Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!


Shells Virtual Desktop
BMail.ag - Secure Email Service
Server.net
CPLicense.net
VPS Server
Buy VPN
Vultr
VMs for AI
HostDare
ReliableSite White-Label Dedicated Hosting for Resellers
InterServer VPS
BMail.ag - Secure Email Service
Best VPN
High-Performance Bare Metal Server Solutions
Karvl.com
Server Mania Cloud Hosting
DataWagon Hosting
AlphaVPS Hosting
Evoxt.com
Clouvider
VPS Hosting with NVMe
Residential IPs in the US & 4G Mobile Proxies in EU & US with Unlimited Bandwidth
ReliableSite White-Label Dedicated Hosting for Resellers
Rabisu - Hosting Solutions
Shells Virtual Desktop
New on LowEndTalk? Please Register and read our Community Rules.

All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.

Provider with highest throughput between USA and NL

Hi All,

I've noticed that on a couple of VPS's I've used (racknerd, naranjatech) the up/download speeds between a VPS in the Netherlands and one in Dallas, TX, USA is mostly around 32Mbit (around 4 Mb/s) and latency between 100-150 ms. I use this to sync between two servers.

I was wondering if any of you have any experiences with better bandwidth/latency between VPS's that sync between Europe and the USA. It is hard to find this information because 1 or 10 GB network doesn't really tell you this.

Comments

  • jayjayjayjay Member, Patron Provider

    Do you already have existing services in these locations? DM me the IPs and I can test the speeds from our servers in the Netherlands and viceversa, I can share the results to see if they suit what you need.

    Thanked by 1b00n
  • allthemtingsallthemtings Member, Megathread Squad
    Thanked by 2PureVoltage b00n
  • Thanked by 1b00n
  • @jayjay said:
    Do you already have existing services in these locations? DM me the IPs and I can test the speeds from our servers in the Netherlands and viceversa, I can share the results to see if they suit what you need.

    I do, I will DM you. I'll put a test file on the server first.

    Thanked by 1jayjay
  • PureVoltagePureVoltage Member, Patron Provider

    Thanks!
    @b00n
    We got you covered for this good sir!
    Speeds to Amsterdam on our 10G servers hit 10g. :)

    Our VPS lineup should do wonders for you as well.

    https://purevoltage.com/blackfriday.php

    Thanked by 2b00n gks
  • @PureVoltage said:

    Thanks!
    @b00n
    We got you covered for this good sir!
    Speeds to Amsterdam on our 10G servers hit 10g. :)

    Our VPS lineup should do wonders for you as well.

    https://purevoltage.com/blackfriday.php

    Was just reading through that on an older topic. What I can't tell from there: do you offer a Dallas based VPS on that BF deal? I only see NY on your website.

  • @b00n said:

    @PureVoltage said:

    Thanks!
    @b00n
    We got you covered for this good sir!
    Speeds to Amsterdam on our 10G servers hit 10g. :)

    Our VPS lineup should do wonders for you as well.

    https://purevoltage.com/blackfriday.php

    Was just reading through that on an older topic. What I can't tell from there: do you offer a Dallas based VPS on that BF deal? I only see NY on your website.

    NY would likely be more optimal for you. Give it a run

    https://lg.nyc.purevoltage.com/

  • b00nb00n Member
    edited December 2024

    @Petey_Long said:

    @b00n said:

    @PureVoltage said:

    Thanks!
    @b00n
    We got you covered for this good sir!
    Speeds to Amsterdam on our 10G servers hit 10g. :)

    Our VPS lineup should do wonders for you as well.

    https://purevoltage.com/blackfriday.php

    Was just reading through that on an older topic. What I can't tell from there: do you offer a Dallas based VPS on that BF deal? I only see NY on your website.

    NY would likely be more optimal for you. Give it a run

    https://lg.nyc.purevoltage.com/

    I'm sure it will be ;) but for my use case I need it to be a Dallas (or at least TX) based server.

  • PureVoltagePureVoltage Member, Patron Provider

    @b00n said:

    @Petey_Long said:

    @b00n said:

    @PureVoltage said:

    Thanks!
    @b00n
    We got you covered for this good sir!
    Speeds to Amsterdam on our 10G servers hit 10g. :)

    Our VPS lineup should do wonders for you as well.

    https://purevoltage.com/blackfriday.php

    Was just reading through that on an older topic. What I can't tell from there: do you offer a Dallas based VPS on that BF deal? I only see NY on your website.

    NY would likely be more optimal for you. Give it a run

    https://lg.nyc.purevoltage.com/

    I'm sure it will be ;) but for my use case I need it to be a Dallas (or at least TX) based server.

    Dalllas we should have up early Jan for our VPS nodes out there. :)
    Right now just NY which would be the best performance to NL

    Thanked by 1b00n
  • I've found updating sysctl.conf with the following parameters causes most of my VMs to max out file download/upload speeds between any host US to EU etc.

    net.core.default_qdisc=fq
    net.ipv4.tcp_congestion_control=bbr
    net.core.rmem_max = 134217728
    net.core.wmem_max = 134217728
    net.ipv4.tcp_rmem = 4096 87380 134217728
    net.ipv4.tcp_wmem = 4096 65536 134217728
    net.core.netdev_max_backlog = 300000
    net.ipv4.tcp_moderate_rcvbuf = 1
    net.ipv4.tcp_no_metrics_save = 1
    net.ipv4.tcp_mtu_probing = 1

    sysctl -p (to apply)

  • Install > @zorker said:

    I've found updating sysctl.conf with the following parameters causes most of my VMs to max out file download/upload speeds between any host US to EU etc.

    net.core.default_qdisc=fq
    net.ipv4.tcp_congestion_control=bbr
    net.core.rmem_max = 134217728
    net.core.wmem_max = 134217728
    net.ipv4.tcp_rmem = 4096 87380 134217728
    net.ipv4.tcp_wmem = 4096 65536 134217728
    net.core.netdev_max_backlog = 300000
    net.ipv4.tcp_moderate_rcvbuf = 1
    net.ipv4.tcp_no_metrics_save = 1
    net.ipv4.tcp_mtu_probing = 1

    sysctl -p (to apply)

    I'd explore sysctl confs with https://tuned-project.org/ profiles.

    Thanked by 2b00n t0m
  • Interesting, thanks for sharing, I will test this!

  • This is iperf3 with bbr enabled, run between RackNerd (NYC) and HeartBeat-it (NL).

    Basic System Information:
    ---------------------------------
    Uptime     : 135 days, 19 hours, 17 minutes
    Processor  : Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
    CPU cores  : 1 @ 2799.998 MHz
    AES-NI     : ✔ Enabled
    VM-x/AMD-V : ❌ Disabled
    RAM        : 582.7 MiB
    Swap       : 640.0 MiB
    Disk       : 9.2 GiB
    Distro     : Debian GNU/Linux 12 (bookworm)
    Kernel     : 6.1.0-23-amd64
    VM Type    : KVM
    IPv4/IPv6  : ✔ Online / ❌ Offline
    
    IPv4 Network Information:
    ---------------------------------
    ISP        : HostPapa
    ASN        : AS36352 HostPapa
    Host       : RackNerd LLC
    Location   : Buffalo, New York (NY)
    Country    : United States
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
    -----           | -----                     | ----            | ----            | ----
    HeartBeat-it    | Eygelshoven, NL (1G)      | 487 Mbits/sec   | 568 Mbits/sec   | 89.5 ms
    
  • @zorker said:
    I've found updating sysctl.conf with the following parameters causes most of my VMs to max out file download/upload speeds between any host US to EU etc.

    net.core.default_qdisc=fq
    net.ipv4.tcp_congestion_control=bbr
    net.core.rmem_max = 134217728
    net.core.wmem_max = 134217728
    net.ipv4.tcp_rmem = 4096 87380 134217728
    net.ipv4.tcp_wmem = 4096 65536 134217728
    net.core.netdev_max_backlog = 300000
    net.ipv4.tcp_moderate_rcvbuf = 1
    net.ipv4.tcp_no_metrics_save = 1
    net.ipv4.tcp_mtu_probing = 1

    sysctl -p (to apply)

    Dude, you are THE absolute bomb! After applying this to both ends, my servers fly ;) I now pull in files with 1gbit ;)

    Thanked by 1zorker
  • @vicaya said:
    Install > @zorker said:

    I've found updating sysctl.conf with the following parameters causes most of my VMs to max out file download/upload speeds between any host US to EU etc.

    net.core.default_qdisc=fq
    net.ipv4.tcp_congestion_control=bbr
    net.core.rmem_max = 134217728
    net.core.wmem_max = 134217728
    net.ipv4.tcp_rmem = 4096 87380 134217728
    net.ipv4.tcp_wmem = 4096 65536 134217728
    net.core.netdev_max_backlog = 300000
    net.ipv4.tcp_moderate_rcvbuf = 1
    net.ipv4.tcp_no_metrics_save = 1
    net.ipv4.tcp_mtu_probing = 1

    sysctl -p (to apply)

    I'd explore sysctl confs with https://tuned-project.org/ profiles.

    This is something @1gservers had mentioned for using boxes with 10g interfaces. I've found it works for just about any system to max throughput (assuming both ends are set this way).

    Thanked by 11gservers
  • I have the same issue as @b00n from NL to CA and the main issue is the low speed for 1 single connection.

    For example:
    If I do a speedtest with yabs or nws script (iperf3) the result is 900mbit/sec on a 1G line for example.
    If I upload a single file of 10GB via SFTP it results in only 4mbit/sec. (Bandwidth seems throttled).
    If I upload the same file with a VPS in NY as a proxy in between, it hits 100mbit/sec.

    Does anyone know if there's a way to upload files with multithreading and encryption on the fly?

  • @t0m said:
    I have the same issue as @b00n from NL to CA and the main issue is the low speed for 1 single connection.

    For example:
    If I do a speedtest with yabs or nws script (iperf3) the result is 900mbit/sec on a 1G line for example.
    If I upload a single file of 10GB via SFTP it results in only 4mbit/sec. (Bandwidth seems throttled).
    If I upload the same file with a VPS in NY as a proxy in between, it hits 100mbit/sec.

    Does anyone know if there's a way to upload files with multithreading and encryption on the fly?

    Please apply the reply from zorker on both servers and try again. My problem has vanished and it is maxing out now! ;) Thanks @zorker!

  • dfroedfroe Member, Host Rep
    edited December 2024

    From my experience for example EasyVM in NYC (Telehouse Teleport) has great connectivity towards Europe.
    They still have their 75% Black Friday offers on their website (easyvm.net)

    iperf3 running on a VPS from EasyVM in NYC, US with Arelion/Telia routing against Leaseweb in AMS, NL resulting in solid 1.5 Gbps per tcp flow in both directions and only 75 ms RTT.

    iperf:

    root@vps-nyc:~# iperf3 -c speedtest.ams1.nl.leaseweb.net
    Connecting to host speedtest.ams1.nl.leaseweb.net, port 5201
    [  5] local 2602:fa7c:10:XXX port 52530 connected to 2001:1af8:5300:a018::77 port 5201
    [ ID] Interval           Transfer     Bitrate         Retr  Cwnd
    [  5]   0.00-1.00   sec   113 MBytes   946 Mbits/sec    0   28.1 MBytes
    [  5]   1.00-2.00   sec   210 MBytes  1.76 Gbits/sec    0   34.0 MBytes
    [  5]   2.00-3.00   sec   212 MBytes  1.78 Gbits/sec    0   33.9 MBytes
    [  5]   3.00-4.00   sec   214 MBytes  1.79 Gbits/sec    0   33.0 MBytes
    [  5]   4.00-5.00   sec   211 MBytes  1.77 Gbits/sec    0   34.2 MBytes
    [  5]   5.00-6.00   sec   211 MBytes  1.77 Gbits/sec    0   33.6 MBytes
    [  5]   6.00-7.00   sec   211 MBytes  1.77 Gbits/sec    0   33.9 MBytes
    [  5]   7.00-8.00   sec   211 MBytes  1.77 Gbits/sec    0   35.2 MBytes
    [  5]   8.00-9.00   sec   210 MBytes  1.76 Gbits/sec    0   33.6 MBytes
    [  5]   9.00-10.00  sec   211 MBytes  1.77 Gbits/sec    0   35.2 MBytes
    - - - - - - - - - - - - - - - - - - - - - - - - -
    [ ID] Interval           Transfer     Bitrate         Retr
    [  5]   0.00-10.00  sec  1.97 GBytes  1.69 Gbits/sec    0             sender
    [  5]   0.00-10.08  sec  1.90 GBytes  1.62 Gbits/sec                  receiver
    
    root@vps-nyc:~# iperf3 -c speedtest.ams1.nl.leaseweb.net -R
    Connecting to host speedtest.ams1.nl.leaseweb.net, port 5201
    Reverse mode, remote host speedtest.ams1.nl.leaseweb.net is sending
    [  5] local 2602:fa7c:10:XXX port 49214 connected to 2001:1af8:5300:a018::77 port 5201
    [ ID] Interval           Transfer     Bitrate
    [  5]   0.00-1.00   sec  62.5 MBytes   524 Mbits/sec
    [  5]   1.00-2.00   sec   164 MBytes  1.38 Gbits/sec
    [  5]   2.00-3.00   sec   165 MBytes  1.38 Gbits/sec
    [  5]   3.00-4.00   sec   167 MBytes  1.40 Gbits/sec
    [  5]   4.00-5.00   sec   171 MBytes  1.43 Gbits/sec
    [  5]   5.00-6.00   sec   173 MBytes  1.45 Gbits/sec
    [  5]   6.00-7.00   sec   183 MBytes  1.54 Gbits/sec
    [  5]   7.00-8.00   sec   191 MBytes  1.60 Gbits/sec
    [  5]   8.00-9.00   sec   200 MBytes  1.68 Gbits/sec
    [  5]   9.00-10.00  sec   211 MBytes  1.77 Gbits/sec
    - - - - - - - - - - - - - - - - - - - - - - - - -
    [ ID] Interval           Transfer     Bitrate         Retr
    [  5]   0.00-10.07  sec  1.67 GBytes  1.42 Gbits/sec    0             sender
    [  5]   0.00-10.00  sec  1.65 GBytes  1.41 Gbits/sec                  receiver
    
    root@vps-nyc:~# iperf3 -c speedtest.ams1.nl.leaseweb.net -P 4
    Connecting to host speedtest.ams1.nl.leaseweb.net, port 5201
    [  5] local 2602:fa7c:10:XXX port 56888 connected to 2001:1af8:5300:a018::77 port 5201
    [  7] local 2602:fa7c:10:XXX port 56894 connected to 2001:1af8:5300:a018::77 port 5201
    [  9] local 2602:fa7c:10:XXX port 56898 connected to 2001:1af8:5300:a018::77 port 5201
    [ 11] local 2602:fa7c:10:XXX port 56906 connected to 2001:1af8:5300:a018::77 port 5201
    [...]
    [SUM]   0.00-10.00  sec  6.22 GBytes  5.34 Gbits/sec    8             sender
    [SUM]   0.00-10.08  sec  6.07 GBytes  5.17 Gbits/sec                  receiver
    

    mtr:

    root@vps-nyc:~# mtr -r -c 50 speedtest.ams1.nl.leaseweb.net
    HOST: vps-nyc                     Loss%   Snt   Last   Avg  Best  Wrst StDev
      1.|-- lo1.nyc-eqxny2-cr1.parall  0.0%    50    0.4   0.4   0.3   0.6   0.1
      2.|-- ???                       100.0    50    0.0   0.0   0.0   0.0   0.0
      3.|-- ???                       100.0    50    0.0   0.0   0.0   0.0   0.0
      4.|-- nyk-b11-link.ip.twelve99.  0.0%    50    0.9   0.9   0.7   1.1   0.1
      5.|-- nyk-bb2-v6.ip.twelve99.ne 92.0%    50    1.4   1.4   1.3   1.5   0.1
      6.|-- ldn-bb2-v6.ip.twelve99.ne 88.0%    50   74.8  74.8  74.6  75.0   0.1
      7.|-- adm-bb2-v6.ip.twelve99.ne 86.0%    50   74.9  74.8  74.7  75.0   0.1
      8.|-- leaseweb-ic-308104.ip.twe 82.0%    50   75.6  75.4  75.0  75.8   0.3
      9.|-- leaseweb-ic-308104.ip.twe 64.0%    50   75.2  75.4  75.0  75.7   0.2
     10.|-- 2001:1af8::81:17:35:200    8.0%    50   75.7  75.4  75.1  75.8   0.2
     11.|-- 2001:1af8::210             0.0%    50   74.9  75.0  74.8  75.8   0.2
     12.|-- speedtest.ams1.nl.leasewe  0.0%    50   75.0  75.0  74.8  75.3   0.1
    

    YABS:

    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #              Yet-Another-Bench-Script              #
    #                     v2024-06-09                    #
    # https://github.com/masonr/yet-another-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    Sat Oct 19 00:50:29 CEST 2024
    
    Basic System Information:
    ---------------------------------
    Uptime     : 14 days, 10 hours, 4 minutes
    Processor  : Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz
    CPU cores  : 2 @ 2596.974 MHz
    AES-NI     : ✔ Enabled
    VM-x/AMD-V : ✔ Enabled
    RAM        : 3.8 GiB
    Swap       : 0.0 KiB
    Disk       : 49.9 GiB
    Distro     : Debian GNU/Linux 12 (bookworm)
    Kernel     : 6.1.0-26-amd64
    VM Type    : KVM
    IPv4/IPv6  : ✔ Online / ✔ Online
    
    IPv6 Network Information:
    ---------------------------------
    ISP        : Aquatic Tech LLC
    ASN        : AS26930 Parallax
    Host       : Parallax
    Location   : Secaucus, New Jersey (NJ)
    Country    : United States
    
    fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/vda3):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 116.16 MB/s  (29.0k) | 179.20 MB/s   (2.8k)
    Write      | 116.46 MB/s  (29.1k) | 180.14 MB/s   (2.8k)
    Total      | 232.62 MB/s  (58.1k) | 359.34 MB/s   (5.6k)
               |                      |
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 207.29 MB/s    (404) | 218.86 MB/s    (213)
    Write      | 218.30 MB/s    (426) | 233.44 MB/s    (227)
    Total      | 425.60 MB/s    (830) | 452.31 MB/s    (440)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
    -----           | -----                     | ----            | ----            | ----
    Clouvider       | London, UK (10G)          | 2.75 Gbits/sec  | 978 Mbits/sec   | 67.7 ms
    Eranium         | Amsterdam, NL (100G)      | 4.10 Gbits/sec  | 3.73 Gbits/sec  | 75.1 ms
    Uztelecom       | Tashkent, UZ (10G)        | 1.91 Gbits/sec  | 646 Mbits/sec   | 160 ms
    Leaseweb        | Singapore, SG (10G)       | 1.90 Gbits/sec  | 1.41 Gbits/sec  | 265 ms
    Clouvider       | Los Angeles, CA, US (10G) | 3.40 Gbits/sec  | 1.36 Gbits/sec  | 57.4 ms
    Leaseweb        | NYC, NY, US (10G)         | 5.33 Gbits/sec  | 4.26 Gbits/sec  | 2.28 ms
    Edgoo           | Sao Paulo, BR (1G)        | 4.61 Gbits/sec  | 842 Mbits/sec   | 110 ms
    
    iperf3 Network Speed Tests (IPv6):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
    -----           | -----                     | ----            | ----            | ----
    Clouvider       | London, UK (10G)          | 2.74 Gbits/sec  | 1.50 Gbits/sec  | 67.6 ms
    Eranium         | Amsterdam, NL (100G)      | 3.84 Gbits/sec  | 3.30 Gbits/sec  | 75.2 ms
    Uztelecom       | Tashkent, UZ (10G)        | 1.59 Gbits/sec  | 599 Mbits/sec   | 160 ms
    Leaseweb        | Singapore, SG (10G)       | 1.94 Gbits/sec  | 1.44 Gbits/sec  | 265 ms
    Clouvider       | Los Angeles, CA, US (10G) | 3.17 Gbits/sec  | 1.18 Gbits/sec  | 57.5 ms
    Leaseweb        | NYC, NY, US (10G)         | 5.41 Gbits/sec  | 4.10 Gbits/sec  | 2.11 ms
    Edgoo           | Sao Paulo, BR (1G)        | 4.56 Gbits/sec  | 1.06 Gbits/sec  | 110 ms
    
    Geekbench 6 Benchmark Test:
    ---------------------------------
    Test            | Value
                    |
    Single Core     | 816
    Multi Core      | 1517
    Full Test       | https://browser.geekbench.com/v6/cpu/8375014
    
    YABS completed in 17 min 46 sec
    
    Thanked by 1b00n
  • @t0m said:
    I have the same issue as @b00n from NL to CA and the main issue is the low speed for 1 single connection.

    For example:
    If I do a speedtest with yabs or nws script (iperf3) the result is 900mbit/sec on a 1G line for example.
    If I upload a single file of 10GB via SFTP it results in only 4mbit/sec. (Bandwidth seems throttled).
    If I upload the same file with a VPS in NY as a proxy in between, it hits 100mbit/sec.

    Does anyone know if there's a way to upload files with multithreading and encryption on the fly?

    SFTP has a lot of CPU overhead and SSH in general doesn't like higher latencies. You might be better off using rclone over HTTPS/Webdav. I actually run ZeroTier combined with Rclone/Webdav over HTTP to move files from EU to US with full 1g speeds.

  • @t0m said: Does anyone know if there's a way to upload files with multithreading and encryption on the fly?

    rclone, 100%

  • @t0m said:
    Does anyone know if there's a way to upload files with multithreading and encryption on the fly?

    Sender:
    rclone serve webdav --user abcabc --pass xyzxyz --addr :9999 ./
    

    Receiver:
    rclone config
    ...
    
    rclone copy your_remote_name:/ ./ -P --transfers 16
    

    Transfer test from NL (HeartBeat-IT) to Dallas (EasyVM):

    Thanked by 2b00n Clept0
  • truemagictruemagic Member
    edited December 2024

    -removed-

  • @b00n said:

    @zorker said:
    I've found updating sysctl.conf with the following parameters causes most of my VMs to max out file download/upload speeds between any host US to EU etc.

    net.core.default_qdisc=fq
    net.ipv4.tcp_congestion_control=bbr
    net.core.rmem_max = 134217728
    net.core.wmem_max = 134217728
    net.ipv4.tcp_rmem = 4096 87380 134217728
    net.ipv4.tcp_wmem = 4096 65536 134217728
    net.core.netdev_max_backlog = 300000
    net.ipv4.tcp_moderate_rcvbuf = 1
    net.ipv4.tcp_no_metrics_save = 1
    net.ipv4.tcp_mtu_probing = 1

    sysctl -p (to apply)

    Dude, you are THE absolute bomb! After applying this to both ends, my servers fly ;) I now pull in files with 1gbit ;)

    what actually does this do?

  • @cybertech said:

    @b00n said:

    @zorker said:
    I've found updating sysctl.conf with the following parameters causes most of my VMs to max out file download/upload speeds between any host US to EU etc.

    net.core.default_qdisc=fq
    net.ipv4.tcp_congestion_control=bbr
    net.core.rmem_max = 134217728
    net.core.wmem_max = 134217728
    net.ipv4.tcp_rmem = 4096 87380 134217728
    net.ipv4.tcp_wmem = 4096 65536 134217728
    net.core.netdev_max_backlog = 300000
    net.ipv4.tcp_moderate_rcvbuf = 1
    net.ipv4.tcp_no_metrics_save = 1
    net.ipv4.tcp_mtu_probing = 1

    sysctl -p (to apply)

    Dude, you are THE absolute bomb! After applying this to both ends, my servers fly ;) I now pull in files with 1gbit ;)

    what actually does this do?

    I don't honestly know. I just see the results. 1Gservers posted it a long time ago and they didn't know where they found it either. I'm surprised more LG servers don't do this. I found an LG in Taiwan that I can pull 3-5Gbps from to the US.

  • Should also mention if you need a test site, hit up 1Gservers LG https://1gservers.com/network.html and do a before and after test

  • It's so incredible, it's like magic.. 😀

  • The important one that's kind of ridiculously big is net.core.netdev_max_backlog = 300000, and it's the number of packets that can be in flight before blocking. It's normally 1000. This change makes that absolutely massive, and could probably cause you to end up consuming a massive amount of memory when there's significant packet loss.

    It's probably more sensible to set it to something more like 65536 (about 96MB maximum) rather than the potentially half GB this example could consume.

    Thanked by 2tiitae b00n
Sign In or Register to comment.