Howdy, Stranger!

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

Sign In Register

Quick Links


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

Categories

In this Discussion

Home › Requests
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.

Hetzner alternative

13

Comments

  • remyremy Member

    Enabling swap with ceph storage can only lead to disappointing results :)

    Thanked by 2emgh MassiveGRID
  • MassiveGRIDMassiveGRID Member, Patron Provider

    @lukast__ said:
    @SashkaPro you could try to run Geekbench 4, its results are a lot better with <= 1 GB RAM.
    @MassiveGRID is the disk limited to 1000 IOPS?

    Yes, for VPS is limited to 1000 IOPS. For VDS to 4000 IOPS. We've seen that these limits are adequate for the majority of the scenarios and for the rest, we custom upgrade based on needs.

    This strategy allows for consistent and predictable performance, no sudden slow downs and busy neighbor problems.

    As we get more orders, we add more Nodes to our H/A Clusters allowing us to continue offering the consistent performance.

    Thanked by 2emgh lukast__
  • MassiveGRIDMassiveGRID Member, Patron Provider
    edited September 2024

    @remy said:
    Enabling swap with ceph storage can only lead to disappointing results :)

    Swap should be avoided in general. Even with the fastest, directly connected SSD, it's orders of magnitude (100-1000x) slower than RAM.

  • emghemgh Member, Megathread Squad
    edited September 2024

    @MassiveGRID said:

    @remy said:
    Enabling swap with ceph storage can only lead to disappointing results :)

    Swap should be avoided in general. Even with the fastest, directly connected SSD, it's orders of magnitude (100-1000x) slower than RAM.

    (Off-site, if possible) snapshots for some % extra of disk cost would be awesome.

    Thanked by 1MassiveGRID
  • MassiveGRIDMassiveGRID Member, Patron Provider

    @emgh said:

    @MassiveGRID said:

    @remy said:
    Enabling swap with ceph storage can only lead to disappointing results :)

    Swap should be avoided in general. Even with the fastest, directly connected SSD, it's orders of magnitude (100-1000x) slower than RAM.

    (Off-site, if possible) snapshots for some % extra of disk cost would be awesome.

    Absolutely! We're working on snapshots, backups and ability to attach more than 1 H/A SSD Disks in your server.

    Thanked by 1emgh
  • DrNutellaDrNutella Member

    @Arkas said:
    OVH is probably the closest. That doesn't mean it's as good, but as good as you'll get If you do not go with hetzner for whatever reason you may have.

    I agree. A cheap ARM will underperform a cheaper VPS. Just saying from experience with the awesome shit I got from @crunchbits - they got me hooked for life.

  • SashkaProSashkaPro Member

    Horray, 1C2G now:

    curl -sL yabs.sh | bash
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
#              Yet-Another-Bench-Script              #
#                     v2024-06-09                    #
# https://github.com/masonr/yet-another-bench-script #
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #

Sat Sep 28 17:24:23 UTC 2024

Basic System Information:
---------------------------------
Uptime     : 0 days, 0 hours, 0 minutes
Processor  : Intel(R) Xeon(R) CPU E5-2683 v4 @ 2.10GHz
CPU cores  : 1 @ 2099.998 MHz
AES-NI     : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM        : 1.7 GiB
Swap       : 4.0 GiB
Disk       : 27.4 GiB
Distro     : AlmaLinux 9.4 (Seafoam Ocelot)
Kernel     : 5.14.0-427.37.1.el9_4.x86_64
VM Type    : KVM
IPv4/IPv6  : ✔ Online / ❌ Offline

IPv4 Network Information:
---------------------------------
ISP        : Massivegrid LTD
ASN        : AS49683 MASSIVEGRID LTD
Host       : MassiveGRID
Location   : Frankfurt am Main, Hesse (HE)
Country    : Germany

fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/sda3):
---------------------------------
Block Size | 4k            (IOPS) | 64k           (IOPS)
  ------   | ---            ----  | ----           ----
Read       | 3.93 MB/s      (983) | 62.33 MB/s     (973)
Write      | 3.95 MB/s      (988) | 62.65 MB/s     (979)
Total      | 7.88 MB/s     (1.9k) | 124.98 MB/s   (1.9k)
           |                      |
Block Size | 512k          (IOPS) | 1m            (IOPS)
  ------   | ---            ----  | ----           ----
Read       | 141.46 MB/s    (276) | 143.33 MB/s    (139)
Write      | 148.98 MB/s    (290) | 152.87 MB/s    (149)
Total      | 290.44 MB/s    (566) | 296.20 MB/s    (288)

iperf3 Network Speed Tests (IPv4):
---------------------------------
Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
-----           | -----                     | ----            | ----            | ----
Clouvider       | London, UK (10G)          | 1.06 Gbits/sec  | 987 Mbits/sec   | 14.6 ms
Eranium         | Amsterdam, NL (100G)      | 1.06 Gbits/sec  | 1.00 Gbits/sec  | 7.33 ms
Uztelecom       | Tashkent, UZ (10G)        | 946 Mbits/sec   | 608 Mbits/sec   | 103 ms
Leaseweb        | Singapore, SG (10G)       | 721 Mbits/sec   | 555 Mbits/sec   | 247 ms
Clouvider       | Los Angeles, CA, US (10G) | 584 Mbits/sec   | 376 Mbits/sec   | 147 ms
Leaseweb        | NYC, NY, US (10G)         | 974 Mbits/sec   | 844 Mbits/sec   | 81.5 ms
Edgoo           | Sao Paulo, BR (1G)        | 751 Mbits/sec   | 448 Mbits/sec   | 203 ms

Geekbench 6 Benchmark Test:
---------------------------------
Test            | Value
                |
Single Core     | 630
Multi Core      | 641
Full Test       | https://browser.geekbench.com/v6/cpu/8028900

YABS completed in 22 min 24 sec
    Thanked by 2emgh maverick
  • WhiteRoseGWhiteRoseG Member

    Lol the yabs is way below Hetzer Cloud, it's not comparable. It's more like contabo except the line speed is decent

  • MassiveGRIDMassiveGRID Member, Patron Provider

    @WhiteRoseG said:
    Lol the yabs is way below Hetzer Cloud, it's not comparable. It's more like contabo except the line speed is decent

    Which yabs are you referring to? Is it with same resources CPU, RAM, etc in both cases?

  • emghemgh Member, Megathread Squad

    @WhiteRoseG said:
    Lol the yabs is way below Hetzer Cloud, it's not comparable. It's more like contabo except the line speed is decent

    About the same as CX, no?

    https://www.vpsbenchmarks.com/yabs/hetzner-2c-4gb-c8653d

    Starting at 1.11 bucks a month (a little more with 2GB RAM though, needed to properly run YABS and get a similar score)

    Thanked by 1MassiveGRID
  • emghemgh Member, Megathread Squad

    @MassiveGRID said:

    @WhiteRoseG said:
    Lol the yabs is way below Hetzer Cloud, it's not comparable. It's more like contabo except the line speed is decent

    Which yabs are you referring to? Is it with same resources CPU, RAM, etc in both cases?

    To be fair their CPU's on the CPX line are newer

    By the way, on the Contabo promo page it says that London is using Gold 6230 but on WHMCS it says E5-2683v4

  • MassiveGRIDMassiveGRID Member, Patron Provider

    @SashkaPro said:
    Horray, 1C2G now:

    curl -sL yabs.sh | bash
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
#              Yet-Another-Bench-Script              #
#                     v2024-06-09                    #
# https://github.com/masonr/yet-another-bench-script #
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #

Sat Sep 28 17:24:23 UTC 2024

Basic System Information:
---------------------------------
Uptime     : 0 days, 0 hours, 0 minutes
Processor  : Intel(R) Xeon(R) CPU E5-2683 v4 @ 2.10GHz
CPU cores  : 1 @ 2099.998 MHz
AES-NI     : ✔ Enabled
VM-x/AMD-V : ✔ Enabled
RAM        : 1.7 GiB
Swap       : 4.0 GiB
Disk       : 27.4 GiB
Distro     : AlmaLinux 9.4 (Seafoam Ocelot)
Kernel     : 5.14.0-427.37.1.el9_4.x86_64
VM Type    : KVM
IPv4/IPv6  : ✔ Online / ❌ Offline

IPv4 Network Information:
---------------------------------
ISP        : Massivegrid LTD
ASN        : AS49683 MASSIVEGRID LTD
Host       : MassiveGRID
Location   : Frankfurt am Main, Hesse (HE)
Country    : Germany

fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/sda3):
---------------------------------
Block Size | 4k            (IOPS) | 64k           (IOPS)
  ------   | ---            ----  | ----           ----
Read       | 3.93 MB/s      (983) | 62.33 MB/s     (973)
Write      | 3.95 MB/s      (988) | 62.65 MB/s     (979)
Total      | 7.88 MB/s     (1.9k) | 124.98 MB/s   (1.9k)
           |                      |
Block Size | 512k          (IOPS) | 1m            (IOPS)
  ------   | ---            ----  | ----           ----
Read       | 141.46 MB/s    (276) | 143.33 MB/s    (139)
Write      | 148.98 MB/s    (290) | 152.87 MB/s    (149)
Total      | 290.44 MB/s    (566) | 296.20 MB/s    (288)

iperf3 Network Speed Tests (IPv4):
---------------------------------
Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
-----           | -----                     | ----            | ----            | ----
Clouvider       | London, UK (10G)          | 1.06 Gbits/sec  | 987 Mbits/sec   | 14.6 ms
Eranium         | Amsterdam, NL (100G)      | 1.06 Gbits/sec  | 1.00 Gbits/sec  | 7.33 ms
Uztelecom       | Tashkent, UZ (10G)        | 946 Mbits/sec   | 608 Mbits/sec   | 103 ms
Leaseweb        | Singapore, SG (10G)       | 721 Mbits/sec   | 555 Mbits/sec   | 247 ms
Clouvider       | Los Angeles, CA, US (10G) | 584 Mbits/sec   | 376 Mbits/sec   | 147 ms
Leaseweb        | NYC, NY, US (10G)         | 974 Mbits/sec   | 844 Mbits/sec   | 81.5 ms
Edgoo           | Sao Paulo, BR (1G)        | 751 Mbits/sec   | 448 Mbits/sec   | 203 ms

Geekbench 6 Benchmark Test:
---------------------------------
Test            | Value
                |
Single Core     | 630
Multi Core      | 641
Full Test       | https://browser.geekbench.com/v6/cpu/8028900

YABS completed in 22 min 24 sec

    So glad you used the upgrade function to upgrade only RAM. We strongly believe it's a nice feature to allow customers fine tune the specs to their needs. We hope that customers will find this useful.

    Still 1 core though, so single and multi-core scores are the same. At least now, there's enough RAM to run the multi-core properly.

    Thank you for running these tests for visibility.

    Thanked by 1emgh
  • WhiteRoseGWhiteRoseG Member

    Don't get me wrong it's still a good price for a VPS

    Thanked by 1emgh
  • MassiveGRIDMassiveGRID Member, Patron Provider

    @emgh said:

    @WhiteRoseG said:
    Lol the yabs is way below Hetzer Cloud, it's not comparable. It's more like contabo except the line speed is decent

    About the same as CX, no?

    https://www.vpsbenchmarks.com/yabs/hetzner-2c-4gb-c8653d

    Starting at 1.11 bucks a month (a little more with 2GB RAM though, needed to properly run YABS and get a similar score)

    Thanks @emgh

    We see that we get better scores at the same specs (2 Cores, 4 GB RAM):

    MassiveGRID (ref: yabs measurement from @MMMMMM previously)
    Single Core: 833
    Multi Core: 1336

    Hetzner (ref: https://www.vpsbenchmarks.com/yabs/hetzner-2c-4gb-c8653d)
    Single Core: 677
    Multi Core: 1185

    Thanked by 1emgh
  • SashkaProSashkaPro Member

    @MassiveGRID said: Still 1 core though, so single and multi-core scores are the same. At least now, there's enough RAM to run the multi-core properly.

    Yeah but for my tasks that's more than enough. But, may be on LET promo there will be double core option :smiley:

    Thanks for deal!

    Thanked by 2emgh MassiveGRID
  • MassiveGRIDMassiveGRID Member, Patron Provider
    edited September 2024

    @emgh said:

    @MassiveGRID said:

    @WhiteRoseG said:
    Lol the yabs is way below Hetzer Cloud, it's not comparable. It's more like contabo except the line speed is decent

    Which yabs are you referring to? Is it with same resources CPU, RAM, etc in both cases?

    To be fair their CPU's on the CPX line are newer

    By the way, on the Contabo promo page it says that London is using Gold 6230 but on WHMCS it says E5-2683v4

    We have both processors on our London H/A Cluster (Gold 6230 and E5-2683v4). We've changed to E5-2683v4 on the webpage you mentioned just to make sure that it's aligned with the info on WHMCS, although some VPSes will be on Gold 6230 after order :-)

    Thank you for pointing it out.

    Thanked by 1emgh
  • MassiveGRIDMassiveGRID Member, Patron Provider

    @WhiteRoseG said:
    Don't get me wrong it's still a good price for a VPS

    Not at all, we just want to make sure that the comparison is fair in order to avoid misconceptions.

  • MassiveGRIDMassiveGRID Member, Patron Provider

    @SashkaPro said:

    @MassiveGRID said: Still 1 core though, so single and multi-core scores are the same. At least now, there's enough RAM to run the multi-core properly.

    Yeah but for my tasks that's more than enough. But, may be on LET promo there will be double core option :smiley:

    Thanks for deal!

    You're welcome and that's exactly is the point to be able to choose the resources you need independently. Thanks for choosing us!

  • CasualCanvasCasualCanvas Member

    @MassiveGRID are there plans on putting up something in LA? I've checked my tracert to NY but sadly it's hopping up until 26, haha

  • FrankCastleFrankCastle Member

    @MassiveGRID

    Could you elaborate on your HA offerings? It seems like by default anyone that signs up does NOT have high availability. We have to submit a ticket to be processed and put on the HA cluster(s). Now this isn't a big deal to submit a ticket to be moved over but why wouldn't that be the default for all customers to just start on the HA cluster?

    Thanked by 1silun
  • tenperatenpera Member

    Almost bought one, still............

  • tenperatenpera Member
    edited September 2024

    connect to host xxx.xxx.xxx.75 port 51821: Connection timed out, Ticket #996387

  • MassiveGRIDMassiveGRID Member, Patron Provider

    @tenpera said:
    connect to host xxx.xxx.xxx.75 port 51821: Connection timed out, Ticket #996387

    I see that it's resolved. We remain available for anything else you need.

  • MassiveGRIDMassiveGRID Member, Patron Provider

    @FrankCastle said:
    @MassiveGRID

    Could you elaborate on your HA offerings? It seems like by default anyone that signs up does NOT have high availability. We have to submit a ticket to be processed and put on the HA cluster(s). Now this isn't a big deal to submit a ticket to be moved over but why wouldn't that be the default for all customers to just start on the HA cluster?

    It'll be default soon. You're 100% correct on your feedback.

    Thanked by 1FrankCastle
  • MassiveGRIDMassiveGRID Member, Patron Provider

    @CasualCanvas said:
    @MassiveGRID are there plans on putting up something in LA? I've checked my tracert to NY but sadly it's hopping up until 26, haha

    Yes, most probably Q1 2025.

  • SilvestSilvest Member
    edited September 2024

    Keep in mind that that the GB6 benchmark probably tries to eat your swap. Hence the low results. Hetzner vpses have swap disabled by default.

    Thanked by 1MassiveGRID
  • SilvestSilvest Member
    edited September 2024

    @MassiveGRID Maybe have swap disabled by default ? I don't use swap in general.

  • silunsilun Member
    edited September 2024

    @MassiveGRID said:

    @FrankCastle said:
    @MassiveGRID

    Could you elaborate on your HA offerings? It seems like by default anyone that signs up does NOT have high availability. We have to submit a ticket to be processed and put on the HA cluster(s). Now this isn't a big deal to submit a ticket to be moved over but why wouldn't that be the default for all customers to just start on the HA cluster?

    It'll be default soon. You're 100% correct on your feedback.

    I was not aware of that and I have not written such a ticket, but it says H/A in multiple places on my services:

    • In the product name
    • In the services overview, there's a column "H/A Server Status"
    • On the right sidebar of the product details, "H/A Cluster Status"

    So how do I know whether or not my server is on the H/A cluster? Where would I have been able to find this information if I hadn't seen that post?

    Edit: This is in Frankfurt, if that matters. Also, @FrankCastle how did you find that out?

    Thanked by 2SashkaPro emgh
  • FrankCastleFrankCastle Member

    @silun said:

    @MassiveGRID said:

    @FrankCastle said:
    @MassiveGRID

    Could you elaborate on your HA offerings? It seems like by default anyone that signs up does NOT have high availability. We have to submit a ticket to be processed and put on the HA cluster(s). Now this isn't a big deal to submit a ticket to be moved over but why wouldn't that be the default for all customers to just start on the HA cluster?

    It'll be default soon. You're 100% correct on your feedback.

    I was not aware of that and I have not written such a ticket, but it says H/A in multiple places on my services:

    • In the product name
    • In the services overview, there's a column "H/A Server Status"
    • On the right sidebar of the product details, "H/A Cluster Status"

    So how do I know whether or not my server is on the H/A cluster? Where would I have been able to find this information if I hadn't seen that post?

    Edit: This is in Frankfurt, if that matters. Also, @FrankCastle how did you find that out?

    I am THAT guy that reads all the fine print. Like you because all of the branding having HA everywhere I initially assumed that was the case but upon additional research I found something in their knowledge base that said we had to submit a ticket so I did.

    It is nice to know that they are working to make this the default going forward. That way not everyone will need to do extra research or read this forum to benefit.

    Thanked by 4SashkaPro emgh MassiveGRID dev077
  • emghemgh Member, Megathread Squad

    @FrankCastle said:

    @silun said:

    @MassiveGRID said:

    @FrankCastle said:
    @MassiveGRID

    Could you elaborate on your HA offerings? It seems like by default anyone that signs up does NOT have high availability. We have to submit a ticket to be processed and put on the HA cluster(s). Now this isn't a big deal to submit a ticket to be moved over but why wouldn't that be the default for all customers to just start on the HA cluster?

    It'll be default soon. You're 100% correct on your feedback.

    I was not aware of that and I have not written such a ticket, but it says H/A in multiple places on my services:

    • In the product name
    • In the services overview, there's a column "H/A Server Status"
    • On the right sidebar of the product details, "H/A Cluster Status"

    So how do I know whether or not my server is on the H/A cluster? Where would I have been able to find this information if I hadn't seen that post?

    Edit: This is in Frankfurt, if that matters. Also, @FrankCastle how did you find that out?

    I am THAT guy that reads all the fine print. Like you because all of the branding having HA everywhere I initially assumed that was the case but upon additional research I found something in their knowledge base that said we had to submit a ticket so I did.

    It is nice to know that they are working to make this the default going forward. That way not everyone will need to do extra research or read this forum to benefit.

    But you still can’t see yourself if you’re actually in a HA cluster or not?

Sign In or Register to comment.