Jesper Dangaard Brouer

Merging this as it is conflicting with my other PR

Thanks for working on this "homework" assignment ;-)

I'm considering if we should rename the example director `trie-free-latency` - to something with `LPM` in the name, to make the connection with the `BPF_MAP_TYPE_LPM_TRIE` What about these proposals: -...

Thanks for addressing everything - going to merge

Added it as as a TODO for tomorrow

I think something **more** than bool handling is wrong. I wrote a oneliner reproducer that shows other `args` are also wrong: ``` sudo bpftrace -e ' tracepoint:cgroup:cgroup_rstat_locked {@bool[args->contended]=count(); @cpus[args->cpu]=count(); @level[args->level]=count();}...

Question: Does other tools get this right? Trying to record same tracepoint with `perf` like this: ``` perf record -e cgroup:cgroup_rstat_locked -a sleep 10 ``` While running this `cat` command...

Ftrace format: ``` sudo cat /sys/kernel/tracing/events/cgroup/cgroup_rstat_locked/format name: cgroup_rstat_locked ID: 303 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int...

Ran: ``` sudo bpftrace -d all -e ' tracepoint:cgroup:cgroup_rstat_locked {@bool[args->contended]=count(); @cpus[args->cpu]=count(); @level[args->level]=count();} interval:s:10 {time("\n%H:%M:%S\n"); print(@bool); print(@cpus); print(@level); exit(); }' > bpftrace_debug01.txt 2>&1 ``` File: [bpftrace_debug01.txt](https://github.com/user-attachments/files/16897716/bpftrace_debug01.txt)

As per discussion with @donaldh and @maryamtahhan