Set common ports

Participating clusters must use the same port numbers for the daemons LIM, RES, MBD, and SBD.

By default, all clusters have identical settings, as shown:
LSF_LIM_PORT=7869
LSF_RES_PORT=6878
LSB_MBD_PORT=6881
LSB_SBD_PORT=6882
LSF_LIM_PORT change
The default for LSF_LIM_PORT changed in LSF version 7.0 to accommodate IBM® EGO default port configuration. On EGO, default ports start with lim at 7869, and are numbered consecutively for the EGO pem, vemkd, and egosc daemons.

This is different from previous LSF releases where the default LSF_LIM_PORT was 6879. LSF res, sbatchd, and mbatchd continue to use the default pre-version 7.0 ports 6878, 6881, and 6882.

Upgrade installation preserves existing port settings for lim, res, sbatchd, and mbatchd. EGO pem, vemkd, and egosc use default EGO ports starting at 7870, if they do not conflict with existing lim, res, sbatchd, and mbatchd ports.

Troubleshooting
To check your port numbers, check the LSF_TOP/conf/lsf.conf file in each cluster. (LSF_TOP is the LSF installation directory. On UNIX, this is defined in the install.config file). Make sure you have identical settings in each cluster for the following parameters:
  • LSF_LIM_PORT
  • LSF_RES_PORT
  • LSB_MBD_PORT
  • LSB_SBD_PORT

Set common resource definitions

For resource sharing to work between clusters, the clusters should have common definitions of host types, host models, and resources. Each cluster finds this information in lsf.shared, so the best way to configure multicluster is to make sure lsf.shared is identical for each cluster. If you do not have a shared file system, replicate lsf.shared across all clusters.

If it is impossible to have the same lsf.shared file for all clusters, LSF still allows for different host types, host models or resources in the lsf.shared file. In this case, the general rules for MC resource configuration are:
  1. Local cluster information overrides remote cluster information (host type, host model, or resource attributes and order of specification in configuration files).
  2. The local cluster ignores remote cluster configuration if the remote type/host model/resource does not exist in local cluster.

Define participating clusters and valid management hosts

To enable multicluster, define all participating clusters in the Cluster section of the LSF_TOP/conf/lsf.shared file.
  1. For ClusterName, specify the name of each participating cluster. On UNIX, each cluster name is defined by LSF_CLUSTER_NAME in the install.config file.
  2. For Servers, specify the management host and optionally candidate management hosts for the cluster. A cluster will not participate in multicluster resource sharing unless its current management host is listed here.

Example 

Begin Cluster
ClusterName  Servers 
Cluster1     (hostA hostB)
Cluster2     (hostD)
End Cluster
In this example, hostA should be the management host of Cluster1 with hostB as the backup, and hostD should be the management host of Cluster2. If the management host fails in Cluster1, MultiCluster will still work because the backup management host is also listed here. However, if the management host fails in Cluster2, MultiCluster will not recognize any other host as the management host, so Cluster2 will no longer participate in MultiCluster resource sharing.