A low-cost infrastructure for high precision high volume performance measurements of web clusters

We present a software monitoring infrastructure for distributed web servers for precise measurements of one-way delays of TCP packets to parameterize, validate and verify simulation and state-space based models of the system. A frequency synchronization of the clocks is not sufficient, both frequency and phase (offset) of all clocks have to be in sync to correctly estimate distributions of the involved delays. We present a cost-effective combination of standard methods with own additions and improvements to achieve this goal. The solution we developed is based on using only one CPS receiver in combination with NTP and the PPS-API for the time synchronization of all object systems' clocks with a precision in the range of one microsecond. The timestamping and generation of the event trace is done in a Linux kernel module. In addition, example measurements generated with our infrastructure are presented.