Topas Command Explanation

Topas Command Explanationwww.educity.cnPublished by: Bigfeet Source:Network Reprint Release Date: May 19, 2014 article comments published articles

1.AIX System version

-bash-3.00$ Oslevel

5.3.0.0

2.topas command

Topas Monitor for Host: Aix events/queues File/tty

Sun Jan 8 12:51:10 interval:2 cswitch 5529 readch 11620

Syscall 6767 Writech 4357.3K

Kernel 1.7 |# | Reads 7 Rawin 1

User 1.6 |# | Writes Ttyout 403

Wait 0.3 |# | Forks 0 Igets 0

Idle 96.4 |############################| Execs 0 Namei 6

Runqueue 0.0 dirblk 0

Network KBPS i-pack o-pack kb-in kb-out waitqueue 0.0

EN0 0.9 2.0 3.0 0.3 0.7

Lo0 0.1 1.0 1.0 0.0 0.0 PAGING MEMORY

Faults 8 REAL,MB 1904

Disk busy% KBPS TPS kb-read kb-writ steals 0 Comp 46

Hdisk0 11.5 4.2K 27.5 0.0 4.2K pgspin 0 Noncomp 11

Hdisk1 0.0 0.0 0.0 0.0 0.0 pgspout 0 Client 11

cd0 0.0 0.0 0.0 0.0 0.0 Pagein 0

Pageout 1064 PAGING SPACE

Name PID CPU% pgsp Owner Sios 1064 SIZE,MB 512

Python 2400440 1.3 6.0 sutl% used 43

　　python 2433268 1.2 6.8 sutl NFS (calls/sec)% free 57

Trclogio 1650830 0.3 0.5 matthewh ServerV2 0

Dtgreet 340036 0.1 1.3 root ClientV2 0 Press:

Topas 1953858 0.1 1.7 xifenfei ServerV3 0 "h" for help

MUXATMD 106652 0.0 0.6 root ClientV3 0 "q" to quit

Gil 69666 0.0 0.9 root

XMGC 49176 0.0 0.4 root

sshd 2257092 0.0 2.8 Pillow

sshd 1101952 0.0 1.6 Xifenfei

　　Ping 848098 0.0 0.3 sylaryy

X 331840 0.0 1.6 root

Bash 2756856 0.0 0.6 Pillow

CTLCALLP 1966120 0.0 0.2 aug_gucc

Ctlsmsno 1622246 0.0 0.2 aug_gucc

Jobcente 1237188 0.0 0.2 aug_gucc

sshd 1744962 0.0 0.9 nanmingy

SEARCHPL 1015886 0.0 0.2 aug_gucc

Ctlinfos 254072 0.0 0.3 aug_gucc

Msgcente 1511494 0.0 0.2 aug_gucc

3.topas parameter list

Usage:topas [-D number_of_monitored_hot_disks]

[-H show help information]

[-I. Monitoring_interval_in_seconds]

[-M use monochrome mode-no colors]

[-N Number_of_monitored_hot_network_interfaces]

[-P number_of_monitored_hot_processes]

[-W NUMBER_OF_MONITORED_HOT_WLM classes]

[-C Number_of_monitored_hot_cpus]

[-P show Full-screen Process Display]

[-L Show Full-screen Logical Partition Display]

[-u username-show username owned processes With-p]

[-D show Full-screen Disk Display]

[-W show Full-screen WLM Display]

[-C Show Full-screen Cross-lpar (CEC) Panel]

[-R background Cross-lpar (CEC) recording mode]

[-I remote monitoring interval in seconds]

[-o availmem=total memory size allocated in MB]

[-O unavailmem=total memory size unallocated in MB]

[-O availcpu=total CPUs allocated on the HMC]

[-O unavailcpu=total CPUs unallocated on the HMC]

[-O partitions=number of partitions defined on the HMC]

[-O reconfig=reconf interval in sec 30/60 (default)/90/120/180/240/300]

[-O poolsize=defined Pool Size required if HMC PUA restricts access]

[-O managedsys=managed system name under which this partition is configured]

[-O HMC=HMC name under which this partition is configured]

HMC Configuration and recording information documented in:

/usr/lpp/perfagent/readme.perfagent.tools

4. Main parameter description

-D: Specifies the number of disks to monitor. This is also the maximum number of disks that can be displayed if the area displayed on the screen is large enough. When this value exceeds the number of disks actually installed, it only monitors and displays information about the installation disk, which defaults to 20.

-I: Sets the interval for monitoring time (in seconds), which defaults to 2 seconds.

-N: Sets the number of network interfaces being monitored. This is also the maximum number of network interfaces displayed on the screen, and when this value exceeds the number of network interfaces actually installed, only the installed network interface information is monitored and displayed. The default value of the parameter is 20, and if the value is set to 0, no network information is monitored.

-P: Specifies the number of processes being monitored. This is also the maximum number of processes that are displayed on the screen. The default value is 20, and if this value is 0, no process information is monitored . The resulting process information is the main overhead of Topas. If process information is not required, this parameter is typically used to specify which process information is not desired.

-W: Indicates the value of the monitored WLM class. This is also the maximum WLM value displayed on the screen, when this value exceeds the actual number of WLM installed, only the information of those installed WLM classes is displayed, the default value is 20, and if this value is 0, no information is displayed.

-C: Indicates the number of CPUs being monitored. This is also the maximum CPU value displayed on the screen, when this value exceeds the actual number of CPUs installed, only displays information about those installed CPUs, the default value is 20, and if this value is 0, no information is displayed.

-P: Displays the entire full screen process display. Displays a list of the busiest processes, similar to the default display, where each process displays only a few columns and can be sorted by any column.

-W: Displays the full-screen WLM (load manager) class. The top displays a series of WLM classes, similar to those shown in the WLM class.

In fact the Topas command is equivalent to: TOPAS-D20-I2-N20-P20-W20-C20

5. Some sub-command description

A This key shows all the different parts (cpu,network,disk,wlm,process) that are monitored .

C This key switches between the cumulative report and the busiest CPU.

D This key switches between the busiest disk and the total disk activity of the system.

H Displays help information.

n This key switches between the busiest interface and the total network activity of the system.

W This key switches between the switches of the WLM class.

P Switch between the switches of this key process.

P This key replaces the default display with full-screen process display.

W This key replaces the default display with the full-screen WLM class display.

F move the cursor to a WLM class, which displays a sequence of processes at the bottom of the WLM screen.

Q quit the program.

R update display.

6.topas Content Description

6.1) reflect CPU usage and operating conditions

user%: Displays the percentage of CPU consumed by the running user program;

kern%: Displays the percentage of CPU consumed by the running kernel program;

wait%: Displays the percentage of CPU consumed by the wait IO operation;

idel%: Displays the percentage of CPU idle.

6.2) reflect the network usage rate

Interf: The name of the network interface;

KBPS: Total traffic in m per second during monitoring, which includes the sum received and sent per second.

I-pack: The number of packets received per second during monitoring;

O-pack: The number of packets sent per second during monitoring;

Kb-in: Number of bytes received per second during monitoring (in k units);

Kb-out: The number of bytes sent per second during monitoring (in K).

6.3) reflect the status of disk usage

Disk: The name of the physical disk;

busy%: Percentage of disk busy, that is, the maximum IOPS (IO operations per second) that the disk can meet and the current number of IO

KBPS: The number of bytes read and written per second during monitoring (in k);

TPS: The amount of data transferred to the physical disk per second. A single transfer refers to an I/O request;

Kb-read: The number of K bytes read from the physical disk per second;

Kb-write: The number of K bytes written to the physical disk per second.

6.4) reflect the status of the process

Name: Names of executable programs;

Process ID: The ID number of the session;

%CPU utilization: CPU Average utilization of the process, which refers to the average usage of the process over the life cycle;

Paging space used: the size of paging spaces allocated to the process;

Process Owner: The user name that owns the process;

Workload Management (WLM) class: Which WLM class the process belongs to.

6.5) events/queues Status

Cswitch: The number of context conversions per second during monitoring;

Syscall: The total number of system calls running per second during monitoring;

Reads: The number of read system calls per second during monitoring;

Writes: The number of write system calls per second during monitoring;

Forks: The number of times the derived system call runs per second during monitoring;

Execs: The number of times per second that a system call is run during monitoring;

Runqueue: The average number of threads waiting for the processor to be idle to run;

Waitqueue: The average number of threads waiting for paging to complete;

6.6) File/tty Status

READCH: The number of bytes read per second by a system call during monitoring;

Writech: The number of bytes written per second through write system calls during monitoring;

Rawin: The number of bare bytes read through ttys per second during monitoring;

Ttyout: The number of bytes written to TTYs per second during monitoring;

Igets: The number of calls per second to the node to find the routine during monitoring ;

Namei: Number of calls per second path lookup routine during monitoring;

DIRBLK: The number of directory blocks scanned per second by the directory search routine during the monitoring process;

6.7) Paging section shows the number of pagination per second

Faults: The total number of paging errors that occur per second during monitoring;

Steals: A frame of 4k of physical memory stolen by the virtual Memory manager every second during monitoring;

Pgspin: The number of 4k pages per second read from the paging space during monitoring;

Pgspout: The number of 4k pages per second that are written to the paging space during monitoring;

Pagein: The number of 4k pages read per second during monitoring, which includes paging activity related to the file system read operation, and subtracting the value of Pgspin from this value is the paging activity associated with the file system read operation per second;

Pageout: The number of 4k pages written per second during monitoring, which includes paging activity related to file system writes, and subtracting the value of pgspout from this value is the paging activity associated with the file system write operation per second;

Sios: The number of I/O requests received through the virtual Memory manager during monitoring ;

6.8) The Momory section shows the actual memory and the memory in use

REAL,MB: The actual memory in m units;

%comp: The percentage of memory currently allocated to the compute paging fragment for the actual memory. The calculation of the paging fragment is generated by the paging space.

%nocomp: The percentage of memory currently allocated for non-computed paging fragments. Non-computed paging fragments include those file spaces, data files, executable files, or shared library files.

%client: The percentage of memory currently allocated to buffer remote mounted files to actual memory.

6.9) paing space shows the size and utilization of paging spaces

SIZE,MB: The size of all paging space in the system, in m units;

%used: The percentage of total space currently used for paging space;

%free: The percentage of total space that is currently free of paging space.

6.10) NFS (calls/sec) status

Display NFS stats in calls per second

Topas Command Explanation