• The USE method was developed by Brendan Gregg to study performance problems in a systematic way.1 It provides a simple, top-down approach to identify bottlenecks quickly and reliably. The gathering of performance metrics is usually done […]

  • At Circonus we are collecting a number of metrics about block devices. An interesting one is the average length of the request queue, which is exposed by iostat[1]: aqu-sz The average queue length of the […]

  • Avoid spike erosion with Percentile – and Histogram – Aggregation It has become common wisdom that the lossy process of averaging measurements leads to all kinds of problems when measuring performance of services (see Schlossnagle2015,  Ugurlu2013, […]