How Global Payments Inc. improved their tail latency using request hedging with Amazon DynamoDB
Database Blog
Global Payments Inc. (GPN) improved their DynamoDB-powered credit card authorization platform's performance by implementing request hedging, reducing tail latency by 30%.
- Request hedging involves sending a duplicate request if the initial request exceeds a specified time threshold
- Tested different delta values to optimize latency and duplicate request rates
- Best performance achieved at 80th percentile delta value, with:
- 29% latency improvement
- 8% duplicate request rate
- Suitable for high-throughput systems with strict low-latency requirements
- Differs from standard SDK retry behavior by monitoring both original and duplicate requests simultaneously
The approach helps manage tail latency in distributed systems, particularly for mission-critical financial transactions processing millions of requests daily.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Oct 1
2025
2025
Modernization of real-time payment orchestration on AWS
Aug 19
2025
2025
Improve Amazon EMR HBase availability and tail latency using generational ZGC
Jul 24
2025
2025
Optimize tick-to-trade latency for digital assets exchanges and trading platforms on AWS
Aug 15
2025
2025
Enhanced throttling observability in Amazon DynamoDB
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.