1) What kind of hardware are you running on L0? ('ubuntu-bug linux' and filing a bug would collect the necessary info)
2) What kind of load are you seeing in L0, L1?
3) Can you give me the output of 'tail /sys/module/kvm_intel/parameters/*' ?
4) You could setup crashdump to dump on a hang (if we think its the right one), or just have a full backtrace on a softlockup by adding the following to the kernel cmdline:
softlockup_all_cpu_backtrace=1
Having a single vCPU could either be reducing the load, or avoiding a race; it would be hard to tell without a proper backtrace of the hang itsself.
This seems like a pretty simple testcase, I will put it on my list of things to try and reproduce.
@baco-1
1) What kind of hardware are you running on L0? ('ubuntu-bug linux' and filing a bug would collect the necessary info) kvm_intel/ parameters/ *' ? all_cpu_ backtrace= 1
2) What kind of load are you seeing in L0, L1?
3) Can you give me the output of 'tail /sys/module/
4) You could setup crashdump to dump on a hang (if we think its the right one), or just have a full backtrace on a softlockup by adding the following to the kernel cmdline:
softlockup_
Having a single vCPU could either be reducing the load, or avoiding a race; it would be hard to tell without a proper backtrace of the hang itsself.
This seems like a pretty simple testcase, I will put it on my list of things to try and reproduce.