ps
* Grammar: ps [options]
Note: This command looks at the instantaneous running state of a process at a given time, and looks at it discontinuously.
Three options are supported:
UNIX options such as - a (prefix -)
BSD options such as a
Display processes in the current terminal by default
The a option includes processes in all terminals
The x option includes processes with disconnected terminals (processes with TTY status of?
The u option displays information about the process owner
The f option shows the parent process of the process
The o attribute... Options to display customized information:
pid,comm,%cpu,%mem,state,tty,euser,ruser***
[14:38 root@Centos6.8/proc/10]# ps aux
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1 0.0 0.0 19352 1548 ? Ss 08:46 0:02 /sbin/init
root 2 0.0 0.0 0 0 ? S 08:46 0:00 [kthreadd]
root 2007 0.0 0.0 4064 544 tty2 Ss+ 08:48 0:00 /sbin/mingetty /dev/tty2
root 2012 0.0 0.0 4064 540 tty3 Ss+ 08:48 0:00 /sbin/mingetty /dev/tty3
root 2014 0.0 0.0 4064 544 tty4 Ss+ 08:48 0:00 /sbin/mingetty /dev/tty4
root 2017 0.0 0.0 4064 540 tty5 Ss+ 08:48 0:00 /sbin/mingetty /dev/tty5
root 2019 0.0 0.0 4064 544 tty6 Ss+ 08:48 0:00 /sbin/mingetty /dev/tty6
root 2028 0.0 0.1 12640 2876 ? S< 08:48 0:00 /sbin/udevd -d
root 2060 0.0 0.1 164924 3564 ? Sl 08:48 0:00 /usr/libexec/gdm-simple-slave --display-id /org/gnome/DisplayManager
root 2064 0.0 1.5 196384 29084 tty1 Ssl+ 08:48 0:04 /usr/bin/Xorg :0 -br -verbose -audit 4 -auth /var/run/gdm/auth-for-g
root 2087 0.0 0.1 1036464 3360 ? Sl 08:48 0:00 /usr/sbin/console-kit-daemon --no-daemon
gdm 2159 0.0 0.0 20044 696 ? S 08:48 0:00 /usr/bin/dbus-launch --exit-with-session** USER: Users who initiate the process
PID:PID number
% CPU: Percentage of CPU used
% MEM: Percentage of memory used
VSZ: Virtual memory SiZe, virtual memory set, linear memory
RSS: ReSidentSize, Permanent Memory Set
TTY: Terminally related
STAT: Process state
START: Process Start Time
TIME: The time that a process actually runs on the CPU, not on the hang-up table
COMMANDD: The command to initiate a process, [If the command has middle brackets, it represents a kernel process]**
ps - Sort by how much memory the process consumes
ps -eo rss,pmem,pcpu,vsize,args | sort -k 1 -r -n | less
top
top
top - 16:55:12 up 4 days, 19:15, 3 users, load average: 0.00, 0.00, 0.00
Tasks: 169 total, 1 running, 168 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.7%us, 0.7%sy, 0.0%ni, 98.3%id, 0.0%wa, 0.0%hi, 0.3%si, 0.0%st
Mem: 1004768k total, 876500k used, 128268k free, 114876k buffers
Swap: 2031612k total, 8k used, 2031604k free, 388272k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
4635 w 20 0 291m 17m 14m S 1.0 1.8 8:20.21 vmtoolsd
1552 root 20 0 173m 8104 4540 S 0.7 0.8 15:36.70 vmtoolsd
3074 mysql 20 0 895m 73m 12m S 0.7 7.5 6:55.30 mysqld
4572 w 20 0 494m 10m 8192 S 0.7 1.1 0:12.53 gnome-settings-
7 root 20 0 0 0 0 S 0.3 0.0 9:44.50 events/0
24 root 20 0 0 0 0 S 0.3 0.0 3:02.92 ata_sff/0
729 root 20 0 0 0 0 S 0.3 0.0 0:28.84 vmmemctl
3492 root 20 0 134m 9528 1052 S 0.3 0.9 7:19.99 redis-server
4983 root 20 0 99976 4048 3088 S 0.3 0.4 0:03.41 sshd
5373 root 20 0 15032 1272 928 R 0.3 0.1 0:00.17 top
1 root 20 0 19356 1544 1228 S 0.0 0.2 0:07.43 init
2 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kthreadd
3 root RT 0 0 0 0 S 0.0 0.0 0:00.00 migration/0
4 root 20 0 0 0 0 S 0.0 0.0 0:56.32 ksoftirqd/0
5 root RT 0 0 0 0 S 0.0 0.0 0:00.00 stopper/0
6 root RT 0 0 0 0 S 0.0 0.0 0:13.14 watchdog/0
8 root 20 0 0 0 0 S 0.0 0.0 0:00.00 events/0
9 root 20 0 0 0 0 S 0.0 0.0 0:00.00 events_long/0
10 root 20 0 0 0 0 S 0.0 0.0 0:00.00 events_power_ef
11 root 20 0 0 0 0 S 0.0 0.0 0:00.00 cgroup
12 root 20 0 0 0 0 S 0.0 0.0 0:00.00 khelper
13 root 20 0 0 0 0 S 0.0 0.0 0:00.00 netns
14 root 20 0 0 0 0 S 0.0 0.0 0:00.00 async/mgr
15 root 20 0 0 0 0 S 0.0 0.0 0:00.00 pm
16 root 20 0 0 0 0 S 0.0 0.0 0:06.45 sync_supers uptime
CPU load in the past 15 minutes
16:58:37 up 109 days, 16:57, 1 user, load average: 0.00, 0.00, 0.00
If this number is divided by the number of CPU s, the result above 5 indicates that the system is overloaded. Normally, it should be controlled within the range of less than 1. Usually we first look at the 15-minute load, if the load is very high, then look at the 1-minute and 5-minute load to see if there is a downward trend.
The first line is the task queue information, along with the execution results of the uptime command. Its contents are as follows:
01:06:48 Current Time
up 1:22 system runtime in time:
1 user Current number of logged-in users
load average: 0.06, 0.60, 0.48 system load, that is, the average length of the task queue.
The three values are 1 minute, 5 minutes and 15 minutes ago to the present average.
Second, third, the information of behavior process and CPU. When there are multiple CPUs, these contents may exceed two lines. The contents are as follows:
Tasks: 29 total process total
1 Number of running processes
Number of Sleeping Processes
Number of processes stopped by 0 stopped
Number of zombie botnet processes
Cpu(s): 0.3% us user space as a percentage of CPU
1.0% sy Kernel Space Percentage of CPU
Percentage of CPU occupied by processes that changed priority in 0.0% ni user process space
98.7% id idle CPU percentage
Percentage of CPU time for 0.0% wa to wait for input and output
0.0% hi
0.0% si
The last two behaviors are memory information. The contents are as follows:
Mem: 191272k total physical memory
Total physical memory used by 173656k user
17616k free Total Free Memory
The amount of memory 22052k buffers use as kernel caches
Swap: Total exchange area 192772k
Total switching area used by 0k user
Total Free Exchange Area 192772k
The total number of switches buffered by 123988k cache.
vmstat
procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu-----
r b swpd free buff cache si so bi bo in cs us sy id wa st
0 0 0 629036 269024 553024 0 0 6 4 163 109 1 2 97 0 0 When the value of SY is relatively high, it means that the CPU time consumed by the kernel is more; if us+sy exceeds 80%, it means that the CPU resources are insufficient.
r represents the run queue (that is, how many processes are actually allocated to the CPU), and if this value exceeds the number of CPUs, there will be CPU bottlenecks, which are related to the top load.
b denotes a blocking process
swpd virtual memory has been used size, if greater than 0 means machine physical memory is insufficient
Free denotes the size of free physical memory.
The buff linux/unix system is a cache used to store contents, permissions, etc. in a directory.
Cache is used to remember the files we open, to cache the files, and to cache the files and directories with the spare physical memory. It is to improve the performance of program execution when the program uses memory. Buffer / cache will be used quickly
The size of virtual memory read from disk by si per second, if greater than 0, indicates that physical memory is insufficient
so virtual memory per second is written to disk in the same size as above
The number of blocks received per second by a bi block device. The block device here is essentially all disks and other block devices on the system. The default block size is 1024 byte.
The number of blocks sent per second by bo devices is close to 0 for bi and bo Ibanez. Otherwise, IO is too frequent and needs to be adjusted.
The bi+bo reference value set here is 1000, and if it exceeds 1000 and wa value is relatively large, it indicates that the system disk IO performance bottleneck.
in the number of CPU interrupts per second, including time interrupts.
The number of context switching per second of cs, such as when we call system functions, we need to switch context, thread switching, and process context switching. The smaller the value, the better, the larger the value. We should consider lowering the number of threads or processes. For example, in web servers such as apache and nginx, we usually do thousands of concurrent or even tens of thousands of concurrent performance tests. Testing, the process of selecting the web server can be downgraded by the peak value of the process or thread until CS reaches a relatively small value, and the number of processes and threads is the appropriate value. System calls are also, every time we call system functions, our code will enter the kernel space, leading to context switching, which is very resource-intensive, but also try to avoid frequent calls to system functions. Too many context switching times mean that most of your CPU is wasted on context switching, resulting in less time for CPU to do serious work, and CPU is not fully utilized, which is not advisable.
U user CPU time, I used to do encryption and decryption on a very frequent server, you can see us close to 100,r run queue up to 80 (the machine in stress testing, poor performance).
When the value of us is relatively high, it means that the CPU time consumed by the user process is too much. If the CPU time is longer than 50%, we need to consider the optimization program.
When the value of SY is relatively high, it means that the CPU time consumed by the kernel is more; if us+sy exceeds 80%, it means that the CPU resources are insufficient.
sy system CPU time, if too high, means long system call time, such as frequent IO operations.
ID idle CPU time, generally speaking, id + us + sy = 100, generally I think id is idle CPU usage, us is user CPU usage, sy is system CPU usage.
wa waits for IO CPU time.
The wa list shows the percentage of CPU time IO waits take. The higher wa value, the more serious IO waiting. If wa value exceeds 20%, IO waits seriously.
Get memory usage information for a particular process
Get the pid of the mysqld process
[root@6 ~]# pidof mysqld
top Specifies View PID
[root@6 ~]# top -p 21538
Viewing Threads for a Specific Process
top -H -p
Change from: http://www.mamicode.com/info-detail-1519419.html
https://my.oschina.net/u/1396185/blog/366043