A faulty platform update can now reach at most five servers a day, so it meets a handful of servers long before it could reach yours.
Last week it went the other way. Our platform build with the new read limits reached 76 servers, 43% of our fleet, in three days, and on three of them it stopped writes until the servers were restarted. The limits are switched off everywhere (read-limits update). The deeper fault was speed: updates were reaching servers far faster than we meant them to. That was our mistake, and this is the fix.
What changes for your server
Platform updates now go out slowly on purpose: at most five servers a day across the whole fleet, and routine updates wait while the builds across the fleet are under 30 days old on average. Typically every server is refreshed about once a quarter, some sooner, some later. Most servers were updated recently, so routine updates are paused for a few weeks. Nothing changes for the services running on your server.
Security fixes are the exception
A security fix is not held back by the five-a-day limit. It still goes out in small batches.
If you press Update in your control panel
Your request joins the same queue. You get an email that says it is queued, with an estimated date.
Why slow is the safer choice
A server that updates later misses a few weeks of improvements. A faulty update on every server could take everyone's service down at once. The full story, with the numbers, is on our Substack: Our faulty build reached 76 servers in three days. Now it's five a day.
Best Regards,
Väinämöinen
Pulsed Media Support
(Seven hundred years patient; updates can wait)
Monday, November 9, 2026
