Catch up on stories from the past week (and beyond) at the Slashdot story archive

 


Forgot your password?
Close
typodupeerror
×
Linux Software

HP Publishs First Linux TPC-C Benchmarks 208

Posted by chrisd from the the-benchmark-with-a-shady-past dept.
The first ever official TPC-C benchmark on a Linux system has been published. This was run on a cluster of 32 HP servers with Intel Xeon CPUs, running Redhat Linux and Oracle RDBMS. The system had over 18 terabytes of storage, and cost over 2 million US dollars. Performance was higher than a similar system running on MS Windows.
This discussion has been archived. No new comments can be posted.

HP Publishs First Linux TPC-C Benchmarks More

HP Publishs First Linux TPC-C Benchmarks

Comments Filter:

  • Just imagine... (Score:1, Redundant)

    by countach ( 534280 )
    Having a Beowulf cluster...

    Oh never mind.

  • TPC-C (Score:1, Funny)

    by Anonymous Coward
    Is about 1,100 difference in the TPC-C that big of a deal? I dont know what TPC-C measures so for all I know it could be the difference between a yugo and a delorean.
    • Well, the other difference is the cost.. the cluster w/ linux on it costs $200k AND ran faster.. if only so slightly I think the combination of those factors should've been taken into account.. i know i would like to keep 200k if i could ;) I wonder how many times you would have to reboot nodes on a win cluster :P
    • But, it means that this setup, clusters of good intel hardware running redhat, and oracle's cluster stuff is a very, very serious contender when it comes to large databases.

      ANd if you look at it on a cost basis, it's a HUGE contender.

  • Windows or Oracle (Score:3, Interesting)

    by Anonymous Coward on Thursday September 19, 2002 @03:20AM (#4287180)
    One wonders where the slowdown lies. It would be nice to find out if it lies withing the Win32 version of Oracle or within Windows. Seeing as Windows does have the top score in the Clustered TPC-C results, I'm leaning more towards Oracle being the slow one. (everyone else here would disagree no doubt)

  • Still not the fastest price/performance.... (Score:3, Interesting)

    by Anonymous Coward on Thursday September 19, 2002 @03:21AM (#4287186)
    If you look at the top results in a price/performance comparison, Windows 2000/SQL server are still winning.
    http://www.tpc.org/tpcc/results/tpcc_price_perf_re sults.asp?resulttype=cluster&version=5 [tpc.org]

    It's interesting, though, that Red Hat had the cheapest Oracle implementation.
    • Indeed. However, notice that numbers 5 and 6 on that $/tcp table are the two systems this story is about.

      It takes only a small leap of faith to believe that whatver HP did to their old #5 system to push it down into slot 6 could also be applied to their #s 1, 2 and 3 systems.

      For example, and _purely hypothetically_, assuming a 7.26% improvement for those systems too on migrating to Lunix would give results of
      $12.14, $13.09, $13.94

      Which would leave the table at
      Lunix $12.14
      Doze $13.02
      Lunix $13.09
      Lunix $13.94
      Doze $14.04
      Doze $14.96

      The majority of the rating improvement (>6%) was through diminished _cost_, which is pretty much guaranteed by migration to Lunix. Only a small part (1%) was through improved performance.

      So the leap of faith really isn't that huge.
      Maybe HP were hoping to convert their #5 Doze machine into a #4 machine, ousting IBM, but failed.They currently don't actually need to improve their #1 position.

      Only time will tell.

      THL.

  • "Publishs" (Score:3, Funny)

    by great throwdini ( 118430 ) on Thursday September 19, 2002 @03:27AM (#4287205)

    This just in: ditors at Slashdot ar no longr prmittd to us th lttr '' in articl titls!

  • Inconclusive (Score:4, Insightful)

    by BlowCat ( 216402 ) on Thursday September 19, 2002 @03:29AM (#4287207)
    The Windows system was tested with 24 clients, the Linux system was tested with 16 clients. The model name of the cluster is a bit different (DL580-0200032P vs. DL580-PDC 32P C/S). I have no idea if it means different hardware or software.

    On the other hand, the difference in performance is 17.21 vs. 18.46, i.e. approximately 6%. I think that the result is inconclusive (except that Linux can complete in this area at all).

    • It is a benchmark, after all ;-)

      The nice thing about statistics, benchmarks, or anything else that tries to assign a number with some sort of value to something that's much more complicated is there are so many factors in the complicated thing, and thus ways to fsck up. Therefore, there are equally many ways to fudge.

    • Re:Inconclusive (Score:2, Informative)

      by Tim Colgate ( 519024 )
      As the cost of the clients is so much less than the servers, I'm sure that they will just add clients until the server cluster reaches maximum throughput.

      I noticed a few things when looking at the break-down of costs:

      For the clients, a 1G 133Mhz SDRAM DIMM is $880! ouch. The cost per client is $7172, for which you get a dual 1.4Ghz Pentium III with 4Gb of RAM ... and a whopping 15" CRT. The clients only make up 5% of the overall cost though.

      The Oracle software is $35000/CPU, for 3 years. What happens after 3 years? Does Oracle lease the software or something? Oracle support is shown as 2,000 * 24. Where does the 24 come from?

    • Score 4 for this _non-fact_:
      "the difference in performance is 17.21 vs. 18.46, i.e. approximately 6%"
      !?!?

      Those weren't the measure of _performance_.

      If you'd read the summaries you'd know that the majority of the increased rating was due to a difference in _price_, and only marginally due to an increase in _performance_.

      Yes, I'm a pedant. Sue me.

      THL.

    • Re:Inconclusive (Score:3, Insightful)

      by rseuhs ( 322520 )
      On the other hand, the difference in performance is 17.21 vs. 18.46, i.e. approximately 6%. I think that the result is inconclusive (except that Linux can complete in this area at all).

      ... and HP is willing to publish TCP-C benchmarks for Linux.

      That's exactly what Linux needs: Marketing.

    • This is a good point. I'd like to add that the Windows test was done 3.5 months earlier, and that the cost was based on the Total System. We all know how quickly prices drop for hardware. Given the very small cost difference between the Windows setup and Linux setup this fact alone could put them on equal financial ground.
      • Completely agree. Further the difference in performance could easily be due to:

        * Different transaction monitors
        * Different Oracle optimizations
        * Newer/faster/cheaper components in the machines

        Still interesting that HP is touting Linux, but the point is accurate that the difference is inconclusive. I find it also interesting that the putatively cheapest solution (the only difference here would be attributed to OS price) did not make the top 10 price/perf ratio.

  • more TPC-C scores... (Score:2, Informative)

    by MrFenty ( 579353 )
    Some more TPC-C benchmarks of big iron kit... found here [ideasinternational.com]

  • Comparable cost between windows and linux cluster (Score:5, Informative)

    by Wizard of OS ( 111213 ) on Thursday September 19, 2002 @03:31AM (#4287216)
    I did a quick compare and was kind of surprised by the following:
    Linux cluster:
    Total System Cost 2,380,546 US $

    TPC-C Throughput 138,362
    Price/Performance 17.21 US $

    Windows cluster:
    Total System Cost 2,533,095 US $

    TPC-C Throughput 137,261
    Price/Performance 18.46 US $

    Note that the number of clients in the windows tests is higher 24 instead of 16), with smaller CPU's. Also, the server's aren't identical.

    Besides from the small differences in setup, it's plain that hardware-costs greatly outnumber software costs. Yeah, linux has a small bit more performance (less than 1%) for a bit lower price (6%) but these aren't real shocking numbers. Of course, I'll get flamed for not bashing microsoft, but the difference really isn't that big.
    • Of course, I'll get flamed for not bashing microsoft

      Don't be silly. :)

      From this FAQ [tpc.org] you'll see:

      In general, TPC benchmarks are system-wide benchmarks, encompassing almost all cost dimensions of an entire system environment the user might purchase, including terminals, communications equipment, software (transaction monitors and database software), computer system or host, backup storage, and three years maintenance cost. Therefore, if the total system cost is $859,100 and the throughput is 1562 tpmC, the price/performance is derived by taking the price of the entire system ($859,100) divided by the performance (1562 tpmC), which equals $550 per tpmC.

      Most people would focus on the hardware cost, but in reality the highlighted maintenance cost took the precedence.

      Most midrange UNIX server has outragous maintenance cost. The maintenance cost of a UNIX server in the third year could be exceeding the cost of the hardware itself. It's due to the fact that older parts are difficult to find, thus make maintaining older servers more difficult. Besides, they really want to cut older production lines in favor of newer servers production.

      x86 platform is known to have flat and lower maintenance cost, due to the low cost hardware and high compability with older hardware, i.e. older parts can be found easily. That's why Microsoft could easily beat the TPC pissing races.

      Doomsday finally comes to Microsoft when Linux is entering the database market. Although at this moment big corps are still offering Linux maintenance with cost comparable to UNIX package, that's not surprising when Linux engineers are not as abandon as MCSE. However, it'll not be the case in the future. I think Microsoft would eventaully lose this pissing race in the long run.
      • TPC suffer from arse-elbow syndrome:

        http://www.tpc.org/tpcc/faq.asp : ... and three years maintenance cost.

        http://www.tpc.org/tpcc/detail.asp : ... maintenance costs over 5 years.

        THL.
      • Hardware replacement availability is rarely a factor, as a good service organization will have a way to get parts for anything they support. As an extreme example a fellow tech of mine about 4 years ago went onsite to a company that had a dead pc, it turned out it was an IBM PC XT with a dying MFM hdd 20MB I believe, the hdd had on it some customer terminal program for interfacing with an IBM mainframe back at corporate hq. He bandged the drive a couple of times on the table to get the motor to spin up and told the customer not to turn off the pc, he then put in a service request for a replacement drive, not really expecting it to be fulfilled. Low and behold our parts people found a vendor that had like 20 of the necessary drive in storage and the customer bought 2 just to make sure they had one in case the replacement died (probably in another 15 years or so).

    • it's not about not paying for the software (Score:5, Insightful)

      by g4dget ( 579145 ) on Thursday September 19, 2002 @04:46AM (#4287363)
      Using Linux as the server OS is not about getting the OS for free--as you observe, the cost of the OS is pretty much lost in the noise.

      The reason to use Linux is all aspects of its openness and compatibility with other systems. With Linux, you aren't locked into a single vendor. You use tools and APIs that have been around for nearly two decades and are available, in multiple implementations, from dozens of vendors. And you control how you upgrade, when you upgrade, and what path you follow with the software. And if you don't like Linux anymore, you can switch to any of a dozen other, compatible platforms.

      With Windows, you are locked into a single, proprietary implementation and Microsoft has you by the proverbial precious body parts; there is no other vendor you can get a compatible implementation of Windows or all the Windows libraries from. Every couple of years, Microsoft completely changes their computing paradigms to ape what they perceive is a threat from some other company, and when the threat is gone, they just drop the initiative and move on to the next thing.

      You can get stability buy paying a premium to a company like IBM, which is committed to providing it, or through open systems available from multiple vendors or open source, where you control your future. But building a large, long-lived infrastructure on Microsoft platforms is a costly folly--the company has proven that they will change approach every couple of years and that they will force their customers to move along.

      • With Linux, you aren't locked into a single vendor.

        This benchmark tested Oracle. If you put 18TB of data into an Oracle database you are locked into a single vendor anyway.

        And if you don't like Linux anymore, you can switch to any of a dozen other, compatible platforms.

        No, you can switch to whatever platforms Oracle supports. Because you have 18TB of data in it.

        With Windows, you are locked into a single, proprietary implementation and Microsoft has you by the proverbial precious body parts; there is no other vendor you can get a compatible implementation of Windows or all the Windows libraries from.

        I'm using an Oracle database. Why do I need compatible implementations of all the Windows libraries if I decide I want to migrate that database cluster to another host OS?
        • This benchmark tested Oracle. If you put 18TB of data into an Oracle database you are locked into a single vendor anyway.

          But being locked into 2 vendors is worse than being locked into one single vendor, don't you agree?

          Also, migrating between databases is not *that* hard, it's all SQL after all.

          • Also, migrating between databases is not *that* hard, it's all SQL after all.

            But does PostgreSQL, Oracle's closest free competitor, scale to an 18 TB database under the loads they're testing?

            • I don't know, but IBM's DB2 surely can.

              So you are not locked into a single vendor. Period.

              • I love how everyone pulls out DB2 and Oracle anytime there is a DB debate. The fact is none of the largest 5 commercial databases run on either of them. Walmart for instance uses NCR Terradata Warehouse db software. This DB is well over 100TB. Informix is another leader in very large databases, as is Hitachi data systems.
      • The reason to use Linux...

        Another reason to use Linux is that had Linux finished behind Windows on this benchmark, it wouldn't take long before someone figured out and fixed the Linux kernel and released the patch. I don't remember the exact test, but this very situation happened a few years ago.

        I can't imagine Microsoft releasing a patch to address this (admitedly small) performance deficit, and if they did, who knows what other damage it would cause. Again, I don't remember the exact situation, but Microsoft has definitely released service packs that were considered to be avoided.

      • "Using Linux as the server OS is not about getting the OS for free--as you observe, the cost of the OS is pretty much lost in the noise."

        Percentage-wise, you may say so, but I'll take the $152,549 difference anyday (=$4767.15 per CPU at 32 CPUs...)

        With the current prices, that difference in money will buy you 200 brand new desktops for your office workers...

    • > Yeah, linux has a small bit more performance (less than 1%) for a bit lower price (6%) but these aren't real shocking numbers.

      Huh? The cost of the Windows software adds $150K more. That is a lot of money. Think of it this way: if I have two laptops studded with diamonds that cost 2.3 mil each (before the OS is installed), and the OS for one is free while the OS for the other is 150K - the latter seems very expensive when you look at the software budget

      I think that you should break out the costs of these systems and look at the hardware and software seperately. "The systems cost the same in hardware, but there is a $150k difference in software." is a much cleaner analysis.

      • The Register had this article yesterday where they added that the HP system is not available until next year (so how do they know the real cost) while the IBM-Microsoft system is a year old.

        A new system is certainly going to cost less than an older one. Not true of cars unfortunately, but true of computers.

        What would be nice is a true apples-to-apples test on the same hardware.
      • No, if you read the report the cost of Windows adds about $14K more - and part of that is for the 8 additional client licenses since they tested the Windows system against 24 clients intead of the 16 used against Linux. You have to also consider the fact that the cost of hardware goes down over time, and that the Windows system was built 3.5 months before the Linux system - this can easily make up for the $150K, and then some.

        Finally, it's not about the softare cost - it's about the bottom line: price/performance. These reports can't really be scientifically compared. One can speculate that Windows would have beat the price/performance ratio of the Linux system given an even playing field, but it's just that - speculation. The real point here is that Linux is _competing_ in the enterprise and has been taken seriously enough to actually get benchmarked.
    • OTOH, you could look at it this way: all other things being (relatively) equal, an OS developed by a bunch of guys around the world for free performed as well as an OS developed by a bunch of millionaires for $billions.
    • Of course, I'll get flamed for not bashing microsoft, but the difference really isn't that big.

      I'm not bashing you, I just don't see your point.

      If you get a car for 20000$ at dealer A and the same car for 19500$ at dealer B, will you say "Hey, it's just a small difference" and buy from dealer B?

      Let's not forget, this is about database-servers here and both run the very same database (Oracle). The underlying OS is irrelevant, you don't have to run MS Office or "the Sims" on this thing.

      So please tell us stupid Microsoft-bashers what is your point.

      • The point he was trying to make was that the decision is not based on finances at this point. The performance AND cost difference is inconclusive because they are different configurations. If one completely blew the other out of the water, we could maybe claim a winner, but that simply didn't happen.

        And the difference between the two system costs from an OS licence standpoint is far less (see the full report). To correct your analogy:

        $20000 dealer A
        $19900 dealer B

        It's not based on money the initial purchase. It's based on the TCO, how it will integrate with your existing infrastructure, and whethor or not you prefer one of the other (for a variety of reasons).
  • Look at the availability date: 03/05/03. That's six months from now.

  • hmm... different setup, little difference (Score:1, Insightful)

    by Anonymous Coward
    If you really want to compare 2 operating systems, you should rule out as many factors as possible. The windows cluster was set up differently (it had less memory, for example). I would guess that on the same hardware, the difference would be even less...

  • How does it scale (Score:2, Insightful)

    by oku ( 609226 )
    It would surely be also interesting to see how this cluster scaled, i.e., use only 1, 2, 4, 8, 16 of the 32 machine available. Do we still see a linear at the full size, indicating that adding more machines would be any good? Or did the performance already top off, indicating that you can get better price/performance figures when restricting yourself to fewer machines?

    I do not hazard a guess, but it is surely interesting what Linux can do best, instead of comparing it to Windows, only.

    • Re:How does it scale (Score:2, Informative)

      by Alvandaar ( 35055 )
      It does scale! The cluster TPC-C Benchmark is not very conclusive IMHO, it has very few intra-process communication, so you can basically scale it almost indefinitely.

      AL

  • A bit flawed.. (Score:4, Insightful)

    by Chicane-UK ( 455253 ) <chicane-uk.ntlworld@com> on Thursday September 19, 2002 @03:39AM (#4287237) Homepage
    As many other people have pointed out, the system configuration was vastly different despite being 'similar' - yes, I want to see Linux out perform Windows but I would rather see it run on identical systems! When benchmarks are weighted like this, it just makes Linux look like the inferior product which is not the kind of image it should be getting for itself!
    • ... yes, I want to see Linux out perform Windows ...

      It happens every day! All you have to do to see it is take whatever M$ junk you are using and replace the software. All the PitA you see on a desktop with poor security and stability, obscure and changing protocals, propriatory data formats, unmodifiable applications, ad nauseum, translate.

      We have at least one multi-processor Dell "server" where I work and the folks responsible for it are not happy. Keeping it up has been a quality of life killer. The problem is not in the hardware.

      • Just so you know.. maybe I didn't phrase what I wrote exactly how I wanted it.

        I already know that Linux is a great solution - I use it for every server I setup where I work.. I just mean that it would be nice to see some official figures of Windows getting a beating ;)
  • There are 32 xeon processors used, but only 16 computers.

  • Off Topic? (Score:2, Interesting)

    by _ganja_ ( 179968 )
    Sorry that this might be off topic and cheerleading (right place though).

    GNU/Linux impresses me a great deal. I've been running it for a few years now, mainly at home and in some positions when I can get away with it and its easy to take it for granted. But its articles like this that make me step back and think about what as really been achived by a bunch of mainly unpaid developers who provide all their source code for free.

    Sure there a few places where Windows is more suitable but everyday, these few places get fewer.

    So to any Linux developers and supporters who read this, thank you all.

  • HP follup on lkml (Score:4, Interesting)

    by awptic ( 211411 ) <(moc.xelpmoc) (ta) (etinifni)> on Thursday September 19, 2002 @04:30AM (#4287339)
    There was a followup message on the lkml from hp discussing how these numbers can improved even further, you can see it at http://marc.theaimsgroup.com/?l=linux-kernel&m=103 237327405644&w=2 [theaimsgroup.com]

    • Re:HP follup on lkml (Score:3, Interesting)

      by Quixote ( 154172 )
      I read Andy's post, and it highlights one of Linux's strengths: the fact that an enduser was able to tweak the kernel parameters, take third-party patches (Ben's) and in general muck around the kernel to get the best performance. You will never see Microsoft give this kind of freedom to its customers ("we know best! just give us the money and we'll take care of it... sometime!").

  • And it's a valid comparision? (Score:3, Insightful)

    by blowdart ( 31458 ) on Thursday September 19, 2002 @04:32AM (#4287341) Homepage

    The Windows TPC benchmark was on last years hardware (IBM xSeries 370, released last year).

    The Oracle TPC benchmark is on next years hardware (HP ProLiant DL580R - not available till May 2003).

    Crowing about how performance is higher under Linux is FUD. It's not a fair comparison. Or didn't the story submitter understand that hardware always affects performance?

    • Crowing about how performance is higher under Linux is FUD. It's not a fair comparison. Or didn't the story submitter understand that hardware always affects performance?


      Yeah, TPC comparisions are always a bit of a game. And it takes some effort (and cost) to sort out the hardware and run the test.

      That Linux has a point on the graph that isn't disimilar from other systems may help dispel some doubts about Linux scaleability and potential as a back office platform. IMHO that's more significant than whether today's TPC ratings put it slightly above or slightly below Windows.

    • The Windows TPC benchmark was on last years hardware (IBM xSeries 370, released last year).

      The Oracle TPC benchmark is on next years hardware (HP ProLiant DL580R - not available till May 2003).

      Err... are you talking about the TPC benchmarks refered to in the links? Both were run on 8 ProLiant DL580's with a total of 32 Xeon 900s. The Linux setup is marked in the full disclosure as being available March 5 2003, Hardware available now.
    • The Windows benchmark is running on a DL580 as well. That being said, your statement is valid. The systems are NOT identical. Click on the executive summary links at the bottom of each and you will see the detailed hardware specs for each.

      Also, the clients are not only different in number, but the Linux clients are running a faster CPU as well (1400 Mhz vs. 1000 Mhz).

      The only conclusion I think we can draw is that Linux plays "in the same ballpark" as Windows, performance-wise.

  • Run the benchmark non-clustered (Score:2, Insightful)

    by Anonymous Coward
    Clustered TPC-C benchmarks are of dubious value. I've yet to encounter any business that implements an OLTP system like this and it's for a good reason. Clusters of this sort are very difficult to implement and operate. You basically end up having to physcally partition your database across dozens of servers!

    What I would love to see is Linux TPC-C benchmark running on a 8 way machine. Particularly the IBM x440. It scored 91,000 + tpmCs running Windows .NET...it would be interesting to see how Linux compares.

    http://www.tpc.org/tpcc/results/tpcc_result_deta il .asp?id=102072201
    • "Clustered TPC-C benchmarks are of dubious value. I've yet to encounter any business that implements an OLTP system like this and it's for a good reason. Clusters of this sort are very difficult to implement and operate. You basically end up having to physcally partition your database across dozens of servers!"

      This is not true if you use Oracle 9i and Real Application Cluster.
  • In a 2+ million dollar system software cost is a very small percentage of the total cost.

    However, in reality, a lot companies have $10,000 or even $5,000 DB servers.

    When you factor the cost of Windows into these systems the difference in Price/Performance is much greater than 6 percent.

  • Price/Performance was low (Score:3, Interesting)

    by -ryan ( 115102 ) on Thursday September 19, 2002 @05:29AM (#4287435)
    As far as price/performance it was in the middle of the top ten. I think if they had used PostgreSQL (or maybe SapDB, dunno haven't used it) instead of Oracle it could have been higher in the results.
    • The big problem in getting the cost lowered by replacing Windows w/ Linux, Oracle w/ PostgreSQL, etc. is that most of these benchmark test systems cost huge bucks -- bucks contributed by the hardware & software manufacturers. If you were HP, would you rather foot the entire cost of putting one of these systems together with open source, or split the cost with Oracle and/or MS? Your hardware lands on the list either way.

      The real challenge here is finding the money to build competing open source - based machines. MS has lots of monopoly money to dedicate to getting their products on the lists. Linux has no similar war chest.

    • Re:Price/Performance was low (Score:1, Interesting)

      by Anonymous Coward
      You make a SERIOUSLY faulty assumption...

      That PostgreSQL will scale (like Oracle).

      OK. Take out Oracle, save a bundle. Put in PostgreSQL, now you cannot handle this transaction load. The result - Your price/performance is now worse.

      I would be interested in seeing PostgreSQL run simultaneously on more than one node and access the same files (ie RAC) or comprimise a single database (ie distributed).
    • Ya, but then the DBA's would have had to actually code against PostgreSQL. The decreased moral would've lowered productivity and therefore increased the TCO. :-)

  • Upon Close Inspection .. (Score:4, Interesting)

    by peatbakke ( 52079 ) <peat AT peat DOT org> on Thursday September 19, 2002 @07:08AM (#4287608) Homepage
    ... while a similarly priced Windows machine may have been slower, Windows based systems own ALL of the Top 10 Price/Performance [tpc.org] spots. The Linux solution ranks 5th in the Top 10 Price/Performance Clusters [tpc.org] .. but the rest are Windows machines.

    Dangit. IBM, Dell, HP ... get to it!
    • Microsoft has been desperately pushing to get SQL Server higher in the TCPC ranking by subsidizing dell, hp and other companies. If you look at clustered vs non-clustered results, you'll see that #4 a non-clustered setup beat #5 which is clustered. The fujitsu server was using 128 563mhz sparc, whereas #5 uses 128 P3 700mhz. Of course the fujitsu setup costs more than double, so make a decision for yourself.

      The two aren't equal for numerous reasons, like different kinds of hardware, varying level of redundancy, reliability of the hardware and ability to partition and hot-swap. DBA's that deal with hardcore realtime data and realtime backup don't use SQL Server. When you try to do things like realtime backup, with a clustered database setup, it gets very complicated. It's even harder to find DBA's with that level of experience and skill. That whole price/performance thing is a nice starting point, but it's just the beginning of the iceburg.

      • Oh, I absolutely agree with ya. I was just trying to make the point that while it's nice to get into the TPC rankings (for whatever hardware platform), there's still a whole lot more butt whuppin' to do. :)
    • Number of times that OS apears in TPC-C
      - Microsoft .NET/Windows/... Server - 62
      - AIX - 10 times
      - HP UX - 8 times
      - Compaq Tru64 UNIX - 4 times
      - Solaris - 4
      - OS/400 - 2
      - Linux - 1

      The rest are Windows because only now the Companies
      use Linux for these benchmark.
  • It really doesn't matter that the results don't give MS much reason to tremble. Linux made the list, which I suspect is an important form of validation in the corporate world. If it wasn't, why would MS spend so much time tweaking their setups to beat the TPC?
    • Comment removed based on user account deletion
      • Oracle's appliance toaster thingy didn't really do all that well, and I suspect it is because people who are willing to spend 100k for a RDBMS want the flexibility to tune the underlying system.

        Besides, Oracle tends to appropriate, customize and rebrand, not recode. Examples: Oracle Application Server is simply Apache with a custom Oracle Module, JDeveloper is simply a cosmetically modified Borland JBuilder with custom Oracle EJB Components.

        In fact, I suspect that Oracle is profoundly lazy when it comes to new development. Oracle Forms 6i is just a Java implementation of the Oracle Forms Runtime Client, everything else is the same, (but slower), and if you've ever seen the underlying PL/SQL in some of their industry targeted applications then you know they are all about code monkeys and are in no way concerned with elegance or even efficiency.


  • Don't make me break out the "it's the hardware stupid" baseball bat and smack you upside the head....

    Yes, Linux is cheaper, but the OS in these tests matters about as much as what the admin was drinking during the test...
  • I always wondered how PostgreSQL performs relative to the proprietary DBs. Are there any benchmarks available?

    On a side note, doesn't anyone else find it ridiculous that you are not allowed to publish "unauthorized" benchmarks for the proprietary databases?
  • While the systems are pretty close and Windows people say there are no real cost savings, they are negating the fact that you will have to repay for the windows OS depending on your license. The benchmarks are only showing initial setup costs, the windows software will actually cost more over a period of a few years. You will be required to upgrade just when you have the system working the way you want them to. When you do upgrade, you can hope that the features and tools that you need stay put....... You can only hope.

    When Windows XP2(?) arrives you will have to retrain your key people. Do test deployments, do a deployment plan, find replacement applications for those that are no longer working, work with and pay your inhouse developers to check, and redo your older homegrown programs, develop a hardware compatibility list with your vendors, repeat every three years.
    • Thats a little too far. As far as I know you are not forced to upgrade and things will not just stop working when you do. (We're just about to move to .NET Server for performance reasons) The benchmark does include maintenance support costs. For version 5 of the benchmark its 3years 24x7 (used to be 5years 8x5)
  • If you look at the Executive Summary PDF's, it shows that the 24 Windows clients were running W2k Server. Anybody have an idea why they would do this?

    I understand some of the subtleties of the differences between W2K Server vs W2K pro, but given a dedicated client app, I'd think the slight memory management issues wouldn't have that big of an effect on the performance.

    Client Software
    ---------------
    BEA Tuxedo 6.5 Teir 1
    Microsoft Windows 2000 Server

    Client Software
    ---------------
    BEA Tuxedo 8.0 Teir 1
    Red Hat Linux Personal

  • Almost. IANODBA (Oracle DBA) but I do have a very good understanding how MS SQL clustered/federated database systems work. There is a hardware difference - the server NICs - that would make a pretty large difference for MSSQL federations. The Redhat/Oracle cluster uses two 64-bit Gigabit NICs [compaq.com] per server, and the MS/Oracle cluster uses a 64-bit dual 10/100 NIC. [compaq.com] Both, of course, used appropriate switches. Now, to be fair, the WinOracle cluster used 1120 disks to host the data, vs 976 in the LinOracle scenario. If you're wondering, more disks/arms CAN result in better performance, and it's possible that is the case here. FWIW, we use a lot of the same hardware here - 4x2MBXeon900 DL580s and MSA1000 disk arrays. We also use 8x DL760s. All running Win2k AS / MSCS / MSSQL2k - not federated clusters, just HA.
  • What's TCP-C? Can somebody convert it into the Pop Science(TM) units for me so I can understand?
  • In the executive summary:

    Disk Drives 976 18.2-GB 15K
    Disk Drives 16 18.2-GB 10K
    Total Storage 18054 GB
    Tape Drives 1 12/24-Gigabyte DAT

    Huh? How many tapes for a full backup?

    And uh, 976*18.2+16*18.2=18054.4.

    No RAID either?

    How do transaction processing people protect their data?

    At all?

Slashdot Top Deals

The use of anthropomorphic terminology when dealing with computing systems is a symptom of professional immaturity. -- Edsger Dijkstra

Close