The Right 'AIR' Mix: Fueling High-Performance Platforms
Submitted Apr 1, 2025
Topic of your submission:
Platform engineering
Type of submission:
30 mins talk
I am submitting for:
Rootconf Annual Conference 2025
At Flipkart, the widespread adoption of our homegrown managed platforms across engineering teams operating at an enormous scale has positioned our platforms offerings as mission-critical infrastructure. Supporting this scale across a multi-cloud environment necessitates high availability, uncompromising resilience, sustained performance, and continuous optimization.
Recent press release about our platform: https://aerospike.com/news/aerospike-database-on-kubernetes-enabled-95-million-transactions-per-second-on-e-commerce-platform-for-festive-sale/
This session explores the intricate challenges and solutions involved in operating one of the vital DbaaS platform with focus on:
A - AVAILABILITY
We will delve into the practical realities of measuring true platform Availability in real-time, moving beyond theoretical nines to scientific computation.
I - INTELLIGENCE
Strategies fused with intelligence for continuous optimization aimed at enhancing platform maintainers productivity and reducing on-call burden.
R - RESILIENCE
Dissecting the complex resiliency trade-offs inherent in multi-cloud DbaaS, especially under the pressure of major events.
DETAILS
https://docs.google.com/presentation/d/1t_y185GV0PeOfeRXHcRowyhn6CRJdbvuWp4HTBnEC9U/edit#slide=id.p
(Slides w.i.p)
KEY TAKEAWAYS FOR ATTENDEES:
- A blueprint for thinking about managed platforms as a holistic ecosystem.
- Practical approaches to measure and improve real-world availability and resilience in multi-cloud setups.
- Proven techniques for optimizing platform operations, enhancing team productivity, and managing opex effectively.
- Inspiration and practical examples for leveraging LLMs to build smarter, self-sufficient infrastructure platforms.
- Valuable insights drawn froms experience operating critical database services at extreme scale.
TARGET AUDIENCE:
Site Reliability Engineers (SREs), Database Administrators (DBAs) & Database Engineers
Platform Engineers & Architects
DevOps & Cloud Infrastructure Professionals
Technical Leads & Engineering Managers overseeing large-scale systems
Anyone interested in multi-cloud strategies, database reliability, operational efficiency, and applied AI in infrastructure.
BIO
A Platform Engineer, currently a Tech Lead, with one of the platform team operating at massive scale of nearly 9 digit TPS.
{{ gettext('Login to leave a comment') }}
{{ gettext('Post a comment…') }}{{ errorMsg }}
{{ gettext('No comments posted yet') }}