Hello Alex,

unfortunately this is OM question
We are using custom client side JS to measure network characteristics
ping/jitter/upload/download
to made this check more "realistic" we are measuring both
upload/download+processing time
i.e. while downloading we are generating new byte sequence, on uploading
read every byte being sent
maybe this might be improved

On Thu, 12 Nov 2020 at 15:23, Ninnig, Alexander <
alexander.nin...@rechnungshof.rlp.de> wrote:

> Hello,
>
> to check the performance I just startet several network tests via
> openmeetings.
> What's weird: the network-test via openmeetings4 shows significally better
> download-rates (20 Mb/sec) than openmeetings 5 (4 Mb/sec).
> Those values seem to be low altogether, because I am doing these tests in
> a gigabit-network.
>
> * Both openmeetings-servers are virtual machines (VMware, VM-Version 11)
> with 8 CPU-cores and 8 GB RAM and VMXNET3-LAN-Cards.
> * Both are connected to gigabit-switches.
> * Openmeetings 4 runs on Ubuntu 18.04.5 LTS, openmeetings 5 runs on Ubuntu
> 20.04.1 LTS.
> * Clients are configured to open the website directly (not using proxy).
> * I entered some commands to display the ubuntu-network-adapter-details
> and the results are pasted below. Both servers show "Speed: 10000Mb/s" and
> "Duplex: Full". The openmeetings5-server additionally shows some
> docker-network-details, I'm not familiar with.
>
> I guess this is a linux-question, not an openmeetings-question, but maybe
> someone in here experienced similar behaviour and found ways to increase
> the performance.
>
> - why are the upload-rates way better than the download-rates?
> - why are these values so low (in a gigabit-environment)?
>
>
>
> ----------
>
> openmeetings 5-server
>
> ethtool ens160
> Settings for ens160:
>         Supported ports: [ TP ]
>         Supported link modes:   1000baseT/Full
>                                 10000baseT/Full
>         Supported pause frame use: No
>         Supports auto-negotiation: No
>         Supported FEC modes: Not reported
>         Advertised link modes:  Not reported
>         Advertised pause frame use: No
>         Advertised auto-negotiation: No
>         Advertised FEC modes: Not reported
>         Speed: 10000Mb/s
>         Duplex: Full
>         Port: Twisted Pair
>         PHYAD: 0
>         Transceiver: internal
>         Auto-negotiation: off
>         MDI-X: Unknown
> Cannot get wake-on-lan settings: Operation not permitted
>         Link detected: yes
>
> dmesg |grep eth0
> [    2.272277] vmxnet3 0000:03:00.0 eth0: NIC Link is Up 10000 Mbps
> [    2.295532] vmxnet3 0000:03:00.0 ens160: renamed from eth0
> [  476.320685] eth0: renamed from vethc10076e
> [196875.071160] vethc10076e: renamed from eth0
> [196916.660163] docker0: port 1(veth095d6f5) entered blocking state
> [196916.660166] docker0: port 1(veth095d6f5) entered disabled state
> [196916.660313] device veth095d6f5 entered promiscuous mode
> [196917.010394] eth0: renamed from veth426fe1f
> [196917.030295] IPv6: ADDRCONF(NETDEV_CHANGE): veth095d6f5: link becomes
> ready
> [196917.030352] docker0: port 1(veth095d6f5) entered blocking state
> [196917.030355] docker0: port 1(veth095d6f5) entered forwarding state
>
> ----------
>
> openmeetings 4-server
>
> ethtool ens160
> Settings for ens160:
>         Supported ports: [ TP ]
>         Supported link modes:   1000baseT/Full
>                                 10000baseT/Full
>         Supported pause frame use: No
>         Supports auto-negotiation: No
>         Supported FEC modes: Not reported
>         Advertised link modes:  Not reported
>         Advertised pause frame use: No
>         Advertised auto-negotiation: No
>         Advertised FEC modes: Not reported
>         Speed: 10000Mb/s
>         Duplex: Full
>         Port: Twisted Pair
>         PHYAD: 0
>         Transceiver: internal
>         Auto-negotiation: off
>         MDI-X: Unknown
> Cannot get wake-on-lan settings: Operation not permitted
>         Link detected: yes
>
> dmesg |grep eth0
> [    2.450005] vmxnet3 0000:03:00.0 eth0: NIC Link is Up 10000 Mbps
> [    2.457827] vmxnet3 0000:03:00.0 ens160: renamed from eth0
>
> ----------
>
> Best regards,
> Alex
>


-- 
Best regards,
Maxim

Reply via email to