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) Core(TM) CPU i7-7700K @ 4.20GHz, 32 GB RAM
Software
Ubuntu 20.04 gcc 9.4.0
OnixS FIX Engine for .NET Core / .NET 6 v 1.9.0
QuickFIXn.Core v 1.10.0
Throughput (msg/sec)
Message length: 131 bytes.
|
Mode
|
OnixS
|
QuickFIXn
|
% OnixS faster
|
|
Send side
|
377,118
|
30,044
|
13x
|
|
Receive side
|
376,499
|
30,314
|
12x
|
Latency (microseconds)
Message length: 144 bytes.
|
Mode
|
OnixS
|
QuickFIXn
|
% OnixS faster
|
|
Internal send min
|
0.632
|
2.727
|
4.3x
|
|
Internal send median
|
0.755
|
3.424
|
4.5x
|
|
Internal send 99%
|
0.887
|
4.051
|
4.6x
|
|
Overall send min
|
2.915
|
80.798
|
27.7x
|
|
Overall send median
|
3.189 |
87.259
|
27.3x
|
|
Overall send 99%
|
3.833
|
153.346
|
40x
|
|
RTT/2 min
|
4.410
|
50.124
|
11.3x
|
|
RTT/2 median
|
5.722
|
57.879
|
10.1x
|
|
RTT/2 99%
|
6.540
|
74.791
|
11.4x
|
Parsing (msg/sec)
|
Message size
|
OnixS
|
QuickFIXn
|
% OnixS faster
|
|
Small (106 bytes)
|
2,651,736
|
465,146
|
5.7x
|
Notes:
-
There is no ability to measure internal receive latency in QuickFIXn because there is no onReceivedBytes analog as in the OnixS FIX Engine.
-
The QuickFIXn 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.
