sched_clock
来源:互联网 发布:算法设计与分析 王红梅 编辑:程序博客网 时间:2024/06/06 09:48
sched_clock 分为两部分.分为arch_timer 初始化前和初始化后.
初始化前会在main.c 中的start_kernel中调用sched_clock_postinit 来初始化sched_clock
void __init sched_clock_postinit(void)
{
/*
* If no sched_clock() function has been provided at that point,
* make it the final one one.
*/
if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
update_sched_clock();
/*
* Start the timer to keep sched_clock() properly updated and
* sets the initial epoch.
*/
hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
sched_clock_timer.function = sched_clock_poll;
hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
}
这个if条件是成立的,因为cd的定义如下,可以看到cd.actual_read_sched_clock = jiffy_sched_clock_read
static struct clock_data cd ____cacheline_aligned = {
.read_data[0] = { .mult = NSEC_PER_SEC / HZ,
.read_sched_clock = jiffy_sched_clock_read, },
.actual_read_sched_clock = jiffy_sched_clock_read,
};
这个时候调用sched_clock_register 来注册一个sched_clock。,这个clock的read函数如下,可以看到精度就是jiffies。
static u64 notrace jiffy_sched_clock_read(void)
{
/*
* We don't need to use get_jiffies_64 on 32-bit arches here
* because we register with BITS_PER_LONG
*/
return (u64)(jiffies - INITIAL_JIFFIES);
}
当arch_timer 开始初始化后,会调用sched_clock_register 注册一个sched——clock。
arch_timer_acpi_init->arch_timer_init->arch_timer_common_init->arch_counter_register
从sched_clock_register 注册来看并没有比较所注册的clock的精度有没有和之前已经注册的clock的精度做比较,而是默认以最后一次注册的为准,个人感觉这部分可以优化一下.
void __init
sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
{
u64 res, wrap, new_mask, new_epoch, cyc, ns;
u32 new_mult, new_shift;
unsigned long r;
char r_unit;
struct clock_read_data rd;
if (cd.rate > rate)
return;
WARN_ON(!irqs_disabled());
/* Calculate the mult/shift to convert counter ticks to ns. */
clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
new_mask = CLOCKSOURCE_MASK(bits);
cd.rate = rate;
/* Calculate how many nanosecs until we risk wrapping */
wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL);
cd.wrap_kt = ns_to_ktime(wrap);
rd = cd.read_data[0];
/* Update epoch for new counter and update 'epoch_ns' from old counter*/
new_epoch = read();
cyc = cd.actual_read_sched_clock();
ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
cd.actual_read_sched_clock = read;
rd.read_sched_clock = read;
rd.sched_clock_mask = new_mask;
rd.mult = new_mult;
rd.shift = new_shift;
rd.epoch_cyc = new_epoch;
rd.epoch_ns = ns;
update_clock_read_data(&rd);
r = rate;
if (r >= 4000000) {
r /= 1000000;
r_unit = 'M';
} else {
if (r >= 1000) {
r /= 1000;
r_unit = 'k';
} else {
r_unit = ' ';
}
}
/* Calculate the ns resolution of this counter */
res = cyc_to_ns(1ULL, new_mult, new_shift);
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
bits, r, r_unit, res, wrap);
/* Enable IRQ time accounting if we have a fast enough sched_clock() */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
pr_debug("Registered %pF as sched_clock source\n", read);
}
其他函数可以通过sched_clock 来调用sched_clock。
unsigned long long notrace sched_clock(void)
{
u64 cyc, res;
unsigned long seq;
struct clock_read_data *rd;
do {
seq = raw_read_seqcount(&cd.seq);
rd = cd.read_data + (seq & 1);
cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
rd->sched_clock_mask;
res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
} while (read_seqcount_retry(&cd.seq, seq));
return res;
}
这个函数逻辑很简单就是读取全局变量cd的值.
初始化前会在main.c 中的start_kernel中调用sched_clock_postinit 来初始化sched_clock
void __init sched_clock_postinit(void)
{
/*
* If no sched_clock() function has been provided at that point,
* make it the final one one.
*/
if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
update_sched_clock();
/*
* Start the timer to keep sched_clock() properly updated and
* sets the initial epoch.
*/
hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
sched_clock_timer.function = sched_clock_poll;
hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
}
这个if条件是成立的,因为cd的定义如下,可以看到cd.actual_read_sched_clock = jiffy_sched_clock_read
static struct clock_data cd ____cacheline_aligned = {
.read_data[0] = { .mult = NSEC_PER_SEC / HZ,
.read_sched_clock = jiffy_sched_clock_read, },
.actual_read_sched_clock = jiffy_sched_clock_read,
};
这个时候调用sched_clock_register 来注册一个sched_clock。,这个clock的read函数如下,可以看到精度就是jiffies。
static u64 notrace jiffy_sched_clock_read(void)
{
/*
* We don't need to use get_jiffies_64 on 32-bit arches here
* because we register with BITS_PER_LONG
*/
return (u64)(jiffies - INITIAL_JIFFIES);
}
当arch_timer 开始初始化后,会调用sched_clock_register 注册一个sched——clock。
arch_timer_acpi_init->arch_timer_init->arch_timer_common_init->arch_counter_register
从sched_clock_register 注册来看并没有比较所注册的clock的精度有没有和之前已经注册的clock的精度做比较,而是默认以最后一次注册的为准,个人感觉这部分可以优化一下.
void __init
sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
{
u64 res, wrap, new_mask, new_epoch, cyc, ns;
u32 new_mult, new_shift;
unsigned long r;
char r_unit;
struct clock_read_data rd;
if (cd.rate > rate)
return;
WARN_ON(!irqs_disabled());
/* Calculate the mult/shift to convert counter ticks to ns. */
clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
new_mask = CLOCKSOURCE_MASK(bits);
cd.rate = rate;
/* Calculate how many nanosecs until we risk wrapping */
wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL);
cd.wrap_kt = ns_to_ktime(wrap);
rd = cd.read_data[0];
/* Update epoch for new counter and update 'epoch_ns' from old counter*/
new_epoch = read();
cyc = cd.actual_read_sched_clock();
ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
cd.actual_read_sched_clock = read;
rd.read_sched_clock = read;
rd.sched_clock_mask = new_mask;
rd.mult = new_mult;
rd.shift = new_shift;
rd.epoch_cyc = new_epoch;
rd.epoch_ns = ns;
update_clock_read_data(&rd);
r = rate;
if (r >= 4000000) {
r /= 1000000;
r_unit = 'M';
} else {
if (r >= 1000) {
r /= 1000;
r_unit = 'k';
} else {
r_unit = ' ';
}
}
/* Calculate the ns resolution of this counter */
res = cyc_to_ns(1ULL, new_mult, new_shift);
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
bits, r, r_unit, res, wrap);
/* Enable IRQ time accounting if we have a fast enough sched_clock() */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
pr_debug("Registered %pF as sched_clock source\n", read);
}
其他函数可以通过sched_clock 来调用sched_clock。
unsigned long long notrace sched_clock(void)
{
u64 cyc, res;
unsigned long seq;
struct clock_read_data *rd;
do {
seq = raw_read_seqcount(&cd.seq);
rd = cd.read_data + (seq & 1);
cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
rd->sched_clock_mask;
res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
} while (read_seqcount_retry(&cd.seq, seq));
return res;
}
这个函数逻辑很简单就是读取全局变量cd的值.
0 0
- sched_clock
- sched_clock()、current_kernel_time()、getnstimeofday()
- sched_clock为什么要retry
- sched_clock精度不够导致统计cpu占用率发生跳变故障
- 如何获取Android唯一标识(唯一序列号)
- 连续子数组的最大和
- 深入 printf / wprintf / console下的unicode output
- Linux查看物理CPU个数、核数、逻辑CPU个数
- JQuery+Ajax无刷新分页
- sched_clock
- Android系统的所有的挂载
- php优化 nginx优化 mysql优化
- 使用Zlib对内存流及标准输入流进行压缩与解压缩
- JVM启动报错: Could not reserve enough space for object heap error
- Android 系列 1.9引用库以实现外部
- Java 正则表达式
- ubantu下编译hadoop
- U盘或者光驱win7iso镜像系统安装图解教程