Embedded x86 Benchmarks v0.0.20180202
Lonnie Abelbeck
lists at lonnie.abelbeck.com
Sat Feb 3 20:17:09 CET 2018
Greetings,
I have a collection of lower-end (embedded) x86 boxes that I use for testing with our AstLinux project.
I previously posted WireGuard performance results for v0.0.20171211 ...
Embedded x86 Benchmarks
https://lists.zx2c4.com/pipermail/wireguard/2017-December/002204.html
Results for v0.0.20180202 are below.
Executive summary, v0.0.20180202 ranges from 0.7% slower to 2.9% faster than v0.0.20171211.
If nothing else, a good sanity check.
Lonnie
=================================
All WireGuard endpoints:
Linux 3.16.51
WireGuard 0.0.20180202
Common "Server" endpoint:
VMware VM
x86_64, 2-core, 3.7 GHz Xeon E5-1620
--
vmware-vm ~ # iperf3 -s
--
"Client" endpoints:
Qotom Q190G4N-S07
x86_64, 4-core, 2.0 GHz Celeron J1900
--
[ 4] 0.00-30.00 sec 3.03 GBytes 867 Mbits/sec 14 sender
[ 4] 0.00-30.00 sec 3.03 GBytes 867 Mbits/sec receiver
--
0.7% slower than v0.0.20171211
Jetway NF9HG-2930
x86_64, 4-core, 1.8 GHz Celeron N2930
--
[ 4] 0.00-30.00 sec 3.03 GBytes 867 Mbits/sec 11 sender
[ 4] 0.00-30.00 sec 3.03 GBytes 866 Mbits/sec receiver
--
0.7% slower than v0.0.20171211
Lanner FW-7541D
x86_64, 2-core,4-thread, 1.8 GHz Atom D525
--
[ 4] 0.00-30.00 sec 2.33 GBytes 668 Mbits/sec 0 sender
[ 4] 0.00-30.00 sec 2.33 GBytes 667 Mbits/sec receiver
--
0.1% slower than v0.0.20171211
PC Engines APU2
x86_64, 4-core, 1.0 GHz AMD GX-412TC
--
[ 4] 0.00-30.00 sec 1.84 GBytes 526 Mbits/sec 0 sender
[ 4] 0.00-30.00 sec 1.83 GBytes 525 Mbits/sec receiver
--
2.9% faster than v0.0.20171211
Lanner LEC-7220-N4
i686, 2-core,4-thread, 1.9 GHz Atom N2800
--
[ 4] 0.00-30.00 sec 1.15 GBytes 328 Mbits/sec 0 sender
[ 4] 0.00-30.00 sec 1.14 GBytes 327 Mbits/sec receiver
--
0.9% faster than v0.0.20171211
Soekris net5501
i586, 1-core, 0.5 GHz AMD Geode LX
--
[ 4] 0.00-30.00 sec 76.9 MBytes 21.5 Mbits/sec 0 sender
[ 4] 0.00-30.00 sec 76.8 MBytes 21.5 Mbits/sec receiver
--
0.5% faster than v0.0.20171211
=================================
More information about the WireGuard
mailing list