ML
    • Recent
    • Categories
    • Tags
    • Popular
    • Users
    • Groups
    • Register
    • Login

    GeekBench Results for Cloud Servers

    IT Discussion
    vultr linode digital ocean aws azure geekbench benchmark
    8
    63
    7.9k
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • scottalanmillerS
      scottalanmiller
      last edited by

      Amazing that Vultr's low end systems also outperform everyone else! That's crazy how big the gap is between them and basically everyone else.

      1 Reply Last reply Reply Quote 1
      • A
        Alex Sage @Emad R
        last edited by

        @emad-r said in GeekBench Results for Cloud Servers:

        I think Vultr is the best for CPU and IO speed from what I feel

        I agree, and Price too 🙂

        1 Reply Last reply Reply Quote 0
        • Emad RE
          Emad R @Emad R
          last edited by

          @emad-r said in GeekBench Results for Cloud Servers:

          @scottalanmiller

          Topic like this should be pinned and done every year or so. No one keeps alot of track about this.

          What else we can test efficiently...

          RAM Speed ? but who cares about this.

          How we can test VM Cloud Download/Upload

          Thought about Network testing and came up with this:

          iperf3 -c bouygues.iperf.fr -t 30	 = upload
          iperf3 -Rc bouygues.iperf.fr -t 30	= download
          

          0_1536616495008_Untitled.png

          S 1 Reply Last reply Reply Quote 1
          • S
            StorageNinja Vendor @1337
            last edited by

            @pete-s said in GeekBench Results for Cloud Servers:

            As you said it might be the best cost performance ratio for cloud deployment.

            ehhhhhhh. It's the best cost for selling someone a modernish core for hosting that lacks any real scaling issues, or licensing per core/socket concerns.

            1 Reply Last reply Reply Quote 1
            • S
              StorageNinja Vendor @Emad R
              last edited by

              @emad-r said in GeekBench Results for Cloud Servers:

              Thought about Network testing and came up with this:

              That's just a testing of peering.

              Emad RE 1 Reply Last reply Reply Quote 1
              • Emad RE
                Emad R @StorageNinja
                last edited by Emad R

                @storageninja said in GeekBench Results for Cloud Servers:

                @emad-r said in GeekBench Results for Cloud Servers:

                Thought about Network testing and came up with this:

                That's just a testing of peering.

                Help us out then, I think we at ML need to come up with standard for testing Cloud.

                And how is it peering ? cause peering means:
                the exchange of data directly between Internet service providers, rather than via the Internet.

                I am using the same separate server of iperf on both nodes and both nodes are located in the same geolocation.

                JaredBuschJ 1 Reply Last reply Reply Quote 0
                • JaredBuschJ
                  JaredBusch @Emad R
                  last edited by

                  @emad-r said in GeekBench Results for Cloud Servers:

                  @storageninja said in GeekBench Results for Cloud Servers:

                  @emad-r said in GeekBench Results for Cloud Servers:

                  Thought about Network testing and came up with this:

                  That's just a testing of peering.

                  Help us out then, I think we at ML need to come up with standard for testing Cloud.

                  And how is it peering ? cause peering means:
                  the exchange of data directly between Internet service providers, rather than via the Internet.

                  I am using the same separate server of iperf on both nodes and both nodes are located in the same geolocation.

                  The point is you cannot test certain things. Such as network throughput and disk speed when it comes to cloud.

                  You can test throughput to your office. But again based on peering agreements, you could get get hugely varying results compared to someone on another ISP to the same cloud service.

                  Emad RE 1 Reply Last reply Reply Quote 1
                  • scottalanmillerS
                    scottalanmiller
                    last edited by

                    Right, the base problem is that because you can't control everything, you really can't test cloud servers in a super meaningful way.

                    To some extent, this goes far beyond cloud servers and kind of applies to all systems that are shared or cross the Internet. It's a more general problem.

                    1 Reply Last reply Reply Quote 0
                    • Emad RE
                      Emad R @scottalanmiller
                      last edited by Emad R

                      @scottalanmiller

                      does vultr also needs to create root account with your instances ? i dont think i ever saw this.

                      Like Vultr secondary root cloud account ? with your installed system ? Btw the image below is from OVH

                      0_1536693726841_2018-09-11 22_21_38-Accounts - centos.ovh.net.png

                      scottalanmillerS 1 Reply Last reply Reply Quote 0
                      • scottalanmillerS
                        scottalanmiller @Emad R
                        last edited by

                        @emad-r can't need to as you can remove them. It doesn't even need to control root itself.

                        Emad RE 1 Reply Last reply Reply Quote 0
                        • Emad RE
                          Emad R @scottalanmiller
                          last edited by

                          @scottalanmiller said in GeekBench Results for Cloud Servers:

                          @emad-r can't need to as you can remove them. It doesn't even need to control root itself.

                          It is locked account actually, seems like it is only needed the first time

                          1 Reply Last reply Reply Quote 0
                          • Emad RE
                            Emad R @JaredBusch
                            last edited by

                            @jaredbusch said in GeekBench Results for Cloud Servers: @StorageNinja

                            @emad-r said in GeekBench Results for Cloud Servers:

                            @storageninja said in GeekBench Results for Cloud Servers:

                            @emad-r said in GeekBench Results for Cloud Servers:

                            Thought about Network testing and came up with this:

                            That's just a testing of peering.

                            Help us out then, I think we at ML need to come up with standard for testing Cloud.

                            And how is it peering ? cause peering means:
                            the exchange of data directly between Internet service providers, rather than via the Internet.

                            I am using the same separate server of iperf on both nodes and both nodes are located in the same geolocation.

                            The point is you cannot test certain things. Such as network throughput and disk speed when it comes to cloud.

                            You can test throughput to your office. But again based on peering agreements, you could get get hugely varying results compared to someone on another ISP to the same cloud service.

                            Will speedtest-cli test also wont count as an effective test ? wont it show you some of your limitations of your DL/UL

                            [root@centos ~]# ./speedtest-cli
                            Retrieving speedtest.net configuration...
                            Testing from *************************
                            etrieving speedtest.net server list...
                            Selecting best server based on ping...
                            Hosted by Vodafone DE (Frankfurt) [143.90 km]: 5.199 ms
                            Testing download speed................................................................................
                            Download: 97.13 Mbit/s
                            Testing upload speed................................................................................................
                            Upload: 99.50 Mbit/s
                            
                            
                            1 Reply Last reply Reply Quote 0
                            • ObsolesceO
                              Obsolesce
                              last edited by

                              Here's the TurnkeyInternet.net results that I'm using, the T80 plan.

                              Turnkey Internet, 8 vCPU, 8GB RAM $20 (black friday special)

                              Single CPU: 1846
                              Multi-Core: 6715

                              https://browser.geekbench.com/v4/cpu/9946852

                              0_1537334248860_4febd5f4-9326-4660-9416-204237c37bd2-image.png

                              ObsolesceO 1 Reply Last reply Reply Quote 0
                              • ObsolesceO
                                Obsolesce @Obsolesce
                                last edited by

                                @obsolesce

                                Horrible results compared to Vultr, but for $20 a month...

                                scottalanmillerS 1 Reply Last reply Reply Quote 0
                                • scottalanmillerS
                                  scottalanmiller @Obsolesce
                                  last edited by

                                  @obsolesce said in GeekBench Results for Cloud Servers:

                                  @obsolesce

                                  Horrible results compared to Vultr, but for $20 a month...

                                  The "for $20" only means so much if you get less. The RAM is good for that price, but the CPU is mediocre for that price. If you are RAM bound, this might be a "deal", if CPU bound, likely it isn't. Eight cores to get less performance than two elsewhere is bad, faster, fewer threads gives better overall performance.

                                  No wonder their "standard" deal is 65% off!

                                  ObsolesceO 1 Reply Last reply Reply Quote 1
                                  • A
                                    Alex Sage
                                    last edited by

                                    Hetzner Cloud CX11 - 1vCPU - 2GB - 20GB - 2.49 Euro / Month

                                    0_1537365108634_a1b2b38d-d182-479d-bd40-4876abb8e01d-image.png

                                    https://browser.geekbench.com/v4/cpu/9954828

                                    1 Reply Last reply Reply Quote 0
                                    • A
                                      Alex Sage
                                      last edited by

                                      Assuming you're OK with having a server in Europe , it's hard to beat Hetzner Cloud for Price/Performance.

                                      scottalanmillerS 1 Reply Last reply Reply Quote 1
                                      • scottalanmillerS
                                        scottalanmiller @Alex Sage
                                        last edited by

                                        @aaronstuder said in GeekBench Results for Cloud Servers:

                                        Assuming you're OK with having a server in Europe , it's hard to beat Hetzner Cloud for Price/Performance.

                                        Those are great scores, what a price.

                                        A 1 Reply Last reply Reply Quote 0
                                        • A
                                          Alex Sage @scottalanmiller
                                          last edited by Alex Sage

                                          @scottalanmiller Here is the full pricing

                                          0_1537370613205_6d57478c-62bf-4592-8b59-7ea107430a9a-image.png

                                          A 1 Reply Last reply Reply Quote 0
                                          • A
                                            Alex Sage @Alex Sage
                                            last edited by

                                            Oh, and Hetzner Cloud supports Custom ISO's too - you just have a submit a ticket 😉

                                            1 Reply Last reply Reply Quote 1
                                            • 1
                                            • 2
                                            • 3
                                            • 4
                                            • 3 / 4
                                            • First post
                                              Last post