Building a Flexible and Resource-Light Monitoring Platform for a WLCG-Tier2

School of Physics and Astronomy, The University of Edinburgh, James Clerk Maxwell Building, Peter Guthrie Tait Road, Edinburgh, EH9 3FD

^* e-mail: rob.currie@ed.ac.uk
^** e-mail: wenlong.yuan@ed.ac.uk

Published online: 6 May 2024

Abstract

Software development projects at Edinburgh identified a desire to build and manage our own monitoring platform. This better allows us to support the developing and varied physics and computing interests of our Experimental Particle Physics group. This production platform enables oversight of international experimental data management, local software development projects and active monitoring of lab facilities within our research group.

Larger sites such as CERN have access to many resources to support generalpurpose centralised monitoring solutions such as MONIT. At a WLCG Tier2 we only have access to a fraction of these resources and manpower. Recycling nodes from grid storage and borrowed capacity from our Tier2 Hypervisors has enabled us to build a reliable monitoring infrastructure. This also contributes back to our Tier2 management improving our operational and security monitoring.

Shared experiences from larger sites gave us a head-start in building our own service monitoring (FluentD) and multi-protocol (AMQP/STOMP/UDP datagram) messaging frameworks atop both our Elasticsearch and OpenSearch clusters. This has been built with minimal hardware and software complexity, maximising maintainability, and reducing manpower costs. A secondary design goal has also been the ability to migrate and upgrade individual components with minimal service interruption. To achieve this, we made heavy use of different layers of containerisation (Podman/Docker), virtualization and NGINX web proxies.

This presentation details our experiences in developing this platform from scratch with a focus on minimal resource use. This includes lessons learnt in deploying and comparing both an Elasticsearch and OpenSearch clusters, as well as designing various levels of automation and resiliency for our monitoring framework. This has culminated in us effectively indexing, parsing and storing >200GB of logging and monitoring data per day.