1 |
On Friday, 15 January 2021 22:43:36 GMT thelma@×××××××××××.com wrote: |
2 |
|
3 |
> The fact that I'm logged via ssh over VPN to a remote network should not |
4 |
> have any influence over network speed. |
5 |
|
6 |
It may influence speed if you're trying to push a large file through the |
7 |
tunnel. TCP over TCP tends to choke due to retransmissions: |
8 |
|
9 |
http://sites.inka.de/bigred/devel/tcp-tcp.html |
10 |
|
11 |
Is the VPN you mention using a TCP or UDP tunnel? |
12 |
|
13 |
|
14 |
> I just made a loop: |
15 |
> Network A ==> Internet ==> Network B |
16 |
> ssh back to Network A over internet and run "rsync" I got same speed (as if |
17 |
> I run the command locally) on Network A 112MB/s |
18 |
> |
19 |
> So the limiting factor is somewhere else. |
20 |
|
21 |
I'm sorry, but I fail to understand with any clarity what runs where and how |
22 |
when you test things locally, Vs remotely. I mean: |
23 |
|
24 |
- Network topology; |
25 |
- Network Protocols; |
26 |
- Applications & application protocols; |
27 |
- Relevant services on each peer; |
28 |
- Actions on each peer; |
29 |
- Results per action. |
30 |
|
31 |
As already mentioned iperf or netcat/telnet results will confirm if this is |
32 |
purely a network issue, ISPs performing deep packet inspection/throttling |
33 |
affecting throughput asymmetrically, etc. |
34 |
|
35 |
SSDs are typically faster than spinning disks, but not always as fast as |
36 |
ramdisks/tmpfs, especially if write amplification takes place, TRIM kicks in, |
37 |
etc. |
38 |
|
39 |
Stacking network + application protocols can also have an adverse effect. |
40 |
Applications like rsync which compare file names, sizes, hashes and what not, |
41 |
do not offer a reliable speed comparison. |
42 |
|
43 |
Methodically testing each component of the transmission system should get you |
44 |
an answer at the end. |