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 ... Read More »

Starting today, hard-disk servers set their own read limits, at the point where their disks get the most reading done. On three servers where the first limits were tighter than the disks needed, this let 1.6 to 2.4 times more data be read per second. Yesterday's per-account read limits (announcement 725) made small reads on shared disks ... Read More »