April 16, 2014

When it’s faster to use SQL in MySQL NDB Cluster over memcache API

Memcache access for MySQL Cluster (or NDBCluster) provides faster access to the data because it avoids the SQL parsing overhead for simple lookups – which is a great feature. But what happens if I try to get multiple records via memcache API (multi-GET) and via SQL (SELECT with IN())? I’ve encountered this a few times […]

Virident vCache vs. FlashCache: Part 2

This is the second part in a two-part series comparing Virident’s vCache to FlashCache. The first part was focused on usability and feature comparison; in this post, we’ll look at some sysbench test results. Disclosure: The research and testing conducted for this post were sponsored by Virident. First, some background information. All tests were conducted […]

Write contentions on the query cache

While doing a performance audit for a customer a few weeks ago, I tried to improve the response time of their top slow query according to pt-query-digest‘s report. This query was run very frequently and had very unstable performance: during the time data was collected, response time varied from 50µs to 1s. When I ran […]

ALTER TABLE: Creating Index by Sort and Buffer Pool Size

Today I was looking at the ALTER TABLE performance with fast index creation and without it with different buffer pool sizes. Results are pretty interesting. I used modified Sysbench table for these tests because original table as initially created only has index on column K which initially contains only zeros, which means index is very […]

Performance problem with Innodb and DROP TABLE

I’ve been working with an application which does a lot of CREATE and DROP table for Innodb tables and we’ve discovered DROP TABLE can take a lot of time and when it happens a lot of other threads stall in “Opening Tables” State. Also contrary to my initial suspect benchmarking create/drop table was CPU bound […]

How well does your table fits in innodb buffer pool ?

Understanding how well your tables and indexes fit to buffer pool are often very helpful to understand why some queries are IO bound and others not – it may be because the tables and indexes they are accessing are not in cache, for example being washed away by other queries. MySQL Server does not provide […]

Impact of the sort buffer size in MySQL

The parameter sort_buffer_size is one the MySQL parameters that is far from obvious to adjust. It is a per session buffer that is allocated every time it is needed. The problem with the sort buffer comes from the way Linux allocates memory. Monty Taylor (here) have described the underlying issue in detail, but basically above […]

Cache Miss Storm

I worked on the problem recently which showed itself as rather low MySQL load (probably 5% CPU usage and close to zero IO) would spike to have hundreds instances of threads running at the same time, causing intense utilization spike and server very unresponsive for anywhere from half a minute to ten minutes until everything […]

Scaling: Consider both Size and Load

So lets imagine you have the server handling 100.000 user accounts. You can see the CPU,IO and Network usage is below 10% of capacity – does it mean you can count on server being able to handle 1.000.000 of accounts ? Not really, and there are few reasons why, I’ll name most important of them: […]

How is join_buffer_size allocated?

When examining MySQL configuration, we quite often want to know how various buffer sizes are used. This matters because some buffers (sort_buffer_size for example) are allocated to their full size immediately as soon as they are needed, but others are effectively a “max size” and the corresponding buffers are allocated only as big as needed […]