Sui Ji Zhi
Senior R&D Engineer, AliCloud Native
Introduction: Currently in the AliCloud observable team, as a senior research and development engineer, AliCloud Prometheus product core research and development engineers, in the observable field, especially the indicator scenarios have a wealth of experience, for large-scale cluster indicator collection and processing has more production practice accumulation, collection probe performance tuning and stability construction has been practiced on the ground. In the observable field of metrics scenarios, he has put forward effective technical solutions for typical problems and large-scale cluster acquisition requirements, and has practiced on the ground in Aliyun ASI large-scale cluster acquisition scenarios.
Topic
AliCloud Prometheus Distributed Acquisition Probe Practice in Hyperscale Cluster Scenarios
Introduction: Introduction to the collection and storage split architecture used in AliCloud Prometheus products, Master-salve's self-developed distributed collection probe architecture design, low consumption, high performance, ultra-stable collection probe research and development experience, and self-developed HPA horizontal self-expansion capabilities to realize the technology. Distributed collection probe in AliCloud ASI large-scale cluster scene landing practice, how to adapt to the cluster collection indicators wide range of fluctuations, how to build data integrity to reduce false alarms, how to achieve low operation and maintenance, high performance, high efficiency collection goals. Outline: 1. AliCloud Prometheus product collection and storage architecture split introduction 2.Aliyun self-developed Master-salve distributed collection probe architecture design, HPA horizontal self-expansion principle 3.Master-salve distributed collection probe in AliCloud ASI large-scale cluster landing practice
