User Guide
Abstract
Page
Contents
Page
Page
7.1.2 Configuring sudo support
Page
Page
Figures
Tables
Examples
1 Overview
1.1.3Compute node administration
1.1.4System disk replication
2 Installing and upgrading HP Insight CMU
2.1.2 Planning for compute node installation
Two IP addresses are required for each compute node
•Determine the IP address for the NIC on the administration network
2.1.3 Disk space requirements
2.1.4 Firmware upgrade requirements
2.1.7 Configuring the BIOS
2.1.7.1DL3xx, DL5xx, DL7xx, Blades
COM1
COM2
NIC 1 PXE boot or PXE enabled NIC 2 Disabled
•16 addresses on the c7000 Enclosure
•8 addresses on the c3000 Enclosure
To configure the iLO cards:
1.Open a browser to the OA
2.In the right window, select Device Bays
System
Direct
◦DHCP Disabled
Enabled
Always
2.1.7.4 SL2x170z G6 and DL170h G6 Servers BIOS setting
Last state
Delayed
BMC
Shared
2.2Preparing for installation
2.2.1 HP Insight CMU kit delivery
2.2.2Preinstallation limitations
2.2.3 Operating system support
2.2.3.1 RHEL 6 support
HP Smart Array warning with RHEL6 and future Linux releases
/dev/sd
/dev/cciss/c*d
2.2.5 HP Insight CMU installation checklist
Preparing the management node:
Preparing the compute nodes:
Preparing the GUI client workstation:
2.2.6 Login privileges
2.3Installation procedures
#chkconfig --addcmu
Install HP Insight CMU on the GUI client workstation. For details, see
“Installing HP Insight CMU on the GUI client workstation” (page 135)
2.4Installing HP Insight CMU with high availability
“Defining a cluster with HP Insight CMU” (page 32)
Page
2.4.1 HA hardware requirements
The hardware requirements for HP Insight CMU under HA control are:
•Two or more management servers
•One shared storage accessed by both servers
2.4.2Software prerequisites
2.4.4 Configuring HA control of HP Insight CMU
If HP Insight CMU is running, set audit mode before you stop HP Insight CMU:
cmuadmin1#
/etc/init.d/cmu set_audit
cmuadmin1# /etc/init.d/cmu stop
5.Start cmuserver:
Start
# /etc/init.d/cmuserver start
cmuadmin1# /etc/init.d/cmu start
Correct possible errors and unset audit mode:
cmu ha:cmu service needs (re)start
7.Run the appropriate command for your HA software to start HP Insight CMU
8.To verify that HP Insight CMU is still running correctly, review the
/var/log/cmuservice_hostname.log file for errors
file for errors
2.4.5 HP Insight CMU configuration considerations
cmu_ha_postinstall
“Configuring HA control of HP Insight CMU” (page 26)
cmuconf0-xxxx.sav
cmuconf1-yyyy.sav
tftp
cmugui.jar
3 Defining a cluster with HP Insight CMU
Figure 4 (page 32) contains four main areas:
•The top bar allows you to perform configuration commands
•A filter allows you to show specific resources
The central frame displays the global cluster view. In
3.2.2X server requirements
3.2.3 Administrator mode
Click Options→Enter Admin Mode
atime
3.2.4Quitting administrator mode
3.3 High-levelchecklist for building an HP Insight CMU cluster
3.4 Cluster administration
3.4.1 Node management
3.4.1.1 Scanning nodes
Cluster Administration→Node Management→Scan Node
Figure 8 Scan node dialog
Figure 8 (page 36)
To launch the scan node process:
3.4.1.2 Adding nodes
3.4.1.3 Modifying nodes
NOTE: The node name cannot be changed
3.4.1.4 Importing nodes
Cluster Administration→Node Management→Import Node
All the imported nodes belong to the default logical group
3.4.2Network entity management
3.4.2.1 Adding network entities
3.4.2.2Deleting network entities
4 Provisioning a cluster with HP Insight CMU
4.1.1Modifying logical groups
4.1.2 Deleting logical groups
4.1.3 Renaming logical groups
4.2 Autoinstall
•Adds support for SLES and Debian
4.2.1Autoinstall requirements
Autoinstall
Autoinstall template
4.2.4 Using autoinstall from GUI
4.2.4.1 Enabling autoinstall
# /etc/init.d/cmu restart
4.2.4.2Creating an autoinstall logical group
Figure 18 New autoinstall logical group
•autoinst.tmpl.orig—Anexact copy of the autoinstall file
•repository—Alogical link to the autoinstall repository
For example:
#ls -l /opt/cmu/image/rh5u5_autoinstall/ total
4.2.5 Using autoinstall from CLI
4.2.5.1 Registering an autoinstall logical group
cmucli
4.2.5.2Adding nodes to autoinstall logical group
cmu> add_to_logical_group node to logical_group_name
4.2.6 Customization
cmuserver.conf
autoinstall
template files
present, in autoinstall templates
4.2.7 Restrictions
This implementation contains the following restrictions:
•The repository must be on the local storage of the management node
•The repository must be exported by NFS only. Do not use HTTP, Samba, or FTP
•Updates must be applied through autoinstall post installation scripts
/opt/cmu/image
4.4 Cloning
Figure 23 Cloning status
When cloning is complete, a popup window displays the results
The cloning procedure has the following limitations:
“Cloning mechanisms” (page 120)
4.4.1Preconfiguration
pre_reconf.sh
/opt/cmu/ etc/pre_reconf.sh
/opt/cmu/image/myimage/pre_reconf.sh
The default content of pre_reconf.sh is:
4.4.2 Reconfiguration
/opt/cmu/etc/reconf.sh
/opt/cmu/image/myimage/ reconf.sh
The reconf.sh script expects the following parameters:
CMU_RCFG_PATH
4.5 Node static info
Figure 24 Node static info
4.6 Rescan MAC
Figure 25 Rescan MAC
4.7 HP Insight CMU image editor
1.Use the cmu_image_open command to expand the image
2.Make changes
3.Use the cmu_image_commit command to save the image
4.7.1 Expanding an image
4.7.2 Modifying an image
chroot
chroot mount /proc
chroot mount /sys
mount
4.8.2 Operating systems supported
On the management node
Install the rpm file system-config-netboot-cmd-cmu-0.1.45.1_X-Y.noarch.rpm
Install the rpm file
python-xml
4.8.5Activating the diskless feature
1.Edit /opt/cmu/etc/cmuserver.conf to activate CMU_DISKLESS:
Edit
to activate
2.Restart the HP Insight CMU server:
Page
From the CLI
1.Start the HP Insight CMU CLI:
# /opt/cmu/cmucli
cmu> probe_kernel
4.8.9 Adding nodes into the logical group
1.Select nodes to add to the diskless image logical group
2.Click Add
Figure 28 Adding nodes to logical groups
Add the node into the logical group as follows:
4.8.12.1files.custom
4.8.12.2Using reconf-diskless-image.sh
4.8.12.3Using reconf-diskless-snapshot.sh
The script is invoked with the following four input parameters:
•CMU_RCFG_PATH—Thepath to the snapshot directory of the
node. /opt/cmu/image/<imageName>/snapshot/<nodeName
4.8.13Best practices for diskless clusters
•Do not update the /opt/cmu/image/<imageName>/root directory
>/root
Reasons for not updating this directory are:
•You can make several diskless images
4.8.14Configuring additional NFS servers
To build a large-scalediskless cluster with HP Insight CMU:
•Not more than 256 nodes per NFS server
•4GB of (non-SATA)storage per compute node on each NFS server
On Red Hat
On SLES
# chkconfig nfsserver on
RPCNFSDCOUNT
/etc/sysconfig/nfs
RPCNFSDCOUNT=8
4.8.15 Comments on High Availability (HA)
5 Monitoring a cluster with HP Insight CMU
5.3 Monitoring the cluster
Launch the HP Insight CMU GUI
Figure 31 Main window
•By network entity
•By logical group
5.3.1 Node and group status
5.3.2Selecting the central frame display
5.3.3Global cluster view in the central frame
5.3.4 Resource view in the central frame
Monitoring values can be visualized by:
•Global cluster
•A specific logical group
•A specific network entity
5.3.5 Gauge widget
5.3.6 Node view in the central frame
5.3.7Using time view
5.3.7.1 Getting started
To launch HP Insight CMU with Time View:
•From the web:
Go to http:
yourcluster
5.3.7.4 Bindings and options
5.3.7.4.3 Custom cameras
•e – Set perspective view
•z – Set history view
•s – Set front view
5.3.7.4.4 Options
5.3.8 Archiving user groups
1.Delete a user group
Answer Yes to Do you want to archive this User Group? See
Figure 40 (page 76)
Figure 40 Archiving deleted user groups
5.4 Stopping HP Insight CMU monitoring
5.5 Tuning HP Insight CMU monitoring
5.5.1 Action and alert files
Sensors, alerts, and alert reactions are described in the /opt/cmu/etc
ActionAndAlertsFile.txt file
5.5.2 Actions
Each action contains the following fields:
Name
Description
Time multiple
5.5.3 Alerts
5.5.4 Alert reactions
Condition
The reaction is performed under this condition
CMU_ALERT_NAME
The name of the alert that caused the reaction
CMU_ALERT_LEVEL
collectl
5.5.6.2Modifying the ActionAndAlerts.txt file
#collectl –c1 -s+C --exportlexpr
waiting for 1 second sample
Create the monitoring lines by using these variables
Native HP Insight CMU lines and collectl lines can be mixed in the
ActionAndAlertFile.txt file
colplot
Import the common directory created on the administration server for
#vi /etc/fstab
X.X.X.X:/var/log/collectl
/var/log/collectl nfs
defaults
5.5.7 Monitoring GPUs and coprocessors
5.5.7.1 Monitoring NVIDIA GPUs
Use the script
/opt/cmu/contrib/install_nvidia.pl
/opt/cmu/contrib/ install_nvidia.README
/opt/cmu/bin/cmu_config_nvidia
“Action and alert files” (page 77)
5.5.7.2 Monitoring AMD GPUs
/opt/cmu/contrib/cmu_install_amd
/opt/cmu/contrib/ cmu_install_amd.README
5.5.7.3 Monitoring Intel coprocessors
a.# cd /tmp
b.# tar xvzf driver-file.tgz
c.# cd created-driver-directory
#sudo yum install --nogpgcheck --noplugins --disablerepo=**.rpm
5.5.8 Monitoring HP Insight CMU alerts in HP Systems Insight Manager
ActionAndAlertFile.txt
“Alerts” (page 79)
“Alert reactions” (page 79)
Figure 44 (page 89)
5.5.9 Extended metric support
ipmitool
/opt/cmu/ contrib/cmu_IPMI_monitoring.README
/opt/cmu/ contrib/cmu_IPMI_monitoring
EXTENDED
Page
6 Managing a cluster with HP Insight CMU
To select a terminal emulator other than the default:
1.Edit /opt/cmu/etc/cmuserver.conf
Six blocks of variable names begin with
CMU_REMOTE_TERMINAL
6.4 Management card connection
“SSH connection” (page 91)
6.5 Virtual serial port connection
6.6 Shutdown
Figure 46 Halt dialog
6.8 Boot
Figure 48 Boot dialog box
6.9 Reboot
Figure 49 Reboot dialog box
6.10 Change UID LED status
6.11 Multiple windows broadcast
Figure 50 Multiple windows broadcast command
6.12 Single window pdsh
pdsh
•cmudiff (default)
6.12.1cmudiff examples
Page
#vi /root/.ssh/config
6.13 Parallel distributed copy (pdcp)
To copy the file:
1.Right-clickthe nodes you want to copy to
6.14User group management
6.14.1Adding user groups
Figure 53 User group management
6.14.2Deleting user groups
1.In the User Group Management window, select the user group to delete
2.Click Delete
6.14.3Renaming user groups
1.In the User Group Management window, select the user group to rename
6.15.2Checking BIOS versions
Vendor
Version
Release Date
dsh_bak
6.16.1Saving user settings
cmu_gui_local_settings
6.17 HP Insight CMU CLI
6.17.1 Starting a CLI interactive session
#cmucli
Help commands
help
cmu> help
Getting help for a command
To get detailed information and the exact syntax of a command:
6.17.3 Specifying nodes
Using the HP Insight CMU CLI, you can execute a command on any number of nodes
The nodes command:
•Displays node information
•Tests regular expressions for selecting nodes before executing a command
Executing a command on a list of nodes
To execute a command on multiple nodes, you must specify the names of nodes
cmu> boot o185i222 o185i233 o185i243
active node list selected: o185i222 o185i233 o185i243 cmu
Executing a command on a range of nodes
6.17.4 Administration and cloning commands
Booting a set of nodes
The boot modes are:
•Normal mode boots nodes on the default device, generally the hard drive
•Network mode fills the dhcpd.conf file to boot nodes over the network
To broadcast on all nodes of the cluster:
cmu> broadcast all
Rebooting a set of nodes
cmu> reboot delay "message" cmu_nodes_regular_expression
reboot
Please read /opt/cmu/log/PowerOff.log for errors. cmu
Setting the locator LED on or off
cmu> Locate on|off cmu_nodes_regular_expression
Locate on|off
cmu> locate on o185i192
Adding a new logical group
add_logical_group
cmu> add_logical_group image_name "device
cmu> add_logical_group my_logical_group "cciss/c0d0
processing 1 logical group
where:
test_julien
is the name of the logical group containing the node being backed up
sda1,sda5,sda9
are the partitions on the hard drive
Modifying a management card password
Modifies the management card password in the HP Insight CMU database
cmu> modify_password ILO|ILOCM|lo100i
cmu> modify_password lo100i
login> hp password> service
6.17.5 Administration utilities pdcp and pdsh
HP Insight CMU includes the open source software pdcp and pdsh
Usage example of pdcp:
#/opt/cmu/bin/pdcp -wcn0001,cn0002 source /tmp/dest
is a file on the management node
7 Advanced topics
sudo
Table 4 HP Insight CMU GUI features and their corresponding commands
7.1.3 Examples
shutdown
reboot
ALL
localhost
7.2.1 Build diskless image
build_image
-l <CMU diskless logical group name
The name of the new logical group
-g <"golden node
7.2.3 Configure diskless node
The name of the diskless logical group
-s <NFS server IP
The IP address of the NFS server
-n <nodename
7.2.6 Diskless check
diskless_check
unconfigure_node
boot_node
After these programs are created, tested, and installed in the /opt/cmu
ILOCM
The method for integration with HP Moonshot 1500 Chassis
/opt/cmu/ hardware
HW_TYPE
/opt/cmu/hardware/ILO
7.4Customizing kernel arguments for the HP Insight CMU provisioning kernel
default
/opt/cmu/etc/bootopts
/opt/cmu/etc/ bootopts/default
/opt/cmu/etc/bootopts
7.5Support for ScaleMP
CMU_vSMP_PREFIX=vSMP
network boot
For more details, see the ScaleMP documentation
7.6 Cloning mechanisms
During cloning, secondary servers boot from the primary server
Then, each compute node boots from its secondary server
Page
8 Support and other resources
•Installation and user guides for your specific operating system
8.3Typographic conventions
This document uses the following typographical conventions:
%, $, or #
audit(5)
(5)
Page
A Troubleshooting
cmuserver
•An incorrect MAC address in the HP Insight CMU database
•The HP Insight CMU configuration on the management node is lost
Troubleshooting switch issues
1.Verify that the management node pings the iLO and the nodes
2.Verify that broadcast is enabled and is redirected to the switch
3.Verify that the spanning tree is disabled on all ports connected to a node
4.Verify that « multicast IGMP snoop loop » is disabled on the switch
A.4 Cloning issues
A.5 Administration command problems
A.6 GUI problems
# /etc/init.d/cmu status
4.Verify that the HP Insight CMU rpm is properly installed on all nodes
Figure 54 Certificate error
The detailed Java exception is:
Figure 55 Java control panel
Page
B Detailed installation instructions
•On SLES:
#chkconfig nfsserver on
#/etc/init.d/nfsserver start
B.4 Verifying the DHCPD listen interface
#grep DHCPD_INTERFACE= /etc/sysconfig/dhcpd
In the example, DHCPD listens to the interface eth2
#chkconfig dhcpd on
B.5 Firewall configuration
B.8 Installing HP Insight CMU licensing
Copy the content of all Flexlm license key files to /opt/cmu/etc/cmu.lic
B.9 Setting the Java PATH
CMU_JAVA_BIN
#CMU_JAVA_BIN="/usr/java/jre1.6.0_31/bin/java
B.11 Starting HP Insight CMU
starting cmu service
cmu:core(standard)
configured (audit mode)
not running (audit mode)
B.12 Configuring HP Insight CMU to start automatically
B.13 Verifying the HP Insight CMU state
B.14 Installing HP Insight CMU on the GUI client workstation
B.14.1 Configuring the GUI client on Linux workstations
Using an ssh tunnel
# /etc/init.d/sshd restart
# ssh x.x.x.x -lroot
# echo $DISPLAY
B.14.2 Activating the HP Insight CMU GUI
•By copying the HP Insight CMU GUI Java file onto the client
Launching the HP Insight CMU GUI using a web browser
CMU_THTTPD_PORT
To launch the HP Insight CMU GUI:
Page
HP Insight CMU manpages
cmu_show_nodes(8)
NAME
SYNOPSIS
/opt/cmu/bin/cmu_show_nodes
DESCRIPTION
EXAMPLES
Default behavior:
#/opt/cmu/bin/cmu_show_nodes
cn0004
cn0005
cmu_show_logical_groups(8)
#/opt/cmu/bin/cmu_show_logical_groups <-h | [logical_group_name]
#/opt/cmu/bin/cmu_show_logical_groups
#/opt/cmu/bin/cmu_show_logical_groups rhel6
cmu_show_network_entities(8)
cmu_show_user_groups(8)
cmu_show_archived_user_groups(8)
cmu_show_archived_user_groups --Show archived user groups
/opt/cmu/bin/cmu_show_archived_user_groups
Show archived user groups
pretty print (add blank lines for readability)
cmu_add_node(8)
cmu_add_node --Add node(s) to the HP Insight CMU database
#/opt/cmu/bin/cmu_add_node <-h | -s | -i | -f filename
#/opt/cmu/bin/cmu_add_node -H|--hostname hostname -I|--ip ipaddress
[-M|
Command-linemode:
Interactive mode:
In interactive mode, you are prompted for node parameters:
#/opt/cmu/bin/cmu_add_node -i hostname> n10
hostname
cmu_add_network_entity(8)
#/opt/cmu/bin/cmu_add_network_entity <-f filename | -h
#/opt/cmu/bin/cmu_add_network_entity rack1 rack2
#/opt/cmu/bin/cmu_add_network_entity -fnetwork_entity_list
cmu_add_logical_group(8)
#/opt/cmu/bin/cmu_add_logical_group <-n | -i | -f filename | -s
#/opt/cmu/bin/cmu_add_logical_group <-n name -d devicename
#/opt/cmu/bin/cmu_add_logical_group -ntest -dcciss/c0d0
#/opt/cmu/bin/cmu_add_logical_group -flogical_group_file
cmu_add_to_logical_group_candidates(8)
/opt/cmu/bin/cmu_add_to_logical_group_candidates
#/opt/cmu/bin/cmu_add_to_logical_group_candidates -trh6u0_x86_64 node1
cmu_add_user_group(8)
#/opt/cmu/bin/cmu_add_user_group <-f filename | -h
#/opt/cmu/bin/cmu_add_user_group <user_group_name1, user_group_name2
#/opt/cmu/bin/cmu_add_user_group user1 user2
#/opt/cmu/bin/cmu_add_user_group -fuser_group_list
cmu_add_to_user_group(8)
#/opt/cmu/bin/cmu_add_to_user_group <-h | -t user_group nodename
#/opt/cmu/bin/cmu_add_to_user_group <-t user_group nodename -f nodenamefile
#/opt/cmu/bin/cmu_add_to_user_group -tgroup1 cn0003
#/opt/cmu/bin/cmu_add_to_user_group -tgroup1 -fnodenamefile
cmu_change_active_logical_group(8)
/opt/cmu/bin/cmu_change_active_logical_group
#/opt/cmu/bin/cmu_change_active_logical_group -trh6u0_x86_64 cn0001
/opt/cmu/bin/cmu_change_active_logical_groups
cmu_change_network_entity(8)
#/opt/cmu/bin/cmu_change_network_entity <-h | -t network_entity nodename1
#/opt/cmu/bin/cmu_change_network_entity -track1 cn0001
#/opt/cmu/bin/cmu_change_network_entity -track2 -fnodenamefile
cmu_del_from_logical_group_candidates(8)
cmu_del_from_network_entity(8)
#/opt/cmu/bin/cmu_del_from_network_entity <-h | -t network_entity nodename1
#/opt/cmu/bin/cmu_del_from_network_entity -track1 node1
#/opt/cmu/bin/cmu_del_from_network_entity -track2 -fnodenamefile
cmu_del_archived_user_group(8)
#/opt/cmu/bin/cmu_del_archived_user_group [-h]| [-v] [-ttimeout] [-d]
#/opt/cmu/bin/cmu_del_archived_user_group -njob1, job2, job[12–145]
cmu_del_from_user_group(8)
#/opt/cmu/bin/cmu_del_from_user_group <-h | -t user_group nodename1
#/opt/cmu/bin/cmu_del_from_user_group <-t user_group nodename -f nodenamefile
#/opt/cmu/bin/cmu_del_from_user_group -tuser1 node1
#/opt/cmu/bin/cmu_del_from_user_groups -tuser2 -fnodenamefile
cmu_del_logical_group(8)
#/opt/cmu/bin/cmu_del_logical_group <-f filename | -h
#/opt/cmu/bin/cmu_del_logical_group rh5u5_x86_64 sles11sp1_x86_64
#/opt/cmu/bin/cmu_del_logical_group -flogical_group_list
cmu_del_network_entity(8)
#/opt/cmu/bin/cmu_del_network_entity <-f filename | -h
#/opt/cmu/bin/cmu_del_network_entity rack1 rack2
#/opt/cmu/bin/cmu_del_network_entity -fnetwork_entity_list
cmu_del_node(8)
#/opt/cmu/bin/cmu_del_node <-f filename | -h
#/opt/cmu/bin/cmu_del_node <node_name1, node_name2
#/opt/cmu/bin/cmu_del_node node1 node2
#/opt/cmu/bin/cmu_del_node -fnode_list
cmu_del_snapshots(8)
/opt/cmu/bin/cmu_del_snapshots
cmu_del_user_group(8)
#/opt/cmu/bin/cmu_del_user_group <-f filename | -h> [-a] [-m]
#/opt/cmu/bin/cmu_del_user_group <user_group1, user_group2
#/opt/cmu/bin/cmu_del_user_group user1 user2
#/opt/cmu/bin/cmu_del_user_group -fuser_group_list
cmu_console(8)
cmu_console --Connect to compute node management ports
#/opt/cmu/bin/cmu_console <compute_node_hostname
cmu_power(8)
cmu_power --Perform power actions on compute nodes
-paction
specifies the action to perform; valid actions are:
OFF
.cmu_power -pOFF -ncn0001
.cmu_power -pOFF -uuser1
.cmu_power -pBOOT -lrh6u0_x86_64
./cmu_power -pUID_ON -uuser2
cmu_custom_run(8)
#/opt/cmu/bin/cmu_custom_run <-h | -l | -t command_title [-f nodefile]
#/opt/cmu/bin/cmu_custom_run -l
# /opt/cmu/bin/cmu_custom_run -taudit|lspci
cmu_clone(8)
RETURN CODES
cmu_backup(8)
#/opt/cmu/bin/cmu_backup <-h>| <-l logical_group -n compute_nodename-p
./cmu_backup -lmyimage -nnode20 -p"cciss/c0d0p3,cciss/c0d0p1
./cmu_backup -lmyimage -nnode20 -r3 -e /tmp/err.log
cmu_scan_macs(8)
OPTIONS (naming)
-hhostname
%xi
%xL
OPTIONS (general)
-ifirst_ip_addr
first_ip_addr
-tBMC_type
String specifying the BMC type. (e.g. ILO, ILOCM)
Example
Page
cmu_rescan_mac(8)
#/opt/cmu/tools/cmu_rescan_mac -nnodename [N NIC_num] [-h]
#/opt/cmu/tools/cmu_rescan_mac -no184i116
cmu_mod_node(8)
#/opt/cmu/bin/cmu_mod_node <-h | -s | -i | -f filename
#/opt/cmu/bin/cmu_mod_node -H|--hostname hostname [-I|--ip ipaddress]
/opt/cmu/bin/cmu_mod_node
#/opt/cmu/bin/cmu_mod_node -i hostname> n10
Modifying multiple nodes using a file:
#/opt/cmu/bin/cmu_mod_node -fnodes.txt
cmu_monstat(8)
NODE AND GROUP OPTIONS
#/opt/cmu/bin/cmu_monstat --nodes=n0001,n0002,n00[01-11]
#/opt/cmu/bin/cmu_monstat --all-sensors --all-nodes
#/opt/cmu/bin/cmu_monstat --all-alerts --prefix --lg=sles11_x86_64
#/opt/cmu/bin/cmu_monstat --sensors=cpuload,memory_used --nodes=n[1-2]
#/opt/cmu/bin/cmu_monstat --sensors=cpuload --alerts=login_alert
cmu_image_open(8)
#/opt/cmu/bin/cmu_image_open <-h | -i imagename
#/opt/cmu/bin/cmu_image_open -irh5u5_x86_64
cmu_image_commit(8)
#/opt/cmu/bin/cmu_image_commit <-h | -i imagename [-n new_image_name]
#/opt/cmu/bin/cmu_image_commit -irh5u5_x86_64
# /opt/cmu/bin/cmu_image_commit -irh5u5_x86_64 -nrh5u5_x86_64_new
cmu_config_nvidia(8)
cmu_config_nvidia --Configure NVIDIA GPU monitoring
/opt/cmu/ etc/ActionAndAlertsFile.txt
print this help text
replace earlier HP Insight CMU GPU monitoring with this monitoring
cmu_config_amd(8)
cmu_config_amd --Configure AMD GPU monitoring
/opt/cmu/bin/cmu_config_amd
cmu_config_intel(8)
#/opt/cmu/bin/cmu_config_intel <-h | -r | -n
cmu_mgt_config(8)
MODE
Page
cmu_firmware_mgmt(8)
#/opt/cmu/bin/cmu_firmware_mgmt [-h] [-d -f <nodefile
#/opt/cmu/bin/cmu_firmware_mgmt –v –fnodes.txt
#/opt/cmu/bin/cmu_firmware_mgmt –d –fnodes.txt
#/opt/cmu/bin/cmu_firmware_mgmt –uCP019061.scexe –fnodes.txt
Glossary
Page
Index