#!/usr/bin/stap
#
# Copyright (C) 2007 Oracle Corp. Chris Mason <chris.mason@oracle.com>
#
# This was implemented to find the most common causes of schedule during
# the AIO io_submit call.  It does this by recording which pids are inside
# AIO, and recording the current stack trace if one of those pids is
# inside schedule.
# When the probe exits, it prints out the 30 most common call stacks for
# schedule().
#
# This file is free software. You can redistribute it and/or modify it under 
# the terms of the GNU General Public License (GPL); either version 2, or (at
# your option) any later version.

global in_iosubmit
global traces

/*
 * add a probe to sys_io_submit, on entry, record in the in_iosubmit
 * hash table that this proc is in io_submit
 */
probe syscall.io_submit {
  in_iosubmit[tid()] = 1
}

/*
 * when we return from sys_io_submit, record that we're no longer there
 */
probe syscall.io_submit.return {
  /* this assumes a given proc will do lots of io_submit calls, and
   * so doesn't do the more expensive "delete in_iosubmit[p]".  If
   * there are lots of procs doing small number of io_submit calls,
   * the hash may grow pretty big, so using delete may be better
   */
  in_iosubmit[tid()] = 0
}

/*
 * every time we call schedule, check to see if we started off in
 * io_submit.  If so, record our backtrace into the traces histogram
 */
probe kernel.function("schedule") {
  if (tid() in in_iosubmit) {
    traces[backtrace()]++

    /*
     * change this to if (1) if you want a backtrace every time
     * you go into schedule from io_submit.  Unfortunately, the traces
     * saved into the traces histogram above are truncated to just a
     * few lines.  so the only way to see the full trace is via the
     * more verbose print_backtrace() right here.
     */
    if (0) {
      printf("schedule in io_submit!\n")
      print_backtrace()
    }
  }
}

/*
 * when stap is done (via ctrl-c) go through the record of all the
 * trace paths and print the 30 most common.
 */
probe end {
  foreach (stack in traces- limit 30) {
    printf("%d:", traces[stack])
    print_stack(stack);
  }
}