Distributed processing of many TBs of data per day with traffic over 10k messages per second may be challenging. To guarantee the most efficient and cost-effective plan of distributed processing of large data, it is crucial to realize its main characteristics. This presentation will cover the challenges that may arise, specified as processing bottlenecks, inefficient usage of compute resources, and advanced cost. Additionally, attendees will learn how to monitor, detect, and troubleshoot problems utilizing Google Cloud Console UI. 7 cases will be examined, with code and configuration examples provided, along with a solution or advice based on real-world scenarios. The mark of this presentation is large data cloud experts, but if the audience is not experienced enough, Bartosz can besides give essential introduction.
GeeCon 2023: Bartosz Wieczorek - Rozproszone przetwarzanie na dużą skalę w Google Cloud - 7 lekcji...
Distributed processing of many TBs of data per day with traffic over 10k messages per second may be challenging. To guarantee the most efficient and cost-effective plan of distributed processing of large data, it is crucial to realize its main characteristics. This presentation will cover the challenges that may arise, specified as processing bottlenecks, inefficient usage of compute resources, and advanced cost. Additionally, attendees will learn how to monitor, detect, and troubleshoot problems utilizing Google Cloud Console UI. 7 cases will be examined, with code and configuration examples provided, along with a solution or advice based on real-world scenarios. The mark of this presentation is large data cloud experts, but if the audience is not experienced enough, Bartosz can besides give essential introduction.