At the time of writing, Lemmyworld has the second highest number of active users (compared to all lemmy instances)

Also at the time of writing, Lemmyworld has >99% uptime.

By comparison, other lemmy instances with as many users as Lemmyworld keep going down.

What optimizations has Lemmyworld made to their hosting configuration that has made it more resilient than other instances’ hosting configurations?

See also Does Lemmy cache the frontpage by default (read-only)? on !lemmy_support@lemmy.ml

  • Ruud@lemmy.worldM
    link
    fedilink
    arrow-up
    4
    ·
    1 year ago

    Thank you for all the compliments.

    This ride reminds me of Mastodon.world in November. Details on that are here: https://blog.mastodon.world/and-then-november-happened

    So I started lemmy.world on a 2CPU/4GB VPS. Keeping an eye on the performance. Soon I decided to double that. And after the first few thousand of users joined, doubled it again to 8CPU/16GB. That also was the max I could for that VPS type.

    But, already I saw some donations come in, without really asking. That reminded me of the willingness to donate on Mastodon, which allowed me to easily pay for a very powerful server for mastodon.world, one of the reasons it grew so fast. Other (large) servers crashed and closed registrations, I (mainly) didn’t.

    So, I decided to buy the same large server (32cpu/64threads with 128GB RAM) as for masto (but that masto one has double the RAM). With the post announcing that, I also mentioned the donation possibilities. That brought a lot of donations immediately, already funding this server for at least 2 months. (To the anonymous person donating $100 : wow!).

    Now next: to solve the issue with post slowness. That’s probably a database issue.

    And again: migration took 4 minutes downtime, and that could have been less if I wasn’t eating pizza at the same time. So if any server wants to migrate: please do! If you have the userbase, you’ll get the donations for it. Contact me if you have questions.

    • million@lemmy.world
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      Nice job, thanks very much for the write up.

      Out of curiosity are you cloud hosting or do you own a server on a rack somewhere? Scaling with Kubernetes or VMs or just running bare-metal?

    • Xaphanos@lemmy.world
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      As someone “in the business”, but not nearly as technical as you… How far can a single instance scale? Can a load balancer spread it over mulitple front-ends to handle user load? Can the back-end be re-worked to handle hundreds of millions of user operations per second? Can it work with a CDN? Can a single “Lemmy.World” site exist as a distributed site - with hundreds of servers spread across dozens of sites across the globe?

      I expect this entire line of thought is antithetical to the entire Lemmy philosophy of distributed operation. I expect that the “correct” way is to spin off “NA.Lemmy.World”, EMEA. Lemmy.World", APAC.Lemmy.World", etc. as separate servers. Is that correct?

      Thanks.

  • andrew@radiation.party
    link
    fedilink
    arrow-up
    1
    ·
    1 year ago

    Likely experience and knowledge improving the quality of deployment. Most instances are likely underspecced, are on hosts that aren’t easy to scale up with, or are maxed out in their current offering tier (lemmy.ml comes to mind there)

  • PriorProject@lemmy.world
    link
    fedilink
    arrow-up
    0
    ·
    1 year ago

    I’m not an admin, but have followed the sizing discussions around the lemmyverse as closely as I can from my position of lacking first-hand knowledge:

    • lemmy.ml is the biggest instance by user count, but runs on incredibly modest 8-cpu hardware. Their cloud provider doesn’t provide any easy scale up options for them, so they can’t trivially restart on a bigger VM with their db and disk in place. I suspect this means that instance is going to suffer for a bit as they figure out what to do next.
    • lemmy.world on the other hand was running on a box at least twice as big as lemmy.ml at last count, and I believe they can go quite a bit bigger if they need to.
    • The lemmy.world admins also run mastodon.world and lived through the twitterpocalypse, seeing peak user registrations rates of 4k per hour. So this is not their first rodeo in terms of explosive growth, I’m sure that experience gives them some tricks up their sleeve.
    • The admin team is pretty clearly technically strong. If I recall correctly, ruud is a professional database admin. One of the spooky parts of Lemmy performance-wise is the db. If ruud or others on the admin team custom-tuned their pg setup based on their own analysis of how/why it’s slow, they may be getting more performance per CPU cycle than other instances running more stock configs or that are cargo-culting tweaks that aren’t optimal for their setup without understanding what makes them work.

    I’m surprised that sh.itjust.works isn’t growing faster. They also have a hefty hardware setup and seemingly the technical admins to handle big user counts. I wonder if it’s a branding problem, where lemmy.world sounds inviting and plausibly serious where sh.itjust.works sounds like clowntown even though it’s run by a capable and serious team.

    • Retro@lemmy.world
      link
      fedilink
      arrow-up
      2
      ·
      edit-2
      1 year ago

      I originally signed up with sh.itjust.works, but I wanted to be on the instance with the majority of migrants.

      Also, it sounds dumb, but I think the sh.itjust.works domain is just kinda weird, technically has a “curse word” in it (not that I personally care), and they don’t support NSFW content (which isn’t just used for porn). So, it didn’t make sense to have that as my home instance. 🤷‍♂️

      Edit: Also, this is my first comment on here! Hello world! 👋

      • PriorProject@lemmy.world
        link
        fedilink
        arrow-up
        2
        ·
        1 year ago

        Yeah, I get it. Naming optics aside, it seems an instance with a lot of headroom relative to others, with a capable team. Would be near the top of my word-of-mouth options in spite of the idiosyncratic name.

    • Master@lemmy.world
      link
      fedilink
      arrow-up
      2
      arrow-down
      1
      ·
      1 year ago

      Can confirm… I didnt sign up for sh.itjust.works solely because of the name… I dont particularly want that attached to every post I make.

    • WaffleFriends@lemmy.world
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      I had a very similar thought process when choosing my instance. lemmy.world seemed like it would be more open to new users than an instance named sh.itjust.works. Idk why that was my thought process but I’m here now

    • StrayPizza@lemmy.world
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      I hope lemmy.ml can upgrade at some point. A lot of the slowness I’m running into is trying to browse/discovery communities that happen to live on that instance.

    • Druidgrove@lemmy.world
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      I’m now going to start incorporating “Sounds like clowntown” into my everyday conversations - that’s funny!

    • Pspspspspsps@lemmy.world
      link
      fedilink
      arrow-up
      1
      ·
      edit-2
      1 year ago

      I wonder if it’s a branding problem, where lemmy.world sounds inviting and plausibly serious where sh.itjust.works sounds like clowntown

      That was my thought process when choosing an instance tbh. I’m not a tech person, I looked at the list and lemmy.world was the first ‘safest feeling’ instance that had open sign up. I saw sh.itjust.works and didn’t even check their sign up process, there was too many periods in the strange name and it just looks weird to me as someone not used to these things. Edit: spelling

      • s4if@lemmy.world
        link
        fedilink
        arrow-up
        2
        ·
        1 year ago

        nah, I’m bit regretting not signing up on their instance. sh.itjust.works is a cool name and can be a brag point. lol. lemmy world is a bit too generalist, but I won’t migrate there as ruud (the admin of lemmyworld) is doing a good job managing the instance. I appreciate that. :)

      • Z______@lemmy.world
        link
        fedilink
        arrow-up
        0
        ·
        edit-2
        1 year ago

        I definitely second the motion on it being a branding problem. Stuff like sh.itjust.works seem to me like something that dark basement tech nerds would come up with that is “edgy” and really only used by them and other people like them.

        I’m not really into the ironic “edgy” aesthetic and part of the struggle with this transition for me has been orienting myself in the space because I don’t want to commit to some “sketchy” edgelord URL

        • DarkwingDuck@sh.itjust.works
          link
          fedilink
          arrow-up
          1
          ·
          1 year ago

          something that dark basement tech nerds would come up with that is “edgy” and really only used by them and other people like them.

          That’s exactly what it is and why I love it. The whole thing about this federated networking is that it doesn’t matter where you signed up.