May 18, 2011

Starcounter high-speed memory-centric object-oriented DBMS, coming soon

Since posting recently about Starcounter, I’ve had the chance to actually talk with the company (twice). Hence I know more than before. :) Starcounter:

Starcounter’s value propositions are programming ease (no object/relational impedance mismatch) and performance. Starcounter believes its DBMS has 100X the performance of conventional DBMS at short-request transaction processing, and 10X the performance of other memory-centric and/or object-oriented DBMS (e.g. Oracle TimesTen, or Versant). That said, Starcounter has not yet tested VoltDB. Starcounter does not claim performance much beyond that of disk-based DBMS on analytic tasks such as aggregations.

The key technical aspect to Starcounter is integration between the DBMS and the virtual machine, so that the same copy of the data is accessed by both the DBMS and the application program, without any movement or transformation being needed. (Starcounter isn’t aware of any other object-oriented DBMS that work this way.) Transient and persistent data are handled in the same way, seamlessly.

Other Starcounter technical highlights include: 

*I thought Starcounter said that the core that runs the operating system communicates the acknowledgement via Direct Memory Access to a core that runs the Starcounter DBMS, obviating the need for an interrupt (except to the core that runs the operating system). But upon reflection, that doesn’t really seem to make sense.

Comments

3 Responses to “Starcounter high-speed memory-centric object-oriented DBMS, coming soon”

  1. Peter Idestam-Almquist on May 18th, 2011 8:08 am

    Curt,
    if I may clarify three things.

    1) Starcounter support SQL queries including joins, both traditional joins and implicit joins using path expressions.

    2) The manipulation of data in the database is done using native language operations in your programming language, as for example the new operator and variable assignments.

    3) Starcounter writes to the transaction log on disk using Direct Memory Access.

    Kind regards
    PhD Peter Idestam-Almquist
    CTO Starcounter

  2. Joachim Wester on May 20th, 2011 10:35 am

    Curt,

    Let’s hope all transaction aren’t inserts. Then we’ll be in trouble.

    / Jack

  3. Joachim Wester on May 22nd, 2011 9:54 am

    Peters comment about the join is important to us. Starcounter is not an really an ODBMS. Its data operates on a UNION of the following constructs:

    1. The relational tuple
    2. The object
    3. The graph node
    4. The key/value store
    5. The document element (both structured and unstructured)

    It uses a single unified model. Actually, the union of the these entities has no real contradiction. We will not abide to any single religion. We will love them all with equal passion. We are working on a JSON access layer to be binary compatible with CouchDB as well as an ODBC driver that allows us to be a SQL-92 RDBMS.

Leave a Reply




Feed: DBMS (database management system), DW (data warehousing), BI (business intelligence), and analytics technology Subscribe to the Monash Research feed via RSS or email:

Login

Search our blogs and white papers

Monash Research blogs

User consulting

Building a short list? Refining your strategic plan? We can help.

Vendor advisory

We tell vendors what's happening -- and, more important, what they should do about it.

Monash Research highlights

Learn about white papers, webcasts, and blog highlights, by RSS or email.