This document introduces Beeswax, a startup founded by ex-Googlers that provides a bidder-as-a-service platform for programmatic advertising. Their solution processes over 1 million bid requests per second with 99% responding within 20 milliseconds. It offers services like data integration, bidding algorithms, and reporting APIs. Beeswax is moving to Kubernetes to improve infrastructure efficiency while maintaining performance and to provide a consistent operational interface for customers instead of requiring them to co-locate on AWS for latency reasons.
1. Confidential please do not distribute
Introducing the Bidder-as-a-Service
info@beeswax.com
2. Who are we ?
Startup based out of NYC, founded by ex-Googlers
3. We do RTB (Real time bidding)
Publisher
Ad Exchange
Beeswax Bidder
Scale: O(M) QPS
Latency_99 : 20 ms
- Target campaigns
- Target user profiles
- Optimize for ROI
- Customize
< 200 ms
Step 1:
Send ad request & userid
Step 2:
Broadcast bid request
Step 3:
Submit bid & ad markup
Step 4:
Show ad to user
Auction
4. Building a bidder is very hard
Need scale to deliver campaigns
- To reach the desired audience, bidder needs to process at least 1M QPS
- Deployment has to be in multiple regions to guarantee reach
Performance
- The timeout from ad exchanges is 100ms including the RTT over internet
- 99%ile tail latency for processing a bid request is 20 ms
Complex ecosystem
- Manage integrations with ad exchanges, third party data providers and vendors
- Requires a lot of domain expertise to optimize the bidder for maximizing performance
5. Our Solution: Beeswax Programmatic Cloud
A full-stack solution
deployed for each
customer in a sandbox
Services
you control
Pre-built
ecosystem
and supply
relationships
Cookies,
Mobile ID’s, 3rd
Party
Data
Bidding
and Targeting
Engine
Campaign
Management UI/API
Reporting
UI/API
Custom
bidding
algos
Log-level
streaming
RESTful APIs
Direct
connections to
customer-hosted
services
Fully managed ad tech platform on
7. We have some hard problems to solve
Reduce infrastructure cost and maintain performance
- Business is doubling, the customers are doubling, the infrastructure cost should not.
- Containers improve resource utilization but what is the impact on performance ?
Simplify operations on a complex system
- We currently have autoscale groups on EC2 that are updated via AWS CodeDeploy
- Kubernetes provides us with a consistent operational interface for cluster management
Business requirements
- Latency constraints require our customers to co-locate with us on AWS.
- We would instead prefer to securely execute their code on our network.