drogonframework/drogon

jemalloc benchmarks

Open

#635 opened on Nov 25, 2020

View on GitHub
 (6 comments) (4 reactions) (0 assignees)C++ (10,462 stars) (1,014 forks)batch import
enhancementgood first issue

Description

Hey, I recently benchmarked using jemalloc on my NUMA servers, and the difference was quite large. Using the system allocator I got 710k req/s, while with jemalloc I got 830k req/s. That's 17% faster just by dynamically linking with a library.

Anyone else tried this?

Contributor guide

Tech stack
cpp
Domain
backendperformance
Issue type
research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
C++ knowledgeBenchmarking experienceUnderstanding of memory allocators
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20
Research direction
The issue asks for benchmarking results comparing jemalloc vs system allocator on the Drogon framework. To investigate, set up a Drogon server on a NUMA machine, compile with jemalloc linked dynamically, and run benchmarks (e.g., using wrk or similar). Compare requests per second and latency. Look at existing benchmark scripts in the repository, if any. Since no specific benchmark code is provided, you would need to create a minimal server and run tests.