Loading

Server load

This is the situation we are trying to deal with, high load from AI bot crawlers (left).
When that CPU utilization is under 20% the servers earn 'credit'. That credit can build to a maximum, and is used when the load is over 20%.

The high load causes the slow loading of pages, which may exceed a time setting to cause the 'Gateway' error message. But in the current extreme case, rather than coping with a short peak load, it is persistent. So all of the credit is eventually used, with the very likely display of the Gateway error, until you are lucky enough to get a page delivered.

The effect of taking the servers off-line for maintenance yesterday can be seen with the very low dip. Both in terms of the low load allowing the credit to build, and of throwing off the AI bots. Until they woke up again.

Our amateur skills are not sufficient for solving this problem and we are seeking outside help.
Visible by: Everyone
(more information)

More information

Visible by: Everyone

All rights reserved

Report this photo as inappropriate

20 comments

David G Johnson said:

Many thanks to everyone - for all that you do,. Everything on 'iper' appears to be running very smooth at the moment,.. // Dj.
4 days ago

J. Gafarot said:

Thank you very much for your words and for your work,
You are very considerate.
4 days ago

Valeriane ♫ ♫ ♫¨* said:

Merci pour votre travail ! A bientôt ! remerciements à toute l'équipe♫
4 days ago ( translate )

Pam J said:

GO GET EM LADS !!!!
4 days ago ( translate )

HelenaPF en longue p… said:

Mille mercis pour tous les efforts que l'équipe déploie! depuis hier tout marche bien! Espérons que cela durera. Bonne semaine à toute l'équipe.
4 days ago ( translate )

David Slater (Spodde… said:

Thank you for all your efforts. I appreciate all you do and only wish I had technical knowledge so I could help in some way.
4 days ago

Tanja - Loughcrew said:

Danke für die Infos und Euere Bemühungen…wenn wir verstehen, worum es geht,
verstehen wir auch warum es nicht geht! Danke!
4 days ago ( translate )

Roger (Grisly) said:

Thank you, both for the effort and the explanation AI already appears to have much to answer for.
4 days ago

DOMCHO said:

En faisant des recherches pour bloquer les bots IA
www.ethersys.fr/actualites/20240918-bloquer-les-bots-ia
4 days ago ( translate )

* ઇଓ * replied to DOMCHO:

That's a good indication!
4 days ago

Malik Raoulda said:

Un remarquable travail qui donne déjà de bons résultats..
Bonne continuation.
4 days ago ( translate )

Keith Burton said:

We're not the only site suffering from AI bot crawlers.........I read today that Wikipedia is struggling as well..........and I suspect that's only the tip of the iceberg..!!

Thank you to everyone involved for your hard work in keeping our heads above the water..!!
4 days ago

William Sutherland said:

What does it take to utilize a captcha mechanism to filter out bots?
4 days ago

Team said:

www.privacyjournal.net/block-llm-crawlers
"There is a downside: no text behind a CAPTCHA can appear on a search engine. That’s why sites tend to only use CAPTCHA to protect personal accounts. However, it’s a good solution to protect parts of your website, even if you can’t cover the whole thing without getting delisted."
3 days ago

StoneRoad2013 said:

Thanks for the explanation - it must be very frustrating.
Hopefully a solution can be found.
3 days ago