Recent searches
Search options
Is the fediverse about to get Fryed? (Or, “Why every toot is also a potential denial of service attack”)
I should probably stop replying to people now, shouldn’t I?
But I won’t!
I WILL NOT LIVE IN FEAR!
@aral have you considered using pleroma instead? It's supposedly much less resource intensive.
I guess migrating the data would be a pain if you want to keep your toots
, can you share your thoughts on pleroma? I've also heard the performance is better for instances-of-one.@noeldemartin @aral I'm still in the process of setting up my instance-of-one (I'm just slow, it doesn't seem complicated) but I don't have the kind of follow(er/ing) counts that I will be able to say much about performance. Especially since I never ran a mastodon instance
@martijn @aral I also have a similar situation. I've been running my instance-of-one and I haven't had any performance issues. But of course, I know that's because I don't have that many connections.
So when I read @aral's post I found it very interesting, and I wonder if he's got any thoughts on pleroma or other projects. After all, that's one of the nice things about the fediverse. Different use-cases can leverage different implementations instead of having a one-size-fits-all solution.
A long time ago, before even Geocities, I had a blog that had enough traffic to get noticed, and I was approached by a researcher at the University of Georgia offering me free hosting so long as uptime wasn't critical.
The site was called Dragonfire. The experiment was squeezing as much power out of a commodity white box as technically possible. It was overclocked to the hilt, water cooled, and the name was chosen after some coffee spilled on the case and started boiling.
@aral that's the screen I (and probably every #mastoadmin) was checking regularly in the last few days 
Our instance is not that big, but seems to be integrated in the network, we hit 500k 1.5 weeks ago, steering towards 1M events/day.
It's really interesting when you're hosting the hardware yourself (especially as a hobby project) and can't easily scale up CPUs, but switching to nvme really payed off. We currently run 2 sidekiq processes at 10 treads each, with basically zero queue backlog.
@stux@mstdn.social @aral @stux
Mastodon admins = fearless in the face of tidal waves & earthquakes
and still patient with newbies
thank you all!
But there seem to be some scaling effects, we're currently at roughly 2.9k events per active user, I wonder how that compares.
@aral does it count when you reply to yourself? 
@aral Wow! 
In light of this, I’m even more impressed that you actually thanked me in person for the birthday wish. I only just now - thanks to @Saket - realized how many followers you have and what that means for your instance as you interact with folks here. Hats off to you, sir! Now, let’s see you *not* reply to this. You can do it!
@ClaudetteK Alas, I have failed :)
@aral That's ONE user? Oh wow, amazing! :D
@aral It's super good that you are vocal about the costs though. I think we need to contribute to the code to make it cheaper for people to run instances :)
@aral looks like a regular and stable heart beat. You’ll be just fine!
@aral you are impressive you know that?