April 20, 2014

Is there room for more MySQL IO Optimization?

I prefer to run MySQL with innodb_flush_method=O_DIRECT in most cases – it makes sure there is no overhead of double buffering and I can save the limited amount of file system cache I would normally have on database server for those things which need to be cached — system files, binary log, FRM files, MySQL […]

Minimizing Downtime from Lengthy AWS Outages

Well, it happened again…  Another lengthy EBS outage in the US-East region impacted several sites across the net.  While failures like this are rare, they can be quite costly and translate into headaches for the operations team when impact production systems for any length of time.  At Percona, we routinely help clients architect and deploy […]

Review of MySQL 5.6 Defaults Changes

James Day just posted the great summary of defaults changes in MySQL 5.6 compared to MySQL 5.5 In general there are a lot of good changes and many defaults are now computed instead of hardcoded. Though some of changes are rather puzzling for me. Lets go over them: back_log = 50 + ( max_connections / […]

ext4 vs xfs on SSD

As ext4 is a standard de facto filesystem for many modern Linux system, I am getting a lot of question if this is good for SSD, or something else (i.e. xfs) should be used. Traditionally our recommendation is xfs, and it comes to known problem in ext3, where IO gets serialized per i_node in O_DIRECT […]

Percona XtraDB Cluster Feature 1: High Availability

There and in coming posts I am going to cover main features of Percona XtraDB Cluster. The first feature is High Availability. But before jumping to HA, let’s review general architecture of the Percona XtraDB Cluster.

Review of Virident FlashMAX MLC cards

I have been following Virident for a long time (e.g. http://www.mysqlperformanceblog.com/2010/06/15/virident-tachion-new-player-on-flash-pci-e-cards-market/). They have great PCIe Flash cards based on SLC NAND. I always thought that Virident needed to come up with an MLC card, and I am happy to see they have finally done so. At Virident’s request, I performed an evaluation of their MLC […]

Clustrix benchmarks under tpcc-mysql workload

I’ve been working with Clustrix team for long time on the evaluation of Clustrix product, and this is the report on performance characteristics of Clustrix under tpcc-mysql workload. I tested tpcc 5000W (~500GB of data in InnoDB) on Clustrix systems with 3, 6, 9-nodes and also, to have base for comparison, ran the same workload […]

Flexviews – part 3 – improving query performance using materialized views

Combating “data drift” In my first post in this series, I described materialized views (MVs). An MV is essentially a cached result set at one point in time. The contents of the MV will become incorrect (out of sync) when the underlying data changes. This loss of synchronization is sometimes called drift. This is conceptually […]

Modeling MySQL Capacity by Measuring Resource Consumptions

There are many angles you can look at the system to predict in performance, the model baron has published for example is good for measuring scalability of the system as concurrency growths. In many cases however we’re facing a need to answer a question how much load a given system can handle when load is […]

How InnoDB handles REDO logging

Xaprb (Baron) recently blogged about how InnoDB performs a checkpoint , I thought it might be useful to explain another important mechanism that affects both response time and throughput – The transaction log.