404
Lemmy.world down, probably following the upgrade. A reminder to move to smaller instances for a better experience
(files.catbox.moe)
this post was submitted on 29 Jul 2023
404 points (92.6% liked)
Fediverse
17698 readers
2 users here now
A community dedicated to fediverse news and discussion.
Fediverse is a portmanteau of "federation" and "universe".
Getting started on Fediverse;
- What is the fediverse?
- Fediverse Platforms
- How to run your own community
founded 5 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
A reminder that this constant advice people blindly parrot to install and flock to smaller instance has now created something like 1000 new servers in 50 days that are poorly run and already going offline as quickly as they went online.
Github Issue 2910 is the kind of PostgreSQL problems that the developers ignored for months and people still defend the developer choices to have the code doing real-time counting of every single comment and post for numbers nobody needs to needs done in real-time.
PostgreSQL is voodoo to this project, they do everything they can to avoid going to !postgresql@lemmy.ml community and asking for help, learning 101 about how to fix their SQL TRIGGER logic like Github Issue 2910 spelled out June 4.
I know you are salty about how you are getting treated over at GitHub, but you should look at it objectively, Blaze is clearly advocating that people join top instances that's not lemmy.world or lemmy.ml, not nobody instances that only have 1-2 users. They certainly aren't going offline as quickly as they come online.
No, it isn't about my personal treatment. It's about the cultist attitude you have towards Lemmy and the leaders without any ability to see what they are doing behind the scenes with the code. I know cults and religious faith is how many people enjoy the world.
A 2-line SQL TRIGGER removal takes about minutes to fix. It was crashing the entire site constantly. They sat by and asked for donations of money.
What is a SQL trigger and why is it taking down servers? Do you know how to fix it?
I think 0.18.3 fixed some of it, but there are likely some more performance issues related to PostgreSQL lurking in Lemmy.
A TRIGGER in SQL is a logic that executes based on other activity.
Lemmy uses them so that when you create a new comment or post, it executes code to insert tracking record for votes and comments on a post. One of the things Lemmy does is called site_aggregates, and there was a bug where it was updating the counts for 1500 servers instead of just the one server. That got fixed in 0.18.3
Deleting accounts in lemmy was causes crashes. I'm not sure if that has been entirely resolved. These things are all kind of hidden in the background of the code, so a lot of developers overlooked that there were problems in them.
Isn’t there a logstream they could tap into to have a separate async tally going on instead of doing it synchronously? Probably a lot of things could be delegated to an async job performed when server load allows?
I've had to really adjust my thinking with this project. They want to do things a very particular way and it goes back 4 years, and a lot of the mistakes are just now getting noticed/attention. For example, comments were not deleting on all the servers, I was testing that after comparing server copies of the same communities and found they were not the same. It just didn't seem to have a lot of people spot-checking it for mistakes. I am learn to just "go with the flow" and face that it's more like how musicians would approach design and running a project. Media-focused systems can be that way.
Going with the flow is both ways. It’s a community project so everyone’s opinion matters, especially those who contribute PRs.