You are just getting started with MySQL on OpenSolaris. You've installed the OpenSolaris Community Edition and CoolStack MySQL. To explore this new environment you decide to run some tests using the sysbench benchmark. After running a number of tests you realize that for some reason the options you are setting in /etc/my.cnf are not getting used.

What is going on? Not to worry, you've just hit a problem common to new users of MySQL on OpenSolaris.

Run this command:

 # /opt/coolstack/mysql/bin/mysqladmin | more

page down until you see:

Default options are read from the following files in the given order:
/etc/my.cnf /etc/mysql/my.cnf /opt/coolstack/mysql/etc/my.cnf ~/.my.cnf

This shows …

Introduction to the Innodb IO subsystem

Basics When a client connects to MySQL, it creates a thread to handle it. This thread executes SQL queries and interacts with the storage engine (for simplicity, lets call them user threads). Innodb uses a four (4) additional threads to implement asynchronous io1. Although Innodb has an option innodb_file_io_threads to control the number of IO handler threads, it has no effect on how many IO handler threads are actually created. These IO handler threads wait and process events in a loop. Each IO handler thread processes different kinds of events. (Insert buffer writes, log writes, datafile writes, and read-ahead or prefetch) Let us now see how different types of IO are handled by Innodb.

Reads Using a simple sysbench read-only test, we notice that all user threads issue reads (pread(2)) to the data files. We can …

Introduction to the Innodb IO subsystem

Basics When a client connects to MySQL, it creates a thread to handle it. This thread executes SQL queries and interacts with the storage engine (for simplicity, lets call them user threads). Innodb uses a four (4) additional threads to implement asynchronous io1. Although Innodb has an option innodb_file_io_threads to control the number of IO handler threads, it has no effect on how many IO handler threads are actually created. These IO handler threads wait and process events in a loop. Each IO handler thread processes different kinds of events. (Insert buffer writes, log writes, datafile writes, and read-ahead or prefetch) Let us now see how different types of IO are handled by Innodb.

Reads Using a simple sysbench read-only test, we notice that all user threads issue reads (pread(2)) to the data files. We can …

Understanding and programming MySQL data load into the DataGridView control is a must for Windows Application Developers today. Many times, in real production environment the end-users need to see a result set of data to make daily business decisions. The main question is about how many records they need to see when the control gets loaded. The answer of the question is defined by the client's business rules. At this point application performance is a critical issue for Application Developers. In this paper I'll show you how load MySQL data into the DataGridView control using VB.NET bound and unbound programming modes. A timer class named Stopwatch for VB.NET will be used to measure the execution time between theses two programming modes.

We're building a MySQL 5.0.67 with OurDelta d7 patchset. This includes some mysql bugfixes, patch fixes (reserved words and backward compatibility) and a few new (and IMHO very interesting) patches. You may have seen a lot of bug/issue/feature completion on launchpad earlier today. The release post will contain full change info.

After successful testruns, we're now just tweaking the scripts responsible for the new build process, so everything is automated and repeatable. Peter Lieverdink is once again doing great work in Debian and bash scripting land.
To have a clean result, we'll restart on all platforms at the end of the tweaking - since all builds feed off the same patched tarball now. Won't take too long. This release will also include a proper source package for each distro, making things much easier for those wanting to indulge with the sources ;-)

…

Sun Microsystems, Inc. today announced Sun Systems for MySQL™, a set of solutions designed to radically change the economics of Web service delivery for enterprise customers deploying MySQL-based Web Infrastructure on Sun servers. Proven customer deployments have shown the ability to improve performance by 300 percent, reduce power consumption by 83 percent and offer up to 10 times better price/performance, with higher system reliability and faster time to market.

To view a video of John Fowler, executive vice president of Sun's Systems Group, and Marten Mickos, senior vice president of Sun's Database Group, discussing the new solutions, please visit: www.sun.com/mysqlsystems.

I've been wondering about that for years and well, I've suddenly been placed into this position, which leads me to believe that somewhere there is a deity bent on playing parlour games with my life. Even as of two weeks ago I wasn't quite sure what a community manager did. I mean, it's not like I get to "manage" all of you people, I can't write reports or evaluate any of you.

This week, as I move away from my previous duties and into the new ones under the care and guidance of my new Community Team family, headed by chief whipmaster Giuseppe, and trying very hard to avoid the smoking pits of doom that I might fall prey to, I think I'm getting a small vision of my future.

It involves multiple presentations. Good thing I like public speaking. Too bad you may all hate my publicly speaking :)

So what's upcoming? I'm preparing two presentations, one of which I know I have to give and that is to the New York PHP …

If you are a MySQL 5.x/6.0 InnoDB replication user, right now you take a significant performance hit on the replication master simply by turning on the binlog. The good news is that we've taken a big step toward eliminating that performance gap. I'll describe the problem, how I was able to track down the root cause, and point to a patch that fixes the problem. Since the changes are in the InnoDB code, right now we're waiting on Oracle/Innobase to review the fix and formally commit it. Once that happens, you should see it show up in binary releases. In the meantime, if you build your own binaries you can test the prototype patch yourself.

One of the things I have been working on quite a bit over the past several months is scalability of the nodes within a MySQL scale-out replication environment.  The reason being that there has been a rapid …

If you are a MySQL 5.x/6.0 InnoDB replication user, right now you take a significant performance hit on the replication master simply by turning on the binlog. The good news is that we've taken a big step toward eliminating that performance gap. I'll describe the problem, how I was able to track down the root cause, and point to a patch that fixes the problem. Since the changes are in the InnoDB code, right now we're waiting on Oracle/Innobase to review the fix and formally commit it. Once that happens, you should see it show up in binary releases. In the meantime, if you build your own binaries you can test the prototype patch yourself.

One of the things I have been working on quite a bit over the past several months is scalability of the nodes within a MySQL scale-out replication environment.  The reason being that there has been a rapid …

Here is a short summary of CMON news:

• it is now on launchpad
• versioning has restarted at 0.1 (I have realized this is how it should be done :) )
• cmon 0.1 is available for download at Severalnines (see screenshots below)
• how to install it has been updated and details added for e.g fedora.
• bugs should be reported on launchpad/cmon (get a launchpad account now!)
  

Feature update of cmon 0.1 (the same as cmon 1.2.2 plus):

• monitor your mysql servers (add/remove mysql servers that should be monitored)
• view status and variables of your mysql servers
• view …