---
title: "Benchmark Shows MongoDB Atlas Manages Thousands of Payments Per Second with Zero Data Loss"
description: "A benchmark of the Icon Payments Framework (IPF), trusted by Citi, NatWest, and BNP Paribas, on MongoDB Atlas demonstrated extreme performance and resilience for instant payment processing. The system sustained 6,000 end-to-end payments per second, requiring approximately 430,000 simultaneous database operations, with a mean end-to-end latency of 0.51 seconds and persistence latency below 30 milliseconds. Upgrading from MongoDB Atlas 8.0 to 8.3 reduced persistence latency by roughly 50%, from 40 to 20 milliseconds at 4,000 payments per second, and throughput scaled near-linearly across the 500 to 6,000 range while latency remained flat until peak and hot-shard CPU utilization sat at about half. During a primary failover, a new node was elected in five seconds with zero data loss and no application restart. An application node failure recovered to 3,500 transactions per second in 90 seconds with zero data loss."
---

# Benchmark Shows MongoDB Atlas Manages Thousands of Payments Per Second with Zero Data Loss

[MongoDB](https://yomu.fyi/company/mongodb) · Sep 9, 2026

**Type:** Benchmark

## Summary

A benchmark of the Icon Payments Framework (IPF), trusted by Citi, NatWest, and BNP Paribas, on MongoDB Atlas demonstrated extreme performance and resilience for instant payment processing. The system sustained 6,000 end-to-end payments per second, requiring approximately 430,000 simultaneous database operations, with a mean end-to-end latency of 0.51 seconds and persistence latency below 30 milliseconds. Upgrading from MongoDB Atlas 8.0 to 8.3 reduced persistence latency by roughly 50%, from 40 to 20 milliseconds at 4,000 payments per second, and throughput scaled near-linearly across the 500 to 6,000 range while latency remained flat until peak and hot-shard CPU utilization sat at about half. During a primary failover, a new node was elected in five seconds with zero data loss and no application restart. An application node failure recovered to 3,500 transactions per second in 90 seconds with zero data loss.

## Context

As instant payment rails replace legacy batch systems worldwide, banks need public proof that modern data architectures can scale without compromising resilience. The Icon Payments Framework (IPF), trusted by Tier 1 banks including Citi, NatWest, and BNP Paribas, was tested on MongoDB Atlas under extreme load and failure conditions.

## Approach / What changed

A rigorous ladder test evaluated key performance metrics across a range of 500 to 6,000 payment transactions per second, with simulated disaster conditions including primary failover and application node failure.

## Takeaways

- MongoDB Atlas on the IPF sustained 6,000 end-to-end payment transactions per second with a mean latency of 0.51 seconds and 430,000 database operations per second.
- Upgrading from MongoDB Atlas 8.0 to 8.3 reduced persistence latency by approximately 50%, e.g., from 40ms to 20ms at 4,000 transactions per second.
- During a primary failover, a new node was elected in five seconds with zero data loss and no application restart; an application node failure recovered to 3,500 transactions per second in 90 seconds with zero data loss.

## FAQ

### What throughput did MongoDB Atlas achieve for payment transactions?

The system achieved 6,000 end-to-end payment transactions per second, with 430,000 database operations per second and sub-second latency.

### How did the system behave during node failures?

During a primary failover, a new node was elected in five seconds with zero data loss and no application restart. An application node failure temporarily reduced throughput but recovered to 3,500 transactions per second in 90 seconds with zero data loss.

### What impact did upgrading MongoDB Atlas have on performance?

Upgrading from version 8.0 to 8.3 reduced persistence latency by approximately 50%, for example from 40ms to 20ms at 4,000 transactions per second.

**Tags:** [Benchmark](https://yomu.fyi/topic/benchmark), [High Availability](https://yomu.fyi/topic/high-availability), [MongoDB Atlas](https://yomu.fyi/topic/mongodb-atlas), [Payments](https://yomu.fyi/topic/payments), [Performance](https://yomu.fyi/topic/performance)

- Source: [MongoDB](https://www.mongodb.com/company/blog/news/benchmark-shows-atlas-manages-thousands-of-payments-per-second-zero-data-loss)
- Source URL: https://www.mongodb.com/company/blog/news/benchmark-shows-atlas-manages-thousands-of-payments-per-second-zero-data-loss
- Ingested by Yomu: 2026-09-20T08:16:47.477Z

[Read original post](https://www.mongodb.com/company/blog/news/benchmark-shows-atlas-manages-thousands-of-payments-per-second-zero-data-loss)