Announcement

Collapse
No announcement yet.

Netbook Performance: Ubuntu vs. OpenSolaris

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • #81
    Originally posted by kraftman View Post
    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)

    Comment


    • #82
      Originally posted by kraftman View Post
      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.


      Originally posted by kraftman View Post
      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.


      Originally posted by kraftman View Post
      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.


      Originally posted by kraftman View Post
      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.


      Originally posted by kraftman View Post
      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.


      Originally posted by kraftman View Post
      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.


      Originally posted by kraftman View Post
      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/w...mtap-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.


      Originally posted by kraftman View Post
      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.


      Originally posted by kraftman View Post
      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.






      Originally posted by Apopas View Post
      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.


      Originally posted by Apopas View Post
      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.


      Originally posted by Apopas View Post
      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.


      Originally posted by Apopas View Post
      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.


      Originally posted by Apopas View Post
      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.

      Comment


      • #83
        http://www.xkcd.org/619/

        Comment


        • #84
          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

          Comment


          • #85
            Originally posted by bridgman View Post
            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...raceComparison

            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 design
            But isn't there someone intelligent who directs evolution into proper direction and eventually corrects its mistakes? :>
            Last edited by kraftman; 08-12-2009, 10:54 AM.

            Comment


            • #86
              Originally posted by kraftman View Post
              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.


              Originally posted by kraftman View Post
              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.


              Originally posted by kraftman View Post
              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?


              Originally posted by kraftman View Post
              http://sourceware.org/systemtap/wiki...raceComparison

              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?


              Originally posted by kraftman View Post
              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?


              Originally posted by kraftman View Post
              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.


              Originally posted by kraftman View Post
              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.


              Originally posted by kraftman View Post
              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.


              Originally posted by kraftman View Post
              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.


              Originally posted by kraftman View Post
              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?


              Originally posted by kraftman View Post
              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?


              Originally posted by kraftman View Post
              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.


              Originally posted by kraftman View Post
              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?

              Comment


              • #87
                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

                Burn Sun, burn...

                And yes, RCU :>

                Originally posted by kebabbert View Post
                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.
                Last edited by kraftman; 08-13-2009, 05:02 PM.

                Comment


                • #88
                  Originally posted by kraftman View Post
                  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.


                  Originally posted by kraftman View Post
                  :> 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

                  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.


                  Originally posted by kraftman View Post
                  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.


                  Originally posted by kraftman View Post
                  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?


                  Originally posted by kraftman View Post
                  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.



                  Originally posted by kraftman View Post
                  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?

                  Comment


                  • #89
                    Originally posted by kraftman View Post
                    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.



                    Originally posted by kraftman View Post
                    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?



                    Originally posted by kraftman View Post
                    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).


                    Originally posted by kraftman View Post
                    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.






                    Originally posted by kraftman View Post
                    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.




                    Originally posted by kraftman View Post
                    That's the point I stick with my opinions and you stick with yours. However, opinions change.
                    Yes, but facts/claims doesnt not change.


                    Originally posted by kraftman View Post
                    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.


                    Originally posted by kraftman View Post
                    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???"


                    Originally posted by kraftman View Post
                    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.



                    Originally posted by kraftman View Post
                    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.

                    Originally posted by kraftman View Post
                    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.
                    Last edited by kebabbert; 08-14-2009, 07:22 AM.

                    Comment


                    • #90
                      Originally posted by kebabbert View Post
                      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
                      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

                      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.
                      Last edited by kraftman; 08-15-2009, 04:55 AM.

                      Comment

                      Working...
                      X