The perf flamegraph data from scylladb is coming out weird.
Currently, our scylladb is running on kubernetes, and perf was performed directly in the pod, but scylladb-related function call graphs are not visible.
perf record -p $(pidof scylla) --call-graph dwarf – sleep 60
perf script | ./stackcollapse-perf.pl > out.perf-folded
./flamegraph.pl out.perf-folded > perf.svg