1 |
On 1/16/21 11:55 AM, Michael wrote: |
2 |
> On Friday, 15 January 2021 22:43:36 GMT thelma@×××××××××××.com wrote: |
3 |
> |
4 |
>> The fact that I'm logged via ssh over VPN to a remote network should not |
5 |
>> have any influence over network speed. |
6 |
> |
7 |
> It may influence speed if you're trying to push a large file through the |
8 |
> tunnel. TCP over TCP tends to choke due to retransmissions: |
9 |
> |
10 |
> http://sites.inka.de/bigred/devel/tcp-tcp.html |
11 |
> |
12 |
> Is the VPN you mention using a TCP or UDP tunnel? |
13 |
|
14 |
The VPN is using UDP tunnel. |
15 |
|
16 |
> |
17 |
>> I just made a loop: |
18 |
>> Network A ==> Internet ==> Network B |
19 |
>> ssh back to Network A over internet and run "rsync" I got same speed (as if |
20 |
>> I run the command locally) on Network A 112MB/s |
21 |
>> |
22 |
>> So the limiting factor is somewhere else. |
23 |
> |
24 |
> I'm sorry, but I fail to understand with any clarity what runs where and how |
25 |
> when you test things locally, Vs remotely. I mean: |
26 |
|
27 |
What I did is log-in to a remote network over ssh, from remote network I logged back to my network PC using ssh and tested the transfer speed. |
28 |
|
29 |
> - Network topology; |
30 |
> - Network Protocols; |
31 |
> - Applications & application protocols; |
32 |
> - Relevant services on each peer; |
33 |
> - Actions on each peer; |
34 |
> - Results per action. |
35 |
> |
36 |
> As already mentioned iperf or netcat/telnet results will confirm if this is |
37 |
> purely a network issue, ISPs performing deep packet inspection/throttling |
38 |
> affecting throughput asymmetrically, etc. |
39 |
> |
40 |
> SSDs are typically faster than spinning disks, but not always as fast as |
41 |
> ramdisks/tmpfs, especially if write amplification takes place, TRIM kicks in, |
42 |
> etc. |
43 |
> |
44 |
> Stacking network + application protocols can also have an adverse effect. |
45 |
> Applications like rsync which compare file names, sizes, hashes and what not, |
46 |
> do not offer a reliable speed comparison. |
47 |
> |
48 |
> Methodically testing each component of the transmission system should get you |
49 |
> an answer at the end. |
50 |
|
51 |
On a remote network there are 5-pcs |
52 |
- two of them are Windows PC |
53 |
- 3-pcs are Gentoo |
54 |
|
55 |
I was just testing Getnoo PC's |
56 |
One small PC is about 20-30meters away from the switch and connected by CAT5 (or CAT5e) |
57 |
that PC is network card is capable of 1000-speed according to "ethtool" but negotiated the speed of 100 according to: |
58 |
/sys/class/net/enp4s0/speed |
59 |
|
60 |
The 2-PCs closer to the switch, negotiated the speed of 1000 according to: |
61 |
/sys/class/net/enpxxxx/speed |
62 |
|
63 |
I have to check (this week) if they are both connected directly to a switch and or firewall Ausus RT-AC66U and the light on the switch. |
64 |
I'll check out/investigate the use of "net-misc/iperf" to check the speed. |