Howdy, Stranger!

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


The most popular KVM servers in Romania on LET
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.

The most popular KVM servers in Romania on LET

FlorinMarianFlorinMarian Member, Host Rep

Hello, darling!

If you are looking for VPS servers with AntiDDoS Voxility or OVH Game protection, with enough hardware resources without overselling that can be paid for with cryptocurrencies, thus preserving your identity, you are in the right place.

What's new this time?

  • We no longer have packages that annually cost the equivalent of a coffee at a gas station (We do not miss the abuses)
  • All VPS servers have a dedicated physical Thread for each vCPU
  • A new profile picture from the holiday in Bulgaria

Without further ado, these are our currently available offers:

2vCPU - 4GB RAM - 120GB SSD Enterprise

  • Location: Romania
  • Starting from €7.49 Euro Monthly (Configurable)
  • CPU E5-2699 V3
  • CPU Speed 2.30GHz ↗ 3.60GHz
  • Memory DDR4 ECC 2133MHz
  • Storage SSD Samsung PM893 Enterprise
  • Network 1Gbps (Shared)
  • AntiDDoS Voxility 1Tbps
  • Order it here

2vCPU - 4GB RAM - 500GB SATA RAID10 Enterprise

  • Location: Romania
  • Starting from €7.49 Euro Monthly (Configurable)
  • CPU E5-2698 V3
  • CPU Speed 2.30GHz ↗ 3.60GHz
  • Memory DDR4 ECC 2133MHz
  • Storage SATA 7200RPM Enterprise
  • Network 1Gbps (shared)
  • AntiDDoS Voxility 1Tbps
  • Order it here

2vCPU - 4GB RAM - 40GB SSD NVMe Enterprise

  • Location: Germany
  • Starting from €9.99 Euro Monthly (Configurable)
  • CPU AMD Ryzen 7 3800X
  • CPU Speed 3.90GHz ↗ 4.50GHz
  • Memory DDR4 2666MHz
  • Storage SSD NVMe SAMSUNG PM983 Enterprise
  • Network 1Gbps (Shared)
  • AntiDDoS OVH Game
  • Order it here

Included With Every Plan

  • Integrated Control Panel
  • KVM Virtualization
  • Root Access
  • Free Technical Support
  • Custom ISO accepted
  • 1-Click Reinstall

Operating Systems:

  • CentOS 7 64bits
  • CentOS 8 64bits
  • CentOS 9 64bits
  • Debian 9 64bits
  • Debian 10 64bits
  • Debian 11 64bits
  • Ubuntu 18.04 64bits
  • Ubuntu 20.04 64bits
  • Ubuntu 22.04 64bits
  • FreeBSD 12.x 32bits
  • FreeBSD 12.x 64bits
  • FreeBSD 13.x 32bits
  • FreeBSD 13.x 64bits

Useful information:

Accepted payment methods:

  • MobilPay (Visa / Maestro / Mastercard)
  • Paysafecard
  • Bitcoin
  • Ethereum
  • USD Coin
  • Dogecoin
  • Litecoin
  • Dai
  • Bitcoin Cash
  • Bank Transfer
Thanked by 1miu
«1

Comments

  • @FlorinMarian said: A new profile picture from the holiday in Bulgaria

    That must be massive improvement on your vps

    Thanked by 2yoursunny brejski
  • FlorinMarianFlorinMarian Member, Host Rep

    @add_iT said:

    @FlorinMarian said: A new profile picture from the holiday in Bulgaria

    That must be massive improvement on your vps

    Yes, since another provider in Romania had wooden racks, we thought of testing an underwater rack prototype.

  • miumiu Member

    @FlorinMarian said:
    What's new this time?

    • A new profile picture from the holiday in Bulgaria

    And not only this.. Also (i assume) you are probably most frequently profile photo changing provider on LET! :+1:

  • miumiu Member
    edited August 2022

    So:

    • The most popular KVM servers in Romania on LET (btw: i do not know about other active RO provider here nowadays, so sure i can agree)
    • The most frequently profile photo changing provider on LET

    We are looking fwd for Autumn and then Winter photos

    In every case, good sale i wish (seems, you growing in these difficult times = praiseworthy, good work)

    And can you post yabs of SATA500 plan pls? thanks

    Thanked by 1FlorinMarian
  • Not_OlesNot_Oles Moderator, Patron Provider

    Hi @FlorinMarian ! Congrats and good luck! 👍

    Thanked by 1FlorinMarian
  • yoursunnyyoursunny Member, IPv6 Advocate
    • Clueless™ administrator! 😀 Florin frequently messes up! 😱
    • Hey! There is no native IPv6! 🤩
    • You will get sudo within your VPS. 🙈🙉🙊
    • Delivery might take a second! 😴
    • No warranty, to the extent permitted by applicable law. No refunds. Not for business use. Intended especially for computer learning and fun! 🤑
    • White Hat stuff only, please! No copyright violations, please. 👍
    • Florin tries to keep the network secured. Frequent firewall mitigations are guaranteed! It's horrifying 😱 or amazing ✨💖✨ how fast-reactions the IPS/IDS is! You start a SYN flood, and -- within a minute or two -- that attack scrolls past while Intrusion Prevention System is kicking in.
    • Please make your own redundant, offsite backups! It's easy to download or sync or clone your backup to a safe place. Please also make sure that you actually can restore from your backups! Please think of your HAZI account as ephemeral! 🤦‍♂️
    • HAZI is an indie project of Florin with help from his awesome brothers. HAZI is neither a lowendtalk.com nor an OVH project. 👨‍💻​
    • Other pool swimmers can see your sunglasses, your smile and grin, and much other information. So, please do not put confidential information on the server. 🤔
  • @yoursunny said:​

    • Other pool swimmers can see your sunglasses, your smile and grin, and much other information. So, please do not put confidential information on the server. 🤔

    If i put pictures of me topless wearing assless chaps, someone will finally recognize me?

    Thanked by 2dahartigan bulbasaur
  • FlorinMarianFlorinMarian Member, Host Rep

    @miu said:
    So:

    • The most popular KVM servers in Romania on LET (btw: i do not know about other active RO provider here nowadays, so sure i can agree)
    • The most frequently profile photo changing provider on LET

    We are looking fwd for Autumn and then Winter photos

    In every case, good sale i wish (seems, you growing in these difficult times = praiseworthy, good work)

    And can you post yabs of SATA500 plan pls? thanks

    Sorry for being late.

    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #              Yet-Another-Bench-Script              #
    #                     v2022-08-20                    #
    # https://github.com/masonr/yet-another-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    Sat Aug 27 16:45:33 EDT 2022
    
    Basic System Information:
    ---------------------------------
    Uptime     : 0 days, 0 hours, 0 minutes
    Processor  : Intel Core Processor (Haswell, no TSX)
    CPU cores  : 2 @ 2299.998 MHz
    AES-NI     : ✔ Enabled
    VM-x/AMD-V : ❌ Disabled
    RAM        : 3.6 GiB
    Swap       : 0.0 KiB
    Disk       : 500.0 GiB
    Distro     : CentOS Stream 9
    Kernel     : 5.14.0-0.rc7.54.el9.x86_64
    
    fio Disk Speed Tests (Mixed R/W 50/50):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ---- 
    Read       | 39.93 MB/s    (9.9k) | 591.02 MB/s   (9.2k)
    Write      | 40.00 MB/s   (10.0k) | 594.13 MB/s   (9.2k)
    Total      | 79.93 MB/s   (19.9k) | 1.18 GB/s    (18.5k)
               |                      |                     
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ---- 
    Read       | 3.49 GB/s     (6.8k) | 4.52 GB/s     (4.4k)
    Write      | 3.68 GB/s     (7.1k) | 4.82 GB/s     (4.7k)
    Total      | 7.18 GB/s    (14.0k) | 9.34 GB/s     (9.1k)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed     
                    |                           |                 |                
    Clouvider       | London, UK (10G)          | 617 Mbits/sec   | 809 Mbits/sec  
    Online.net      | Paris, FR (10G)           | 679 Mbits/sec   | 806 Mbits/sec  
    Hybula          | The Netherlands (40G)     | 664 Mbits/sec   | 769 Mbits/sec  
    Uztelecom       | Tashkent, UZ (10G)        | 398 Mbits/sec   | 509 Mbits/sec  
    Clouvider       | NYC, NY, US (10G)         | 502 Mbits/sec   | 718 Mbits/sec  
    Clouvider       | Dallas, TX, US (10G)      | 384 Mbits/sec   | 634 Mbits/sec  
    Clouvider       | Los Angeles, CA, US (10G) | 367 Mbits/sec   | 643 Mbits/sec  
    
    Geekbench 5 Benchmark Test:
    ---------------------------------
    Test            | Value                         
                    |                               
    Single Core     | 267                           
    Multi Core      | 525                           
    Full Test       | https://browser.geekbench.com/v5/cpu/16911101
    

    GB5 score is quite low but it's caused by that we don't run 24/24 with vCPUs in Performance Mode but in Power Save at least 2 more months when tens of VMs will leave our node.
    Best regards, Florin.

    Thanked by 1miu
  • miumiu Member

    @FlorinMarian said:

    Geekbench 5 Benchmark Test:

    Test | Value
    |
    Single Core | 267
    Multi Core | 525
    Full Test | https://browser.geekbench.com/v5/cpu/16911101
    ```

    GB5 score is quite low but it's caused by that we don't run 24/24 with vCPUs in Performance Mode but in Power Save at least 2 more months when tens of VMs will leave our node.
    Best regards, Florin.

    I guess this VPS is running on PVE node (according to high VM disk I/O => thanks to ZFS R10 caching utilizing of RAM).

    May i ask what number do you have set for this VM in "CPU Units"? ~300-400?

    From my experiences CPU scaling governor set in powersafe mode does not very affect peak performance in high load situations: When server is idling (load low), then this mode cause that CPU clock is strictly decreased down and saving power by this way. But: When high CPU load come (for example when GB5 begin), then nowadays CPUs very fast raise / switch their clock to max and give nearly performance as in permanent performance mode do (when governor is set in performance mode and CPU keep high clocking whole time mandatory, when i good remember, i measured difference in performance around only ~3-5% between these two mentioned cpu modes). So i assume that low GB5 score (for E5-2698 i would be expecting something ~650-700 per thread) is caused that you hard limit its CPU threads in hypervisor, not by fact that host/node OS is running in powersafe CPU governor mode

    Thanked by 1Not_Oles
  • FlorinMarianFlorinMarian Member, Host Rep

    @miu said:

    @FlorinMarian said:

    Geekbench 5 Benchmark Test:

    Test | Value
    |
    Single Core | 267
    Multi Core | 525
    Full Test | https://browser.geekbench.com/v5/cpu/16911101
    ```

    GB5 score is quite low but it's caused by that we don't run 24/24 with vCPUs in Performance Mode but in Power Save at least 2 more months when tens of VMs will leave our node.
    Best regards, Florin.

    I guess this VPS is running on PVE node (according to high VM disk I/O => thanks to ZFS R10 caching utilizing of RAM).

    May i ask what number do you have set for this VM in "CPU Units"? ~300-400?

    From my experiences CPU scaling governor set in powersafe mode does not very affect peak performance in high load situations: When server is idling (load low), then this mode cause that CPU clock is strictly decreased down and saving power by this way. But: When high CPU load come (for example when GB5 begin), then nowadays CPUs very fast raise / switch their clock to max and give nearly performance as in permanent performance mode do (when governor is set in performance mode and CPU keep high clocking whole time mandatory, when i good remember, i measured difference in performance around only ~3-5% between these two mentioned cpu modes). So i assume that low GB5 score (for E5-2698 i would be expecting something ~650-700 per thread) is caused that you hard limit its CPU threads in hypervisor, not by fact that host/node OS is running in powersafe CPU governor mode

    All our VMs have priority 1024, so there are no differences between them.
    I would like to prove you right, but practice won't let me.
    Look, just by switching from "powersave" -> "ondemand" the score increased by 41%. We will not switch to Performance mode at the moment because it would double the energy consumption (already very high because the server is 1U, with 16 drives: 12x 3.5" + 4x 2.5") and has coolers that run permanently at over 10,000 rpm.

    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #              Yet-Another-Bench-Script              #
    #                     v2022-08-20                    #
    # https://github.com/masonr/yet-another-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    Sun Aug 28 02:40:29 AM EDT 2022
    
    Basic System Information:
    ---------------------------------
    Uptime     : 0 days, 0 hours, 0 minutes
    Processor  : Intel Core Processor (Haswell, no TSX)
    CPU cores  : 2 @ 2299.998 MHz
    AES-NI     : ✔ Enabled
    VM-x/AMD-V : ❌ Disabled
    RAM        : 3.6 GiB
    Swap       : 0.0 KiB
    Disk       : 500.0 GiB
    Distro     : CentOS Stream 9
    Kernel     : 5.14.0-0.rc7.54.el9.x86_64
    
    fio Disk Speed Tests (Mixed R/W 50/50):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 61.49 MB/s   (15.3k) | 881.80 MB/s  (13.7k)
    Write      | 61.61 MB/s   (15.4k) | 886.44 MB/s  (13.8k)
    Total      | 123.10 MB/s  (30.7k) | 1.76 GB/s    (27.6k)
               |                      |
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 4.32 GB/s     (8.4k) | 5.03 GB/s     (4.9k)
    Write      | 4.55 GB/s     (8.9k) | 5.37 GB/s     (5.2k)
    Total      | 8.88 GB/s    (17.3k) | 10.40 GB/s   (10.1k)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed
                    |                           |                 |
    Clouvider       | London, UK (10G)          | 720 Mbits/sec   | 832 Mbits/sec
    Online.net      | Paris, FR (10G)           | 557 Mbits/sec   | 828 Mbits/sec
    Hybula          | The Netherlands (40G)     | 686 Mbits/sec   | 777 Mbits/sec
    Uztelecom       | Tashkent, UZ (10G)        | 262 Mbits/sec   | 626 Mbits/sec
    Clouvider       | NYC, NY, US (10G)         | 515 Mbits/sec   | 632 Mbits/sec
    Clouvider       | Dallas, TX, US (10G)      | 392 Mbits/sec   | 319 Mbits/sec
    Clouvider       | Los Angeles, CA, US (10G) | 338 Mbits/sec   | 476 Mbits/sec
    
    Geekbench 5 Benchmark Test:
    ---------------------------------
    Test            | Value
                    |
    Single Core     | 377
    Multi Core      | 747
    Full Test       | https://browser.geekbench.com/v5/cpu/16917935
    
    
    Thanked by 1miu
  • yoursunnyyoursunny Member, IPv6 Advocate

    @FlorinMarian said:
    Look, just by switching from "powersave" -> "ondemand" the score increased by 41%. We will not switch to Performance mode

    • powersave: always run at lowest possible frequency, severely affecting performance, only useful in a laptop when it's almost out of battery
    • performance: always run at highest possible frequency, wasting energy for no reason, unless you are running an industrial control system that requires predictable performance
    • ondemand (and many others): dynamically adjust frequency according to workload, usually the best choice
  • FlorinMarianFlorinMarian Member, Host Rep

    @yoursunny said:

    @FlorinMarian said:
    Look, just by switching from "powersave" -> "ondemand" the score increased by 41%. We will not switch to Performance mode

    • powersave: always run at lowest possible frequency, severely affecting performance, only useful in a laptop when it's almost out of battery
    • performance: always run at highest possible frequency, wasting energy for no reason, unless you are running an industrial control system that requires predictable performance
    • ondemand (and many others): dynamically adjust frequency according to workload, usually the best choice

    My brother is always right, even if it doesn't work to my advantage all the time :)

    Thanked by 2yoursunny Erisa
  • Should a hypervisor be ran on anything BUT performance mode? I know ESXi documentation says to disable power save functionality.

    I mean, a score of 377 is hot garbage.

    All our VMs have priority 1024, so there are no differences between them.

    Lastly, threads are not equal, so I wouldn't expect equivalent performance across threads, especially with powersave features enabled.

  • @FlorinMarian said: Single Core | 267

    Multi Core | 525

    finally! a worthy opponent for the KS-1

    Thanked by 4miu mhn ralf netomx
  • RadiRadi Host Rep, Veteran

    Where were you in Bulgaria on holiday? Just curious.

  • FlorinMarianFlorinMarian Member, Host Rep

    @Radi said:
    Where were you in Bulgaria on holiday? Just curious.

    Golden Sands

  • FlorinMarianFlorinMarian Member, Host Rep

    Since we gave up the location in France, we have for rent our old dedicated server which is a GAME-3, with 16 failover IP addresses included and 1Gbps Inbound/Outbound bandwidth even if the theoretical server should only have 250Mbps.

    We offer access for server management directly from our WHMCS interface and you have the great advantage that you can also pay with cryptocurrencies for this server.

    The asking price is 60 euros/month.

    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #              Yet-Another-Bench-Script              #
    #                     v2022-08-20                    #
    # https://github.com/masonr/yet-another-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    luni 29 august 2022, 09:38:20 +0300
    
    Basic System Information:
    ---------------------------------
    Uptime     : 330 days, 10 hours, 19 minutes
    Processor  : Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
    CPU cores  : 8 @ 4013.899 MHz
    AES-NI     : ✔ Enabled
    VM-x/AMD-V : ✔ Enabled
    RAM        : 62.7 GiB
    Swap       : 0.0 KiB
    Disk       : 438.9 GiB
    Distro     : Debian GNU/Linux 10 (buster)
    Kernel     : 5.4.140-1-pve
    
    fio Disk Speed Tests (Mixed R/W 50/50):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ---- 
    Read       | 146.78 MB/s  (36.6k) | 175.91 MB/s   (2.7k)
    Write      | 147.17 MB/s  (36.7k) | 176.84 MB/s   (2.7k)
    Total      | 293.96 MB/s  (73.4k) | 352.75 MB/s   (5.5k)
               |                      |                     
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ---- 
    Read       | 212.37 MB/s    (414) | 203.75 MB/s    (198)
    Write      | 223.66 MB/s    (436) | 217.32 MB/s    (212)
    Total      | 436.04 MB/s    (850) | 421.07 MB/s    (410)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed     
                    |                           |                 |                
    Clouvider       | London, UK (10G)          | 919 Mbits/sec   | 528 Mbits/sec  
    Online.net      | Paris, FR (10G)           | 908 Mbits/sec   | 536 Mbits/sec  
    Hybula          | The Netherlands (40G)     | 887 Mbits/sec   | 938 Mbits/sec  
    Uztelecom       | Tashkent, UZ (10G)        | 613 Mbits/sec   | 131 Mbits/sec  
    Clouvider       | NYC, NY, US (10G)         | 633 Mbits/sec   | 368 Mbits/sec  
    Clouvider       | Dallas, TX, US (10G)      | 510 Mbits/sec   | 80.6 Mbits/sec 
    Clouvider       | Los Angeles, CA, US (10G) | 491 Mbits/sec   | 239 Mbits/sec  
    
    Geekbench 5 Benchmark Test:
    ---------------------------------
    Test            | Value                         
                    |                               
    Single Core     | 1122                          
    Multi Core      | 4067                          
    Full Test       | https://browser.geekbench.com/v5/cpu/16938255
    
    
    Thanked by 1Zyra
  • mhnmhn Member

    @henix said: finally! a worthy opponent for the KS-1

    Not even close, costs more than a KS-1 with 1/4 the disk.

  • FlorinMarianFlorinMarian Member, Host Rep

    @mhn said:

    @henix said: finally! a worthy opponent for the KS-1

    Not even close, costs more than a KS-1 with 1/4 the disk.

    KS-1 also has 500GB (2TB only if you are lucky), the bandwidth is 10 times lower than with us, you cannot have additional IPv4 addresses while we offer up to 16 IP addresses, we do not charge the installation (10 euros + VAT if I'm not mistaken) and if you add VAT to the calculation, the difference is only 1.5 euros/month.
    Also, I don't think there's any point in talking about technical support at Kimsufi :)

  • @FlorinMarian said: KS-1 also has 500GB

    ks1 has 1tb normally, 2tb if you are lucky

  • FlorinMarianFlorinMarian Member, Host Rep

    @henix said:

    @FlorinMarian said: KS-1 also has 500GB

    ks1 has 1tb normally, 2tb if you are lucky

    I don't know why, but I had the impression that it was 500GB and it was not available on the website to check this information.
    Thanks for the correction

  • ralfralf Member

    @FlorinMarian said:

    @henix said:

    @FlorinMarian said: KS-1 also has 500GB

    ks1 has 1tb normally, 2tb if you are lucky

    I don't know why, but I had the impression that it was 500GB and it was not available on the website to check this information.
    Thanks for the correction

    That changed several years ago. The KS-1 is also only €5.99 per month and setup is €5.99, so the price of yours is the same as KS-1 after 3 months.

  • raindog308raindog308 Administrator, Veteran

    There is no comparison to the KS-1 because the KS-1 is a mythical unicorn that can never actually be ordered.

  • @raindog308 said:
    There is no comparison to the KS-1 because the KS-1 is a mythical unicorn that can never actually be ordered.

    Gravelines are in stock right now. :D

    Thanked by 1raindog308
  • @kasodk said:

    @raindog308 said:
    There is no comparison to the KS-1 because the KS-1 is a mythical unicorn that can never actually be ordered.

    Gravelines are in stock right now. :D

    this unicorn came too soon.

    Thanked by 1ralf
  • BHSBHS Member

    Down for Maintenance (Err 3)

  • FlorinMarianFlorinMarian Member, Host Rep

    @BHS said:
    Down for Maintenance (Err 3)

    Good evening!
    
    We are happy to announce that the problems that appeared approximately 48 hours ago on sv2.hazi.ro have been resolved and currently the performance of the server has not only returned to normal but has also increased because all the KVM SSD servers that were on sv2.hazi.ro were moved to sv4.hazi.ro, where there are only Enterprise SSDs.
    
    Thank you all for your patience and do not hesitate to ask for help if you find that you have problems.
    
    Yours, Florin.
    

    Proof of improvement:

    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #              Yet-Another-Bench-Script              #
    #                     v2022-08-20                    #
    # https://github.com/masonr/yet-another-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    Wed 31 Aug 2022 10:45:21 PM EEST
    
    Basic System Information:
    ---------------------------------
    Uptime     : 0 days, 0 hours, 1 minutes
    Processor  : Intel(R) Xeon(R) CPU E5-2698 v3 @ 2.30GHz
    CPU cores  : 64 @ 1200.000 MHz
    AES-NI     : ✔ Enabled
    VM-x/AMD-V : ✔ Enabled
    RAM        : 251.8 GiB
    Swap       : 0.0 KiB
    Disk       : 3.6 TiB
    Distro     : Debian GNU/Linux 11 (bullseye)
    Kernel     : 5.15.39-4-pve
    
    fio Disk Speed Tests (Mixed R/W 50/50):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 83.25 MB/s   (20.8k) | 2.85 GB/s    (44.5k)
    Write      | 83.47 MB/s   (20.8k) | 2.86 GB/s    (44.8k)
    Total      | 166.73 MB/s  (41.6k) | 5.72 GB/s    (89.4k)
               |                      |
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ----
    Read       | 3.27 GB/s     (6.3k) | 3.25 GB/s     (3.1k)
    Write      | 3.44 GB/s     (6.7k) | 3.46 GB/s     (3.3k)
    Total      | 6.72 GB/s    (13.1k) | 6.72 GB/s     (6.5k)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed
                    |                           |                 |
    Clouvider       | London, UK (10G)          | busy            | busy
    Online.net      | Paris, FR (10G)           | busy            | busy
    Hybula          | The Netherlands (40G)     | busy            | busy
    Uztelecom       | Tashkent, UZ (10G)        | busy            | busy
    Clouvider       | NYC, NY, US (10G)         | busy            | busy
    Clouvider       | Dallas, TX, US (10G)      | busy            | busy
    Clouvider       | Los Angeles, CA, US (10G) | busy            | busy
    
    Running GB5 benchmark test... *cue elevator music*
    Geekbench 5 Benchmark Test:
    ---------------------------------
    Test            | Value
                    |
    Single Core     | 738
    Multi Core      | 13495
    Full Test       | https://browser.geekbench.com/v5/cpu/16992170
    
    Thanked by 1BHS
  • ralfralf Member

    What was the problem and how did you resolve it?

  • FlorinMarianFlorinMarian Member, Host Rep

    @ralf said:
    What was the problem and how did you resolve it?

    At the beginning of July, I played a little through the BIOS and incorrectly adjusted the configurable parameters of the CPU in the performance/energy consumption ratio. With the settings I had, I had created a bottleneck that led to an energy consumption of 500W in a simple benchmark with YABS without the temperature rising too much.
    I realized the problem by following the current consumption during a YABS and I was very surprised to see that from 400W it suddenly dropped to 10W several times under the conditions that normally it would not consume below 250W at all.

  • FlorinMarianFlorinMarian Member, Host Rep

    Server number 4 had a small reboot to activate the tunnel through Route48.

    Any client that owns a KVM server with SSD storage can request an IPv6/64 block.

    Thank you all for your patience and interest!

    Thanked by 1yoursunny
Sign In or Register to comment.