mmpstat command

Reports current performance statistics of IBM Storage Scale.

Synopsis

mmpstat  Metric[,Metric...] | NamedQuery | Measurement | +  
              [-N Nodename | all] [--bucket-size size] [--filter filter]

Availability

Available on all IBM Storage Scale editions.

Description

The mmpstat reports current performance metrics, which are queried from IBM Storage Scale performance metrics collectors. Any metric that is known to the pmcollector can be queried and shown in a table format. This command runs a query and generates a report at every interval (the default interval is 1 second).

Parameters

Metric[,Metric...]: Specifies a comma-separated list of metrics to display metrics in the output.
NamedQuery: Specifies a name of a predefined query.
Measurement: Specifies a name of a predefined measurement.
+: Displays a list of known metrics.
-N or --Node NODENAME | all: Specifies a node from where the metrics are retrieved. Accepts a single node only or all nodes.; For general information about how to specify node names, see Specifying nodes as input to GPFS commands.
--bucket-size BUCKET_SIZE: Specifies the bucket size in seconds for the query and the report interval. The default size is 1 second. For example, if the bucket size is 10, data is queried and reported every 10 seconds.
If the bucket size is smaller than the sensor period of a metric, the reports are generated frequently. But, the list of metrics remains empty. For example, if the bucket size is 1 second and the sensor period is 10 seconds, every 10 seconds the report shows the metric value and all other reports remain empty.
--filter FILTER: Specifies filter criteria for the query to run the query. Use the --filter + option to display a list of known filters.

Exit status

0: Successful completion.
nonzero: A failure occurred.

Security

You must have root authority to run the mmpstat command.

The node on which the command is issued must be able to run remote shell commands on any other node in the cluster without the use of a password and without producing any extraneous messages. For more information, see Requirements for administering a GPFS file system.

Examples

Query the system usage of the local node.
```
# mmpstat usage
```

Query pdisk read/write statistics on an ESS or ECE IO node.

# mmpstat  gpfs_pdds_bytes_read,gpfs_pdds_bytes_written --filter "gpfs_disk_name=.*e1s13.*" -N ess5kio2

Query CPU metrics from all nodes.
```
# mmpstat cpu_user,cpu_system -N all
```

Query file system read/write I/Os for a specific file system for every 10 seconds.

# mmpstat gpfs_fs_bytes_written,gpfs_fs_bytes_read --filter "gpfs_fs_name=ess5k1m" -b 10
# mmpstat  "gpfs_pdds_bytes_written" --filter "gpfs_disk_name=.*e1s13.*" -b 10

A sample output is as follows:

-------------------------------------------------------
          |      scale-51|      scale-51|      scale-51|
          |              |              |              |
Timestamp |    cpu_system|      cpu_user|  cpu_contexts|
-------------------------------------------------------
13:28:16             0.51|          0.00|           499|
13:28:17             1.49|          2.48|           546|
13:28:18             2.53|         19.19|           769|

Location

/usr/lpp/mmfs/bin