AGUCUAGCAUAC

That’s good! There’s some hope that this won’t last forever then. Thanks.

And it’s interesting that the challenge via old.lemmy.ca was so impactful. The first wave of bots that I noticed also came through an Mlmym front-end that I make accessible via tor. But lately they have been hitting directly via the regular front-end.

Thanks! The problem I run into is that the bags end up taking up a lot more space than the components themselves. Yesterday I started testing printing a small label with the component’s code and sticking it into the reel.

Ooh, I like that idea for the larger components that don’t fit into the smaller binder. I bought some trading card sheets to test. Thanks :D

Did this spike for you these past weeks? I’m not sure if it just happens to be our instance’s turn or if they have up-scaled their efforts. I have been playing wack-a-mole with IP ranges.

I do have a wall with similar boxes. From the image, I am not sure if they are the same size. I just measured one of my small drawers and it is 14 cm x 5.5 cm x 5 cm. Since I have many different tiny components, I quickly ran out of space when I tried to give each component its own drawer.

But I think that I might be able to do a better job with these if I take everything out and start organizing again. I set the rules for how to place things before I started buying SMD components, and many of the through-hole components I can combine without problem. An improvement would be if I can find something like this but with many more and much smaller boxes.

When you mix different components into one of the boxes, do you have a system to label them? Or are the components easy enough to recognize by looking at them?

This morning I woke up and a new IP sub-net (43.173.0.0/16) was excessively hitting the site from multiple IPs, probably scraping, making the site unresponsive. I blocked that sub-net and the site is responsive again.

Thank you.

A few days ago, I blocked several IP ranges to solve this. I unblocked them about two days ago in an attempt to solve some federation issues… The bots from this IP range came back.

This time I blocked only the IP range that has the most bot-like activity. Hopefully that resolves it.

Woah! Congratulations!!! 🥳 🎉

For mander.xyz it has been bot scrapers. That time that you are mentioning it was scraping via the onion front end that I am hosting for easier access over Tor. Yesterday an army of bots scraping via Alibaba cloud servers made the server unusable for a few minutes. The instance would receive a bunch of requests from the same IP range (47.79.0.0/16), and denying that full IP range fixed the problem.

Some instances implement anti-bot measures. For example, https://sopuli.xyz/ makes use of Anubis. I think that instances behind Cloudfare get some protection too. I am considering using Anubis for mander.xyz, but for now I have just been dealing with this manually as it does not happen too often.

No problem! Happy to contribute

Thanks!

I don’t see those specific IPs, nor 16514. But now I see what scrapers tend to look like in the logs :)

I am now pretty sure that the cause was scraper-like activity coming from the Mlmym front-end that I am serving over an onion site. I am not sure if it randomly started mis-behaving or if a tor scraper was using it.

After blocking this, federation was restored, performance increased, and CPU use came down:

I just realized that it is not a ‘scraper’, the requests came from the server that I am using to provide an interface to the site as an Onion site. The amount of requests was suspiciously high so maybe a bot is scraping through Tor. I will leave it off for a few days and see if I can turn it back on later.

Thanks! It seems like the lag may have been due to a scraper

I did not update or change anything in the past few days.

But, now that you mentioned an AI scrapper I looked into the logs and noticed some heavy requests to the API from a specific IP.

Requests look consistent to scraping - just consistently and continuously issuing GET requests to different API endpoints.

XX.XX.XX.XX - - [14/Oct/2025:21:28:54 +0000] "GET /api/v3/community/list?limit=20&sort=TopAll HTTP/2.0" 403 107 "-" "Mlmym"

I have started denying their requests and it is the first thing that seems to have actually helped!

I don’t want to speak too early but I think you may have identified the cause. Thanks!

So far, I have been able to ‘control’ the CPU use by setting limits to the process that pulls stuff from the database (pool size, CPU, memory).

This does release some of the CPU for other tasks, but I think that that what creates the lag might actually be the clogged database queries. So, constraining those resources might not solve the lag problem.

Hmm, thanks!

I just made another change. I am not sure why the database suddenly started taking up so many resources, so I have reduced the amount of resources available to it. It did reduce CPU use to 80% as opposed to 100%, but it is still somewhat laggy for me.

I can see that since October 13 the CPU use spiked to 100%…

I just reset the server to check if that would fix it quickly. It don’t think it did.

I can see the processes that are taking up a lot of CPU (parallell database queries it seems), but I still don’t understand what is causing these and why they have spiked since Oct 13. I will need to investigate.

I’d rather pay for preventing the front passenger from reclining into me.