Efforts to improve MySQL's performance have been paying off in the recent past. This talk covers the current state of MySQL performance, both in the server and the InnoDB storage engine, where much of the work has concentrated. We look at what is likely to come next: what is in progress, and problems we're aware of but haven't yet solved.

SANs, even for one datacenter, are usually expensive; when it comes to replicating your data to a remote site costs can easily go beyond scope. With LINBITs open source storage replication solution DRBD not only your on-site data is safe - even backup-sites are capable of having the same consitsent data based on the same free-of-charge technology. Immediate and affordable site-failover has become reality with DRBD.

In this lecture we will show how to build a complete iSCSI, DRBD and pacemaker SAN "drop-in" alternative that even over high-latency IP-routes allows prompt replication to your remote site. You will also learn how such an iSCSI target within seconds can be physically relocated in your data centre and can be brought online within minutes in your disaster recovery location.

This lecture implies basic SAN and iSCSI skills, knowledge of open source- and cluster management might be useful.

High availability is a basic requirement for the IT department nowadays. The best known solution in this area is Linux-HA. The first verison dates back to 1998, the second version evolved 2005 but prooved to be a temporary solution.

In 2007 it was replaced by a collection of other programs. The evolution of the software might be difficult to understand for a beginner. This talk tries to bring order into the several names of the programs, explains the setup of such clusters and tries to take a glance into the not too far future of the software.

This presentation will highlight interesting features such as ZFS Zones, resource management and Crossbow network virtualization. Moreover, it will compare the different systems and development philosophies. Note: the presentation will involve command line demonstrations.

Storage is one of the most important part of a data center, the complexity to design, build and delivering 24/forever availability service continues to increase every year. For these problems one of the best solution is a distributed filesystem (DFS) This talk describes the basic architectures of DFS and comparison among different free software solutions in order to show what makes DFS suitable for large-scale distributed environments. We explain how to use, to deploy, advantages and disadvantages, performance and layout on each solutions. We also introduce some Case Studies on implementations based on openAFS, GlusterFS and Hadoop finalized to build your own Cloud Storage.

People are frustrated with slow web pages. At XING we know how important good performance is. Xing was founded in 2003 as OpenBC, and with just one server started a global business network. We enjoyed a growing and active user-base since then, and now have more than 300 servers providing a fault tolerant and scalable business social network for our customers.

Within our operation we mainly use open source solutions (Linux, Apache, MySQL, and Perl/Java/Ruby). To handle the high traffic we use many different scaling techniques which we want to share in this talk. Besides that we would like to talk about how great performance helps businesses succeed online.

Ensuring data survival through any disaster is equally important as ensuring its availability. The sixty minute session will provide an overview of a large variety of methods to create proper backups of MySQL databases in many environments and show in greater detail some of the most popular and effective ones.