To understand large and busy environments one needs a collection of tools and methodologies. We will discuss how performance analysis, management and diagnostics are done at Facebook, from use cases of our cluster-scale MySQL client pmysql, to how we use additional instrumentation both inside MySQL (table/user statistics, slocket) and outside in the web stack performance reporting. Additionally, we will talk how Poor Man’s Profiler – MySQL internals inspection – can be helpful in production environments.
