Kris Kennaway wrote: > It was pointed out that machdep.hyperthreading_allowed=1 fixes this > bug (it was set to 0). However, hyperthreading was already in use > (partly), because this machine has 2 physical CPUs with HTT, and CPUs > 0, 2 and 3 were running jobs. > > Looks like machdep.hyperthreading_allowed=0 does not work as intended. That's odd. Can you tell me what values the hyperthreading_cpus_mask and hyperthreading_cpus variables in mp_machdep.c have, and what values PCPU_GET(cpumask) returns on the various (virtual) cpus? Colin PercivalReceived on Wed Nov 23 2005 - 09:01:52 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:48 UTC