Test Results
This section contains performance benchmark results for Rumi releases. Results are organized by major release version, with detailed results provided for each specific release tested.
Organization
Performance results are structured as follows:
Release Line (e.g., Rumi 4.0) - Groups results for a major release line
Specific Release (e.g., Rumi 4.0.579-4.0.39) - Contains actual test results for that release (Core version - Bindings version)
Available Results
Rumi 4.0
Rumi 4.0.579-4.0.39 - Core: 4.0.579, Bindings: 4.0.39 (February 2025)
Understanding the Results
Each release results page includes:
Latency Results
50th, 99th, and 99.9th percentile latencies in microseconds
Results for both Indirect and Direct message access methods
Results across MinCPU, Default, and MaxCPU configurations
Latency-optimized configuration results
Throughput Results
Maximum messages per second under saturated load
Results for both Indirect and Direct message access methods
Results across MinCPU, Default, and MaxCPU configurations
Throughput-optimized configuration results
Performance Analysis
Key performance characteristics
Optimal configurations for different use cases
Tuning recommendations
Comparisons with previous releases (where applicable)
Test Methodology
All results are generated using the same canonical benchmark described in the Test Description. This ensures:
Consistency - Direct comparability across releases
Reproducibility - Same hardware, configuration, and methodology
Transparency - Full disclosure of test parameters
Next Steps
View Test Description for complete test methodology
Select a release above to view detailed results
Return to Canonical Benchmark Overview
Explore Performance Benchmark Suite for the full benchmark suite
Last updated