IBM Spectrum LSF 10.1 Fix 488486 for LSF Suite 10.2 Readme File

Abstract

This fix enables the lim -t and lshosts -l commands to show the correct processor numbers, ensures that the MPS daemon ends after using the bkill command to kill an interactive job that uses GPU resources exclusively, and prevents all running jobs from being killed when using ansible to expand or upgrade the cluster.

 

Description

Readme documentation for IBM Spectrum LSF 10.1 Fix 488486 for LSF Suite 10.2 including installation-related instructions, prerequisites and co-requisites, and list of fixes.

This fix addresses the following issues:

1. On POWER hosts, the lim daemon ignores socket level information because the old version of the Hardware Locality (hwloc) does not return the correct socket physical index, which makes the processor always set as 1. This fix upgrades Hardware Locality (hwloc) to version 1.11.8, which returns the correct socket physical index and allows the lim daemon to consider socket level so that the processor is set correctly.

2. When using the bkill command to kill an interactive job that uses GPU resources exclusively, the MPS daemon is not terminated. This fix ensures that such a job is properly terminated.

3. When using the ansible playbook to expand or upgrade the cluster, all running jobs are killed. This fix resolves this issue.

 

 

Readme File for: IBM® Spectrum LSF

Product/Component Release: 10.1

Update Name: Fix 488486

Fix ID: suite-lsf-10.1-build488486

Publication Date: 23 April 2018

Last Modified Date: 23 April 2018

 

Contents

1. List of Fixes

2. Download Location

3. Product or Components Affected

4. System Requirements

5. Installation and Configuration

6. List of Files

7. Product Notifications

8. Copyright and Trademark Information

 

1. List of Fixes

P102521 P102534 P102546

2. Download Locations

Download Fix 488486 from the following location: http://www.ibm.com/eserver/support/fixes/

 

3. Product or Components Affected

Affected product or components include:

LSF/lim

LSF/sbatchd

Ansible playbooks under lsf_installer/playbook

 

4. System Requirements

linux3.10-glibc2.17-ppc64le

 

5. Installation and Configuration

1. Download the .bin file into suite deployer machine.

2. Run the .bin file to extract the rpm into the repository.

3. Then cd to /opt/ibm/lsf_installer/playbook.

If cluster is installed using NFS option:

4a.  Run the following commands:

ansible-playbook -i lsf-inventory lsf-nfs-setup.yml

ansible-playbook -I lsf-inventory lsf-apply-fix.yml

If cluster is not installed using NFS:

4b.  Run this command:

ansible-playbook -i lsf-inventory lsf-apply-fix.yml

 

5. Run "rpm -qa | grep lsf-server" on the host that have the rpm deploy to verify the deployment is successful.

 

6. List of Files

lim

sbatchd

 

7. Product Notifications

To receive information about product solution and patch updates automatically, subscribe to product notifications on the My notifications page ( www.ibm.com/support/mynotifications) on the IBM Support website (support.ibm.com). You can edit your subscription settings to choose the types of information you want to get notification about, for example, security bulletins, fixes, troubleshooting, and product enhancements or documentation changes.

 

8. Copyright and Trademark Information

©Copyright IBM Corporation 2018

 

U.S. Government Users Restricted Rights - Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp.

IBM®, the IBM logo, and ibm.com® are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the Web at "Copyright and trademark information" at www.ibm.com/legal/copytrade.shtml.