Announcement

Collapse
No announcement yet.

Netbook Performance: Ubuntu vs. OpenSolaris

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

  • #31
    Originally posted by kraftman View Post
    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?


    Originally posted by kraftman View Post
    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?


    Originally posted by kraftman View Post
    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.


    Originally posted by kraftman View Post
    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.


    Originally posted by kraftman View Post
    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.techtar...286507,00.html
    "The problems we encountered were because Linux doesn't scale all that well," Rand said."

    Or this one:
    http://searchenterpriselinux.techtar...313798,00.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?

    Originally posted by kraftman View Post
    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".


    Originally posted by kraftman View Post
    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/...ver-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."


    Originally posted by kraftman View Post
    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.

    Originally posted by kraftman View Post
    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.

    Comment


    • #32
      Originally posted by kraftman View Post
      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.

      Comment


      • #33
        @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.

        Originally posted by frantaylor View Post
        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
        Last edited by kraftman; 08-01-2009, 12:49 PM.

        Comment


        • #34
          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.

          Comment


          • #35
            Originally posted by frantaylor View Post
            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.
            Last edited by kraftman; 08-02-2009, 05:56 AM.

            Comment


            • #36
              Don't feed the trolls..

              Comment


              • #37
                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.

                Comment


                • #38
                  Originally posted by yotambien View Post
                  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.

                  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/sol...mssg/3015.html

                  If someone wants 'profffs' :P

                  Don't feed the trolls..
                  And known Yotambien came XD
                  Last edited by kraftman; 08-02-2009, 10:42 AM.

                  Comment


                  • #39
                    Originally posted by kraftman View Post
                    @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?


                    Originally posted by kraftman View Post
                    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.


                    Originally posted by kraftman View Post
                    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.


                    Originally posted by kraftman View Post
                    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 ....".


                    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?

                    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?

                    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.

                    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.

                    Originally posted by kraftman View Post
                    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.

                    Comment


                    • #40
                      Originally posted by kebabbert View Post
                      [...]
                      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

                      Comment


                      • #41
                        Originally posted by kebabbert View Post
                        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...
                        Last edited by kraftman; 08-02-2009, 05:39 PM.

                        Comment


                        • #42
                          Originally posted by kraftman View Post
                          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.

                          Comment


                          • #43
                            Hard performance requirements

                            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.

                            Comment


                            • #44
                              Originally posted by frantaylor View Post
                              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

                              Comment


                              • #45
                                Originally posted by frantaylor View Post
                                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.

                                Comment

                                Working...
                                X