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

    Tonight's Platform Update

    Scheduled Pinned Locked Moved Announcements
    mangolassi
    30 Posts 9 Posters 4.8k Views
    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 @Dashrender
      last edited by

      @Dashrender said:

      Sure, at what point does a colo make more sense than rending VM space from these vendors? Of course the problem with that is a single server, single point of failure.

      When we start getting to the point that having 4-6 physical CPUs and 96GB+ of RAM are needed per site for performance. That is a long, long way off. The platform that we use is so efficient that we are handling close to 100,000 views a day and were only just starting to run into memory constraints on the old system and mostly because the system has grown over the last two years to have so much content that keeping stuff in memory was bogging things down.

      The leap that we have made likely will carry us for more than another two years, every aspect of the system is 300% or more faster or bigger than we had before. We have 300% more cores now, but also 15% more speed per core, that adds up. That's like a 345% total speed increase. That is a lot. And that wasn't our bottleneck. And we have heard numbers up to 300% increase from the database update. And 300% faster disk IO!!! These things all add up. The CPU waits on the disks less, the database requires less of all of the resources, more things are cached in memory - if we were capping out at 100,000 views a day (before people could notice some minor lag) we are guessing that the new system can handle a million or more.

      The amount of growth that we are prepared to handle with zero to trivial effort is pretty enormous. That we will need to consider anything else for a very long time is unlikely.

      Chances are in two years we will want to revisit the architecture and, at that time, there is a very good chance that getting a 100% boost in memory size will be obvious and simple, that per core CPU speeds will have increased, etc. The platform naturally gets faster underneath us in many ways. So the need for moving to a completely different approach is much farther off than you would think. Because of the type of site that we are, the scale that can be handled from the current design is pretty extreme.

      DashrenderD 1 Reply Last reply Reply Quote 1
      • scottalanmillerS
        scottalanmiller @Dashrender
        last edited by

        @Dashrender said:

        Of course the problem with that is a single server, single point of failure.

        With good database backups, we could mitigate that pretty easily. MongoDB does an export, compress, transport, decompress, restore with blinding speed. We just did it last night and it was insane how fast the entire site was able to be transported around.

        1 Reply Last reply Reply Quote 1
        • DashrenderD
          Dashrender @scottalanmiller
          last edited by

          @scottalanmiller said:

          Chances are in two years we will want to revisit the architecture and, at that time, there is a very good chance that getting a 100% boost in memory size will be obvious and simple, that per core CPU speeds will have increased, etc. The platform naturally gets faster underneath us in many ways. So the need for moving to a completely different approach is much farther off than you would think. Because of the type of site that we are, the scale that can be handled from the current design is pretty extreme.

          Actually, this is exactly what I would expect. As the platform under the VMs becomes better as old hardware is replaced, I would expect there to be less need to migrate to something new. Sure you might need to assign more RAM, something that the underlying hardware might have more of now because it was upgraded, but the VM won't because, well that's not how that works. But when the CPU and disk are improved, the VM just gets those gains because everything on the system get those gains - not taking tiered storage into account.

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

            @Dashrender said:

            @scottalanmiller said:

            Chances are in two years we will want to revisit the architecture and, at that time, there is a very good chance that getting a 100% boost in memory size will be obvious and simple, that per core CPU speeds will have increased, etc. The platform naturally gets faster underneath us in many ways. So the need for moving to a completely different approach is much farther off than you would think. Because of the type of site that we are, the scale that can be handled from the current design is pretty extreme.

            Actually, this is exactly what I would expect. As the platform under the VMs becomes better as old hardware is replaced, I would expect there to be less need to migrate to something new. Sure you might need to assign more RAM, something that the underlying hardware might have more of now because it was upgraded, but the VM won't because, well that's not how that works. But when the CPU and disk are improved, the VM just gets those gains because everything on the system get those gains - not taking tiered storage into account.

            Yup, and realistically we grow at a rather steady pace not like we get twenty fold increase in a month. So the underlying hardware tends to grow with us pretty steadily.

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

              NodeBB 1.0.2 is out. Might as well upgrade 🙂 It has been a day of upheaval already.

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

                That was ridiculously fast, lol.

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

                  We did a full update in under a minute!!

                  1 Reply Last reply Reply Quote 1
                  • nadnerBN
                    nadnerB
                    last edited by

                    Huzzah! What did it fix/change?

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

                      @nadnerB said:

                      Huzzah! What did it fix/change?

                      No idea 🙂

                      dafyreD 1 Reply Last reply Reply Quote 0
                      • dafyreD
                        dafyre @scottalanmiller
                        last edited by

                        @scottalanmiller said:

                        @nadnerB said:

                        Huzzah! What did it fix/change?

                        No idea 🙂

                        There's this thing called Changelog... Generally one should read it before applying said updates...

                        0_1458616061260_upload-98bf6ccd-584f-4055-99f0-40a07b2728dd

                        1 Reply Last reply Reply Quote 3
                        • scottalanmillerS
                          scottalanmiller
                          last edited by

                          A month in and Linode is still rocking it!

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