You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
KernelStats::cpu_time is a Vec<CpuTime> where each entry shows the per-CPU utilization information from /proc/stat. However, it discards the CPU index from /proc/stat making it impossible to match the utilization to the originating CPU. For example, here's /proc/stat on a QEMU instance w/ 4 CPUs:
KernelStats::cpu_time will contain 3 entries but without any way to reliably find out which three CPUs are being reported. Corroborating other sources doesn't really work as there may be intervening hot[un]plug operations between reads.
It seems like KernelStats::cpu_time, instead of being a Vec, should be keyed with CPU ID read from /proc/stat.
The text was updated successfully, but these errors were encountered:
htejun
added a commit
to sched-ext/sched_ext
that referenced
this issue
Jun 20, 2023
KernelStats::cpu_time
is aVec<CpuTime>
where each entry shows the per-CPU utilization information from/proc/stat
. However, it discards the CPU index from/proc/stat
making it impossible to match the utilization to the originating CPU. For example, here's/proc/stat
on a QEMU instance w/ 4 CPUs:After taking cpu2 offline with
echo 0 > /sys/devices/system/cpu/cpu2/online
, the file looks as follows:KernelStats::cpu_time
will contain 3 entries but without any way to reliably find out which three CPUs are being reported. Corroborating other sources doesn't really work as there may be intervening hot[un]plug operations between reads.It seems like
KernelStats::cpu_time
, instead of being a Vec, should be keyed with CPU ID read from/proc/stat
.The text was updated successfully, but these errors were encountered: