. I have tried the Mensa web test and emailed Mensa, and they replied that I have a very good chance to enter Mensa. If try the real Mensa test and enter Mensa, then I am more intelligent than ~95% of all people. Can you say the same thing? Maybe the reason I have problems following your logic is not because of me (I have far above average IQ and have studied logic at the university) maybe the problem is that you have not studied logic? Maybe you should do that?

How that's possible you're so dumb? You started talking about some problems and now you're asking? Do you expect I'll explain you a single word, because it seems you've got problems with obvious things and if you're talking nonsenses it's ok?[B] This what problem.
You dont have to call me ugly names, right? We are grown up people. I hope.

And also, I CAN NOT READ YOUR MIND. Please spell it out. Your english is not good. Your logic is wrong. Your thinking is wrong. I understand almost nothing about what you are trying to say. And I CAN NOT READ YOUR MIND.

I wrote: Yes, but facts/claims doesnt change.
You wrote: So, you should worry...
Why should I worry? For what? Let me say that again: I CAN NOT READ YOUR MIND. BE CLEARER.

I just did you a favor, because I noticed you started trolling and I wanted to tell you you're wrong. I believed you don't want to be shamed, but it seems you don't care
That was nice to not ashame me, but I dont care because I am interested to learn more. If you really have good links showing that I am wrong, please post them!

Nope, Solaris is a mess, but dead one.
Question B) How do you know that the Solaris code is a mess? Can you back that claim up? You have several times said that Solaris becomes unstable under large load, and never showed such links. Whereas I have showed links. Can you show links, or can you not?

It's not bug free and it's old pile of crap right now. Call it mature if you want.
Of course Solaris kernel is not bug free. Have I claimed that, somewhere??? If you claim it is a pile of crap, then prove it. Show links that Solaris kernel have problems with stability and scalability. If you can not show such links, then you are wrong. Do you agree? If you want to claim that you are correct, then you must prove that you are correct. That sounds reasonable? Where are your proofs? Links?

You ignored the most important thing in my response:

http://vger.kernel.org/~davem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability (http://vger.kernel.org/%7Edavem/cgi-bin/blog.cgi/2007/04/10#bonwick_scalability)

I'll repeat. It unmasks Sun's propaganda and it shows this company is just bunch of cowards and maggots. Die as "sun" as possible
No, I did not ignore your link. I answered that link. I wrote: "Linux claims to run on 1024 cpu machine, but how well does it run? And such a machine is only used for number crunching - it is not used as big iron server where lots of users login och do office work. And number crunching is easy to do. Server workload is much more difficult, because it is general work. It is like a CPU vs GPU. The GPU can only do one thing and does it fast. The CPU is slower, but can do many more things. A number crunching cluster is like a simple GPU. A server is like a CPU. A GPU can never replace a CPU.

For the other link, about Bonwick talking about Linux scaling bad - well that is a fact. Linux scales bad. It is not FUD or lies. Linus scaling experts admit that Linus v2.4 scales bad on Big Iron. And you know, it takes decades to scale well. Linux v2.6 can impossibly scale well. Maybe Linux v 6-7 can scale well on Big Iron.
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci929755,00.html
And also, you posted a link that showed that Linux scales bad. So how can Bonwick be FUDing? Even YOUR link showed that Linux scaled bad! Is your own link FUD???

I assure you and some other idiots I won't let such FUD to be spread :>
Ok, fine. But then you should have evidence? Proofs? Links that show that Linux scales well on Big Iron? Where are them links? You have showed some benchmarks on a 32 CPU machine - but that is not proof that Linux scales well in GENERAL, on every workload. And you showed a discussion about Linux on 1024 CPU machine - but how well does it run Linux? Maybe Linux sucks on that machine? There are no links on that. You have only showed that Linux compiles on a 1024 cpu machine and that you have showed that there are performance problems on that 1024 CPU machine - which the discussion is about.

You have no links that shows that Linux scales well. If you want to debunk the FUD, then you should show proofs that support you. That you are correct. Right? Then I will get convinced.

You didn't read. Few years. Linux has RCU and that's why performance and scalling is much better then on Solaris.
I told you, RCU is no guarantee that it works well. I can say that a car has a special kind of super engine, but maybe it is not well implemented? Maybe the car is crap, but uses a good engine? If Linux uses RCU, it does not prove anything. Maybe Linux implementation of RCU is crap?

If RCU is soo good for Linux, why does Linux scale bad on Big Iron, then? Admittedly, Linux scales well on large clusters, maybe because of RCU?

Anyway, RCU or not, Linux sucks on Big Iron. But scales well on clusters.

Performance and stability is something why they run Linux instead of such crap.
Question C) Can you prove that claim? Show me links proving that Linux is chosen over Solaris because of performance and stability issues. There are no such links. Why do you lie, then? Are you a liar?

I don't care what you think I just won't let you spred FUD. If someone's and idiot why should I care what he thinks? Your links are jokes and link which I gave eliminates them as "proofs". I gave you some very valuable links.
Fine. If you want me to stop "spreading FUD" I will stop. I promise. But then I need to see some proofs so I can change my mind. Please show me links and proofs that you are correct, and I am wrong. If you can show such links, then I will change my mind. I promise.

Regarding your "valuable links", please do not show links on some guy having problems on installing ancient Solaris v8 - as a proof that Solaris is unstable on large systems. Please show me some real life testimonies. Do not show me a feature list or whatever.

P.S. Don't fool yourself by talking about Tannenbaum.
Que? What do you mean? Do you mean that professor and researcher Tannenbaum says that Linux scales bad? Or do you mean that Tannenbaum does not Linux? What the hell do you mean with this sentence? I CAN NOT READ YOUR MIND.

Ok, now you will face the problems I have with you. What do I mean when I write like this?
"Yes I know but I am correct on Tannenbaum, and your second argument is flawed"
Tell me what I mean. Go ahead. Tell me what I mean. What do I mean? I am easy to understand, yes?

And one thing, please answer my questions A, B and C. I am waiting eagerly.

kebabbert

08-17-2009, 07:51 AM

Well, if for some reason something goes wrong with the official kernel, then each distro will remove or fix the parts they don't like. Also, even now 99% of the distros use their patched/fixed kernels and not the official one that Torvalds releases. They have freedom fortunately. And as long as they keep giving the services they used to do to their customers, then the users will stay to their distro till they find something that meets their needs better of course.
Well I am not convinced on this. If Linus T releases the official Linux distro, then I believe everyone will switch to the official distro. I do not believe customers will stay on some inferior Linux distro. Linus T own distro will get the hottest newest tech, and all other distros will lag behind.

Of course you are biased. I am biased. Everyone is biased. As soon as you state some opinion, you take a bias. Only ignorant people say they are not biased.
Speak for yourself sir, if you feel biased then you know very well that you are not able to make a conversation, so everything we say here is pointless.
I do not speak for myself. If you dont believe you are biased then you should reconsider. That is wrong thinking from you. You ARE biased as soon you state an opinion.

I talked to some guy, he said:
-I have no opinion on this, I just remark that X is better than Y.
-But then you have an opinion! That statement is a opinion. You are subjective!
-No no no, I have no opinion! I just remark that X is better than Y! I am not subjective, I am objective!
-But THAT is an opinion! You HAVE taken a bias! You are subjective!
-Nononono

etc. It took 15 minutes before he understood that he really was subjective. You should study philosophy if you believe that you have no bias. You are wrong on this.

It is like when some girl says:
-You and I share nothing in common
-But you are wrong on this, then we share one thing in common: That we have nothing in common!
Ergo, you can never say to anyone that you have nothing in common. Dumb girl to not understand that.

Apopas

08-17-2009, 09:17 AM

Well I am not convinced on this. If Linus T releases the official Linux distro, then I believe everyone will switch to the official distro. I do not believe customers will stay on some inferior Linux distro. Linus T own distro will get the hottest newest tech, and all other distros will lag behind.
In my previous post I said exactly the same, that everyone is gonna use Torvald's distro if it proves that it's better and not just because he is Torvalds. But again he is just one guy, Redhat, Novell, Canonical, the community and all the other distributions on the other hand have millions of developers. So the chances are totally against him.

I do not speak for myself. If you dont believe you are biased then you should reconsider. That is wrong thinking from you. You ARE biased as soon you state an opinion.

I talked to some guy, he said:
-I have no opinion on this, I just remark that X is better than Y.
-But then you have an opinion! That statement is a opinion. You are subjective!
-No no no, I have no opinion! I just remark that X is better than Y! I am not subjective, I am objective!
-But THAT is an opinion! You HAVE taken a bias! You are subjective!
-Nononono

etc. It took 15 minutes before he understood that he really was subjective. You should study philosophy if you believe that you have no bias. You are wrong on this.

It is like when some girl says:
-You and I share nothing in common
-But you are wrong on this, then we share one thing in common: That we have nothing in common!
Ergo, you can never say to anyone that you have nothing in common. Dumb girl to not understand that.
Well, every time someone says an opinion he is subjective, but not neccessarily biased but I won't expand this for fear that since I'm not native english speaker I understand the word bias with a differnet meaning than you. But the example with the girl is totally irrelevant.

You should study philosophy if you believe that you have no bias. You are wrong on this.
If you believe that from some posts in a forum about hardware and software you can safely claim that someone has studied more or less philosophy than you, you only prove that you must study philosophy in more depth.
Also, a friendly advice since I don't know you and I get no benefit if you accept it or not:
If you want people, especially the ones that don't know you at all (like us here) to take you seriously, stop posting things like your personal achievements in the universities, your masters and your scores in mensa club. They are sayings that proves nothing more than some level of arrogance which does not help at all any debates we have here.

kebabbert

08-17-2009, 10:21 AM

In my previous post I said exactly the same, that everyone is gonna use Torvald's distro if it proves that it's better and not just because he is Torvalds. But again he is just one guy, Redhat, Novell, Canonical, the community and all the other distributions on the other hand have millions of developers. So the chances are totally against him.
So you mean that others would hijack and fork off the Linux kernel?? I dont think so. If Linus T releases THE official Linux distro, then everyone will switch to it, I believe. His devs will follow him and they will support the official Linux distro. What will RedHat etc do? Will they fight and fork of the kernel? I dont think so. Too much job to maintain another kernel. And all Linux people will rather use Linus kernel, than any other. I suspect.

Also, a friendly advice since I don't know you and I get no benefit if you accept it or not:
If you want people, especially the ones that don't know you at all (like us here) to take you seriously, stop posting things like your personal achievements in the universities, your masters and your scores in mensa club. They are sayings that proves nothing more than some level of arrogance which does not help at all any debates we have here.
Ah, great. Have you ever wondered WHY I was forced to post such information? Was it because someone attacked me by saying I was dumb, understood nothing, has intelligence less than average, etc etc etc? So in order to defend myself, I merely stated facts about myself. Instead of telling someone else to calm down, you support him and give "advice" to ME. Maybe you should give advice to him???? But no. Great.

If he hits me, and I hit back - you ask ME why I hit him. Great.

Apopas

08-17-2009, 12:15 PM

So you mean that others would hijack and fork off the Linux kernel?? I dont think so. If Linus T releases THE official Linux distro, then everyone will switch to it, I believe. His devs will follow him and they will support the official Linux distro. What will RedHat etc do? Will they fight and fork of the kernel? I dont think so. Too much job to maintain another kernel. And all Linux people will rather use Linus kernel, than any other. I suspect.
Yup, I said in the very begining of our debate that the kernel would be forked in that case. It will be a hijack from Torvalds' part and not the opposite, as you think. Because it's too much job to maintain another kernel that's why Torvalds' kernel is gonna die. It's easier for Redhat, the other distribution companies and the community of indivinduals in general to maintain a kernel rather than for Torvalds and his fistful of programmers. That's exactly what happened with Xfree86 when it's leader decided to change its license. While it was the standard in each distribution, it was forked to Xorg and in a matter of time was adopted by everyone.

Ah, great. Have you ever wondered WHY I was forced to post such information? Was it because someone attacked me by saying I was dumb, understood nothing, has intelligence less than average, etc etc etc? So in order to defend myself, I merely stated facts about myself. Instead of telling someone else to calm down, you support him and give "advice" to ME. Maybe you should give advice to him???? But no. Great.

If he hits me, and I hit back - you ask ME why I hit him. Great.
You do well and hit back, he does well and hit back, I would do the same. The matter is that you did it with a childish way. If you feel that he acts like a child against you, the right way isn't for sure to continue this.

nanonyme

08-17-2009, 12:32 PM

So you mean that others would hijack and fork off the Linux kernel?? I dont think so. If Linus T releases THE official Linux distro, then everyone will switch to it, I believe. His devs will follow him and they will support the official Linux distro.In theory, maybe. In practise I don't see why on Earth he would want to. He's an engineer and he already has plenty enough if not too much responsibility. I really don't think he'd even want to touch the mess of managing kernel+userland combinations originating from hundreds or thousands of projects. Generally you have to be pretty clueless to start a new distro, it's just too much work. Your point is completely theoretical and thus moot.

kraftman

08-17-2009, 04:41 PM

Forgive me for saying this, but your english is not the best. I admit my english is not perfect either, but I have a hard time understanding your text.

My English shouldn't be a big problem, but your logic is a problem. I have troubles with understanding you sometimes, because you write nonsenses.

I write: "... according to one of the greatest scientists ever, it is pure chance that directs evolution. Pure probability..."

And you:
"I'm according to what Linus said. It was in Linux context, so probability? Btw. ask yourself about probability of this chance. Of course, there are some theories which can help, but I don't buy it..."

Which I dont really understand. "I'm according to what Linux said"? What do you mean? And then you write "It was in Linux context, so probability? ask yourself about probability of this chance" - which chance? I can not read your mind. I actually dont understand what you are trying to say here. Do you mean that there is a low probability that Linux would have evolved to this stage if it were only by random choice? I dont understand. Let me repeat that again: I can not read your mind. Be clearer.People are intelligent, so Linux evolution is driven by some intelligent people not by probability. So many problems with such obvious thing?

Is this SUN advertisement? It is SUN that has written this?
http://lethargy.org/~jesus/writes/choosing-solaris-10-over-linux (http://lethargy.org/%7Ejesus/writes/choosing-solaris-10-over-linux)

Is this SUN advertisement?
http://www.enterprisestorageforum.com/sans/features/article.php/3745996

Has SUN written this?
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1313798,00.html

And this?
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci1286507,00.html

Do you want more links? Where did you see "only" Solaris advertisements and propaganda, in my links? You know, most people would say that these links are real life stories. Not SUN advertisements. I was talking about Sun's advertisements, so why you gave those links?

I have a question. A) Where did you see "only" SUN advertisements?Only Sun, so not Linux's advertisements? Big problems in understanding this? :>

Have you ever considered the possibility that it is you that is dumb? I have intelligence far above average. I have tried the Mensa web test and emailed Mensa, and they replied that I have a very good chance to enter Mensa. If try the real Mensa test and enter Mensa, then I am more intelligent than ~95% of all people. Can you say the same thing? Maybe the reason I have problems following your logic is not because of me (I have far above average IQ and have studied logic at the university) maybe the problem is that you have not studied logic? Maybe you should do that?Nope, because I talked to far smarter and more intelligent people then you and they react far different and they would just stop this discussion long ago. You can try Mensa for idiots test, you should pass. Btw. you will base on what saying you're more intelligent then 95% of all people? All people taken such test? Does such test really measure intelligence? I don't think so. I recommend you to stop believing in such crap. Basing on your posts it's more probable you're more stupid then 95% of all people.

You dont have to call me ugly names, right? We are grown up people. I hope.I hope, but can you proof?

And also, I CAN NOT READ YOUR MIND. Please spell it out. Your english is not good. Your logic is wrong. Your thinking is wrong. I understand almost nothing about what you are trying to say. And I CAN NOT READ YOUR MIND.Nope, it's opposite. If you were intelligent you would just understand everything what I already said :>

I wrote: Yes, but facts/claims doesnt change.
You wrote: So, you should worry...
Why should I worry? For what? Let me say that again: I CAN NOT READ YOUR MIND. BE CLEARER.Yep, if the fact is you're dumb and if you consider facts doesn't change you should worry. However, sentence "You're dumb" can concern some period of time. You're dumb now - a fact. In next few years who knows? Fact won't change, but it's related to some period of time - now, in this case (but who knows :P). Facts don't change, but they become out of date (no longer valid?) if I can say this.

That was nice to not ashame me, but I dont care because I am interested to learn more. If you really have good links showing that I am wrong, please post them!I did. You've got problems. I said I'm not interested in proving you something (maybe I was for a while), because I don't care too much what you think. What I'm interested is you to stop writing a FUD.

Question B) How do you know that the Solaris code is a mess? Can you back that claim up? You have several times said that Solaris becomes unstable under large load, and never showed such links. Whereas I have showed links. Can you show links, or can you not? I explained what I think about some links. It's a mess, because Linux already killed it. It's big pile of old code, so it's hard to manage and/or its devs aren't able to make it better. Some big changes needed?

Of course Solaris kernel is not bug free. Have I claimed that, somewhere??? If you claim it is a pile of crap, then prove it. Show links that Solaris kernel have problems with stability and scalability. If you can not show such links, then you are wrong. Do you agree? If you want to claim that you are correct, then you must prove that you are correct. That sounds reasonable? Where are your proofs? Links?If I say something it's sometimes, because I want to say, not because you claimed. You didn't proof a thing :) Mensa you say - "If you can not show such links, then you are wrong."

If you can not show such links, then you are wrong.This is how your logic works. You don't care about the truth and reality, but you just base on some links which are clear propaganda. Tell me, why should I talk to you?

No, I did not ignore your link. I answered that link. I wrote: "Linux claims to run on 1024 cpu machine, but how well does it run? And such a machine is only used for number crunching - it is not used as big iron server where lots of users login och do office work. And number crunching is easy to do. Server workload is much more difficult, because it is general work... Where are your proofs? It runs better then Solaris, because they use Linux, isn't this obvious? Tell me, what workloads are on this machine used by SGI? How do you know its workloads are less "difficult"? The problem is, this machine isn't a cluster, but it's a Big Iron. If you want to be treated more seriously answer what I asked here.

For the other link, about Bonwick talking about Linux scaling bad - well that is a fact. Linux scales bad. It is not FUD or lies. Linus scaling experts admit that Linus v2.4 scales bad on Big Iron. And you know, it takes decades to scale well. Linux v2.6 can impossibly scale well. Maybe Linux v 6-7 can scale well on Big Iron.
http://searchenterpriselinux.techtarget.com/news/article/0,289142,sid39_gci929755,00.html
And also, you posted a link that showed that Linux scales bad. So how can Bonwick be FUDing? Even YOUR link showed that Linux scaled bad! Is your own link FUD???You're amazing me. You're manipulating the facts. Linux 2.6.xx scales wonderful. It's even mentioned it this article 2.6 (2.6.0, very old kernel) will scale easily up to 16 CPUs. Maybe it take decades for Solaris guys and this is a proof its code is a mess (or rather design). As I showed you Linux 2.6.8 scaled easily up to 64 CPU's and current kernels scales up to 4096 CPUs on big irons. Oh, and Bonwick is a layer, Sun probably paid him. I gave you link which shows he lies.

Ok, fine. But then you should have evidence? Proofs? Links that show that Linux scales well on Big Iron? Where are them links? You have showed some benchmarks on a 32 CPU machine - but that is not proof that Linux scales well in GENERAL, on every workload. And you showed a discussion about Linux on 1024 CPU machine - but how well does it run Linux? Maybe Linux sucks on that machine? There are no links on that. You have only showed that Linux compiles on a 1024 cpu machine and that you have showed that there are performance problems on that 1024 CPU machine - which the discussion is about.Are you dumb? I showed you 2.6.8 scales great to 64 CPUs and it's performance is fantastic.

There are no links on that. You have only showed that Linux compiles on a 1024 cpu machine and that you have showed that there are performance problems on that 1024 CPU machine - which the discussion is about.Thank you. If this discussion is about incompetence you should be shamed now. There's explanation why those people had problems. Not Linux, but configuration fault. If I explained this you should stop replying now. Still, Mensa? XD

I told you, RCU is no guarantee that it works well. I can say that a car has a special kind of super engine, but maybe it is not well implemented? Maybe the car is crap, but uses a good engine? If Linux uses RCU, it does not prove anything. Maybe Linux implementation of RCU is crap?The problem is you don't know a thing. You're just asking, guessing and believing. Stop fooling yourself :). Maybe, maybe, maybe... :) I already showed you Linux scales great, so why such stupid questions? To be completely fair with you there was a bug, but completely not related to what we are talking about here :).