You can install Linux ACE using the installace utility in either interactive or batch mode. After installing, you can run a simple script to verify that PBS and MPICH are working properly.
The installace utility will install the selected Linux ACE software on the specified nodes, and will optionally perform some configuration tasks required for PBS and MPICH. It also creates a file named /etc/ace/nodes on the head node that contains the list of nodes in the cluster; the first node listed is the head node.
To get help for installace, use the -h option. If you want debug information, use the -v option.
 | Note: All nodes in the cluster must be running the Linux operating system in order to use the installace utility. |
The installace utility creates the following files:
/etc/ace/nodes, which contains the hostnames of all nodes in the cluster. The first node listed is the head node.
/etc/ace/installace.log, which contains details of the actions and errors encountered during the install and configuration process.
/etc/ace/installace.conf, which contains the installation configuration information you supply to installace. You can use this file to regenerate the cluster. (This file has the same format as the template install.conf file.)
/etc/ace/manifest, which contains a list of those RPMs that have been installed on each node.
/etc/ace/gmpi.conf, which contains the gm configuration file generated by installace. This file is only generated when installing gm-mpich.
This section tells you how to use installace in interactive mode and provides an example.
To install using interactive mode, do the following:
Log in as root on the host from which you want to perform the installation. Typically, you will do this from the head node.
Insert the Linux ACE CD-ROM.
Mount the CD-ROM by entering the following:
# /bin/mount /dev/cdrom /mnt/cdrom
Change to the /mnt/cdrom directory:
# cd /mnt/cdrom
Note: You must be in this directory. If you are not, installace will not function properly.
Start the installace utility:
# ./installace
If you want to see debug information, use the -v option to installace.
Choose the products you want to install. No matter which package you choose, additional packages for ACE documentation (sgi-acedocs-print and sgi-acedocs) and tools (sgi-ace-tools) will also be installed on the head node .
Note: The following packages are mutually exclusive: lconsole and hoover
mpich and gm-mpich
If you want to choose products individually, you can do so by listing them after the ACE> prompt, separating them with white space.
Examples:
To install the set of products appropriate to an Ethernet environment (mpich, pbs, pcp, and lconsole), enter the following:
ACE> ethernet
Note: You can abbreviate the ethernet and myrinet entries to a unique set of characters. For example, eth. To install just pcp and lconsole, enter the following:
ACE> pcp lconsole
To install the software on multiple nodes, you must provide their hostnames (the output from the hostnames(1) file). Choose the method you prefer:
Option 1, enter the hostnames individually at the ACE> prompt. For example:
Enter your choice (1, 2, 3, or 4). ACE> 1 Enter the hostname of the head node. The head node is the host from which users will launch execution of parallel jobs. ACE> node01 Enter the hostnames for each execution node in the cluster. After you have entered all hostnames, enter '.' or <control-D> to end the list. ACE> node02 node03 node04 ACE> .Note: If you want to use the head node as an execution node for PBS, you can enter the node name here.
Option 2, specify a file containing the list of hostnames. To use this method, you must first create a file that contains a list of the cluster nodes, where the first node listed is the head node. For example, you could create a file named /tmp/ace.config that would contain the following (where node01 is the head node):
node01 node02 node03 node04
You can insert comments in the file by using # as the first character on the line.
You would enter the following:
Enter your choice (1, 2, 3, or 4). ACE> 2 Enter the full pathname of the file containing your list of hostnames. The first node in the list must be the head node (from which users will launch execution of parallel jobs). Enter the full pathname of the file containing hostnames. ACE> /tmp/ace.config
Option 3, specify a pattern for hostnames. This option is useful if you have several nodes that have the same hostname except for a number in sequential order. For example, suppose that you have 7 nodes named node01.acme.com through mode07.acme.com. You would enter the following:
Enter your choice (1, 2, 3, or 4). ACE> 3 Enter the basename of the hostname of the first node in your cluster. For example, if your hostnames have the form "base1.domain.com", enter 'base'. ACE> node Now enter the domain name of each node in your cluster. For example, if your hostnames have the form "base1.domain.com", enter 'domain.com'. ACE> acme.com Now enter the number at which your node numbering starts. For example, if 'base1.domain.com' is the name of your head node, enter '1'. ACE> 01 How many nodes are there in your cluster? For example, if 'base1.domain.com' is the name of your head node and you have 8 nodes in your cluster, enter '8'. ACE> 7
Option 4, install software only on this node. To install only on the node where installace is running, enter the following:
Enter your choice (1, 2, 3, or 4). ACE> 4
The installace utility will verify that all of the nodes are accessible.
Specify whether or not the head node should also be configured as an execution node.
Note: This question is only asked if you install PBS and you have not already listed the head node as an execution node. For example, if the head node will be used only for job submission, enter the following:
Should the head node headnode_name also be configured as an execution node? ACE (y/n)> n
If you want to use the installace(8) utility to allow rsh(1).rsync(1), and rcp(1) access for user accounts to all nodes in the cluster using the /etc/hosts.equiv files, enter 1 or 2. For example:
1) Add the specified hostnames to the existing /etc/hosts.equiv files. If the file does not exist, create it. 2) Replace the current /etc/hosts.equiv file with a new one containing only the specified cluster hostnames. The current /etc/hosts.equiv will be saved as /etc/hosts.equiv.old. 3) Do not change the existing /etc/hosts.equiv file. Enter choice (1, 2, or 3). ACE> 2
For more information, see “/etc/hosts.equiv or $HOME/.rhosts” in Chapter 3.
The following example shows an entire interactive installation.
| Note: The package versions shown in the following output may not match the released system. |
[root@ace08 /root]# /bin/mount /dev/cdrom /mnt/cdrom
[root@ace08 /root]# cd /mnt/cdrom
[root@ace08 cdrom]# ./installace
[root@ace08 cdrom]# ./installace
Advanced Cluster Environment v. 1.4 for Linux i686 includes the
following products:
pbs PBS batch-queuing system
pcp Performance Co-Pilot
mpich MPICH message-passing library - ethernet
gm-mpich Myricom's MPICH message-passing library
gm Myricom's GM driver
lconsole Command-line serial console
hoover Hoover cluster manager & serial console
Enter "ethernet" to select:
mpich pbs pcp lconsole
Enter "myrinet" to select:
gm gm-mpich pbs pcp lconsole
Or enter the individual products separated by white space.
Please enter all desired products separated by white space.
ACE> ethernet
Note: When providing a hostname, use the fully qualified name
such as "foo.domain.com". If the hostname is resolved on all
nodes, you can abbreviate it to "foo".
The installace utility can modify hosts.equiv files on your nodes.
These files are used by MPICH, GM-MPICH, and PBS.
You can choose to provide the information required to edit these files
or avoid this action by entering the appropriate number:
1) Enter the hostnames individually
2) Specify a file containing the list of hostnames
3) Specify a pattern for hostnames (NAME1.domain.com)
4) Install software only on this node
Enter choice (1, 2, 3, or 4).
ACE> 1
Enter the hostname of the head node.
The head node is the host from which users will launch
execution of parallel jobs.
Enter the hostname of the head node.
ACE> ace08
Enter the hostnames for each execution node in the
cluster. After you have entered all hostnames,
Enter '.' or <control-D> on a new line to end the list.
ACE> ace07
ACE> .
Should the head node ace08 also be configured
as an execution node?
ACE (y/n)> y
The install process can update the /etc/hosts.equiv file on all
the hosts in the cluster. The /etc/hosts.equiv will allow access
to the hosts. If /etc/hosts.equiv file is not being used, each user
must update their .rhosts file to allow rcp/rsh type access to all
cluster nodes. Enter one of the following:
1) Add the specified hostnames to the existing /etc/hosts.equiv files.
If the file does not exist, create it.
2) Replace the current /etc/hosts.equiv file with a new one
containing only the specified cluster hostnames. The current
/etc/hosts.equiv will be saved as /etc/hosts.equiv.old.
3) Do not change the existing /etc/hosts.equiv file.
Enter choice (1, 2, or 3).
ACE> 1
Checking rsync/rcp/rsh access ...
Checking disk space requirements ...
Installing selected ACE products on node(s)
ace-tools ........... [yes]
ace-docs ............ [yes]
pcp ................. [yes]
pbs ................. [yes]
mpich ............... [yes]
gm .................. [no]
gm-mpich ............ [no]
lconsole ............ [yes]
hoover .............. [no]
Installing head node software on ace08
Installing package sgi-ace-tools-1.4-1 on ace08 ...
Installing package sgi-acedocs-1.4-1 on ace08 ...
Installing package sgi-acedocs-print-1.4-1 on ace08 ...
Installing package mpich-1.2.1-1 on ace08 ...
MPICH postinstall script
Installing package pcp-2.1.9-12 on ace08 ...
Installing package pcp-pro-2.1.5-2 on ace08 ...
Installing package pcp-ace-1.3.0-4 on ace08 ...
Creating MPI wrapper
...Done, output in /var/tmp/pcp-ace-1.3.0-4-mpi_wrapper
Package textutils-2.0e-3 already installed on ace08, skipping.
Installing package lconsole-1.1-5 on ace08 ...
Installing package OpenPBS-2-3 on ace08 ...
PBS preinstall script
PBS postinstall script
Installing execution node software on ace07
Installing package mpich-1.2.1-1 on ace07 ...
MPICH postinstall script
Installing package pcp-2.1.9-12 on ace07 ...
Installing package pcp-pro-2.1.5-2 on ace07 ...
Installing package pcp-ace-1.3.0-4 on ace07 ...
Creating MPI wrapper
...Done, output in /var/tmp/pcp-ace-1.3.0-4-mpi_wrapper
Package textutils-2.0e-3 already installed on ace07, skipping.
Installing package OpenPBS-mom-2.3 on ace07 ...
PBS mom preinstall script
PBS mom postinstall script
Configuring selected ACE products on node(s) ...
Configuring PBS on head node ace08 ...
Configuring PBS on ace07 ...
All PBS nodes registered as seen via /usr/local/bin/pbsnodes
Starting PCP daemons ...
Starting PCP on ace08 ...
Starting PCP on ace07 ...
Post configuration ...
Adding to the /etc/hosts.equiv file on all nodes ...
Placed node information in ace08:/etc/ace/nodes
Placed log information in ace08:/etc/ace/installace.log
Placed manifest information in ace08:/etc/ace/manifest
Installed ACE documentation in ace08:/usr/doc/sgi/ace-1.4
Placed install configuration file in ace08:/etc/ace/installace.conf
This ACE release also contains third-party evaluation
software. See /mnt/cdrom/ace-demos/README.TXT for
more information.
The installation/configuration process has been completed! |
This section tells you how to use installace in batch mode and provides an example.
To install the Linux ACE software using batch mode, do the following:
Log in as root on the host from which you want to perform the installation. Typically, you will do this from the head node.
Insert the Linux ACE CD-ROM.
Mount the CD-ROM by entering the following:
# /bin/mount /dev/cdrom /mnt/cdrom
Change to the /mnt/cdrom directory:
# cd /mnt/cdrom
Note: You must be in this directory. If you are not, installace will not function properly.
Copy the install.conf file template from the CD-ROM (use the -i option to prompt before an overwrite):
# /bin/cp -i install.conf /tmp/install.conf
Change the permissions on the copy of install.conf:
# chmod 644 /tmp/install.confj
Edit the /tmp/install.conf file so that it contains the required information. Enclose variable settings within double quotation marks. See the comments for more information about each item. For an example of a modified file, see “Batch Mode Example” below.
Note: Do not install both lconsole and hoover. These packages are mutually exclusive. Start the installace utility:
# ./installace /tmp/install.conf
If you want to see debug information, use the -v option to installace.
You will see output similar to the interactive mode as the installace utility proceeds through the installation. If an error occurs, the process will fail.
This section shows you a modified install.conf file and example output.
The following example shows user changes to the install.conf file in bold. This example shows the use of a node as both the head node and an execution node.
# # This file contains Advanced Cluster Environment (ACE) # configuration information that can be used by installace. # # This file must be /bin/sh parsable. # # # Advanced Cluster Environment for Linux, includes the # following products: # # pbs PBS batch-queuing system # pcp Performance Co-Pilot # gm Myricom's GM driver # gm-mpich Myricom's enhanced MPICH message-passing library # mpich MPICH message-passing library # lconsole Command-line serial console # hoover Hoover cluster manager & serial console # # Enter "ethernet" to select: # mpich pbs pcp lconsole # # Enter "myrinet" to select: # gm gm-mpich pbs pcp lconsole # # List all desired products (separated by commas or white space) # in the 'Products' variable. Products="eth" # # ACE needs to know about all the nodes in the cluster. # There are two ways to specify this information: # 1) Create a separate file containing all the nodes in the cluster. # The first node listed must be the head node. # If you want to use this option, list the full pathname in # he 'Nodes_filename' variable below. # # 2) Define the head and execution nodes in this configuration file. # To do this, fill in the 'Head_node' and the 'Execution_nodes' # variables below. # # # List the full path to the file containing all cluster nodes. # The first node listed must be the head node. # Leave empty if you want to specify nodes below. # Nodes_filename="" # # List the head node. The head node is the host from which # users will submit PBS requests and launch the execution of parallel # jobs. Use the fully qualified name such as "foo.domain.com". # # If you have left 'Nodes_filename' variable empty and you do not # fill in a node for 'Head_node', only the software appropriate to # execution nodes will be installed. In this case, you must manually # configure PBS on the head node for the execution nodes. Head_node="ace08" # # NOTE: If you have left 'Nodes_filename' variable empty and # you do not list a node for 'Head_node', only the software # appropriate to execution nodes will be installed. In this case, # you must manually configure PBS for each new execution node # by doing the following: # # 1) Add the name of the head node to /usr/spool/pbs/server_name # on the execution nodes. # 2) Edit /usr/spool/pbs/mom_priv/config on the execution nodes # to add the following: # $logevent 0x1ff # $clienthost # 3) Edit the /usr/spool/pbs/server_priv/nodes file on the head node # and add the name of the execution nodes. # # List all execution nodes in the cluster. They can be comma or # white space, including newline, separated. # Use the fully qualified name such as "foo.domain.com". # # If you want the head to also be an execution node, you # must also list it in the 'Execution_nodes' variable. # Execution_nodes="ace08 ace07" # # The install process can update the /etc/hosts.equiv file on all # the nodes in the cluster. The /etc/hosts.equiv file allows access # to the nodes. The MPICH, PBS, and GM products use rsh/rcp to access # other nodes. If /etc/hosts.equiv is not updated, all users will # have to update their .rhosts file on all nodes. # Set the 'Hosts_equiv_file' variable below to one of # the following values: # # "add") Add the specified nodes to the existing /etc/hosts.equiv files. # If /etc/hosts.equiv does not exist, installace will create one. # "replace") Replace the current /etc/hosts.equiv file with a new one # containing only the specified nodes. The current # /etc/hosts.equiv will be saved as /etc/hosts.equiv.old. # "nochange") Do not change the existing /etc/hosts.equiv file. # If the variable is not set, the default will be "nochange". Hosts_equiv_file="replace" |
When using the preceding file, you would get the following output:
# /bin/cp -i install.conf /tmp/install.conf
# chmod 644 /tmp/install.conf
# vi /tmp/install.conf
# ./installace /tmp/install.conf
Using install config file '/tmp/install.conf'.
Checking rsync/rcp/rsh access ...
Checking disk space requirements ...
Installing selected ACE products on node(s)
ace-tools ........... [yes]
ace-docs ............ [yes]
pcp ................. [yes]
pbs ................. [yes]
mpich ............... [yes]
gm .................. [no]
gm-mpich ............ [no]
lconsole ............ [yes]
hoover .............. [no]
Installing head node software on ace08
Installing package sgi-ace-tools-1.4-1 on ace08 ...
Installing package sgi-acedocs-1.4-1 on ace08 ...
Installing package sgi-acedocs-print-1.4-1 on ace08 ...
Installing package mpich-1.2.1-1 on ace08 ...
MPICH postinstall script
Installing package pcp-2.1.9-12 on ace08 ...
Installing package pcp-pro-2.1.5-2 on ace08 ...
Installing package pcp-ace-1.3.0-4 on ace08 ...
Creating MPI wrapper
...Done, output in /var/tmp/pcp-ace-1.3.0-4-mpi_wrapper
Package textutils-2.0e-3 already installed on ace08, skipping.
Installing package lconsole-1.1-5 on ace08 ...
Installing package OpenPBS-2-3 on ace08 ...
PBS preinstall script
PBS postinstall script
Installing execution node software on ace07
Installing package mpich-1.2.1-1 on ace07 ...
MPICH postinstall script
Installing package pcp-2.1.9-12 on ace07 ...
Installing package pcp-pro-2.1.5-2 on ace07 ...
Installing package pcp-ace-1.3.0-4 on ace07 ...
Creating MPI wrapper
...Done, output in /var/tmp/pcp-ace-1.3.0-4-mpi_wrapper
Package textutils-2.0e-3 already installed on ace07, skipping.
Installing package OpenPBS-mom-2-3 on ace07 ...
PBS mom preinstall script
PBS mom postinstall script
Configuring selected ACE products on node(s) ...
Configuring PBS on head node ace08 ...
Configuring PBS on ace07 ...
All PBS nodes registered as seen via /usr/local/bin/pbsnodes
Starting PCP daemons ...
Starting PCP on ace08 ...
Starting PCP on ace07 ...
Post configuration ...
Replacing /etc/hosts.equiv file on all nodes ...
Placed node information in ace08:/etc/ace/nodes
Placed log information in ace08:/etc/ace/installace.log
Placed manifest information in ace08:/etc/ace/manifest
Installed ACE documentation in ace08:/usr/doc/sgi/ace-1.4
Placed install configuration file in ace08:/etc/ace/installace.conf
This ACE release also contains third-party evaluation
software. See /mnt/cdrom/ace-demos/README.TXT for
more information.
The installation/configuration process has been completed! |
| Note: Special software is not installed on node01 when it is used as both an execution node an a head node. However, configuration will be performed to make it both a head node and an execution node. |