baidu/dperf

dperf: High-Performance Network Load Testing Tool Based on DPDK

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 10 minutes ago
Added to GitGenius on September 12th, 2026
Created on December 21st, 2021
Open Issues & Pull Requests: 1 (+0)
GitHub issues: Enabled
Number of forks: 556
Total Stargazers: 5,604 (+0)
Total Subscribers: 46 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

dperf is a high-performance network load testing tool based on DPDK that generates traffic and measures network performance from a single server.

The tool addresses the need for efficient network performance testing by leveraging DPDK to bypass the kernel networking stack. This approach enables a single x86 server to generate massive traffic volumes, achieving tens of millions of HTTP connections per second, hundreds of gigabits per second throughput, and billions of concurrent connections. The tool provides real-time statistics including connections per second, transactions per second, packets per second, packet drops, socket errors, and HTTP status counts, with visibility into every packet drop or error.

dperf suits organizations testing Layer 4 load balancers, gateways, and cloud infrastructure. It works well for network performance benchmarking, evaluating NIC and CPU packet processing capabilities, and scenarios requiring a high-performance HTTP server or client. The tool's ability to sustain high performance with moderate CPU usage makes it practical for production-grade testing environments where traditional kernel-based tools would be insufficient.

The project maintains active development with regular updates to its codebase and documentation. Contributions are actively welcomed through a defined contribution process. The project includes a granted patent covering its testing methodology, indicating substantial technical innovation in the network testing domain.