Reducing Noisy-Neighbor Impact with a Fuzzy Affinity-Aware Scheduler

Overbooking techniques have been proven efficientto increase overall utilization of cloud datacenters. However,overbooking may also degrade applications performance as (atleast) some applications need to share physical resources suchas CPU or memory. Consequently, interference may increaseamong the virtual machines that share resources, the so callednoisy neighbors effect. We present an affinity-aware schedulerto reduce the impact of such interference. A fuzzy logic engineaccounts for the uncertainty in these environments and estimateswhich CPU cores are currently more suitable for each incomingapplication. This helps the scheduler make virtual machine tophysical resource mapping decisions, also known as vcpu pinning.An experimental evaluation based on a combination of interactiveservices and batch applications confirms that our affinity-awarefuzzy scheduler reduces the interference among applications,enabling more predictable performance and consequently saferoverbooking