Re: [PLUG] slow gigbit FiOS

On Sat, Sep 2, 2017 at 7:47 PM, Sonny To <son.c.to@gmail.com> wrote:

Hi Brent,
thanks for responding.

this is the FIOS
sto@obi:~$ iperf -c localhost -p 1234
------------------------------------------------------------
Client connecting to localhost, TCP port 1234
TCP window size: 2.50 MByte (default)
------------------------------------------------------------
[ 3] local 127.0.0.1 port 42320 connected with 127.0.0.1 port 1234
[ ID] Interval Transfer Bandwidth
[ 3] 0.0-10.3 sec 43.5 MBytes 35.4 Mbits/sec

this is xfinity:
iperf -c localhost -p 1234
------------------------------------------------------------
Client connecting to localhost, TCP port 1234
TCP window size: 2.50 MByte (default)
------------------------------------------------------------
[ 3] local 127.0.0.1 port 42348 connected with 127.0.0.1 port 1234

^C[ ID] Interval Transfer Bandwidth
[ 3] 0.0-164.1 sec 13.8 MBytes 703 Kbits/sec

I had to use localhost because only ssh port is open on the server

fios is clearly faster but unusable with nx. I've used nx before on a 1mbps and it was still usable but for some reason on fios with 35Mbits/sec its almost unusable. I thought it could be something with the default configuration of the verizon's quantum router that causing the problem.

I'm not getting close to your speed probably because of the cable is not cat5e or above. I ordered cat6 cables from amazon to see if it will fix the speed. however, the high latency experienced with nx probably wouldn't go away

sto@jedi:~$ ethtool enp3s0
Settings for enp3s0:
Supported ports: [ TP MII ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Half 1000baseT/Full
Supported pause frame use: Symmetric Receive-only
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Half 1000baseT/Full
Advertised pause frame use: Symmetric Receive-only
Advertised auto-negotiation: Yes
Link partner advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
Link partner advertised pause frame use: Symmetric Receive-only
Link partner advertised auto-negotiation: Yes
Speed: 100Mb/s
Duplex: Full
Port: MII
PHYAD: 1
Transceiver: internal
Auto-negotiation: on
Cannot get wake-on-lan settings: Operation not permitted
Current message level: 0x000000ff (255)
drv probe link timer ifdown ifup rx_err tx_err
Link detected: yes

On Sun, Sep 3, 2017 at 2:29 AM Sonny To <son.c.to@gmail.com> wrote:
thanks for responding. here are the pings

PING shiva.fpmsoft.co (71.59.73.92) 56(84) bytes of data.
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=1 ttl=243 time=151 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=2 ttl=243 time=147 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=3 ttl=243 time=148 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=4 ttl=243 time=152 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=5 ttl=243 time=149 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=6 ttl=243 time=148 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=7 ttl=243 time=149 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=8 ttl=243 time=148 ms
64 bytes from c-71-59-73-92.hsd1.nj.comcast.net (71.59.73.92): icmp_seq=9 ttl=243 time=147 ms
^C
--- shiva.fpmsoft.co ping statistics ---
9 packets transmitted, 9 received, 0% packet loss, time 7997ms
rtt min/avg/max/mdev = 147.352/149.176/152.135/1.532 ms

PING jedi.fpmsoft.co (100.11.74.5) 56(84) bytes of data.
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=1 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=2 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=3 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=4 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=5 ttl=53 time=138 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=6 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=7 ttl=53 time=138 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=8 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=9 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=10 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=11 ttl=53 time=137 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=12 ttl=53 time=138 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=13 ttl=53 time=139 ms
64 bytes from pool-100-11-74-5.phlapa.fios.verizon.net (100.11.74.5): icmp_seq=14 ttl=53 time=142 ms
^C
--- jedi.fpmsoft.co ping statistics ---
14 packets transmitted, 14 received, 0% packet loss, time 12994ms
rtt min/avg/max/mdev = 137.032/138.137/142.720/1.489 ms

On Sun, Sep 3, 2017 at 2:17 AM Lee H. Marzke <lee@marzke.net> wrote:
You didn't mention the actual latency your getting. The throughput of local servers likely doesn't matter as much
with large RTT latencies and tcp windowing issues.

https://www.sd-wan-experts.com/blog/why-your-maximum-thru-put-is-less-than-your-bandwidth/
http://www.kehlet.cx/articles/99.html

Lee

From: "Sonny To" <son.c.to@gmail.com>
To: "Philadelphia Linux User's Group Discussion List" <plug@lists.phillylinux.org>
Sent: Saturday, September 2, 2017 6:33:41 PM
Subject: [PLUG] slow gigbit FiOS
I have two servers one on xfinity 150mbps/10mbps in princeton,nj and the other on fios 1gbps/1gbps in Philly. when I did a speedtest on fios, i'm only getting 100mbps/100mbps. I am not sure why but suspect it could be that the cable is not cat6. I ordered cat6 cable to see if that fixes it.
The unusual thing is the fios connection is laggy when I am using nx via ssh tunneling with compression. the xfinity ,however, is fast and responsive. I couldn't tell that I'm remote. I expect the fios to be more responsive because the upstream is 100mbps but its almost unusable. I'm connecting to both machines from Sofia, Bulgaria. both connection have similar latency reported via ping. can anyone offer an explanation why?

___________________________________________________________________________
Philadelphia Linux Users Group -- http://www.phillylinux.org
Announcements - http://lists.phillylinux.org/mailman/listinfo/plug-announce
General Discussion -- http://lists.phillylinux.org/mailman/listinfo/plug

--
"Between subtle shading and the absence of light lies the nuance of iqlusion..." - Kryptos

Lee Marzke, lee@marzke.net http://marzke.net/lee/
IT Consultant, VMware, VCenter, SAN storage, infrastructure, SW CM

___________________________________________________________________________
Philadelphia Linux Users Group -- http://www.phillylinux.org
Announcements - http://lists.phillylinux.org/mailman/listinfo/plug-announce
General Discussion -- http://lists.phillylinux.org/mailman/listinfo/plug

___________________________________________________________________________
Philadelphia Linux Users Group -- http://www.phillylinux.org
Announcements - http://lists.phillylinux.org/mailman/listinfo/plug-announce
General Discussion -- http://lists.phillylinux.org/mailman/listinfo/plug