Announcement

Collapse
No announcement yet.

Fedora, Debian, FreeBSD, OpenBSD, OpenSolaris Benchmarks

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

  • #31
    Originally posted by kraftman View Post
    Where I advertise it? What I do is trying to figure out why there's sometimes something wrong with it, or some benchmark etc.

    New thread please.

    Exactly what this means. Here: http://www.phoronix.com/forums/showp...3&postcount=21 few posts earlier. Another problems with memory?

    Nope, because afaik you never gave me a single relevant link. Why should I bother? Like I said, start a new thread.
    Linux system also uses different database.

    Comment


    • #32
      Kraftman,
      Aha! Now I understand what you mean with "different RAM amount"! It took a while to figure it out, because you never explained what you meant. I thought for a long time, that you meant: I had posted different benchmarks, one old benchmark where all SAP machines used X GB RAM, and now I try to fool you by posting another benchmark where all machines use Y GB RAM, from another website. I thought you talked about different benchmarks.

      But now at last, I think I understand what you mean with "different RAM amount". You mean that in these SAP benches I posted, from www.sap.com, the machines are differently configured? And the Linux machine has only 128GB RAM whereas the Solaris machine had 256GB RAM? And therefore you wrote "Different memory amount" and didnt explain further what you meant? Ok, now I get it. Well, I checked it up, and let me answer. (I wish you could be much clearer. What is clear to you, is not clear to another person. Half of the posts are me requesting a clarification from you. It is very hard to follow you, you write so terse. Just few words with no explaining: "you know which post I mean" - no, I dont know what you mean. Please clarify!)



      Linux runs on HP machine. It uses 128 GB RAM, and eight 2.8 GHz CPUs and is 7 rack unit.

      Solaris runs on SUN machine. It uses 256 GB RAM and eight 2.6 GHz CPUs and is 4 rack unit.

      The reason Linux uses less RAM in SAP benches, is because HP can use faster memory sticks, they can use PC2-6400! That is the reason. If HP uses 256GB RAM, then HP must use only slow PC2-5300 (which this Solaris machine use)

      When you look at page 15 of the quick specs pdf of the HP DL785G6 speed you will find the following note:
      "When only PC2-6400 DIMMs modules are installed with a processor then memory bus speeds for 4 or fewer, 6 or 8 DIMMs per processor will operate at PC2-6400, PC2-5300 and PC2-4200 respectively. All other processor and memory configurations will operate at PC2-5300 with 4 or fewer DIMMs and PC2-4200"

      The largest memory flavor with PC2-6400 is "8 GB REG PC2-6400 2 x 4 GB". The HP DL785 has 64 DIMM slots. To keep the memory bus at PC6400, you can just populate 32 of them. 32x4=128GB. HP ran the system at the top configuration that allowed them to use faster DIMMs.



      So, not only did the Linux machine use faster CPUs, but also faster RAM. And still the Linux machine is less efficient than Solaris, when scaling to as many as 48 cores. I can promise you that the HP benchmarking team would add another 128GB RAM if that would yield higher SAP benchmarks. It is not like HP does not have memory sticks to spare to run a test, when publicising important SAP benchmarks?

      If you wish, you can check SAP offical certified benchmarks 2009035 and 2009030. Do you know what is there? Linux and Solaris machines - with the same amount of RAM. And which one do you think is faster? Make a wild guess!




      I would call this SAP enterprise benchmark a relevant link showing that Solaris performs better than Linux on Enterprise work loads. I had earlier posted many such links, proving the same fact. I can repost them if you wish?




      Apopas,
      Yes, you showed me earlier, that all 11 million LoC Linux uses, is not relevant. I dropped that argument. You succeeded. The question is, What does Linus T actually mean, when he says that Linux is bloated? What does Andrew Morton mean when he say that "the code quality is declining"? What does Dave mean when he is saying that "the kernel is going to pieces"? What does Alan Cox mean, when he say that "the kernel should be fixed"? I mean, several Linux kernel developers are talking about bloat and bugs and declining quality. I wonder what they actually mean? It is some code language, they are actually talking about some secret plan where they rob a bank, right? They dont mean what they say, no one of them, right? I find it strange that you all can read their minds and know what they actually mean. How can you do that? Have you Extra Sensory Perception? And what does Oracle CEO Larry Ellisson mean, when he say that Solaris is better than Linux, that Solaris is the best Unix out there? I bet he is talking about what he will have for lunch. Or is it about his football, can you interpret? And what does Barak Obama mean, when he says he wants to send more troops? Is he talking about his backyard? Can you interpret?

      Comment


      • #33
        OpenSolaris default memory model

        As mentioned in discussions on earlier articles, the default memory model will skew the OpenSolaris results when compared to other OSes.
        The best example in this round of testing was C-Ray 1.1.

        The commands used to compile this test:

        gcc -O3 -ffast-math -c -o c-ray-mt.o c-ray-mt.c
        gcc -o c-ray-mt c-ray-mt.o -lm -lpthread

        On a 64-bit Linux distro, the above commands will default to 64-bit
        which provides a significant benefit for floating point intensive tests
        such as C-Ray. On OpenSolaris, the above commands will default to
        32-bit which uses the older x87 ISA.

        To show the difference, I booted bare metal OpenSolaris dev build 131
        and Unbuntu 9.04 64 bit on a Toshiba Tecra M10, Intel Core 2 Duo P8400
        (2.26GHz), 4GB. This difference between the T9300 CPU used in the
        ThinkPad for this article should just be a slightly better clock
        (2.5GHz versus 2.26GHz) and double the L2 cache (6MB versus 3MB).

        The default gcc version on OpenSolaris is 3.4.3 (admittedly rather
        old), Ubuntu 9.0.4 is 4.3.3. On OpenSolaris, you also have the option
        to install gcc version 4.3.2. For OpenSolaris, I tested with both
        gcc versions. On each platform the tests were compiled without
        changing any of the above option except to explicitly define the
        memory model by adding -m32 or -m64. The results (in seconds
        where lower is better):

        .........Ubuntu 9.04 64-bit..OpenSolaris...OpenSolaris
        .........gcc 4.3.3...........gcc 3.4.3.....gcc 4.3.2
        .........------------------..-----------...-----------
        m32......460.80..............467.11........454.22
        m64......197.88..............275.35........199.36

        When care is taken to compare the same memory model and
        relatively similar compiler versions, the performance is
        about the same. It certainly isn't the 4X shown for the
        C-Ray v1.1 results in the article. (I'm still uncertain
        how the test run for the article produced 868.13 on a
        faster CPU and larger cache than my result of 467.11
        for the default compiler version and memory model).

        Regards,

        John Martin

        Comment


        • #34
          Operatins System Comparisons

          I noted that the tests used GPL products such as encryption, decryption and archiving software.

          My question is. "What are we testing? Is the compiler efficiency?"

          Is the identical code (allow for different include files) being used for each test?

          My view is that a measure to be included is space/memory used for each operating system, and for each test.

          True enough, a poor scheduling algorithm will alter results and increase elapsed time. Alignment of code on multiple of word size will also affect the look-ahead capability of the microprocessor, whatever the brand.

          My feeling is that each version of linux should use the same kernel version, and likewise for competing bsd versions. Then compare linux versions against each other, and bsd versions against each othr, and using averages for linux and for bsd, produce a simple comparison.

          Leslie

          Comment


          • #35
            @Kebbabert, Orvar Korvar

            Aha! Now I understand what you mean with "different RAM amount"! It took a while to figure it out, because you never explained what you meant. I thought for a long time, that you meant: I had posted different benchmarks, one old benchmark where all SAP machines used X GB RAM, and now I try to fool you by posting another benchmark where all machines use Y GB RAM, from another website. I thought you talked about different benchmarks.
            You didn't know what were you talking about.

            So, not only did the Linux machine use faster CPUs, but also faster RAM
            And this means Linux CPU utilization must be higher in this benchmark? You're really making fool of yourself.

            At your first arrival you said Linux doesn't scale good on Big Irons. I showed you many times it does and here's some nice example:

            http://blog.itaniumsolutions.org/200...AE-processors/

            SGI raised the bar again to recapture undisputed leadership in this benchmark with 9,611,262 Business Operations per Second (BOPS) on Altix 4700 with 512 Itanium 9040 cores,1.6GHz and 18MB cache using Oracle® JRockit, a Java Virtual Machine (JVM). The new SGI record is over 74 percent higher than the previous record.

            Comment


            • #36
              @Kebabbert, Orvar Korvar

              I would call this SAP enterprise benchmark a relevant link showing that Solaris performs better than Linux on Enterprise work loads. I had earlier posted many such links, proving the same fact. I can repost them if you wish?
              Show me Solaris scaling on at least 512CPU machine not some stupid sap papers.

              http://www.internetnews.com/software...+on+Oracle.htm
              http://rcpmag.com/blogs/lee-pender/2...rosshairs.aspx

              Comment


              • #37
                @Orvar

                And what does Oracle CEO Larry Ellisson mean, when he say that Solaris is better than Linux, that Solaris is the best Unix out there?
                He means "we can make some money on it if we'll continue Sun's propaganda, because we've got slowlaris while our competitors, like IBM, don't". Btw where he said Solaris is better?

                http://www.forbes.com/2009/09/22/ora...y-ellison.html

                Comment


                • #38
                  [QUOTE=kraftman;110548]@Orvar

                  He means "we can make some money on it if we'll continue Sun's propaganda, because we've got slowlaris while our competitors, like IBM, don't". ....

                  Actually IBM, Dell and HP do have Solaris.

                  http://www-03.ibm.com/systems/x/solutions/os/solaris/
                  http://h18000.www1.hp.com/products/s...ris/index.html
                  http://www.dell.com/content/topics/g...us&l=en&cs=555

                  Out of curiosity, where did the hostility towards Solaris originate?

                  Comment


                  • #39
                    Originally posted by jmartin View Post
                    @Orvar

                    He means "we can make some money on it if we'll continue Sun's propaganda, because we've got slowlaris while our competitors, like IBM, don't". ....

                    Actually IBM, Dell and HP do have Solaris.

                    http://www-03.ibm.com/systems/x/solutions/os/solaris/
                    http://h18000.www1.hp.com/products/s...ris/index.html
                    http://www.dell.com/content/topics/g...us&l=en&cs=555

                    Out of curiosity, where did the hostility towards Solaris originate?
                    What Ellison said is a part of their marketing:

                    Ellison insisted that Oracle can continue to give full support to the Linux operating system, even as it gears up to promote Solaris, the operating system developed by Sun.
                    You should rather ask someone else where did the hostility towards Linux originate. Did you forget your firm's bull and anti Linux campaign? You both really don't know how to reply properly?

                    Comment


                    • #40
                      I forget to say IBM, HP and Dell do not own Solaris.

                      Comment


                      • #41
                        Originally posted by kraftman View Post
                        You didn't know what were you talking about.
                        Maybe you didnt explain anything? You wrote "different ram amount". What did you mean with that? Now I understand, but what is clear to you, is not clear to others.

                        Originally posted by kraftman View Post
                        And this means Linux CPU utilization must be higher in this benchmark? You're really making fool of yourself.
                        I meant that Linux used faster CPUs and faster RAM. And still Linux had lower SAP score than Solaris. And we also see that Linux had 87% utilization, whereas Solaris had 99%. What conclusions can you infer from these facts?

                        Originally posted by kraftman View Post
                        At your first arrival you said Linux doesn't scale good on Big Irons. I showed you many times it does
                        You did??? Can you post them links again? I must have missed them!

                        Originally posted by kraftman View Post
                        So what are you trying to prove here? Sure, they used 128 blades with 256 CPUs and, for instance, achieved 9,6 million BOP/s in SPECjbb2005. Which is quite respectable.

                        But the SPECjbb2005 benchmark (configured with multiple JVMs) is one of the problems of the "embarrassingly parallel" class. You can scale it by running multiple copies. In the bench, they configured 128 JVMs, exactly the number of blades. The application didnt have to use NUMA link between the blades. The JVMs are working independent from each other, so no communication between the the nodes, too. So the SPECjbb2005 benchmark on an Altix 4700 is not much more than throwing a cluster at a problem it's best at! Hence, this does not prove anything about scalability.

                        We all agree (including Linux scalability experts), Linux scales well on a cluster. That is where Linux strength is, horizontal scaling. As Linux scalability expert Greenblatt says:
                        "Greenblatt: Linux has not lagged behind in scalability, [but] some [Unix] vendors do not want the world to think about Linux as scalable. The fact that Google runs 10,000 Intel processors as a single image is a testament to [Linux's] horizontal scaling".

                        "The true Linux value is horizontal scaling."

                        To my knowledge, there is no single big machine with 10.000 intel processors on the market. Google must be using clusters.

                        Originally posted by kraftman View Post
                        Show me Solaris scaling on at least 512CPU machine not some stupid sap papers.
                        Why are the SAP papers stupid? Is it because Linux looses? If Linux win, then SAP papers are good, yes? So what is a good paper? A paper is good if Linux wins, and bad if Linux looses?

                        To me, a paper is good if it uses official standardized benchmarks, in a fair way, where no one complains. The outcome does not decide if a white paper is good or not. If the white paper has a scientific, reproducible approach, then it is good. Just like in science. The method is extremely important, the outcome is not important in science.

                        But you have proved earlier that the outcome decides if a white paper/benchmark is good, not how good the method is. I think you(?) showed earlier that one guy migrated from 800MHz SPARC to 2.4GHz Intel dual core Linux and therefore you "proved" that Linux is faster. That is just a weird comparison according to me. Not fair. But that doesnt matter to you, as you have "proved" what you want.

                        I want more benches on the SAME hardware. With many CPUs/cores. But I suspect you dont want such benchmarks, because Linux would loose big time. You prefer unfair benches. That is not fair.



                        Regarding Solaris scaling to 512 CPUs, I dont know if there exist such a Sun machine on the market, so I can not show you such benches. But if there existed such a machine, Solaris would of course have higher CPU utiilization, again. Why wouldnt Solaris?

                        You know, just because Linux EXISTS on a big machine, it doesnt mean that Linux scales well. I bet that Linux has a very low utilization on machines with many CPUs, maybe 10% CPU utilization? But I am sure that Solaris utilizes the CPUs far better than Linux on same hardware (machines with many CPUs). As we saw on the SAP benchmark with 48 cores.

                        Originally posted by kraftman View Post
                        Btw where [Larry Ellison] said Solaris is better?
                        http://www.serverwatch.com/news/arti...ent=26258-2761

                        Originally posted by kraftman View Post
                        [Larry Ellison] means "we can make some money on it if we'll continue Sun's propaganda, because we've got slowlaris while our competitors, like IBM, don't".
                        Heh. Dont you know that you need four IBM POWER6 5GHz to match two Intel Nehalem 2.93GHz on TPC-C benchmarks? Dont you know that any modern AMD/Intel CPU is 5-10x faster than a modern IBM Mainframe CPU? Dont you know you need six IBM Power P570 servers with 28 POWER6 CPUs to match one Sun T5440 (that has four 1.4GHz Niagara CPUs) on SIEBEL v8 benches? One P570 costs $413.000 and one Sun T5440 costs $76.000. Dont you know that Linux has the TPC-C record right now, on SUN hardware? IBM has lost it. To me it seems that IBM is slower everywhere.

                        Comment


                        • #42
                          Originally posted by kebabbert View Post
                          Maybe you didnt explain anything? You wrote "different ram amount". What did you mean with that? Now I understand, but what is clear to you, is not clear to others.
                          You're asking here I should treat like an idiot? It was clear also for some another person, it seems it's only you who has problems with understanding things.

                          I meant that Linux used faster CPUs and faster RAM. And still Linux had lower SAP score than Solaris. And we also see that Linux had 87% utilization, whereas Solaris had 99%. What conclusions can you infer from these facts?
                          And Solaris used different DB and twice as much memory as Linux. Conclusion is very simple - on Linux CPU utilization was 87% using different DB and less memory and on Solaris CPU utilization was 99% using different DB and double amount of memory. That's all.

                          You did??? Can you post them links again? I must have missed them!
                          I asked for another thread and you ignored this like a troll.

                          So what are you trying to prove here? Sure, they used 128 blades with 256 CPUs and, for instance, achieved 9,6 million BOP/s in SPECjbb2005. Which is quite respectable.
                          Not trying, but I actually proved you Linux scales great.

                          But the SPECjbb2005 benchmark (configured with multiple JVMs) is one of the problems of the "embarrassingly parallel" class. You can scale it by running multiple copies. In the bench, they configured 128 JVMs, exactly the number of blades. The application didnt have to use NUMA link between the blades. The JVMs are working independent from each other, so no communication between the the nodes, too. So the SPECjbb2005 benchmark on an Altix 4700 is not much more than throwing a cluster at a problem it's best at! Hence, this does not prove anything about scalability.
                          Straw man strikes again. You can safely ignore mentioned benchmark if you want, but it doesn't change the fact that Linux scales great on machines were Solaris probably didn't even try. You should at least point to source of your quoted text, but I already found it:

                          At the moment i have my problems to see why both benchmarks highlight the advantages that make them a better choice for Java. Perhaps BlueToTheBone should stop to use those numbers as examples to convince the world of this opinion in regard of Sun.
                          http://www.c0t0d0s0.org/archives/593...benchmark.html

                          Someone from OpenSolaris user group. I said many times I'm not interested in SUN related people bull. Btw. you pasted someones text here like it was yours.

                          We all agree (including Linux scalability experts), Linux scales well on a cluster. That is where Linux strength is, horizontal scaling. As Linux scalability expert Greenblatt says:
                          "Greenblatt: Linux has not lagged behind in scalability, [but] some [Unix] vendors do not want the world to think about Linux as scalable. The fact that Google runs 10,000 Intel processors as a single image is a testament to [Linux's] horizontal scaling".

                          "The true Linux value is horizontal scaling."

                          To my knowledge, there is no single big machine with 10.000 intel processors on the market. Google must be using clusters.
                          What knowledge? It's about horizontal scaling and what you were talking all the time was about vertical scaling.

                          Why are the SAP papers stupid? Is it because Linux looses? If Linux win, then SAP papers are good, yes? So what is a good paper? A paper is good if Linux wins, and bad if Linux looses?
                          Read links I showed you.

                          I want more benches on the SAME hardware. With many CPUs/cores. But I suspect you dont want such benchmarks, because Linux would loose big time. You prefer unfair benches. That is not fair.
                          Funny to read this. It is you who's giving unfair benches - different memory amount, different db, SUN made benchmarks. Thanks for such bull.

                          Regarding Solaris scaling to 512 CPUs, I dont know if there exist such a Sun machine on the market, so I can not show you such benches. But if there existed such a machine, Solaris would of course have higher CPU utiilization, again. Why wouldnt Solaris?
                          If you can't then what are you trying to do?

                          You know, just because Linux EXISTS on a big machine, it doesnt mean that Linux scales well. I bet that Linux has a very low utilization on machines with many CPUs, maybe 10% CPU utilization? But I am sure that Solaris utilizes the CPUs far better than Linux on same hardware (machines with many CPUs). As we saw on the SAP benchmark with 48 cores.
                          Like I said, meaningless comparison. It wasn't same hardware, so stop lying.

                          I read this, but I don't see where he said such thing. Of course he's doing what he said before:

                          Ellison insisted that Oracle can continue to give full support to the Linux operating system, even as it gears up to promote Solaris, the operating system developed by Sun.

                          Comment


                          • #43
                            Originally posted by kraftman View Post
                            You're asking here I should treat like an idiot? It was clear also for some another person, it seems it's only you who has problems with understanding things.
                            I am just asking you to be clearer by providing more information and relevant links. Is that hard for you to do? I have asked for this over and over again. But still you dont. You just write very terse answers making it hard for me to follow you. The thing is, I think very differently from you, so I am getting confused and I dont understand what you mean. Because you state so weird things sometimes, so I have a hard time understanding what you say "did Kraftman really compare 800MHz SPARC to a 2.4GHz Intel? No, he could not possibly mean it is a fair comparison! Or? What did he mean? I dont get it".

                            I just dont understand you. Therefore I have asked you to be much clearer. But apparently that is very very very difficult for you. Because otherwise you would not make such a big deal of insisting of being terse.

                            For instance, you have posted several links about Oracle and SAP, like this one
                            http://www.internetnews.com/software...+on+Oracle.htm
                            Actually, I dont understand why posted that link. You just posted several such links without an explanation. What did you mean with them? No information at all, from you on this.

                            Look, is it really really really sooooo difficult to provide some more information? I have asked this many times. I dont understand what you are trying to say!

                            So, if this is the only thing that helps: Yes, please treat me like an idiot. Please explain what all those links where about. And when you explain something, please provide some explanation. Can you do that, to an idiot? (Obviously you refuse to provide information when I ask of you)


                            Originally posted by kraftman View Post
                            And Solaris used different DB and twice as much memory as Linux. Conclusion is very simple - on Linux CPU utilization was 87% using different DB and less memory and on Solaris CPU utilization was 99% using different DB and double amount of memory. That's all.
                            So no conclusion can be drawn at all? You dont think that any conclusions can be drawn at all?


                            Originally posted by kraftman View Post
                            I asked for another thread and you ignored this like a troll.
                            Why should I do what you order me? You attacked me when I said that they should try a new release of OpenSolaris, that is all I said. And you called me Troll for that post. So, if you really want another thread, why dont you start it, instead of ordering me to do it, and calling me a Troll? Do you often do like that? Command people to do something that YOU want, and when they dont do it, you call them names?


                            Originally posted by kraftman View Post
                            Not trying, but I actually proved you Linux scales great.
                            You did? Cool! Can you show me those posts, then? You showed that Linux got high scores on parallell work loads with 256 CPUs. But I must have missed your other links. Please treat me like an idiot and repost them here. Can you do that, or is it too difficult (as usual)?


                            Originally posted by kraftman View Post
                            Straw man strikes again. You can safely ignore mentioned benchmark if you want, but it doesn't change the fact that Linux scales great on machines were Solaris probably didn't even try. You should at least point to source of your quoted text, but I already found it:

                            http://www.c0t0d0s0.org/archives/593...benchmark.html

                            Someone from OpenSolaris user group. I said many times I'm not interested in SUN related people bull. Btw. you pasted someones text here like it was yours.
                            Yes, that is the link I got this text from. Earlier I always posted links, but I stopped because of you. Recently, I showed you a Sun page which pointed to these certified SAP white papers on www.sap.com but you explained that these SAP certifications on www.sap.com had been pointed to, from a Sun web page, and therefore these SAP certifications are "Sun propaganda" and not to be trusted. I said that from now on, I will not link to Sun pages, I will copy & paste text. Do you remember this discussion? Therefore I dont provide Sun links anymore.

                            Back to this SPECjbb2005 benchmark. Do you mean the things I wrote down are not correct? So please, point out the incorrect facts here, then. Exactly what is wrong? Or dont you know what is wrong, or maybe everything is correct?

                            "But the SPECjbb2005 benchmark (configured with multiple JVMs) is one of the problems of the "embarrassingly parallel" class. You can scale it by running multiple copies. In the bench, they configured 128 JVMs, exactly the number of blades. The application didnt have to use NUMA link between the blades. The JVMs are working independent from each other, so no communication between the the nodes, too. So the SPECjbb2005 benchmark on an Altix 4700 is not much more than throwing a cluster at a problem it's best at! Hence, this does not prove anything about scalability."


                            Originally posted by kraftman View Post
                            What knowledge? It's about horizontal scaling and what you were talking all the time was about vertical scaling
                            I dont understand this. Could you explain what you mean? I said that Linux doesnt scale well vertically, but scales well horizontally. Just as the Linux scaling experts say.


                            Originally posted by kraftman View Post
                            Read links I showed you.
                            How about you explain a bit, instead? I asked if a benchmark is good if Linux wins, but bad if Linux looses? And to this question you answer, very cryptical: "read links I showed you". Which links, you have posted many links. Can you just explain a bit more? It does not help to ask you of more information, maybe I can get more infomation if you treat me like an idiot. So go ahead, treat me like an idiot. I dont get it, why, oh why, is it so difficult to explain exactly what you mean, so we can follow you? I have asked you many times of this.


                            Originally posted by kraftman View Post
                            Funny to read this. It is you who's giving unfair benches - different memory amount, different db, SUN made benchmarks. Thanks for such bull.
                            So you mean that because Sun made benchmarks therefore you can not trust them? So... who do you think should do the Solaris benchmarks? Should FedEx do the Solari benches?

                            You know, Linux used faster RAM and faster CPUs. The hardware is in favour of Linux, but still Linux is slower on SAP. So we can conclude that Linux is not a good SAP performer, right? You should use Solaris for SAP. Do you agree on this? Linux sucks on SAP - agreed?


                            Originally posted by kraftman View Post
                            If you can't then what are you trying to do?
                            The whole discussion is which OS scales best. If Linux EXISTS on a machine with 256 CPUs, doesnt say how good Linux scales, right? I hope everyone understands this. But, I have showed that Solaris has higher CPU utilization than Linux on 48 cores, on SAP. Solaris scales better on 48 cores. The more cores, Solaris will be faster and faster than Linux.


                            Originally posted by kraftman View Post
                            Like I said, meaningless comparison. It wasn't same hardware, so stop lying.
                            Ok, so if I install Solaris on a machine with 10,000,000 CPUs, and then I start one SPECjbb2005 JVM on each CPU, and run them in parallell, and then I get lots of BOP - does this mean that Solaris scales better than buggy Linux? No? But you are using the same argument here. It doesnt matter if Linux exist on a computer with the slow Itanium CPU, with 128 blades - it does matter how good Linux utilizes the CPUs, how good it scales. These are two different things. Linux existing on a large computer, does not mean it scales well. As we have seen, Linux underperfoms badly on as little as 48 cores. I expect Linux to be really bad on many cores. CPU utilization will drop off sharply. 87% on 48 core, maybe 75% on 64 cores, maybe 50% on 128 cores. On 512 cores, maybe 10%.


                            Originally posted by kraftman View Post
                            I read this, but I don't see where he said such thing. Of course he's doing what he said before:
                            Larry Ellison says Solaris is better than Linux in that link. I copy and paste for you:
                            "We're big supporters of Linux, [but] Solaris is an older and more capable operating system," Ellison said.

                            While he expects to see Solaris primarily at the high end, it will go all the way down to the desktop for development. Nevertheless, he stressed that the high end is the home for Solaris, which could be a cloud of x86 or SUN SPARC machines.

                            "We think it will be a long time before Linux ever catches up," Ellison said"

                            Linux is for low end, and Solaris for high end. Just as it should be.



                            And you never answered to my questions: what does Linus T mean when he says that the kernel is bloated? What does Andrew Morton say when he says that the code quality is declining? What does the kernel developers mean with that?

                            Comment


                            • #44
                              Originally posted by kebabbert View Post
                              "We think it will be a long time before Linux ever catches up," Ellison said"

                              Linux is for low end, and Solaris for high end. Just as it should be.
                              I won't feed you more in this thread. Linux handles many mission critical systems and most demanding workloads, so you're just making fool of yourself. You never started a new thread when asked, so your intention is to pollute this thread. It's enough for me to know Orvar Korvar is a big troll.

                              Look, is it really really really sooooo difficult to provide some more information? I have asked this many times. I dont understand what you are trying to say!
                              I provided you many examples, but it's not my problem you don't understand a thing.

                              As some example look here:

                              The whole discussion is which OS scales best. If Linux EXISTS on a machine with 256 CPUs, doesnt say how good Linux scales, right? I hope everyone understands this.
                              It exists even on bigger machines - 512, 1024CPUs. It scales up to 4096CPUs and Solaris probably don't even scale up to 512CPUs. It says Linux scales up to far more CPUs then Solaris, so Linux scales better.

                              But, I have showed that Solaris has higher CPU utilization than Linux on 48 cores, on SAP. Solaris scales better on 48 cores. The more cores, Solaris will be faster and faster than Linux.
                              You showed two different papers where Linux and Solaris ran on different hardware. That's all.

                              And you never answered to my questions: what does Linus T mean when he says that the kernel is bloated? What does Andrew Morton say when he says that the code quality is declining? What does the kernel developers mean with that?
                              I did, long ago.

                              Comment


                              • #45
                                Originally posted by kebabbert View Post
                                what does Linus T mean when he says that the kernel is bloated?
                                In the very same interview he said kernel is bloated and huge but there is not problem with stability.
                                "I think we've been pretty stable,"
                                "We are finding the bugs as fast as we're adding them — even though we're adding more code."

                                So you imply that Linux is buggy because it is bloated, while Linus in the very same post you mentioned says this is not a fact.
                                So while Linux is bloated and huge, is not buggy. So the problem of bloatness has to do with difficulty to maintain a large amount of code (fortunately kernel has many developers) andmainly a large amount of unecessary code, which while it's still bad doesn't affect Linux' performance.

                                Comment

                                Working...
                                X