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

    ServerBear Performance Comparison of Rackspace, Digital Ocean, Linode and Vultr

    IT Discussion
    serverbear server benchmarking rackspace iaas vps digital ocean vultr centos centos 7 linux linux server kvm xen
    12
    56
    17.7k
    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.
    • S
      scottalanmiller
      last edited by scottalanmiller

      Attempting to compare performance across these three hosting providers to get a base line of capability. In all three cases using an IaaS / VPS VM of 2 vCPU and 2GB RAM on SSD storage. Vultr and Digital Ocean are both KVM and $20/mo and Rackspace is Xen on OpenStack and nearly $60/mo. All three are fully updated CentOS 7.2. All test from ServerBear.

      Digital Ocean Performance Link
      Vultr Performance Link
      Rackspace Performance Link
      Linode Performance Link

      Hoster             UNIX Bench    FIO IOPS (r/w)   IO Rate        Bandwidth    Loc
      
      Digital Ocean      1942.3        58830 / 15980    71 MB/s        111 MB/s     NY
      Vultr              1958.5        34642 / 28842    243 MB/s       96  MB/s     NJ
      Rackspace          1809.5        27626 / 29644    216 MB/s       151 MB/s     VA
      Linode             2176.7        73736 / 69606    876 MB/s       85  MB/s     NY
      
      1 Reply Last reply Reply Quote 0
      • I
        IRJ
        last edited by

        I don't see any info on rackspace

        S 1 Reply Last reply Reply Quote 0
        • S
          scottalanmiller
          last edited by

          We need some latency numbers from around the world. Anyone want to collect some for us?

          Here is the first IP address. A long running ping (hundreds or thousands of pings) would be good, we need the final stats from that:

          • 104.236.119.59
          • 108.61.151.173
          • 172.99.75.133

          We have a good idea on bandwidth, IO, CPU and memory. Network latency is pretty huge.

          J W L 3 Replies Last reply Reply Quote 0
          • S
            scottalanmiller @IRJ
            last edited by

            @IRJ said:

            I don't see any info on rackspace

            ServerBear is still running there, it got loaded last.

            1 Reply Last reply Reply Quote 1
            • J
              JaredBusch @scottalanmiller
              last edited by JaredBusch

              @scottalanmiller said:

              We need some latency numbers from around the world. Anyone want to collect some for us?

              Here is the first IP address. A long running ping (hundreds or thousands of pings) would be good, we need the final stats from that:

              • 104.236.119.59
              • 108.61.151.173
              • 172.99.75.133

              We have a good idea on bandwidth, IO, CPU and memory. Network latency is pretty huge.

              pings running from CentOS 7 VM doing nothing else in a colo in St Louis. remind me later to kill it and get stats.

              0_1458232436389_upload-abaf8162-693e-426a-a799-795e3661de9b

              1 Reply Last reply Reply Quote 1
              • S
                scottalanmiller
                last edited by

                Thanks.

                1 Reply Last reply Reply Quote 0
                • S
                  scottalanmiller
                  last edited by

                  Still waiting on RS.

                  1 Reply Last reply Reply Quote 0
                  • S
                    scottalanmiller
                    last edited by

                    Rackspace info is up.

                    I 1 Reply Last reply Reply Quote 0
                    • I
                      IRJ @scottalanmiller
                      last edited by

                      @scottalanmiller Is lower better?

                      S 1 Reply Last reply Reply Quote 0
                      • D
                        dafyre
                        last edited by dafyre

                        It is odd to see that DO has the lowest IO rate, but the overall second highest score.

                        Edit: Fixed typo.

                        T 1 Reply Last reply Reply Quote 0
                        • T
                          travisdh1 @dafyre
                          last edited by travisdh1

                          @dafyre said:

                          It is odd to see that DO has the lowest IO rate, but the overall highest score.

                          IOPS it makes sense. Yes, write is slower, but read is crazy fast. Or do I have the read/write reversed? I'm used to seeing things listing read first 😳

                          S 1 Reply Last reply Reply Quote 0
                          • W
                            wirestyle22
                            last edited by

                            Vultr with that NJ location. Hi handsome.

                            1 Reply Last reply Reply Quote 1
                            • S
                              scottalanmiller @IRJ
                              last edited by

                              @IRJ said:

                              @scottalanmiller Is lower better?

                              Lower what exactly?

                              I 1 Reply Last reply Reply Quote 0
                              • S
                                scottalanmiller @travisdh1
                                last edited by

                                @travisdh1 said:

                                @dafyre said:

                                It is odd to see that DO has the lowest IO rate, but the overall highest score.

                                IOPS it makes sense. Yes, write is slower, but read is crazy fast. Or do I have the read/write reversed? I'm used to seeing things listing read first 😳

                                I wrote the header backwards.

                                1 Reply Last reply Reply Quote 3
                                • I
                                  IRJ @scottalanmiller
                                  last edited by

                                  @scottalanmiller said:

                                  @IRJ said:

                                  @scottalanmiller Is lower better?

                                  Lower what exactly?

                                  bench

                                  S 1 Reply Last reply Reply Quote 0
                                  • S
                                    scottalanmiller @IRJ
                                    last edited by

                                    @IRJ said:

                                    @scottalanmiller said:

                                    @IRJ said:

                                    @scottalanmiller Is lower better?

                                    Lower what exactly?

                                    bench

                                    Higher is better. I think that IOPS are a small amount, if any, of that score. It's about computational performance.

                                    1 Reply Last reply Reply Quote 0
                                    • W
                                      wirestyle22 @scottalanmiller
                                      last edited by wirestyle22

                                      @scottalanmiller said:

                                      We need some latency numbers from around the world. Anyone want to collect some for us?

                                      Here is the first IP address. A long running ping (hundreds or thousands of pings) would be good, we need the final stats from that:

                                      • 104.236.119.59
                                      • 108.61.151.173
                                      • 172.99.75.133

                                      We have a good idea on bandwidth, IO, CPU and memory. Network latency is pretty huge.

                                      104.236.119.59 = 8 MS Average 1,000 pings
                                      108.61.151.173 = 7 MS Average 1,000 pings
                                      Mangolassi.it (162.242.243.171) = 14 MS average 500 pings

                                      1 Reply Last reply Reply Quote 1
                                      • S
                                        scottalanmiller
                                        last edited by

                                        Whoops, sorry. We just killed the RS node because it is expensive 🙂

                                        You can test that RS ping against mangolassi.it instead. Same location, same node type. Sorry.

                                        D W 2 Replies Last reply Reply Quote 0
                                        • D
                                          dafyre @scottalanmiller
                                          last edited by dafyre

                                          @scottalanmiller said:

                                          Whoops, sorry. We just killed the RS node because it is expensive 🙂

                                          You can test that RS ping against mangolassi.it instead. Same location, same node type. Sorry.

                                          With the RS nodes being so expensive... why would you not stand them up on DO or Vultr?

                                          Edit: I mean for production and not tests like this.

                                          S 1 Reply Last reply Reply Quote 0
                                          • W
                                            wirestyle22 @scottalanmiller
                                            last edited by wirestyle22

                                            @scottalanmiller said:

                                            Whoops, sorry. We just killed the RS node because it is expensive 🙂

                                            You can test that RS ping against mangolassi.it instead. Same location, same node type. Sorry.

                                            Running now. Will update my above post.

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