April 19, 2011

Notes on short-request scale-out MySQL

A press person recently asked about:

… start-ups that are building technologies to enable MySQL and other SQL databases to get over some of the problems they have in scaling past a certain size. … I’d like to get a sense as to whether or not the problems are as severe and wide spread as these companies are telling me? If so, why wouldn’t a customer just move to a new database?

While that sounds as if he was asking about scale-out relational DBMS in general, MySQL or otherwise, short-request or analytic, it turned out that he was asking just about short-request scale-out MySQL. My thoughts and comments on that narrower subject include(d) but are not limited to: 


5 Responses to “Notes on short-request scale-out MySQL”

  1. Jonas Oreland on April 19th, 2011 5:28 am


    Why does not MySQL Cluster fit your list?

    IMO we’re very proven with in short-request scale-out…and is working hard on better query performance.

    /Jonas, MySQL Cluster developer

  2. Curt Monash on April 19th, 2011 11:19 am


    I don’t hear a lot of good things about MySQL Cluster, although I’m sure there are some use cases where it works just fine.

  3. Mat Keep on April 21st, 2011 3:36 am

    Hi Curt
    Disclaimer first – I’m part of the MySQL Cluster product management team

    We do see growing adoption of MySQL Cluster – now around 1,000 downloads per day and an expanding number of case studies from web and telecoms workloads:

    MySQL Cluster was originally designed for in-network telecoms applications which needed ultra-low latency, high write performance and 99.999% availability. These sorts of applications typically had simple access patterns and limited size of data sets. And so use-cases were pretty specific

    Over the past couple of years, MySQL Cluster adoption has been most significant in web use cases, and as such the product has continued to evolve to meet a broader set of use requirements.

    Building upon auto-sharding of the database with multi-master replication to support write-intensive workloads, the ability to scale the cluster on-line, modify the schema without downtime and a variety of Non-SQL interfaces, the latest development release announced last week adds a range of capabilities to enable MySQL Cluster to meet a broader set of use-cases:

    – Adaptive Query Localization which pushes JOIN operations down to the data nodes. We’ve seen 20-40x speed-up in JOIN operations as a result on real-world queries
    – A new memcached API to the cluster, bypassing SQL enabling easy access for web developers and extending memcached with a persistent, scalable, HA back-end
    More about the Development release is here:

    There has been a lot of work also to enhance ease of deployment and management – enabling Devs and DBAs to get up and running much faster, and with a lower learning curve

    Would welcome the opportunity to brief you more on the latest status of Cluster adoption and development – certainly MySQL Cluster has come a long way from its telecoms niche 3+ years ago

  4. Curt Monash on April 21st, 2011 4:28 am

    Thanks for posting. I’d love to be briefed.

    Is this something that should happen while I’m in Redwood Shores next week, or are the relevant people elsewhere?

  5. Target the Business Problem, Not the Product « The I/O Storm on June 2nd, 2011 4:01 pm

    […] an April 19 DBMS2 blog entry Curt Monash talks about just such a strategy for addressing a challenge faced by many Web […]

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:


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.