Performance Tuning

Tuning Aeron is the art of pulling three levers at once — p50, p99, and throughput — knowing that almost every knob trades one against another. This section is the practical playbook.

The one thing to remember

p99 is always about avoiding variance — cache misses, queue depth, context switches, NUMA penalties. p50 is about reducing baseline cost. Throughput is about keeping the pipe full. The hardware-level levers (NUMA, cache, kernel bypass, CPU pinning) have the most dramatic effect on tail latency.

In this section

• Parameter reference — every transport knob and how it pulls p50/p99/throughput.
• Bandwidth-Delay Product (BDP) — sizing windows and buffers to the pipe.
• CPU isolation & pinning — isolcpus, nohz_full, taskset, numactl, and how they compose.
• Kernel bypass — ef_vi / DPDK / VMA and when it’s worth the operational cost.
• JVM warmup — defeating cold-start tail spikes.
• C vs. Java media driver — when to pay for the C driver.

Where to start

1. Get threading mode and idle strategy right (DEDICATED + busy-spin for Sender/Receiver).
2. Isolate and pin cores so the OS scheduler never preempts Aeron’s agents.
3. Size buffers and windows to your BDP.
4. Then measure — see Benchmarking (section coming back soon) — before reaching for kernel bypass.

Note

For why these knobs exist at the protocol level, see The Aeron Files. This section is about what to set and why it moves the numbers.