linuxloadavg algorithm_PHP tutorial

linux loadavg algorithm
Posted by: biti_rainy
Today I read the linux source code about the calculation method of cpu load, and at the same time searched everywhere for reference on Google. After being confused for a long time, I finally figured out the calculation method of cpu load. It is not Simple moving arithmetic average.
For Linux, the sampling calculation load time interval is 5 seconds, which are fixed numbers defined in the source code. Its sampling structure can dynamically obtain timely data through the dynamic memory file system /proc/loadavg. Other tools The output, such as uptime/top/sar, etc. are generated by reading the memory data. We mainly focus on the kernel algorithm here.
For an interval of 5 seconds, the cpu status data is dynamically sampled, that is, the run queue size, which includes the number of processes running in the cpu and the number of processes in the cpu waiting queue. For Linux, 1-minute, 5-minute, and 15-minute moving averages are actually calculated. To do this, we first need to introduce the three constants defined in Linux:
#define EXP_1 1884 /* 1/exp(5sec/1min) */
#define EXP_5 2014 /* 1/exp(5sec/5min) */
#define EXP_15 2037 /* 1/exp(5sec/15min) */
The three constants represent the constants of 1/5/15 minutes respectively. The calculation method is:
1884 = 2048/( power(e,(5/(60*1)))) /* e = 2.71828 */
2014 = 2048/(power(e,(5/(60*5))))
2037 = 2048/(power(e,(5/(60*15))))
We assume that the load calculated according to the constant 1884 at the previous moment is load1(t-1), and the current sampling run queue size is rq1, then the current load1(t) = ((load1(t-1) * 1884) + rq1 * (2048 - 1884))/2048
Similarly, the algorithms that can be used for 5-minute and 15-minute moving averages are load5(t) = ( (load5(t-1) * 2014) + rq1 * (2048 - 2014))/2048 and load_15(t) = ((load15(t-1) * 2037) + rq1 * (2048 - 2037))/2048

It can be seen that the larger the moving average interval, the impact of the current run queue size on the moving average tends to decrease.
As for why this number is chosen, it involves knowledge of calculus, so that the image produced is smoother.

http://www.bkjia.com/PHPjc/532000.htmlwww.bkjia.comtruehttp: //www.bkjia.com/PHPjc/532000.htmlTechArticlelinux loadavg algorithm Posted by: biti_rainy Today I read linux source code about the calculation method of cpu load, and searched on google at the same time After referencing everywhere, I was confused for a long time and finally figured out cpu loa...