OnixS C++ FIX Engine vs QuickFIX C++ performance comparison - updated

Written by Admin | May 1, 2024 1:30:00 PM

The OnixS FIX Engine SDKs include reference implementation source code samples that are an aid for developers to quickly get familiar with, and then adapt to the target contexts.

One of those samples includes performance benchmarks.

We’re often asked, “what is your performance like?”

The best answer is to measure it yourself using the included reference implementation benchmark samples on the target platform(s).

That remains the recommendation, but these are some performance comparison numbers that we are commonly asked about so we’re sharing them here.

Hardware

Intel(R) i9-12900KS @ 5.4GHz 32 GB RAM

Software

Ubuntu 22.04, gcc 12.10

OnixS C++ FIX Engine x64 v 4.10.1
QuickFIX C++ x64 v 1.15.1

Throughput (msg/sec)

Message length: 131 bytes.

Mode	OnixS	QuickFIX	Times OnixS faster
Send side	5.11543e+06	442727	11.4x
Receive side	4.82963e+06	330452	14.6x

Latency (microseconds)

Message length: 144 bytes.

Mode	OnixS	QuickFIX	Time OnixS faster
Internal send min	0.09	0.26	2.8x
Internal send median	0.11	0.28	2.54x
Internal send 99%	0.13	0.29	2.23x
Overall send min	1.0	4.8	4.8x
Overall send median	1.16	5.59	4.9x
Overall send 99%	1.35	6.68	4.9x
RTT/2 min	0.74	1.90	2.56x
RTT/2 median	1.17	2.28	1.94x
RTT/2 99%	1.31	2.82	2.15x

Parsing (msg/sec)

Message size	OnixS	QuickFIX	Times OnixS faster
Small (106 bytes)	1e+07	909090	11x

Notes:

There is no ability to measure internal receive latency in QuickFIX because there is no onReceivedBytes analog as in the OnixS FIX Engine.
The QuickFIX internal send latency, unlike the OnixS FIX Engine internal send latency, does not include the outgoing message serialization and session storage latencies because the toApp callback is called before these processes.

View full post