August 22, 2014

Goal driven performance optimization

When your goal is to optimize application performance it is very important to understand what goal do you really have. If you do not have a good understanding of the goal your performance optimization effort may well still bring its results but you may waste a lot of time before you reach same results as […]

Computing 95 percentile in MySQL

When doing performance analyzes you often would want to see 95 percentile, 99 percentile and similar values. The “average” is the evil of performance optimization and often as helpful as “average patient temperature in the hospital”. Lets set you have 10000 page views or queries and have average response time of 1 second. What does […]

Using GROUP BY WITH ROLLUP for Reporting Performance Optimization

Quite typical query for reporting applications is to find top X values. If you analyze Web Site logs you would look at most popular web pages or search engine keywords which bring you most of the traffic. If you’re looking at ecommerce reporting you may be interested in best selling product or top sales people. […]

MySQL: what read_buffer_size value is optimal ?

The more I work with MySQL Performance Optimization and Optimization for other applications the better I understand I have to less believe in common sense or common sense of documentation writers and do more benchmarks and performance research. I just recently wrote about rather surprising results with sort performance and today I’ve discovered even read_buffer_size […]

COUNT(*) vs COUNT(col)

Looking at how people are using COUNT(*) and COUNT(col) it looks like most of them think they are synonyms and just using what they happen to like, while there is substantial difference in performance and even query result. Lets look at the following series of examples:

Using delayed JOIN to optimize count(*) and LIMIT queries

In many Search/Browse applications you would see main (fact) table which contains search fields and dimension tables which contain more information about facts and which need to be joined to get query result. If you’re executing count(*) queries for such result sets MySQL will perform the join even if you use LEFT JOIN so it […]

Using Sphinx as MySQL data retrieval accelerator

I’ve run into the following thread couple of days ago: Basically someone is using sphinx to perform search simply on attributes (date, group etc) and get sorted result set and claiming it is way faster than getting it with MySQL. Honestly I can well believe it for cases when you want to know number of […]

A case for MariaDB’s Hash Joins

MariaDB 5.3/5.5 has introduced a new join type “Hash Joins” which is an implementation of a Classic Block-based Hash Join Algorithm. In this post we will see what the Hash Join is, how it works and for what types of queries would it be the right choice. I will show the results of executing benchmarks […]

Using any general purpose computer as a special purpose SIMD computer

Often times, from a computing perspective, one must run a function on a large amount of input. Often times, the same function must be run on many pieces of input, and this is a very expensive process unless the work can be done in parallel. Shard-Query introduces set based processing, which on the surface appears […]

Distributed Set Processing with Shard-Query

Can Shard-Query scale to 20 nodes? Peter asked this question in comments to to my previous Shard-Query benchmark. Actually he asked if it could scale to 50, but testing 20 was all I could due to to EC2 and time limits. I think the results at 20 nodes are very useful to understand the performance: […]