On 2024-01-08 19:50, Paul Gevers wrote: > Hi, > > On 08-01-2024 01:45, Aurelien Jarno wrote: > > I am still not sure why it got killed on arm64 and not on other debci > > workers, there as still swap available. Actually looking at the munin > > plot, it seems that the arm64 debci workers stopped using swap around > > September 2023 contrary to the other architectures. > > Can you tell me how you saw that? I neither spotted that, nor is not having > swap a conscious act, so rather a mistake.
From the log you send, I was surprised that OOM happened while none of the swap has been used at all. So I looked at the munin link you gave me by IRC and realized that the Swap in/out plot is stuck as 0.00 for min/avg/max values since September 2023. This is not the case of the workers of the other architectures which use a bit of swap from time to time, and this have a maximum different of 0.00. That still doesn't explain while the problem with glibc seems to have started one week ago. Aurelien -- Aurelien Jarno GPG: 4096R/1DDD8C9B aurel...@aurel32.net http://aurel32.net
signature.asc
Description: PGP signature
