Howdy, Stranger!

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


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.

BERO HOST 10th Anniversary Deals – EPYC Turin / Ryzen 9950X / IPv6-only VPS

1…1113151617

Comments

  • LkwangLkwang Member
    edited October 10

    @ahson said:

    @Diy23 said:
    For the next VPS restock, can I purchase directly via the website, or do I need to pre-load funds into my account?

    isn't this how the normal purchase process works? Isn't this just the pre-order method we used before?

  • ahsonahson Member
    edited October 10

    @Lkwang said:

    @ahson said:

    @Diy23 said:
    For the next VPS restock, can I purchase directly via the website, or do I need to pre-load funds into my account?

    isn't this how the normal purchase process works? Isn't this just the pre-order method we used before?

    Yes. Just explained it, since @Diy23 asked.

  • Sunday is far away. 25tb/y ?

  • I have one instance from the last year sale. How can I cancel the service? it seems like there isn't button/option to cancel?

  • Happy 10th anniversary!
    Picked up an Anniversary XL
    Absolute beast!

  • abitstackabitstack Member
    edited October 10

    @Lkwang said:
    I totally agree with you - high traffic and high storage do have their specific uses. For example, some service providers only have users who download a lot of data.

    yeh, this is basically what the point of the entire cdn industry is all about

    funny: just the other day I clicked on a signature of a comment somewhere here and found an entire chinese mini netflix with even some movies in english with chin. subs - chicken & popcorn;)

  • @boxhan39 said:
    I have one instance from the last year sale. How can I cancel the service? it seems like there isn't button/option to cancel?

    Turn off auto renew and don’t renew when server time expires

  • @boxhan39 said:
    I have one instance from the last year sale. How can I cancel the service? it seems like there isn't button/option to cancel?

    Transfer it to me.

    Thanked by 2Falzo vr10
  • vr10vr10 Member

    @amsaal said:
    https://bero-host.de/customer/support/ticket/view/20972

    want to order Aniversery S , Please add , will do credits later .

    Been using bero host since 2019.

    Doesn't work that way son

  • itachikonohaitachikonoha Member
    edited October 10

    @vr10 said:

    @amsaal said:
    https://bero-host.de/customer/support/ticket/view/20972

    want to order Aniversery S , Please add , will do credits later .

    Been using bero host since 2019.

    Doesn't work that way son

    Actually that was one of the usual procedure. Berohost used to give 3 days trial period and then if you want to keep, just pay the amount and keep it or let it expire.

  • vr10vr10 Member

    @itachikonoha said:

    @vr10 said:

    @amsaal said:
    https://bero-host.de/customer/support/ticket/view/20972

    want to order Aniversery S , Please add , will do credits later .

    Been using bero host since 2019.

    Doesn't work that way son

    Actually that was one of the usual procedure. Berohost used to give 3 days trial period and then if you want to keep, just pay the amount and keep it or let it expire.

    Yes, but that's when Bero was unknown and it's always been a pre-paid service.

    Thanked by 1itachikonoha
  • @boxhan39 said:
    I have one instance from the last year sale. How can I cancel the service? it seems like there isn't button/option to cancel?

    id take it

  • # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #                  Windows-Yet-Bench-Script                   #
    #                       v2026-07-03-win                       #
    #  https://github.com/TeYroXOfficial/windows-yet-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    Thu Oct 08 
    
    Basic System Information:
    ---------------------------------
    Uptime     : x days, 18 hours, 39 minutes
    Processor  : AMD EPYC 9575F 64-Core Processor
    CPU cores  : 4 @ 3300 MHz
    VM-x/AMD-V : ✔ Enabled
    RAM        : 20.0 GiB
    Swap       : 3.0 GiB
    Disk       : 198.9 GiB
    Distro     : Microsoft Windows Server 2025 
    Kernel     : 10.0.26100 Build 26100
    VM Type    : KVM
    IPv4/IPv6  : ✔ Online / ✔ Online
    
    IPv6 Network Information:
    ---------------------------------
    ISP        : Oliver Horscht is trading as "SYNLINQ"
    ASN        : AS44486 synlinq.de
    Host       : Rubv6
    Location   : Frankfurt am Main, Hesse (HE)
    Country    : Germany
    
    fio Disk Speed Tests (Mixed R/W 50/50) (Partition C:):
    ---------------------------------
    Block Size | 4k          |   (IOPS) | 64k         |   (IOPS)
      ------   | ---         |    ----  | ----        |    ----
    Read       | 315.07 MB/s |  (76.9k) | 3.16 GB/s   |  (48.3k)
    Write      | 315.90 MB/s |  (77.1k) | 3.18 GB/s   |  (48.5k)
    Total      | 630.96 MB/s | (154.0k) | 6.34 GB/s   |  (96.8k)
    
    Block Size | 512k        |   (IOPS) | 1m          |   (IOPS)
      ------   | ---         |    ----  | ----        |    ----
    Read       | 6.66 GB/s   |  (12.7k) | 6.08 GB/s   |   (5.8k)
    Write      | 7.02 GB/s   |  (13.4k) | 6.48 GB/s   |   (6.2k)
    Total      | 13.68 GB/s  |  (26.1k) | 12.56 GB/s  |  (12.0k)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
    -----           | -----                     | ----            | ----            | ----
    Clouvider       | London, UK (10G)          | 3.53 Gbits/sec  | 4.76 Gbits/sec  | 12.0 ms
    Eranium         | Amsterdam, NL (100G)      | 3.80 Gbits/sec  | 4.92 Gbits/sec  | 7.0 ms
    Uztelecom       | Tashkent, UZ (10G)        | 796 Mbits/sec   | 4.03 Gbits/sec  | 78.0 ms
    Leaseweb        | Singapore, SG (10G)       | 572 Mbits/sec   | 3.09 Gbits/sec  | 157.0 ms
    Clouvider       | Los Angeles, CA, US (10G) | 15.7 Mbits/sec  | 1.20 Gbits/sec  | 144.0 ms
    Leaseweb        | NYC, NY, US (10G)         | 617 Mbits/sec   | 3.79 Gbits/sec  | 85.0 ms
    Edgoo           | Sao Paulo, BR (1G)        | 275 Mbits/sec   | 1.48 Gbits/sec  | 195.0 ms
    
    iperf3 Network Speed Tests (IPv6):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
    -----           | -----                     | ----            | ----            | ----
    Clouvider       | London, UK (10G)          | 2.73 Gbits/sec  | 4.76 Gbits/sec  | 13.0 ms
    Eranium         | Amsterdam, NL (100G)      | 3.83 Gbits/sec  | 4.84 Gbits/sec  | 6.0 ms
    Uztelecom       | Tashkent, UZ (10G)        | 794 Mbits/sec   | 2.84 Gbits/sec  | 88.0 ms
    Leaseweb        | Singapore, SG (10G)       | 408 Mbits/sec   | 1.36 Gbits/sec  | 158.0 ms
    Clouvider       | Los Angeles, CA, US (10G) | 371 Mbits/sec   | 1.42 Gbits/sec  | 147.0 ms
    Leaseweb        | NYC, NY, US (10G)         | 436 Mbits/sec   | 4.39 Gbits/sec  | 82.0 ms
    Edgoo           | Sao Paulo, BR (1G)        | 189 Mbits/sec   | 1.60 Gbits/sec  | 189.0 ms
    Geekbench 6 Benchmark Test:
    ---------------------------------
    Test            | Value
                    |
    Single Core     | 2135
    Multi Core      | 6770
    
    WYBS completed in 14 min 45 sec
    

    #

    Prepended http:// to 'yabs.sh'
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #              Yet-Another-Bench-Script              #
    #                     v2026-10-07                    #
    # https://github.com/masonr/yet-another-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    Sat Oct 10 18:06:09 UTC 2026
    
    Basic System Information:
    ---------------------------------
    Uptime     : 0 days, 0 hours, 10 minutes
    Processor  : AMD EPYC 9575F 64-Core Processor
    CPU cores  : 1 @ 4099.992 MHz
    AES-NI     : ✔ Enabled
    VM-x/AMD-V : ✔ Enabled
    RAM        : 1.9 GiB
    Swap       : 0.0 KiB
    Disk       : 19.6 GiB
    Distro     : Debian GNU/Linux 13 (trixie)
    Kernel     : 6.12.111+deb13-amd64
    VM Type    : KVM
    IPv4/IPv6  : ✔ Online / ✔ Online
    
    IPv6 Network Information:
    ---------------------------------
    ISP        : Oliver Horscht is trading as \"SYNLINQ\"
    ASN        : AS44486 synlinq.de
    Host       : Rubv6
    Location   : Frankfurt am Main, Hesse (HE)
    Country    : Germany
    
    fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/sda1):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 466.33 MB/s (113.8k) | 4.40 GB/s    (67.2k)
    Write      | 467.56 MB/s (114.1k) | 4.43 GB/s    (67.6k)
    Total      | 933.89 MB/s (228.0k) | 8.83 GB/s   (134.8k)
               |                      |
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 9.50 GB/s    (18.1k) | 4.94 GB/s     (4.7k)
    Write      | 10.01 GB/s   (19.1k) | 5.27 GB/s     (5.0k)
    Total      | 19.52 GB/s   (37.2k) | 10.22 GB/s    (9.7k)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
    -----           | -----                     | ----            | ----            | ----
    Clouvider       | London, UK (10G)          | 2.19 Gbits/sec  | 4.86 Gbits/sec  | 11.8 ms
    Eranium         | Amsterdam, NL (100G)      | 3.04 Gbits/sec  | 4.90 Gbits/sec  | 7.70 ms
    Uztelecom       | Tashkent, UZ (10G)        | 378 Mbits/sec   | 2.09 Gbits/sec  | 93.7 ms
    Leaseweb        | Singapore, SG (10G)       | 600 Mbits/sec   | 1.37 Gbits/sec  | 156 ms
    Clouvider       | Los Angeles, CA, US (10G) | 547 Mbits/sec   | 1.29 Gbits/sec  | 156 ms
    Leaseweb        | NYC, NY, US (10G)         | 917 Mbits/sec   | 2.92 Gbits/sec  | 89.4 ms
    Edgoo           | Sao Paulo, BR (1G)        | 501 Mbits/sec   | 840 Mbits/sec   | 217 ms
    
    iperf3 Network Speed Tests (IPv6):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
    -----           | -----                     | ----            | ----            | ----
    Clouvider       | London, UK (10G)          | 2.29 Gbits/sec  | 4.81 Gbits/sec  | 14.4 ms
    Eranium         | Amsterdam, NL (100G)      | 3.03 Gbits/sec  | 4.84 Gbits/sec  | 6.88 ms
    Uztelecom       | Tashkent, UZ (10G)        | 410 Mbits/sec   | 1.82 Gbits/sec  | 93.6 ms
    Leaseweb        | Singapore, SG (10G)       | 506 Mbits/sec   | 1.23 Gbits/sec  | 158 ms
    Clouvider       | Los Angeles, CA, US (10G) | 534 Mbits/sec   | 1.40 Gbits/sec  | 151 ms
    Leaseweb        | NYC, NY, US (10G)         | 513 Mbits/sec   | 2.59 Gbits/sec  | 82.2 ms
    Edgoo           | Sao Paulo, BR (1G)        | 387 Mbits/sec   | 954 Mbits/sec   | 189 ms
    
    Geekbench 6 Benchmark Test:
    ---------------------------------
    Test            | Value
                    |
    Single Core     | 2182
    Multi Core      | 2187
    
    YABS completed in 14 min 56 sec
    
    Thanked by 1Gr1t
  • @abitstack said:

    @abitstack said:

    @berohost said:
    We're working on restocking. However, due to network restructuring, ...

    Thanks for taking this seriously

    Things are getting better: pings between 2 of my servers are stabilizing at < 0.2ms right now with fewer and smaller outliers in between. The others are still flaky, although a bit better. All of them are on the same subnet. Also the disks on the 2 machines are back to normal, less so on the others, but somewhat better. Fingers crossed things get ironed out after Sunday.

    btw. getting consistent ! sub 0.2ms vm-vm rtt latency inside a hypervisor would already be pretty good on such massive slabs of flat L2 network, from there on its more of a host tuning thing (proxmox, nics offload, IRQs ..) and avoiding overload

    A quick update - TL;DR: nothing changed really so far.
    There seems to be more load - pings and disks got a bit worse (~ 10-20%)
    Tried a production dry run with mirrored traffic - things start ok and fall apart pretty quickly with drops up to 80% - sustained average is around 50% of the old machines (basically same hardware - they are going still well, just net isn't as good as it used to be until last week). There is no particular strain on any component - the pattern is not too heavy on net or disk, maybe a but cpu, but not maxing out). The tail latencies are really bad, so idk. Occasionally performance gets on par with the old cluster, there is hope ...

    Thanked by 1Gr1t
  • berohostberohost Member, Patron Provider

    @abitstack said:

    @abitstack said:

    @abitstack said:

    @berohost said:
    We're working on restocking. However, due to network restructuring, ...

    Thanks for taking this seriously

    Things are getting better: pings between 2 of my servers are stabilizing at < 0.2ms right now with fewer and smaller outliers in between. The others are still flaky, although a bit better. All of them are on the same subnet. Also the disks on the 2 machines are back to normal, less so on the others, but somewhat better. Fingers crossed things get ironed out after Sunday.

    btw. getting consistent ! sub 0.2ms vm-vm rtt latency inside a hypervisor would already be pretty good on such massive slabs of flat L2 network, from there on its more of a host tuning thing (proxmox, nics offload, IRQs ..) and avoiding overload

    A quick update - TL;DR: nothing changed really so far.
    There seems to be more load - pings and disks got a bit worse (~ 10-20%)
    Tried a production dry run with mirrored traffic - things start ok and fall apart pretty quickly with drops up to 80% - sustained average is around 50% of the old machines (basically same hardware - they are going still well, just net isn't as good as it used to be until last week). There is no particular strain on any component - the pattern is not too heavy on net or disk, maybe a but cpu, but not maxing out). The tail latencies are really bad, so idk. Occasionally performance gets on par with the old cluster, there is hope ...

    Have you opened a ticket about this yet?

  • @hyperblast said:

    Geekbench 6 Benchmark Test:
    ---------------------------------
    Test            | Value
                    |
    Single Core     | 2135
    Multi Core      | 6770
    
    WYBS completed in 14 min 45 sec
    

    dropped to this low already...?

  • yyzlongyyzlong Member

    @berohost Quick question on the Anniversary M (49€/yr EPYC plan): the Anniversary page says "Prepaid Linux KVM Rootserver" — can Windows Server be installed on it (via your Windows templates or own ISO), or is it Linux-only? Thanks!

  • @yyzlong said:
    @berohost Quick question on the Anniversary M (49€/yr EPYC plan): the Anniversary page says "Prepaid Linux KVM Rootserver" — can Windows Server be installed on it (via your Windows templates or own ISO), or is it Linux-only? Thanks!

    All Berohost vps be it Linux root or Linux vps or ryzen have windows template and it can be installed (I have installed in all of them as customer)

  • abitstackabitstack Member
    edited 7:47AM

    @berohost said:

    @abitstack said:

    @abitstack said:

    @abitstack said:

    @berohost said:
    We're working on restocking. However, due to network restructuring, ...

    Thanks for taking this seriously

    Things are getting better: pings between 2 of my servers are stabilizing at < 0.2ms right now with fewer and smaller outliers in between. The others are still flaky, although a bit better. All of them are on the same subnet. Also the disks on the 2 machines are back to normal, less so on the others, but somewhat better. Fingers crossed things get ironed out after Sunday.

    btw. getting consistent ! sub 0.2ms vm-vm rtt latency inside a hypervisor would already be pretty good on such massive slabs of flat L2 network, from there on its more of a host tuning thing (proxmox, nics offload, IRQs ..) and avoiding overload

    A quick update - TL;DR: nothing changed really so far.
    There seems to be more load - pings and disks got a bit worse (~ 10-20%)
    Tried a production dry run with mirrored traffic - things start ok and fall apart pretty quickly with drops up to 80% - sustained average is around 50% of the old machines (basically same hardware - they are going still well, just net isn't as good as it used to be until last week). There is no particular strain on any component - the pattern is not too heavy on net or disk, maybe a but cpu, but not maxing out). The tail latencies are really bad, so idk. Occasionally performance gets on par with the old cluster, there is hope ...

    Have you opened a ticket about this yet?

    No, since you asked for patience I thought you were still working on it

  • berohostberohost Member, Patron Provider

    @abitstack said:

    @berohost said:

    @abitstack said:

    @abitstack said:

    @abitstack said:

    @berohost said:
    We're working on restocking. However, due to network restructuring, ...

    Thanks for taking this seriously

    Things are getting better: pings between 2 of my servers are stabilizing at < 0.2ms right now with fewer and smaller outliers in between. The others are still flaky, although a bit better. All of them are on the same subnet. Also the disks on the 2 machines are back to normal, less so on the others, but somewhat better. Fingers crossed things get ironed out after Sunday.

    btw. getting consistent ! sub 0.2ms vm-vm rtt latency inside a hypervisor would already be pretty good on such massive slabs of flat L2 network, from there on its more of a host tuning thing (proxmox, nics offload, IRQs ..) and avoiding overload

    A quick update - TL;DR: nothing changed really so far.
    There seems to be more load - pings and disks got a bit worse (~ 10-20%)
    Tried a production dry run with mirrored traffic - things start ok and fall apart pretty quickly with drops up to 80% - sustained average is around 50% of the old machines (basically same hardware - they are going still well, just net isn't as good as it used to be until last week). There is no particular strain on any component - the pattern is not too heavy on net or disk, maybe a but cpu, but not maxing out). The tail latencies are really bad, so idk. Occasionally performance gets on par with the old cluster, there is hope ...

    Have you opened a ticket about this yet?

    No, since you asked for patience I thought you were still working on it

    Please create a ticket regarding this. We'll be happy to look into it for you.

  • berohostberohost Member, Patron Provider

    We plan to restock the Ryzen VPS (very limited quantity) around 10:45 a.m. today.
    We will restock the EPYC VPS around 11:45 a.m. today.

    IPv6 Only will not be restocked.

    All times are in the German time zone.

  • berohostberohost Member, Patron Provider

    EPYC VPS will be restocked in about 1 hour

  • @berohost said:
    EPYC VPS will be restocked in about 1 hour

    Will it be possible to instease storage in let's say anniversary M?

  • berohostberohost Member, Patron Provider

    @itachikonoha said:

    @berohost said:
    EPYC VPS will be restocked in about 1 hour

    Will it be possible to instease storage in let's say anniversary M?

    Yes, you can upgrade your storage space after placing your order.

  • networknetwork Member

    @berohost said:

    @itachikonoha said:

    @berohost said:
    EPYC VPS will be restocked in about 1 hour

    Will it be possible to instease storage in let's say anniversary M?

    Yes, you can upgrade your storage space after placing your order.

    What's the price for that?

  • berohostberohost Member, Patron Provider

    @network said:

    @berohost said:

    @itachikonoha said:

    @berohost said:
    EPYC VPS will be restocked in about 1 hour

    Will it be possible to instease storage in let's say anniversary M?

    Yes, you can upgrade your storage space after placing your order.

    What's the price for that?

    100 GB NVMe costs 2 euros per month (or 20 euros per year if paid annually)

    Thanked by 1network
  • berohostberohost Member, Patron Provider

    EPYC VPS is now back in stock

  • opnnetopnnet Member

    Thanks Just ordered XD.

  • powderedpowdered Member

    site's acting really slow

Sign In or Register to comment.