lsload - display load information of the hosts
lsload [ -h ] [ -V ] [ -N | -E ] [ -l ] [ -R res_req ] [ -I index_list ] [ -n num_hosts ] [ host_name ... ]
Display the load information of the host. The selection and order sections of res_req control the returned hosts and how they are ordered, respectively (see lsfintro(1) ). If one or more host_names are given, then only load information about the designated hosts that satisfy the resource requirements (-R) is displayed. The displayed load information includes the following fields:
HOST_NAME
The standard host name used by LSF (typically an Internet domain name
with two components).
status
The status of the host. The possible states are ok, busy, lockW,
lockU, and unavail. A minus sign (-) may precede the status, indicating
that the Remote Execution Server (RES) on the host is not running.
Detailed explanations of the host status are as follows:
ok
The host is in normal load sharing state and can accept remote
jobs.
busy
The host is overloaded because some load indices go beyond the
configured threshold (see lsf(5)
). When in this state, the load
index values that caused the host to be busy are preceded by `*'.
The built-in load indices include r15s, r1m, r15m, ut, pg, io,
ls, it, swp, mem and tmp (see below). External load indices are
configured in the file lsf.shared (see lsf.shared(5)
).
r15s
The 15-second exponentially averaged CPU run queue length.
r1m
The 1-minute exponentially averaged CPU run queue length.
r15m
The 15-minute exponentially averaged CPU run queue length.
swp
The amount of swap space available, in Mbytes.
mem
The amount of available memory, in Mbytes.
tmp
The amount of free space in /tmp, in Mbytes.
external-index-name
Any site configured external load indices (see lim(8)
).
Available only when the -l option or -I option with the
index name is used, and only if defined in the lsf.shared
(see lsf.shared(5)
) configuration file.
lockW
The host is locked by its run window. Run windows for a host are
specified in the configuration file (see lsf(5)
) and can be
displayed by lshosts(1)
. A locked host will not accept load
shared jobs from other hosts.
lockU
The host is locked by the LSF administrator or root.
unavail
The host is down or the Load Information Manager (LIM) on the
host is not running.
-h Print command usage to stderr and exit.
-V Print LSF release version to stderr and exit.
-N The returned CPU run queue length load indices are normalized (see lsfintro(1) ). The default is to return raw load indices. -E The returned CPU run queue length load indices are effective run queue lengths (see lsfintro(1) ). The default is to return raw load indices. Options -N and -E are mutually exclusive.
-l Long display format. If specified, host names are not truncated and the IO and external load indices are also shown. This option overrides the index names specified by the -I option.
-R res_req
Resource requirements. If this option is specified, then load information
for only those hosts that satisfy the resource requirements is
returned. See lsinfo(1)
for a list of the built-in resource names.
The loads for the returned hosts are sorted according to the load on
the resource(s) given in res_req, or by default according to CPU and
paging load. If res_req contains special resource names, then only
load information about those hosts that provide these resources are
displayed (see lshosts(1)
to find out what resources are available on
each host).
-I index_list
List of load index names seperated by `:' (e.g. r1m:pg:ut). If this
option is specified then only the given indicies will be displayed.
-n num_hosts
The number of hosts requested. When this option is given, up to
num_hosts hosts that best satisfy the resource requirements are
displayed. If this option is not given, then as many hosts as are eligible
(that is, satisfy the resource requirements) are displayed.
host_name ...
Print host load information only for the hosts specified by host_name
.... If -R res_req is also specified, then only those specified hosts
that satisfy the resource requirement will be displayed.
% lsload -R «select[r1m<=0.5 && swp>=20 && type==ALPHA]"
or in the restricted format:
% lsload -R r1m=0.5:swp=20:type=ALPHA
display the load of ALPHA hosts with at least 20Mbytes of swap space,
and a 1-minute run queue length less than 0.5.
% lsload -R «select[(1-swp/maxswp)<0.75] order[pg]" Display the load of the hosts whose swap space utilization is less than 75%. The resulting hosts are ordered by paging rate.
% lsload -I r1m:ut:io:pg
Display the 1-minute CPU raw run queue length, the CPU utilization,
the disk I/O and paging rates for all hosts in the cluster.
% lsload -E
Display the load of all hosts, ordered by r15s:pg, with the CPU run
queue lengths being the effective run queue lengths (see lsfintro(1)
).
Exit status is -10 if an LSF problem is detected or a bad resource name is specified. Exit status is -1 if a bad parameter is specified, otherwise lsload returns 0.
lsfintro(1) , lsplace(1) , lshosts(1) , lsinfo(1) , lslockhost(8) , ls_load(3)