#!/usr/bin/stap

probe perf.sw.cpu_clock!, timer.profile {
  // NB: To avoid contention on SMP machines, no global scalars/arrays used,
  // only contention-free statistics aggregates.
  tid=tid(); e=execname()
  if (!user_mode())
    kticks[e,tid] <<< 1
  else
    uticks[e,tid] <<< 1
  ticks <<< 1
  tids[e,tid] <<< 1
}

global uticks, kticks, ticks

global tids

probe timer.s(5), end {
  allticks = @count(ticks)
  printf ("%16s %5s %7s %7s (of %d ticks)\n",
          "comm", "tid", "%user", "%kernel", allticks)
  foreach ([e,tid] in tids- limit 20) {
    uscaled = @count(uticks[e,tid])*10000/allticks
    kscaled = @count(kticks[e,tid])*10000/allticks
    printf ("%16s %5d %3d.%02d%% %3d.%02d%%\n",
      e, tid, uscaled/100, uscaled%100, kscaled/100, kscaled%100)
  }
  printf("\n")

  delete uticks
  delete kticks
  delete ticks
  delete tids
}