xCAT/xcat-core
2
0
Fork 0
mirror of https://github.com/xcat2/xcat-core.git synced 2024-11-21 09:02:00 +00:00
Code Issues Releases Wiki Activity
Page: DFM_Service_Node_Hierarchy_support
Pages
2014_10_01_Bash_vulnerability 2014_11_04_Poodle_Attack AIX_NIM_NFSv4_support Add_Extra_Parameters_for_confignics_Postscript CRHS like_function CRHS like_function_enhancements CSM_CFM like_function_to_sync_config_files_to_the_nodes Capture_Linux_Image_from_running_node_to_create_a_stateless statelite_image Chef_databag_support_for_deploying_openstack_in_xCAT Cluster_config_file Conserver_Replacement Coordinated_Cluster_Shutdown_and_Bringup Copycds_enhancement Coral PDU supports Create_osimage_definition_for_Management_Node Cumulus_OS_Upgrade_Support_Test DFM_Service_Node_Hierarchy_support DHCPv6_management DNS_Enhancments DNS_master_slave_support Def_commands_to_display set_nic_attributes_more_easily Deploying_OpenStack_Baremetal_Nodes_Using_xCAT Disable_ssh_root_passwordless_node to node_access Document_large_cluster_tunables,_etc. Dynamic_node_groups_support Energy_Management_for_Flex Energy_management_support_for_blade Enhance_NTP_setup_support Enhancement_of_lsslp_ flexdiscover Enhancement_on_makeroutes_and_snmove_commands Exporting_more_table_attributes_to_nodes Filling_the_osimage_attributes_with_the_files_that_are_found_in_the_search_path Full_Automation_of_DB2_Setup_on_Service_Nodes Function Verification Test Design of xCAT High Availability GPFS_statelite_nodes Getmacs_and_rnetboot_enhancement Getnodetype_performance_imprvoments_ _phase_I HA_NFS_on_AIX_service_nodes HA_Service_Nodes_for_AIX HA_Service_Nodes_for_AIX_ _using_External_NFS_Server HFI_MAC_address_failover HPC_Integration_Phase_1 Hardware_Inventory_for_Node Health_Check_Script_Framework Hierarchical_Design Home Image_Provisioning Image_import_and_export_enhancement_for_Linux Improve_perl_array_search_efficiency_for_scalability Improvement_of_pre creating_mypostscripts_on_linux Initrd_Enhancement_separate_initrd_hacking_from_noteset_get_drivers_from_os_update_distro Kdump_for_Linux_diskless_nodes Linux_AIX_mixed_Clusters_postscripts_cleanup Local_Disk_support_for_statelite Lstree_for_Servicenode_Hardware_and_VM_hierarchies Management_Node_Pool Management_Node_Setup_Verification Managing_Multiple_Sites_and_Clusters Mellanox_Switch_Support Mini design for openbmc python framework Mini design_of_updating_pre defined_groups_for_nodes Minimize_the_install setup_steps_of_xcat_on_the_MN Mkvlan_enhancements Multiple_Zone_Support2 Multiple_pkgdir_support_with_full_installation NFS_Redundancy_Investigation NFS_redundancy New_Cloud_Tables_in_xCAT Node_Status_and_Application_Status Node_definition_installation_service_node_setup_verification Nodeset_defaults_when_node_provmethod=osimage_is_set OS_Deployment_Monitoring_And_Automatic_Retry OS_Distro_Update_xCAT_command_osdistroupdate OpenStack Chef Cookbook_xCAT_Integration OpenStack_Deployment_using_Chef OpenStack_Deployment_using_Puppet Ospkgs_enhancements_to_install upgrade_OS_packages_from_Updates Overview_of_HA_Services_for_Diskless_AIX_Nodes Power8_BE_support Predict_long_nicname_for_RH7 Proposal_for_docker_Support_in_xCAT RHEL7_Support RHEV_support Rcons_hierachy_support Redfish_support Refine_the_usage_of_installnic_and_primarynic_attributes Release processs automation investigation Resolving_Nodenames_for_System_p_HW_Ctrl Run_parallel_commands_for_Ethernet_switches Run_postbootscripts_after_each_diskful_reboot SLES12_Support SLES_11_SP1_SDK_support Secure root support Sequential_Discovery Sequential_Discovery_phase_2 Service_Node_Scenarios_and_Retry_Logic_in_Postscript_Process Service_node_manual_takeover_on_AIX Service_node_take_over Setup_IP_routes_between_the_MN_and_the_CNs Shared data based xCAT MN HA mini design Shared data based xCAT MN HA user case Shared data based xCAT MN HA Specify_the_disk_partitions_during_diskfull_install Steps to install xcat_openbmc_py3 on RH8 Support uploading openbmc firmware in parallel Support_Management_Node_in_the_servicenode_table Support_for_Redundant_BPAs_and_FSPs Support_multiple_hardware_control_points Support_osimage.pkgdir_with_multiple_paths_in_genimage_and_diskfull_installation Support_postscripts_associated_with_rsync_files_to_be_run_after_rsync_in_xdcp Support_to_inject_drivers_from_Driver_RPM_Package Support_xcatd_running_user_defined_sql_scripts_on_start_and_foreign_keys Supporting_driver_update_disk_for_Linux Supporting_the_scalable_functions_for_HX5_blade Switch_Discovery_And_Switch_Management System_p_Discovery_Enhancements System_z_hierarchical_tree Test Design of HA Test Design of TestCase Label Test Design of `goconserver` Regression Testing Test Design of `goconserver` Support Test Design of configib Test Design of cumulus osimage Test Design of cumulus_osimage Test Design of gonconserver redirect logs Test Design of hardware control commands regression Test Design of makegocons option l Test Design of rbeacon python version Test Design of rcons based goconserver Test Design of revenlog python version Test Design of rflash python version Test Design of rinv python version Test Design of rpower python version Test Design of rsetboot python version Test Design of rspconfig python version Test Design of rvitals python version Test Design of syncfiles Test Design of xcat inventory diff Test Design of xcat inventory export import performance Test Design of xcat inventory option e Test Design of xcat inventory osimage environment variables export part Test Design of xcat inventory osimage environment variables Test Design of xcat inventory osimage phase2 Test Design of xcat inventory osimage support share file directory Test Design of xcat inventory osimage Test Design of xcat inventory phase 1 Test Design of xcat inventory regular expression Test Design of xcat inventory save keys Test Design of xcat inventory user case Test Design of xcat terraform provider phase1 Test Report of `goconserver` Test cases against nodeset error handling Test_Case_Designs_FVT The mini design of osimage version control(initial draft) The mini design of syncfiles for cumulus The mini design of using xcat inventory templates to setup xCAT cluster with ansible The_remote_console_support_of_hmc Trace_Facility_for_xCAT Ubuntu_supports_internet_repository Updatenode_Performance_Enhancements Updatenode_Sync_Service_Nodes_for_install Updatenode_enhancement_for_security_keys_and_certificates Updatenode_support_to_run_mypostscript_sections Updatenode_to_the_Management_Node Updates_to_xcatsetup_and_Cluster_Config_File Windows_Multiple_Disks_Partitions_Configuration Windows_Multiple_Nics_Configuration Windows_Multiple_Winpes Windows_Support_to_Run_Postscripts_Postbootscripts_in_Windows_Deployment Wish_List_for_xCAT_2 Wish_List_for_xCAT_FVT XCAT 2 Mini Designs for New Features XCAT_2.10_Release_Notes XCAT_2.11.1_Release_Notes XCAT_2.11_ESP_Release_Notes XCAT_2.11_Release_Notes XCAT_2.12.1_Release_Notes XCAT_2.12.2_Release_Notes XCAT_2.12.3_Release_Notes XCAT_2.12.4_Release_Notes XCAT_2.12.5_Release_Notes XCAT_2.12_Release_Notes XCAT_2.13.10_Release_Notes XCAT_2.13.11_Release_Notes XCAT_2.13.1_Release_Notes XCAT_2.13.2_Release_Notes XCAT_2.13.3_Release_Notes XCAT_2.13.4_Release_Notes XCAT_2.13.5_Release_Notes XCAT_2.13.6_Release_Notes XCAT_2.13.7_Release_Notes XCAT_2.13.8_Release_Notes XCAT_2.13.9_Release_Notes XCAT_2.13_Release_Notes XCAT_2.14.1_Release_Notes XCAT_2.14.2_Release_Notes XCAT_2.14.3_Release_Notes XCAT_2.14.4_Release_Notes XCAT_2.14.5_Release_Notes XCAT_2.14.6_Release_Notes XCAT_2.14_Release_Notes XCAT_2.15.1_Release_Notes XCAT_2.15_Release_Notes XCAT_2.16.1_Release_Notes XCAT_2.16.2_Release_Notes XCAT_2.16.3_Release_Notes XCAT_2.16.4_Release_Notes XCAT_2.16.5_Release_Notes XCAT_2.16_Release_Notes XCAT_2.17_Release_Notes XCAT_2.9.2_Release_Notes XCAT_2.9.2_aix_Release_Notes XCAT_2.9.3_Release_Notes XCAT_2.9.4_Release_Notes XCAT_Cluster_in_SoftLayer XCAT_HPC_Integration_Files_per_OS,_Architecture,_Product XCAT_Health_Check XCAT_IPv6_support_on_AIX XCAT_IPv6_support_on_Linux XCAT_Mini Design_Template XCAT_Monitoring_Failure_Analysis_Conditions_Batched_Events XCAT_Postscripts_framework_enhancements XCAT_Provisioning_OS_on_consistent_disk XCAT_REST_API_enhancements XCAT_Support_for_Kits_and_Kit_Components XCAT_probe XCAT_support_for_multiple_network_domains Xcatexport_and_xcatimport_commands Xcatmon_and_appstatus_for_HPC_products Xeon_Phi_support cofignetwork_for_RH7 confignetwork integrate confignics_configeth_configib functions usage determine_install_disk diskdiscover_and_configraid docker_instances_lifecycle_management enhancement_for_rinstall_command logging pre script to make debug easy makedhcp_append_statement_automatically_rather_than_get_statement_from_nodeset mini design of ZTP based onie switch discovery and configuration minidesign Switch based switch discovery minidesign_xcatprobe node status enhancement ntp_enhancement openbmc_support post.xcat_restructure rflash_streamline_procedure rscan command for hypervisor rspconfig network rspconfig ntpservers rspconfig password scaleup_basedon_xcat_in_openshift_cluster supporting_partitionfile_for_Ubuntu supporting_persistent_kernel_cmdline_after_diskful_installation test_sidebar the mini design of xcat inventory export and import for osimage use fifo pipe to enhance getadapter xCAT Build Schedule xCAT_2.12_ReleaseInformation xCAT_2.13_ReleaseInformation xCAT_2.14_ReleaseInformation xCAT_2.15_ReleaseInformation xCAT_Docker_Image xcatprobe_framework xcatprobe_requests
8 DFM_Service_Node_Hierarchy_support
ligc edited this page 2015-07-30 04:22:49 -04:00
Unescape Escape
Table of Contents
This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

Table of Contents

This Doc will describe the support for Hierarchy support using DFM.

Overview

Previously support for DFM was restricted to all Direct FSP Management being performed from the Management Node. With the new support administrators will be able to configure the SN as the supported DFM control point for nodes which it manages. This document will describe the changes to xCAT required to support this configuration as well as the configuration information that will need to be defined to allow it to work properly.

This support will only be documenting the configuration of the xCAT DB and the Service Nodes to allow xCAT commands to automatically determine when to run on the SN and when to run on the EMS.

  • Every node/nodegroup has explict noderes.servicenode, noderes.xcatmaster, etc., entries. The user must ensure that each servicenode listed in one of those attributes is also added to the servicenode table for correct servicenode install/configuration.
  • The SN will need to have the Cluster Service Network ethernet interfaces defined during OS installation. Descriptions of what xCAT DB entries are needed and what postscripts need to run to configure the network interfaces.

For general hierarchy description it is worth reviewing or referencing the following:

[Hierarchical_Design] section on New_servicenode_Table

For the flow of setting up a Hierarchical Cluster, we can refer to the following two docs:

  • [Setting_Up_an_AIX_Hierarchical_Cluster]
  • [Setting_Up_a_Linux_Hierarchical_Cluster]

MN vs. SN ownership and responsibilities

In order to support DFM hierarchy there needs to be clear roles and responsibilities of the MN and the SN in relation to the DFM and OS image management.

It is clear that the SN cannot manage the CEC power within which it resides since it would never be able to power itself on after a power off. The MN will be the DFM HCP for the SN CEC.

We also need the MN to control all of the frames since the SNs cannot control the frame in which they reside.

Here is a summary of the split in MN and SN ownership for DFM hierarchy:

MN and SN Functional Ownership

function / hardware target MN SN

DFM Frames X

DFM SN CEC X

DFM SN LPAR X

OS image SN LPAR X

DFM SN CEC non-SN LPARs X

OS image SN CEC non-SN LPARs X

DFM non SN CECs X

DFM non SN CEC LPARs X

OS image non SN CEC LPARs X

Note: While DFM for the SN CEC non-SN LPARs is performed by the MN, these LPARs have their OS support provided by the SN. This is done for scaling reasons as a very large cluster would have too many LPARs to support from a single place if it were to support OS images for them all from the MN.

xCAT DB attributes

This section will discuss the xCAT DB attributes which determine the MN and SN hierarchy configuration and control.

The noderes.servicenode entry is used to override the default of the MN by naming a specific SN to be used instead. This can be used to control areas like xdsh by associating an lpar node definition with a noderes.servicenode setting. DFM can be redirected to a SN by associating an FSP or BPA node definition with a specific SN using the noderes.servicenode setting. This control will allow the administrator to define specific associations depending on the capabilities which are being managed. In our previous example there were some CEC LPARs which need to have the OS served by the SN but the DFM controlled by the MN. Using the noderes.servicenode settings we can accomplish this mixed support.

LPARs

The lpar node definitions for the SN CEC non-SN lpars will set noderes.servicenode to this SN.

The lpar node definitions for all non-SN CECs will set noderes.servicenode to this SN.

CECs and Frames

The SN CEC definitions, which is the "parent" of the SN LPAR and all the other LPARs on the SN CEC, will NOT set its noderes.servicenode and therefore use the MN.

All the non-SN CECs definitions will set noderes.servicenode to SN.

All Frame definitions will NOT set noderes.servicenode and therefore use the MN.

Hosts table

The xCAT hosts table is used to allow customers to define any other no OS install network interfaces that need to be defined on that host. We will use this capability to define the SN Cluster Service Network Ethernet interfaces. Adding the interface information for each SN in this table will result in the creation of the hostname entries required for hostname resolution.

Here is an example of what would be done to define a Cluster Service Network ethernet interface for a SN.

Installing RPMs for DFM on the SN

This section will discuss which RPMs are required for the SN to be able to perform hardware control. It will also contain information on how the required RPMs will be distributed to the SN in AIX and Linux. Currently we will require the DFM and the hardware server RPMs.

The "[Setting_Up_an_AIX_Hierarchical_Cluster]" and "[Setting_Up_a_Linux_Hierarchical_Cluster]" documents will need to be updated to include the tasks of installing the DFM and hardware server RPMs on the service node. This information is currently missing from those sections.

Here is the excerpt from this document:

For most operations, the Power 775 is managed directly by xCAT, not using the HMC. This requires the new xCAT Direct FSP Management plugin (xCAT-dfm-*.ppc64.rpm), which is not part of the core xCAT open source, but is available as a free download from IBM. You must download this and install it on your xCAT management node (and possibly on your service nodes, depending on your configuration) before proceeding with this document.

Downloading DFM and hdwr_svr packages

Download DFM and the pre-requisite hardware server package from Fix Central :

Product Group:      Power
Product:            Cluster Software
Cluster Software:   direct FSP management plug-in for xCAT

And

Product Group:      Power
Product:            Cluster Software  
Cluster Software:   HPC Hardware Server
  • xCAT-dfm RPM
  • ISNM-hdwr_svr RPM (linux)
  • isnm.hdwr_svr installp package (AIX)

Installing DFM and hdwr_svr

Installing DFM and hdwr_svr on Linux SN

We should put this part in the section Set Up the Service Nodes for Diskfull Installation of the doc [Setting_Up_a_Linux_Hierarchical_Cluster] to add the DFM and hdwr_svr into the list of packages to be installed on the SN.

 mkdir -p /install/post/otherpkgs/<osver>/<arch>/dfm

For example, for rhels6:

mkdir -p /install/post/otherpkgs/rhels6/ppc64/dfm

And then, put the DFM and hdwr_svr packages in the dfm directory just created.

You should create repodata in your /install/post/otherpkgs/<os>/<arch>/dfm directory so that yum or zypper can be used to install these packages and automatically resolve dependencies for you:

createrepo  /install/post/otherpkgs/&lt;os&gt;/&lt;arch&gt;/dfm

If the createrepo command is not found, you may need to install the createrepo rpm package that is shipped with your Linux OS. (For SLES I think it is on the SDK DVD.)

Next, add rpm names into the service.<osver>.<arch>.otherpkgs.pkglist file. In most cases, this file is already created under /opt/xcat/share/xcat/install/<os> directory. If it is not, you can create your own by referencing the existing ones.

vi /install/custom/install/&lt;os&gt;/service.&lt;osver&gt;.&lt;arch&gt;.otherpkgs.pkglist

Besides the required xCAT packages for service node, and append the following:

dfm/xCAT-dfm
dfm/ISNM-hdwr_svr-RHEL

After the Initialize network boot to install Service Nodes in Power 775 section in (Setting_Up_a_Linux_Hierarchical_Cluster] , the DFM and hdwr_svr will be installed on the Linux SN automatically.

Installing DFM and hdwr_svr on AIX SN

We should put this part in the section Add required service node software in [Setting_Up_an_AIX_Hierarchical_Cluster] or the doc [Setting_Up_an_AIX_Hierarchical_Cluster] to add the DFM and hdwr_svr into the configure file.

mkdir -p /install/post/otherpkgs/aix/ppc64/dfm

Copy the DFM and hdwr_svr the packages to the suggested target location on the xCAT MN:

 /install/post/otherpkgs/aix/ppc64/dfm

Edit the bundle for AIX Service Node. Assuming you are using AIX 71, you should edit the file:

 /opt/xcat/share/xcat/installp_bundles/xCATaixSN71.bnd

And add the following into the bundle file:

 I:isnm.hdwr_svr
 R:xCAT-dfm*

The required software must be copied to the NIM lpp_source that is being used for the service node image. Assuming you are using AIX 7.1 you could copy all the appropriate rpms to your lpp_source resource (ex. 710SNimage_lpp_source) using the following commands:

 nim -o update packages=all -a source=/install/post/otherpkgs/aix/ppc64/dfm 710SNimage_lpp_source

The NIM command will find the correct directories and update the appropriate lpp_source resource directories.

After Initiate a network boot in [Setting_Up_an_AIX_Hierarchical_Cluster] or Initiate a network boot for Power 775 support in [Setting_Up_an_AIX_Hierarchical_Cluster], the DFM and hdwr_svr will be installed on the AIX SN automatically.

Conserver Setting

  • Conserver will always use nodehm.conserver to determine who should have the console for each node.
  • The cmd makeconservercf should be distributed to the service nodes based on nodehm.conserver

[NOTE] The nodehm.conserver should be the same as the service node which is set for the hw ctrl point(CEC) of the node. Otherwise the getmacs/rnetboot will not work.

Setting servicenode, xcatmaster and conserver for DFM HW Ctrl Cmds

There are 5 different nodes which should be considered: SN-CEC, SN, SN-CEC-nonSN-LPARs, non-SN-CEC, and non-SN-CEC-LPARs. The values of the noderes.servicenode and noderes.xcatmaster attributes of the CEC nodes will determine whether the HW Ctrl Cmds will be done by the DFM on the MN directly, or be distributed to the SN. The values of the noderes.servicenode and noderes.xcatmaster attributes of the LPARs nodes will determine whether the software management will be done on the MN directly, or distributed to the SN. The rcons will use the nodehm.conserver attribute in [#Conserver] session which will determine who should have the console for each node.

1. For the SN-CECs

  • Key Attributes:

The noderes.servicenode and noderes.xcatmaster attributes of these CEC are not set, or set to MN.

  • HW Ctrl:

The HW ctrl commands will be done by the DFM on the MN directly.

2. For the SN:

  • Key Attributes:

The nodehm.conserver, noderes.servicenode and noderes.xcatmaster attributes of these SN are not set, or set to MN.

  • HW Ctrl :

The HW ctrl commands will be done by the DFM on the MN directly.

  • Software Management(serving the boot image, xdsh, etc.):

The software management commands will be done on the MN directly.

3. For the SN-CEC-nonSN-LPARs:

  • Key Attributes:

The nodehm.conserver attribute are not set, or set to MN. The noderes.servicenode and noderes.xcatmaster attributes are set to SN for these LPARs nodes.

  • HW Ctrl:

The HW ctrl commands will be done by the DFM on the MN directly.

  • Software Management(serving the boot image, xdsh, etc.):

The software management commands will be distributed to the SN.

4. For the non-SN-CECs

  • Key Attributes:

The noderes.servicenode and noderes.xcatmaster attributes of these CECs are set to SN.

  • HW Ctrl:

The HW ctrl commands will be distributed to the SN.

5. For the non-SN-CEC-LPARs

  • Key Attributes:

The nodehm.conserver, noderes.servicenode and noderes.xcatmaster attributes of these LPARs are set to SN.

  • HW Ctrl:

The HW ctrl commands will be distributed to the SN.

  • Software Management(serving the boot image, xdsh, etc.):

The software management commands will be distributed to the SN.

For Example:

  • If noderes.servicenode is set for a hw ctrl point(CEC), then hw ctrl cmds should be distributed to the SN
    • I.e. if "rpower node1 on" is run, xcat 1st looks up the hcp (e.g. ppc.hcp) of node1. Assume it is called CEC1. Then it looks up noderes.servicenode for CEC1. If that is set, for example, to sn1, then the rpower cmd will be dispatch to sn1 and then sn1 will contact CEC1 to power on node1.
  • If noderes.servicenode is not set for a hw ctrl point CEC, then hw ctrl commands should be run on the MN directly.

**Configuring xCAT SN Hierarchy Ethernet Adapters(Power 775 DFM Only) **

[Configuring xCAT SN Hierarchy Ethernet Adapter DFM Only]

DFM configuration for hardware server connections

This section will discuss what needs to be configured and defined on the SN to allow for DFM to use hardware server to communicate to the CECs and Frames.

Since the CEC and Frame node definitions are already created on the MN, this step is primarily using this data to create the entries in the hardware server configuration file. This task is done by running the mkhwconn command for each FSP of the CECs and BPA of the Frame. The mkhwconn command will run on the MN.

Currently, xCAT supports creating hdwr_svr connections for xCAT(tool type: lpar) and CNM(tool type: fnm).

1. hdwr_svr connections for xCAT(tool type: lpar)

According to the definitions of the CEC in the section [#xCAT_DB_attributes], for <SN-CECs>, the noderes.servicenode and noderes.xcatmaster attributes of these CEC are not set, or set to MN; for <non-SN-CECs>, the noderes.servicenode and noderes.xcatmaster attributes of these CECs are set to SN.

About the SN CEC, the following command will create the connection between the hdwr_svr on the MN and the CEC:

 mkhwconn &lt;sn-CECs&gt; -t
 lshwconn &lt;sn-CECs&gt;

Use the lshwconn command to check the connection state, and the final expected connections state is "LINE　UP"

Before running the hardware control commands which will be distributed to the SN, finishing the OS provision for SN is a required prerequisite.

About the non-SN CEC, this command will create the connections between the hdwr_svr on the SN and the CEC:

 mkhwconn &lt;non-SN-CECs&gt; -t

According to the definitions of the Frame in the section [#xCAT_DB_attributes], the following command will create the connection between the hdwr_svr on the SN and the Frame. Finishing the OS provision for SN is a prerequisite for this command.

 mkhwconn frame -t

And then run the following command to check the connection state, and the final expected connections state is "LINE　UP"

 lshwconn frame

2. hdwr_svr connection for CNM(tool type: fnm)

In xCAT DFM Hierarchy environment, CNM is not support on the SN, and CNM needs a connection to every CEC in the cluster to be able to manage the details of the HFI connectivity. So the hdwr_svr will be available only on the xCAT EMS working with the "fnm" hardware connection. mkhwconn will create the hdwr_svr connections for CNM on the MN to the CECs directly.

 mkhwconn cec -t -T fnm
 lshwconn -T fnm

DFM rpower on flow when OS provision

As part of the rpower flow working with P775 IH cluster, it is important to include power on for all GPFS I/O server nodes prior to compute nodes. And the compute nodes could not get the image from the SNs when the CEC powers up. The SNs should be powered on firstly, and only if the OS provision for SNs is finished, we can power on the computes nodes. So We should require the rpower on order:

 1. power on the CECs to standby state
 2A. power on the SNs  (includes LL servers)
 2B. power on the GPFS I/O server working with DE's
 2C. power on  Utility  nodes (not as important but needed)  
 3. power on the compute nodes

CEC down/up policy

In the DFM Hierarchical environment, the power operating on the non-sn-CECs are done through the service node. So there are some CEC down/up policy should be followed.

CEC Up Policy

1. Power on SN-CECs to standby/operating state
2. Power SNs on with OS 
3. Create the connections from the SNs to the non-sn-CECs
4. Power on the non-sn-CECs
5. Power on all the compute LPARs

CEC down policy

1. Power off all the compute LPARs
2. Power off the non-sn-CECs
3. Power off the SNs
4. Power off the SN-CECs

Firmware update sequence

1. Power off all the CECs
2. Do the firmware update for the Frames' BPAs
3. Do the firmware update for the sn-CECs' FSPs
4. Power on the sn-CECs
5. Power SNs on with OS 
6. Create the connections from the SNs to the non-sn-CECs
7. Do the firmware update for the non-sn-CECs' FSPs

News

History

  • Oct 22, 2010: xCAT 2.5 released.
  • Apr 30, 2010: xCAT 2.4 is released.
  • Oct 31, 2009: xCAT 2.3 released.
    xCAT's 10 year anniversary!
  • Apr 16, 2009: xCAT 2.2 released.
  • Oct 31, 2008: xCAT 2.1 released.
  • Sep 12, 2008: Support for xCAT 2
    can now be purchased!
  • June 9, 2008: xCAT breaths life into
    (at the time) the fastest
    supercomputer on the planet
  • May 30, 2008: xCAT 2.0 for Linux
    officially released!
  • Oct 31, 2007: IBM open sources
    xCAT 2.0 to allow collaboration
    among all of the xCAT users.
  • Oct 31, 1999: xCAT 1.0 is born!
    xCAT started out as a project in
    IBM developed by Egan Ford. It
    was quickly adopted by customers
    and IBM manufacturing sites to
    rapidly deploy clusters.