Platform LSF Administration Guide Version 6.2
Chapter 39
Tuning the Cluster
Administering Platform LSF
559
Changing Default LIM Behavior to Improve
Performance
You may want to change the default LIM behavior in the following cases:
◆
In very large sites. As the size of the cluster becomes large (500 hosts or more),
reconfiguration of the cluster causes each LIM to re-read the configuration files.
This can take quite some time.
◆
In sites where each host in the cluster cannot share a common configuration
directory or exact replica.
In this section
◆
“Default LIM behavior” on page 559
◆
“Change default LIM behavior” on page 559
◆
“Reconfiguration and LSF_MASTER_LIST” on page 560
◆
“How LSF works with LSF_MASTER_LIST” on page 560
◆
“Considerations” on page 561
Default LIM behavior
By default, each LIM running in an LSF cluster must read the configuration files
lsf.shared and lsf.cluster.cluster_name to obtain information about
resource definitions, host types, host thresholds, etc. This includes master and slave
LIMs.
This requires that each host in the cluster share a common configuration directory or an
exact replica of the directory.
Change default LIM behavior
The parameter LSF_MASTER_LIST in lsf.conf allows you to identify for the LSF
system which hosts can become masters. Hosts not listed in LSF_MASTER_LIST will
be considered as slave-only hosts and will never be considered to become master.
By setting this parameter, you can reduce the time it takes to reconfigure a cluster and
requests made to the file server. Only hosts listed in LSF_MASTER_LIST will read
lsf.shared and lsf.cluster.cluster_name. Configuration information will then
be propagated from the master LIM to slave-only LIMs.
Setting LSF_MASTER_LIST (lsf.conf)
1
Edit lsf.conf and set the parameter LSF_MASTER_LIST to indicate hosts that
are candidates to become the master host. For example:
LSF_MASTER_LIST="hostA hostB hostC"
The order in which you specify hosts in LSF_MASTER_LIST is the preferred order
for selecting hosts to become the master LIM.
2
Save your changes.
3
Reconfigure the cluster
%
lsadmin reconfig
%
badmin mbdrestart
.