Developers split over split-lock detection

Posted Dec 13, 2019 6:51 UTC (Fri) by GoodMirek (guest, #101902)
In reply to: Developers split over split-lock detection by tux3
Parent article: Developers split over split-lock detection

It actually sounds like DoSing a cloud provider this way would be an easy task, requiring to continuously create split-locks just on a single thread of a hyperthreaded core. Would that affect just one NUMA node or all of them?

Developers split over split-lock detection

Posted Dec 13, 2019 8:26 UTC (Fri) by bof (subscriber, #110741) [Link] (1 responses)

I'm sure if that ever becomes a thing, there's performance counters to read and recognize split lock membus locking, and automatic termination of contracts afterwards...

Developers split over split-lock detection

Posted Dec 13, 2019 8:47 UTC (Fri) by GoodMirek (guest, #101902) [Link]

Maybe, but the issue could be caused by a faulty software or a hacked VM. Contract termination seems as a last resort, e.g. in case the customer does not cooperate. However, in the meantime there can be a huge performance issue caused to many others.
E.g. if I run 100 faulty worker nodes, spread over 100 random hosts, each host having 48 CPU cores (96 vCPU's due to hyperthreading/SMT), that looks like a potentially significant issue.