Indian automotive giant Mahindra & Mahindra revealed how it handled one of its largest booking events using a cloud-based architecture built on Google Cloud and AMD’s EPYC processors.
When the company opened reservations for the Thar ROXX, its new five-door SUV, the website processed around 2 lakh bookings in roughly an hour and a half, without downtime or performance issues.
The system ran entirely on Kubernetes clusters hosted on AMD EPYC processor-based Google Cloud virtual machines.
According to Abhishek Sukhwal, head of infrastructure at Mahindra Group, this setup reduced compute costs by about 40% compared to alternative configurations.
“This is an experience where you can justify new technologies to your CFO,” he said.
“You can never tell your CFO that going to cloud will save money. Instead, you must say we will earn money by going to cloud,” he said, stating that 2 lakh bookings of a single vehicle cannot be handled in physical showrooms, but only on such high-performance digital infrastructures.
The automotive giant has also migrated its design-oriented HPC, or high computing workloads to Google Cloud virtual machines, powered by AMD’s EPYC CPUs.
Sukhwal claimed that the company is among the few to have achieved this profitably, attributing the cost efficiencies directly to AMD’s hardware.
For context, AMD’s EPYC processors are server-grade CPUs designed for data centres and cloud environments.
Kubernetes, the container orchestration platform originally developed by Google, manages how software components, packaged in containers, are deployed and scaled across servers.
In this case, Kubernetes automatically balanced incoming traffic across clusters of AMD-powered cloud instances, keeping the booking system responsive even under peak load.
Google Cloud provided the backbone for this setup, integrating compute, networking, and storage resources under a managed service layer.
Together, the three technologies, AMD’s processors for raw compute efficiency, Kubernetes for orchestration, and Google Cloud for elasticity formed a unified system that let Mahindra’s digital platform handle unprecedented traffic volumes securely and efficiently.
The company also revealed that plans to extend this model to other business units, promoting the same architecture for several other applications.
The post Mahindra Used AMD’s EPYC & Kubernetes to Handle 2 Lakh Thar Bookings Online appeared first on Analytics India Magazine.
