GrooveYOU

전체 글

구입 목록 2018.04.09
How to use the HMC Commandline 2018.03.22
RHEL7: How to get started with CPU governor 2018.03.20

구입 목록

GrooveYOU 2018. 4. 9. 16:30

2018. 4. 9. 16:30

[세탁기]

-후보1) F19VDWC ( 19kg + 3.5kg ) - 167만원 (KB카드)

http://with.gsshop.com/deal/deal.gs?dealNo=29062909&NaPm=ct=jfrwbdgw|ci=33d69435a8757ee5047fd414af51464f59492685|tr=slsl|sn=1|hk=6e02ab11938a0f95a5308f75ffde9f95bbf57018&media=MA&fromWith=Y

선택 76번

-후보2) F19bfwm (19kg + 4kg) - 175만원

https://search.shopping.naver.com/search/all.nhn?query=F19VDWC&cat_id=&frm=NVSHATC

저작자표시 비영리 변경금지

How to use the HMC Commandline

GrooveYOU 2018. 3. 22. 18:18

2018. 3. 22. 18:18

http://www.unixwerk.eu/aix/hmc-howto.html

This documents contains the most important HMC commands. It covers both, the old power4 commands (up to HMC Version 3) and the new power5 style commands (HMC Version 4-6). A lot of nice commands still available for version 3 (power4) are removed from newer releases. One example of these nice commands is lslpars and it's not available for HMC version 4 and higher. The real reason behind it is that IBM wants to force us to use the web based tools wsm and WebSM or the new HMC browser GUI. This documents helps you to survive with the HMC commands in case working with the web based tools is not feasible.

In the examples below we call a whole power frame (aka Managed System) pserver. We call an LPAR mylpar. If an example output shows more than one LPAR name we enumerate it. LPAR Profiles are shown as myprofile. You have to replace these names with your object names.

If you use power6 systems, you need the new HMC version7. Although the GUI has changed from wsm to a browser based service, the commandline remains compatible. You can just use the power5 examples for power6, power7, and power8. However, additional features have been implemented.with HMC version 7.

HMC Management

LPAR Management: Status Information

LPAR Management: Operations

LPAR Configuation

Operations in an Virtualized Environment

HMC Management

1. HMC Version

hscroot@hmc> lshmc -V
 Version: 3
 Release: 3.2
HMC Build level 20040827.1

power4 HMCs could never show a version higher 3.x - HMC version 4.x and higher are only for power5 systems. Power6 systems need HMCs version 7.x.

2. Network configuration of the HMC

hscroot@hmc> lshmc -n

3. Reboot the HMC

power4 + power5/6/7:

hscroot@hmc> hmcshutdown -t now -r

4. How to change the HMC password (of user hscroot)

power4 + power5/6/7:

hscroot@hmc> chhmcusr -u hscroot -t passwd
Enter the new password:
Retype the new password:

5. How to add an SSH key for remote access

for hscroot

power5/6/7:

hscroot@hmc> mkauthkeys -a "public key"

Use the public key found in the users .ssh directory for public key (i.e. the contents of the file ~/.ssh/id_rsa.pub).

for other users

power5/6/7:

hscroot@hmc> mkauthkeys -u user -a "public key"

6. Show Available Filesystem Space

power5/6/7:

hscroot@hmc> monhmc -r disk -n 0
Filesystem           1K-blocks      Used Available Use% Mounted on
/dev/sda2             16121184   4958484  10343788  33% /
udev                    517300       156    517144   1% /dev
/dev/sda3              6040320   1341736   4391744  24% /var
/dev/sda7              8056524    154132   7493140   3% /dump
/dev/sda8             38669964    203056  36502564   1% /extra

It's just the same as you would expect from the UNIX command df.

LPAR Management: Status Information

1. LPAR Status

That's how you get an overview of all systems controlled by your HMC:

power4:

hscroot@hmc> lslpars

power5/6/7:

hscroot@hmc> lssyscfg -r sys -F name:serial_num:state
pserver1:656D24A:Operating
pserver2:656FFFF:Operating

The format string 'lpar_id:name:serial_num:state' also tells you the serial number of the systems. You can omit the field 'serial_num' if you don't need to know.
However, for every system from the list above you get the LPAR overview as shown below:

hscroot@hmc> lssyscfg -m pserver -r lpar -F name:state

Example:

hscroot@hmc> lssyscfg -m pserver1 -r lpar -F name:state
mylpar1:Running
mylpar2:Running
mylpar3:Not Activated

Don't know where to start? Find all managed systems and LPARs with a query:

hscroot@hmc> for m in $(lssyscfg -r sys -F name); do printf "\n=== $m ===\n" ; \
                                                     lssyscfg -r lpar -m $m -F lpar_id:name:state | sort -n ; done
=== pserver1 ===
1:mylpar1:Running
2:mylpar2:Running
3:mylpar3:Not Activated

=== pserver2 ===
2:mylpar12:Running
3:mylpar13:Running

2. Show Status and LED/LCD Display of an LPAR

power4:

hscroot@hmc> lssyscfg -r lpar -m pserver -n mylpar

power5/6/7:


hscroot@hmc> lsrefcode -m pserver -r lpar --filter "lpar_names=mylpar" -F lpar_name:refcode

You can even see the history of LED codes. Just use -n <NUM> for the last NUM codes. For example, if you want to see the last 5 LED codes of an LPAR type

hscroot@hmc> lsrefcode -m pserver -r lpar --filter "lpar_names=mylpar"  -n 5 -F lpar_name:refcode
mylpar:
mylpar:0c33
mylpar:
mylpar:0539
mylpar:0538

... and for the status LEDs:

hscroot@hmc> lsled -m pserver -r sa -t virtuallpar --filter ""lpar_names=mylpar""

3. Show Status and LED/LCD Display of a Systems Running in FullPartitionMode

power4:

hscroot@hmc> lssyscfg -r sys -n pserver

4. Overview LPAR IDs

power5/6/7:

hscroot@hmc> lssyscfg -r lpar -m pserver -F lpar_id:name:serial_num:state | sort -n
1:vioserver1:Running
2:vioserver2:Running
3:mylpar1:Not Activated
4:mylpar2:Running
5:mylpar3:Running
6:mylpar4:Running
7:mylpar5:Running
8:mylpar6:Running
9:mylpar7:Running
10:mylpar8:Not Activated

5. Overview Connection State

Are all service processors connected to my HMC?

power5/6/7:

hscroot@hmc> lssysconn -r all -F type_model_serial_num:ipaddr:state | sort
9117-570*65AE18C:172.16.255.253:Connected
9117-570*65AE18C:172.16.254.255:Connected
9117-570*65AE2AC:172.16.255.254:Connected
9117-570*65AE2AC:172.16.254.254:Connected
9117-570*650D70D:172.16.255.252:Connected
9117-570*650D70D:172.16.253.255:Connected
9117-570*650D71D:172.16.254.253:Connected
9117-570*650D71D:172.16.255.251:Connected
9131-52A*065F7BB:172.16.253.254:Connected
9131-52A*065F8BA:172.16.254.252:Connected

The link to the name of the managed system is the serial number - not the IP address! The IP addresses listed above are mounted on the service processor's private NIC and managed by the integrated DHCP server of the HMC.

6. Show a List of All I/O Adapters

The command below will show a list of all adapters physically plugged into a Managed System:

power5/6/7:

hscroot@hmc> lshwres -r io -m pserver --rsubtype slot --filter -F lpar_name:drc_name:description
null:U78C0.001.DBJC357-P2-C8-T5:Universal Serial Bus UHC Spec
mylpar1:U78C0.001.DBJC357-P2-C1:Fibre Channel Serial Bus
null:U78C0.001.DBJC357-P2-C2:Fibre Channel Serial Bus
vios2:U78C0.001.DBJC357-P2-T3:RAID Controller
vios2:U78C0.001.DBJC357-P2-C8-T7:Generic XT-Compatable Serial Controller
vios2:U78C0.001.DBJC357-P2-C5:Fibre Channel Serial Bus
vios2:U78C0.001.DBJC357-P2-C6:Ethernet controller
vios2:U78C0.001.DBJC357-P2-C9-T2:PCI-E SAS Controller
vios2:U78C0.001.DBJC357-P2-C9-T1:PCI-E SAS Controller
null:U78C0.001.DBJC373-P2-C8-T5:Universal Serial Bus UHC Spec
mylpar1:U78C0.001.DBJC373-P2-C1:Fibre Channel Serial Bus
null:U78C0.001.DBJC373-P2-C2:Fibre Channel Serial Bus
vios1:U78C0.001.DBJC373-P2-T3:RAID Controller
vios1:U78C0.001.DBJC373-P2-C8-T7:Generic XT-Compatable Serial Controller
vios1:U78C0.001.DBJC373-P2-C5:Fibre Channel Serial Bus
vios1:U78C0.001.DBJC373-P2-C6:Ethernet controller
vios1:U78C0.001.DBJC373-P2-C9-T2:PCI-E SAS Controller
vios1:U78C0.001.DBJC373-P2-C9-T1:PCI-E SAS Controller

A leading "none" indicates that the adapter is not assigned to an LPAR. To show a list of all I/O adapters owned by a specific LPAR use the "--filter" modifier:

power5/6/7:

hscroot@hmc> lshwres -r io -m pserver --rsubtype slot -F lpar_name:drc_name:description --filter "lpar_names=mylpar1"
mylpar1:U78C0.001.DBJC357-P2-C1:Fibre Channel Serial Bus
mylpar1:U78C0.001.DBJC373-P2-C1:Fibre Channel Serial Bus

7. Overview DLPAR status

power5/6/7:

hscroot@hmc> lspartition -dlpar
<#0> Partition:<6*9117-MMB*656D24A, mylpar1.unixwerk.de, 111.111.15.66>
       Active:<0>, OS:<AIX, 5.3, 5300-09-08-1036>, DCaps:<0x0>, CmdCaps:<0x0, 0x0>, PinnedMem:<512>
<#1> Partition:<2*9117-MMB*656D24A, vios1.unixwerk.de, 111.111.15.65>
       Active:<1>, OS:<AIX, 6.1, 6100-06-00-0000>, DCaps:<0x4f9f>, CmdCaps:<0x1b, 0x1b>, PinnedMem:<520>
<#2> Partition:<1*9117-MMB*656D24A, vios2.unixwerk.de, 111.111.15.64>
       Active:<1>, OS:<AIX, 6.1, 6100-06-00-0000>, DCaps:<0x4f9f>, CmdCaps:<0x1b, 0x1b>, PinnedMem:<518>
<#3> Partition:<3*9117-570*656FFFF, mylpar2.unixwerk.de, 111.111.226.4>
       Active:<1>, OS:<AIX, 5.3, 5300-09-04-0920>, DCaps:<0x2f>, CmdCaps:<0xb, 0xb>, PinnedMem:<1707>
<#4> Partition:<1*9117-570*656FFFF, mylpar3.unixwerk.de, 111.111.226.2>
       Active:<1>, OS:<AIX, 5.3, 5300-09-04-0920>, DCaps:<0x2f>, CmdCaps:<0xb, 0xb>, PinnedMem:<884>
<#5> Partition:<1*9133-55A*650D71D, mylpar7.unixwerk.de, 111.111.0.26>
       Active:<1>, OS:<AIX, 5.3, 5300-09-03-0918>, DCaps:<0x2f>, CmdCaps:<0xb, 0xb>, PinnedMem:<406>
<#6> Partition:<4*9117-570*656FFFF, mylpar4.unixwerk.de, 111.111.226.5>
       Active:<1>, OS:<AIX, 5.3, 5300-09-04-0920>, DCaps:<0x2f>, CmdCaps:<0xb, 0xb>, PinnedMem:<967>

A value <1> for Active: should be fine.

LPAR Management: Operations

1. Soft Reset of an LPAR

power4:

hscroot@hmc> chsysstate -m pserver -r lpar -n mylpar -o reset

power5/6/7:

hscroot@hmc> chsysstate -r lpar -m pserver -o shutdown -n mylpar

2. Soft Reset of a System Running in FullPartitionMode

power4:

hscroot@hmc> chsysstate -n pserver -r sys -o reset

3. Hard Reset of an LPAR

power4:

hscroot@hmc> chsysstate -m pserver -r lpar -n mylpar -o off

power5/6/7:

hscroot@hmc> chsysstate -r lpar -m pseries -o shutdown -n mylpar --immed

4. Hard Reset of a System Running in FullPartitionMode

power4:

hscroot@hmc> chsysstate -n pserver -r sys -o off

5. Virtual Console

That's how you get a connection to an LPAR's serial console:

power4 + power5/6/7:

hscroot@hmc> mkvterm -m pserver -p mylpar

If your system is running in FullSystemPartition-Mode you connect with a command like this:

power4:

hscroot@hmc> mkvterm -m pserver

You can escape from the console connection by typing ~~. (twice tilde followed by a dot)

If you cannot connect to the serial console and you get an error message instead:

All available virtual terminal sessions have been opened and are in use. 
To force a new open session, perform a Close Terminal Session operation
which frees up the session.

there is still another active connection to this console. You can close this connection with:

power4 + power5/6/7:

hscroot@hmc> rmvterm -m pserver -p mylpar

If you're not sure which managed system belongs to an LPAR you could walk through the vtmenu:

hscroot@hmc> vtmenu
 Retrieving name of managed system(s) . . . 

 ----------------------------------------------------------
  Managed Systems:
 ----------------------------------------------------------
   1) pserver1
   2) pserver2
   3) pserver3

 Enter Number of Managed System.   (q to quit): 1

 ----------------------------------------------------------
  Partitions On Managed System:  pserver1
 ----------------------------------------------------------
   1)    mylpar1                              Running
   2)    mylpar2                              Running
   3)    mylpar3                              Running
   4)    mylpar4                              Running
   5)    mylpar5                              Running


 Enter Number of Running Partition (q to quit):

Just enter a number and you will be connected to the console of the corresponding LPAR.

6. Activation of an LPAR

power4:

hscroot@hmc> chsysstate -r lpar -m pserver -o on [ -f myprofile ] -n mylpar

power5/6/7:

hscroot@hmc> chsysstate -r lpar -m pserver -o on -f myprofile -n mylpar

7. How to Boot an LPAR into SMS Menu

power4:

You have to create an additional profile. In this profile set the boot mode to 'sms'. We call the profile mysmsprofile. Then start the LPAR with this profile:

hscroot@hmc> chsysstate -r lpar -m pserver -o on -f mysmsprofile -n mylpar

power5/6/7:

With new HMCs a special profile is not any longer needed. The profile's boot mode can be overwirtten with -b:

hscroot@hmc> chsysstate -r lpar -m pserver -o on -f myprofile -b sms -n mylpar

The same way the LPAR can be bootet into the Open Firmware prompt (Bootmode: 'of'):

hscroot@hmc> chsysstate -r lpar -m pserver -o on -f myprofile -b of -n mylpar

8. How to Power on a System Running in FullPartitionMode

power4:

hscroot@hmc> chsysstate -o on -r sys -n pserver -c full

9. Bring the key switch to position NORMAL

This might be necessary on some power5 HMCs when an LPAR does not properly boot after issuing the power on command above. You might see a message like this:

0514-440 cfgcon: failed to create log file: check path name, permissions, and available space

When seeing this you can only access diag mode or boot the LPAR in singleuser mode. This command sets the key switch back to normal position:

power5/6/7:

hscroot@hmc> chsysstate -r lpar -o chkey -k norm -n mylpar -m pserver

LPAR Configuration

1. Change an LPAR's Name

Let's say we have these five LPARs defined on a managed system:

hscroot@hmc> lssyscfg -r lpar -m pserver -F lpar_id:name:state
1:vios1:Running
2:vios2:Running
3:barney:Running
4:mylpar2:Running
5:mylpar3:Running

Now we want to change the name of LPAR 3 from barney to mylpar1:

power5/6/7:

hscroot@hmc> chsyscfg -r lpar -m pserver -i "name=barney,new_name=mylpar1"

We check and see that the name of LPAR 3 indeed has changed to mylpar1:

hscroot@hmc> lssyscfg -r lpar -m pserver -F lpar_id:name:state
1:vios1:Running
2:vios2:Running
3:mylpar1:Running
4:mylpar2:Running
5:mylpar3:Running

2. Rename a Managed System

This would change the name of the manages system pserver to pserver1:

power5/6/7:

hscroot@hmc> chsyscfg -r sys -m pserver -i "new_name=pserver1"

3. DLPAR: Increase the Number of Processing Units of an LPAR

To assign 8 additonal processing units to an LPAR run the following command:

power5/6/7:

hscroot@hmc> chhwres -r proc -m pserver -o a -p mylpar --procunits 8

4. DLPAR: Increase the Amount of Memory of an LPAR

To assign 1 GB additonal memory to an LPAR run the following command:

power5/6/7:

hscroot@hmc> chhwres -r proc -m pserver -o a -p mylpar -q 1024

Operationen in einer virtualisierten Umgebung

HMC Version 7 can run operations on Virtual I/O Servers.

1. Make virtual WWPNs visible to the SAN

The below command would login all virtual adapters of the LPAR with ID 12 to the SAN:

HMC Version 7

hscroot@hmc> chnportlogin -o login -m pserver --id 12

2. Show all virtual WWPNs assigned to an LPAR

e.g. for an LPAR with ID 12, type

HMC Version 7

hscroot@hmc> lsnportlogin -m pserver --filter "lpar_ids=12"
lpar_name=mylpar,lpar_id=12,profile_name=default,slot_num=51,wwpn=c050726660a0002c,wwpn_status=1,logged_in=vios,wwpn_status_reason=null
lpar_name=mylpar,lpar_id=12,profile_name=default,slot_num=51,wwpn=c050726660a0002d,wwpn_status=1,logged_in=vios,wwpn_status_reason=null
lpar_name=mylpar,lpar_id=12,profile_name=default,slot_num=52,wwpn=c050726660a0002e,wwpn_status=1,logged_in=vios,wwpn_status_reason=null
lpar_name=mylpar,lpar_id=12,profile_name=default,slot_num=52,wwpn=c050726660a0002f,wwpn_status=1,logged_in=vios,wwpn_status_reason=null

You can also list the status of more than one LPAR in one go:

HMC Version 7

hscroot@hmc> lsnportlogin -m pserver --filter "\"lpar_ids=12,13\""

3. Logout virtual WWPNs from the SAN

HMC Version 7

hscroot@hmc> chnportlogin -o logout -m pserver --id 12

저작자표시 비영리 변경금지

RHEL7: How to get started with CPU governor

GrooveYOU 2018. 3. 20. 17:57

2018. 3. 20. 17:57

https://www.certdepot.net/rhel7-get-started-cpu-governor/

RHEL7: How to get started with CPU governor.

Presentation of CPU Governor

The modern x86 processors provide two mechanisms to reduce power consumption when idle. Useful for a portable PC, it can also help for physical servers with limited workload.

However, don’t think about virtual machines, they are not concerned.

CPU Idle States

In the x86 architecture several CPU states, called C-states, have been defined, allowing systems to save power by decreasing CPU functionalities. These C-states are broadly similar across processors but the exacts details may vary.

C0: The processor is working as usual.
C1: The processor doesn’t execute any instruction but can start working again without any delay.
C2: The processor is stopped but keeps the complete state of its registers and caches. A delay is necessary for the processor to start working again.
C3: The processor is sleeping and doesn’t keep its caches. A longer delay than in C2 state is needed for the processor to start working again.

CPU Freq

CPU Freq or CPU speed scalling is a way to reduce power consumption by adjusting the clock speed of the processor.
Five CPU Freq governors are available in RHEL 7:

performance: with this static governor you get the highest possible clock frequency but without any power saving benefit. It is best suited for heavy workload when the CPU is almost never idle.
powersave: here your CPU gets the lowest possible clock frequency but at the cost of the lowest CPU performance. One serious drawback of this static governor happens when the system experiences unexpected high loads: in this case it can consume more power than other governors with higher clock frequencies. For this reason, it is not recommended to use it except when overheating is a problem.
ondemand: this dynamic governor sets the maximum clock frequency when system load is high and minimum clock frequency when idle, but without intermediate state. This allows the system to adjust power consumption according to system load but at the expense of latency. In case switches between idle and heavy workloads happen too often, performance and power saving can suffer. Otherwise, it is one of the best options.
userspace: with this governor, any process running as root can set the clock frequency.
conservative: this dynamic governor is very similar to the ondemand governor except it adjusts clock frequency more gradually. Instead of choosing between maximum and minimum clock frequencies, it selects the clock frequency according to usage. This more granular approach provides significant power saving but at the expense of an ever greater latency than the ondemand governor.

Installation Procedure

Install the kernel-tools package to get access to the cpupower command:

# yum install -y kernel-tools

Note: The kernel-tools package and the cpupower command are not strictly needed to manipulate CPU governors. They only provide a convenient interface. All operations can be done using the /sys/devices/system/cpu/ path and the echo command.

Basic Operations

To get the list of the various idle states supported by the CPU number 0 (available idle states are given for various types of servers), type:

# cpupower idle-info
CPUidle driver: intel_idle
CPUidle governor: menu
analyzing CPU 0:
...
Available idle states: POLL C1E-ATM C2-ATM C4-ATM C6-ATM (Atom CPU N2800)
Available idle states: POLL C1-IVB C1E-IVB C3-IVB C6-IVB (Xeon CPU E3-1245 V2)
Available idle states: POLL C1-NHM C1E-NHM C3-NHM C6-NHM (Core i5 CPU M 430)
Available idle states: POLL C1-HSW C1E-HSW C3-HSW C6-HSW C7s-HSW C8-HSW C9-HSW C10-HSW (Celeron 2961Y)
...

To get the same information for all the CPUs on a server, type:

# cpupower -c all idle-info

Note: The -c option can be replaced with –cpu.

To get the list of the available governors for the CPU number 0, type:

# cpupower frequency-info -g
analyzing CPU 0:
  available cpufreq governors: conservative userspace powersave ondemand performance

Note: The -g option can be replaced with –governors.

To get all the details about the available CPU frequencies for the CPU number 0, type:

# cpupower frequency-info
analyzing CPU 0:
 driver: acpi-cpufreq
 CPUs which run at the same hardware frequency: 0
 CPUs which need to have their frequency coordinated by software: 0
 maximum transition latency: 10.0 us
 hardware limits: 1.20 GHz - 2.27 GHz
 available frequency steps: 2.27 GHz, 2.27 GHz, 2.13 GHz, 2.00 GHz, 1.87 GHz, 1.73 GHz, 1.60 GHz, 1.47 GHz, 1.33 GHz, 1.20 GHz
 available cpufreq governors: conservative userspace powersave ondemand performance
 current policy: frequency should be within 1.20 GHz and 2.27 GHz.
                 The governor "conservative" may decide which speed to use
                 within this range.
 current CPU frequency: 1.20 GHz (asserted by call to hardware)
 boost state support:
 Supported: yes
 Active: yes
 1900 MHz max turbo 2 active cores
 1900 MHz max turbo 1 active cores

Note1: Without the -c option, only the information about the CPU number 0 is displayed.
Note2: The governor conservative is the current configuration.

To change the governor to performance for all the CPUs, type:

# cpupower frequency-set -g performance
Setting cpu: 0
Setting cpu: 1
Setting cpu: 2
Setting cpu: 3

Note1: Without the -c option, all the CPUs are affected.
Note2: To only change for the CPUs number 0, 1 and 2, type: # cpupower -c 0-2 frequency-set -g performance
Note3: The -g option can be replaced with –governor.

# cpupower -c all frequency-info
...
 current policy: frequency should be within 1.20 GHz and 2.27 GHz.
                 The governor "performance" may decide which speed to use
                 within this range.
...

To specify the governor userspace for the CPU number 1 with a CPU frequency of 1.2GHz, type:

# cpupower -c 1 frequency-set -f 1.2
Setting cpu: 1
# cpupower -c 1 frequency-info -p
analyzing CPU 1:
  current policy: frequency should be within 1.20 GHz and 2.27 GHz.
                  The governor "userspace" may decide which speed to use
                  within this range.
# cpupower -c 1 frequency-info -f
analyzing CPU 1:
  current CPU frequency: 1199000 (asserted by call to kernel)
# cpupower -c 1 frequency-info --hwlimits
analyzing CPU 1:
  hardware limits: 1.20 GHz - 2.27 GHz

Note: Only the governor userspace allows frequencies to be set.

Standard Operations

All commands seen previously don’t persist after reboot. The standard way to set up CPU governor in a persistent way is through the tuned daemon and the governor directive (alternatively, using rc.local only works if the tuned service is disabled).

If we look at the throughput-performance tuned profile (/usr/lib/tuned/throughput-performance/tuned.conf), we can see:

...
[cpu]
governor=performance
energy_perf_bias=performance
min_perf_pct=100
...

Note: The energy_perf_bias directive allows software on supported Intel processors to more actively contribute to determining the balance between optimum performance and saving power.

Therefore, if you want to define a specific configuration, create a new tuned profile with the tuned inheritance mechanism in the /etc/tuned directory (see the tuned tutorial):

[main]
include=throughput-performance

[cpu]
...

Behaviour Analysis

To get a better understanding of the way your system behaves, install the powertop package:

# yum install -y powertop

Then, run the powertop command:

# powertop
PowerTOP 2.3      Overview   Idle stats   Frequency stats   Device stats   Tunables            

Summary: 528.4 wakeups/second,  0.0 GPU ops/seconds, 0.0 VFS ops/sec and 4.1% CPU use

                Usage       Events/s    Category       Description
              2.2 ms/s     177.5        Interrupt      PS/2 Touchpad / Keyboard / Mouse
            445.2 us/s      44.4        Timer          tick_sched_timer
              3.4 ms/s      39.2        Interrupt      [27] nvkm
            318.1 us/s      29.2        Timer          hrtimer_wakeup
            137.7 us/s      19.4        Process        [rcu_sched]
...

By pressing the tab key, you get access to different kinds of information (more details are available in the powertop manual):

the Overview tab displays a general state of the system.
the Idle stats tab presents the CPUs and GPUs currently loaded in the system in relationship with their C-states.
the Frequency stats tab shows the P-states of a system in relationship with the idle state.
the Device stats tab presents the list of devices in the system that consume the most power.
the Tunables tab lists the devices that are present on the system. You can tune the system to be power friendly by toggling each item from bad to good.

Source: RHEL 7 Power Management Guide.

저작자표시 비영리 변경금지

'IBM PowerLinux' 카테고리의 다른 글

Amber off (0)	2018.07.05
Scale-out LC System Event Log Collection Tool (0)	2018.06.19
리눅스에서 LVM 구성 및 사용방법 (0)	2018.03.06
LVM home삭제후 root 증설 (0)	2018.02.14
Linux samba 설정 (0)	2017.08.04

PREV 이전 1 ···4 5 6 7 8 9 10 ···32 NEXT 다음

GrooveYOU

전체 글

구입 목록

How to use the HMC Commandline

Contents

HMC Management

LPAR Management: Status Information

LPAR Management: Operations

LPAR Configuation

Operations in an Virtualized Environment

HMC Management

1. HMC Version

2. Network configuration of the HMC

3. Reboot the HMC

4. How to change the HMC password (of user hscroot)

5. How to add an SSH key for remote access

6. Show Available Filesystem Space

LPAR Management: Status Information

1. LPAR Status

2. Show Status and LED/LCD Display of an LPAR

3. Show Status and LED/LCD Display of a Systems Running in FullPartitionMode

4. Overview LPAR IDs

5. Overview Connection State

6. Show a List of All I/O Adapters

7. Overview DLPAR status

LPAR Management: Operations

1. Soft Reset of an LPAR

2. Soft Reset of a System Running in FullPartitionMode

3. Hard Reset of an LPAR

4. Hard Reset of a System Running in FullPartitionMode

5. Virtual Console

6. Activation of an LPAR

7. How to Boot an LPAR into SMS Menu

8. How to Power on a System Running in FullPartitionMode

9. Bring the key switch to position NORMAL

LPAR Configuration

1. Change an LPAR's Name

2. Rename a Managed System

3. DLPAR: Increase the Number of Processing Units of an LPAR

4. DLPAR: Increase the Amount of Memory of an LPAR

Operationen in einer virtualisierten Umgebung

1. Make virtual WWPNs visible to the SAN

2. Show all virtual WWPNs assigned to an LPAR

3. Logout virtual WWPNs from the SAN

RHEL7: How to get started with CPU governor

Presentation of CPU Governor

CPU Idle States

CPU Freq

Installation Procedure

Basic Operations

Standard Operations

Behaviour Analysis

'IBM PowerLinux' 카테고리의 다른 글

+ Recent posts

티스토리툴바