Just turned off some network stuff on my Fedora 23 client and ran this time through a silent network TP-Link Archer C5 v1.2’s build in switch.
This section with desktop running iperf -c to the -s on Rockstor with the intel GT in and we have:-
------------------------------------------------------------
Client connecting to 192.168.0.101, TCP port 5001
TCP window size: 85.0 KByte (default)
------------------------------------------------------------
[ 3] local 192.168.0.100 port 57370 connected with 192.168.0.101 port 5001
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 101 MBytes 846 Mbits/sec
[ 3] 1.0- 2.0 sec 102 MBytes 851 Mbits/sec
[ 3] 2.0- 3.0 sec 102 MBytes 852 Mbits/sec
[ 3] 3.0- 4.0 sec 102 MBytes 852 Mbits/sec
[ 3] 4.0- 5.0 sec 102 MBytes 854 Mbits/sec
[ 3] 5.0- 6.0 sec 101 MBytes 847 Mbits/sec
[ 3] 6.0- 7.0 sec 102 MBytes 854 Mbits/sec
[ 3] 7.0- 8.0 sec 102 MBytes 852 Mbits/sec
[ 3] 8.0- 9.0 sec 102 MBytes 852 Mbits/sec
[ 3] 9.0-10.0 sec 102 MBytes 852 Mbits/sec
[ 3] 0.0-10.0 sec 1015 MBytes 851 Mbits/sec
So now consistent and a better result than before. The reverse is pretty much the same as before.
And just for comparison I ran the same tests but this time with the lesser Realtek RTL8169C in the Rockstor machine:-
Again on a silent network through the TP-Link’s build in switch.
iperf -s on Rockstor machine first
------------------------------------------------------------
Client connecting to 192.168.0.101, TCP port 5001
TCP window size: 85.0 KByte (default)
------------------------------------------------------------
[ 3] local 192.168.0.100 port 57396 connected with 192.168.0.101 port 5001
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 69.0 MBytes 579 Mbits/sec
[ 3] 1.0- 2.0 sec 69.1 MBytes 580 Mbits/sec
[ 3] 2.0- 3.0 sec 42.1 MBytes 353 Mbits/sec
[ 3] 3.0- 4.0 sec 78.8 MBytes 661 Mbits/sec
[ 3] 4.0- 5.0 sec 69.1 MBytes 580 Mbits/sec
[ 3] 5.0- 6.0 sec 86.4 MBytes 725 Mbits/sec
[ 3] 6.0- 7.0 sec 85.1 MBytes 714 Mbits/sec
[ 3] 7.0- 8.0 sec 86.4 MBytes 725 Mbits/sec
[ 3] 8.0- 9.0 sec 86.4 MBytes 725 Mbits/sec
[ 3] 9.0-10.0 sec 86.2 MBytes 724 Mbits/sec
[ 3] 0.0-10.0 sec 759 MBytes 636 Mbits/sec
and the reverse so the Rockstor RTL8169 is running iperf -c desktop-f23-ip
Client connecting to 192.168.0.100, TCP port 5001
TCP window size: 85.0 KByte (default)
------------------------------------------------------------
[ 3] local 192.168.0.101 port 55672 connected with 192.168.0.100 port 5001
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 69.6 MBytes 584 Mbits/sec
[ 3] 1.0- 2.0 sec 69.4 MBytes 582 Mbits/sec
[ 3] 2.0- 3.0 sec 69.4 MBytes 582 Mbits/sec
[ 3] 3.0- 4.0 sec 69.5 MBytes 583 Mbits/sec
[ 3] 4.0- 5.0 sec 69.4 MBytes 582 Mbits/sec
[ 3] 5.0- 6.0 sec 69.4 MBytes 582 Mbits/sec
[ 3] 6.0- 7.0 sec 69.4 MBytes 582 Mbits/sec
[ 3] 7.0- 8.0 sec 69.2 MBytes 581 Mbits/sec
[ 3] 8.0- 9.0 sec 69.4 MBytes 582 Mbits/sec
[ 3] 9.0-10.0 sec 69.5 MBytes 583 Mbits/sec
[ 3] 0.0-10.0 sec 694 MBytes 582 Mbits/sec
as can be seen the performance is significantly less with this very common realtek chip, at least it used to be pretty common.
so to summarise:-
Intel PRO/1000 GT card in Rockstor - 851/877 Mbps
Realtek RTL8169C in Rockstor -636/582 Mbps
Note that the Intel GT card is a desktop class network card not a server class.
I have posted these results as I’ve been meaning to test this routers switch again and given your post and my finding the same model network card here it seemed like an opportunity to provide context.
The Rockstor machine was a single core Celeron with 2MB ram.