readprofile

readprofile 是一个跟踪内核性能的工具，其主要分析schedule/sleep/kvm 这三方面的性能。
要使能这个性能需要通过kernel command line传递__setup("profile=", profile_setup);
int profile_setup(char *str)
{
	static const char schedstr[] = "schedule";
	static const char sleepstr[] = "sleep";
	static const char kvmstr[] = "kvm";
	int par;
	#检查用于是要跟踪哪一个性能，目前只支持三个且同时只能支持一个
	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
#ifdef CONFIG_SCHEDSTATS
		force_schedstat_enabled();
		prof_on = SLEEP_PROFILING;
		if (str[strlen(sleepstr)] == ',')
			str += strlen(sleepstr) + 1;
		if (get_option(&str, &par))
			prof_shift = par;
		pr_info("kernel sleep profiling enabled (shift: %ld)\n",
			prof_shift);
#else
		pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
#endif /* CONFIG_SCHEDSTATS */
	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
		prof_on = SCHED_PROFILING;
		if (str[strlen(schedstr)] == ',')
			str += strlen(schedstr) + 1;
		if (get_option(&str, &par))
			prof_shift = par;
		pr_info("kernel schedule profiling enabled (shift: %ld)\n",
			prof_shift);
	} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
		prof_on = KVM_PROFILING;
		if (str[strlen(kvmstr)] == ',')
			str += strlen(kvmstr) + 1;
		if (get_option(&str, &par))
			prof_shift = par;
		pr_info("kernel KVM profiling enabled (shift: %ld)\n",
			prof_shift);
	} else if (get_option(&str, &par)) {
		prof_shift = par;
		prof_on = CPU_PROFILING;
		pr_info("kernel profiling enabled (shift: %ld)\n",
			prof_shift);
	}
	return 1;
}

这个函数是profile的初始化的入口函数，可见收集到的数据都是保存在proc/profile 这个目录下
int __ref create_proc_profile(void)
{

	entry = proc_create("profile", S_IWUSR | S_IRUGO,
			    NULL, &proc_profile_operations);
	if (!entry)
		goto err_state_onl;
	proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));

	return err;

}
static const struct file_operations proc_profile_operations = {
	.read		= read_profile,
	.write		= write_profile,
	.llseek		= default_llseek,
};
static ssize_t
read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
	unsigned long p = *ppos;
	ssize_t read;
	char *pnt;
	unsigned int sample_step = 1 << prof_shift;

	profile_flip_buffers();
	if (p >= (prof_len+1)*sizeof(unsigned int))
		return 0;
	if (count > (prof_len+1)*sizeof(unsigned int) - p)
		count = (prof_len+1)*sizeof(unsigned int) - p;
	read = 0;

	while (p < sizeof(unsigned int) && count > 0) {
		if (put_user(*((char *)(&sample_step)+p), buf))
			return -EFAULT;
		buf++; p++; count--; read++;
	}
	pnt = (char *)prof_buffer + p - sizeof(atomic_t);
	if (copy_to_user(buf, (void *)pnt, count))
		return -EFAULT;
	read += count;
	*ppos += read;
	return read;
}
我们从read_profile 函数中可以看到保存已经收集的数据是以binary的形式保存的，无法直接分析，因此要用用户态
工具readprofile来解析