Skip to content

3.2 orcmd

lrrajesh edited this page Sep 14, 2016 · 1 revision

Sensys runtime daemons are root level resource manager daemons launched in all compute nodes and aggregator nodes during cluster boot up process. These daemons collect RAS monitoring data from the compute nodes and logs in to the database.

At startup, each node boots its own orcmd. The daemon detects the local node inventory and reports it to the aggregator in an initial "I'm alive" message. The aggregator enters the inventory in the database, and forwards the "I'm alive" message to the scheduler so it can construct an in-memory map of the cluster (nodes + inventory).

The orcmd daemon running on each node collects the RAS monitoring data using the sensor framework and its components, these components are configurable by using MCA parameters during build time and runtime.

The monitoring data collected from the compute nodes goes through a analytics framework for data reduction before gets stored in the database.

The ‘orcmd’ tool command line options are described below:

Usage: orcmd [OPTIONS]
  Open Resilient Cluster Manager Daemon

   -am <arg0>            Aggregate MCA parameter set file list
   -gomca|--gomca <arg0> <arg1>
                         Pass global MCA parameters that are applicable to
                         all contexts (arg0 is the parameter name; arg1 is
                         the parameter value)
-h|--help                This help message
-l|-config-file|--config-file <arg0>
                         Logical group configuration file for this orcm
                         chain
   -omca|--omca <arg0> <arg1>
                         Pass context-specific MCA parameters; they are
                         considered global if --gomca is not used and only
                         one context is specified (arg0 is the parameter
                         name; arg1 is the parameter value)
-p|-port-number|--port-number <arg0>
                         The user specified port number of this orcm daemon
-s|-site-file|--site-file <arg0>
                         Site configuration file for this orcm chain
   -tune <arg0>          Application profile options file list
-v|--verbose             Be verbose
-V|--version             Print version and exit
   -validate-config|--validate-config
                         Validate site file and exit

Note: To get the list of MCA parameters
  'orcm-info --param <arg0> <arg1>'
                         The first parameter is the
                         framework (or the keyword "all"); the second
                         parameter is the specific component name (or the
                         keyword "all").

Following is an example to start the orcmd daemon using a configurable mca parameter:

shell$ orcmd –-omca sensor heartbeat,cpufreq,pwr,ipmi

The above will configure orcmd to select the following components for the sensor data collection: heartbeat, cpufreq, pwr and ipmi. The heartbeat module is method to send the periodically collected data to the aggregator, the time interval for data collection and reporting to the aggregator is another configurable parameter in the orcm configuration file.

Clone this wiki locally