The scope of this test

Our primary objective for this project is quite extensive, so we have narrowed our scope a little more for this article.

Firstly, we focused on single and dual processing systems.

Secondly, we focused on "read" performance. This means that our benchmarks do not try to write information in the tables, but rather, always fetch and report information from one or more tables.

There are two reasons for this:
  1. We narrow our focus to a certain kind of application based on when write performance plays a minor part compared to read performance.
  2. We want to focus on operation, which involves little harddisk activity, and focus on the platform: the processor(s) and the interaction with the memory.
The benchmarks were inspired by the fact that in many cases, people simply search and browse for information on a website, intranet or another RDBMS application.

So, this article is not about a typical large central database of banks that need to handle a large number of transactions, with frequent writes operations. It is more about a server that needs to handle a lot of ad-hoc queries. AnandTech readers who are searching for a certain article, who like to read the news of the day, or who are checking out the Realtime pricing guide are perfect examples of ad-hoc queries.

Other examples of typical "read heavy" applications are data warehousing applications. The write heavy databases in a company send data to a data warehouse during the night to produce statistical data, which in turn is a read-heavy process.

In these cases, a Systems Administrator or database administrator will try to cache as much information as possible in the fast RAM memory. Database applications and SQL Queries tend to be optimised to be "RAM cache friendly".

Considering that even the best harddisk RAID system accesses information in Milliseconds while RAM memory does the same job in Nanoseconds (Nano is one millionth of Milli), making good use of caching and avoiding storage I/O offers superb performance boosts. As a result, storage I/O limited databases are, in many cases, high end database applications that are run on much more expensive machines than the ones which we are discussing in this article.



Lastly, we test on SUSE SLES 8 (SUSE Enterprise Edition) SP3, Linux kernel 2.4.21. Rest assured that a new report with kernel 2.6 will follow. However, we think that the results might still interest a lot of people as the enterprise market does not upgrade as quickly as desktop users. We found SUSE SLES 8 SP3 Kernel 2.4.21 to be a very stable environment for our database tests.

As a final comment before we move to the benchmarks, I have been working with Anand and his great team for a couple of weeks, and together with your feedback, we will make sure that this project improves over time.

A gigantic market The benchmark
POST A COMMENT

46 Comments

View All Comments

  • markwrob - Friday, February 04, 2005 - link

    Great article. One thing I'm looking for on
    this and similar comparisons is how the rigs
    or their components do on power consumption.

    Are there any places to find that out easily?
    Reply
  • markwrob - Friday, February 04, 2005 - link

    Reply
  • vaxinator - Monday, December 13, 2004 - link

    Very interesting review. I think you are wise to narrow your scope to basically in-memory queries, since this pretty much ensures you are testing just the CPU and memory. Disk I/O is another topic.

    I would be interested to know a few more details about the database (the data model) and the actual queries used.

    But the key element you need to watch for is ensuring your client box is not overloaded. I have seen lots of "performance reviews" where the client box was smaller than the device under test...wrong! It should be under-utilized and the cpu consumption/memory use etc should be reported as well. If necessary use lots of client boxes, but watch the network load.
    Reply
  • rogerjlarsson - Monday, December 06, 2004 - link

    MySQL v. IBM DB2 Single v. Dual
    "MySQL doesn't seem to scale as well as DB2."

    Yea, right... It all depends on what level you start from!

    MySQL _Single_ Xeon Concurrency 50: 157
    DB2 _Dual_ Xeon Concurrency 50: 102

    MySQL scales a little to _Dual_ Conc. 50: 222

    DB2 is not even near!!! MySQL might be network
    limited rather than Memory or CPU...
    Reply
  • davesbeer - Sunday, December 05, 2004 - link

    Decoder

    Oracle's ETL tool is $5k also comes with
    JDeveloper
    Forms Designer
    Reports Designer
    etc.
    etc

    I've worked with some of the biggest financial institutions in the world including ABN Amro... etc...
    Oracle's DB also is less costly then MS.. Not thier EE version but then again MS has nothing to compete with that one..

    Also you mentioned MS tools are the best.. not likely.. they are the easiest to use but far from the best.. The worlds biggest datawarehouses, datamarts etc.. are not on MS and they don't use MS's tools... except for maybe MS's themselves...
    Reply
  • jensend - Sunday, December 05, 2004 - link

    Comparing these systems in 32-bit mode with a 2.4-based distro makes very little sense. Among a lot of other reasons, the 2.4 scheduler is AFAIK rather poorly suited for use with combined SMT & SMP. Reply
  • marcuri - Saturday, December 04, 2004 - link

    as #5 methods are far from being anywhere remotely 'mature' as the article states. Actually, after talking to people who run databases, its close to useless. The benchmarks used test cpu speed, not memory or memory management. Opterons are a better solution because they are 64 bit and thus handel the management of 4+gigs of memory much better (it starts in excess of 1gig that 64 helps out i believe). By using a data set of 1 gig the benchmarks are completely missing whats important, its niave at best. Reply
  • Decoder - Saturday, December 04, 2004 - link

    davesbeer:

    I've worked with Oracle 8i, 9, IBM UDB v7, SQL Server 6.5,7, 2K and 2005. I also do J2EE, ETL (Informatica, Datastage, DTS), .NET etc. $ for $, MS SQL Server 2005 is a much better value.

    Have you ever built a data mart using MS SQL Server DTS? It's an ETL tool that comes with MS SQL server for free. Try building a data mart on Oracle and you will find yourself spending 100K US for an ETL tool. Also from a developers perspective, SQL Server tools are the best (Read up on SQL Profiler, Query Analyzer etc).

    .NET not scalable? Scalable compared to what? J2EE EJB's?? Please. Sure there's a limit to scalability on 32-bit boxes, but with x86-64 and 64bit OS's, that limit will go away.

    davesbeer: "SQL Server is for people who can't program real databases"

    Program databases? Please elaborate. You code to a database, design a database, write procs for a database but what does program databases mean?

    Also, tell that to the Finanical Services companies in New York.

    davesbeer: "SQL Server will be delayed again... (you can remember I said that) and the technology is already outdated."

    SQL Server 2005 will be extremely popular. Also SQL Server 2005 DTS (a complete rewrite) will penetrate the ETL market.


    Reply
  • davesbeer - Saturday, December 04, 2004 - link

    Decoder.

    I work with companies that have over 6000 processors actively running multiple databases in thier environments. MS just does'nt compete.. .Net is interesting but again you are stuck with M$ and scalabilty is just not there for real apps. Most financial industries run Sybase... its thier last bastion of full fledged support, I worked with 15 of the largest American Financial institutes, I know what I am taking about. I currently work with some of the largest IT departments in the world. Thousands of developers in a single company alone.. I know IT.
    Oracle, DB2 etc's 64 bit knowledge is far superior to M$ and will remain that way for a long time.. they'll been writing 64bit code for years. SQL Server will be delayed again... (you can remember I said that) and the technology is already outdated. SQL Server is for people who can't program real databases (can feel the flames now) sorry Anandtech but your databases are lightweight... once they grow up you will switch to Oracle or DB2 etc..
    Reply
  • at80eighty - Saturday, December 04, 2004 - link

    First off: Welcome Johan : )

    next...im a frickin n00b, so pardon my ignorance : )

    my questions may not be entirely on topic, but i hope someone...ANYONE can help...

    im lookin to *build* an entry level server, so i've got the following doubts (based on the following factors) :

    Company: startup...less than a year old

    Expected # of initial users: 8 (2 people will be responsible for writing data, all employees will read db) requirements should go up to 15-20 people (2-4 write: all read) by year end (should business expand as planned)

    Server: Mail + DB + File server in one

    Cost: would be nice to keep things economical , but im willing to stretch for a middle ground : )

    1) What CPU is best bang for buck?
    2) OS will be Windows SBS Premium...was going for this since i gathered MS SQL is the best way to go (more so coz Anandtech uses SQL too :p )...after reading some of the comments im a little confused viz. DB2 v/s Oracle v/s MS SQL...plus Exchange looks kinda sweet too : )
    3) Should i wait for SQL 2005? What benefits if any (with reference to costs) ?
    4) Which is the best front-end in your opinion? i was looking to use Infopath as i found the GUI VERY easy to use and frankly the look is quite easy on the eyes too : p. Also, its important to note that I am *supposedly* the most computer literate in my company...so im looking to create a DB with an easy interface for my employees : p
    5) Is Crystal Reports easy to integrate into MS SQL (or any of the above for that matter)? OR im lookin for a back-end that can export data to Excel, so that i can analyse & crunch numbers
    6) Will i *need* an in-house IT guy to manage the DB? ...or even the server as a whole? (looking to keep costs to a minimum)
    7)


    i've got TONS of further queries (and i dont want to attention-whore on the thread :), so, should anyone have any spare time (and any inclination in the first place : ) to help a fellow AT'er, my mail add is: ucanmailme AT gmail DOT com

    Thanks in advance
    Cheers

    '80'
    Reply

Log in

Don't have an account? Sign up now