Abstract
Cloud computing has quickly become the de facto means to deploy large scale systems in a robust and cost effective manner. Central to the maintenance of large scale systems is monitoring which allows for the detection of faults, errors and anomalies and the enacting of optimisation and corrective measures. Monitoring large scale systems is significant challenge requiring the low latency movement of large volumes of data and near real time analysis. This challenge is magnified by elasticity and other cloud properties which previous monitoring systems do not yet fully account for. In this paper we propose Varanus1 a cloud aware monitoring tool that provides robust, fault tolerant monitoring at scale. We describe in detail the mechanisms which enable Varanus to function effectively and explore the performance of Varanus through a detailed evaluation.
Highlights
Monitoring is a fundamental part of designing and maintaining reliable and effective software systems
We eschew the use of third party coordination tools in favour of a dedicated out of band mechanism which is intended to tolerate a wide variety of failure modes in order to facilitate monitoring and maintain a small footprint. For this purpose we look towards peer to peer overlay networks as a means to provide a highly robust basis for developing a monitoring solution
Evaluation summary Our evaluation demonstrates that Varanus is able to perform low latency monitoring with conservative CPU usage even at scale
Summary
Monitoring is a fundamental part of designing and maintaining reliable and effective software systems. The coordination services uses a gossip protocol to propagate updates to the configuration store, update membership and detect failure. Adding immutable nodes to the store can be performed by any participant (where as mutable values can only be committed via the leader) and can make use the the previously described gossip protocol to quickly disseminate state to other participants.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
