Data collection

To diagnose the cause of an issue, it might be necessary to gather some extra information from the cluster. This information can then be used to determine the root cause of an issue.

Collection of debugging information, such as configuration files and logs, can be gathered by using the gpfs.snap command. This command gathers data about GPFS, operating system information, and information for each of the protocols. Following services can be traced by gpfs.snap command:

GPFS + OS: GPFS configuration and logs plus operating system information such as network configuration or connected drives.
CES: Generic protocol information such as configured CES nodes.

NFS: CES NFS configuration and logs.
SMB: SMB and CTDB configuration and logs.
OBJECT: Openstack Swift and Keystone configuration and logs.
AUTHENTICATION: Authentication configuration and logs.
PERFORMANCE: Dump of the performance monitor database.

Information for each of the enabled protocols is gathered automatically when the gpfs.snap command is run. If any protocol is enabled, then information for CES and authentication is gathered.

To gather performance data, add the --performance option. The --performance option causes gpfs.snap to try to collect performance information.

Note: Gather the performance data only if necessary, as this process can take up to 30 minutes to run.

If data is only required for one protocol or area, the automatic collection can be bypassed. Provided one or more of the following options to the --protocol argument: smb,nfs,object,ces,auth,none

If the --protocol command is provided, automatic data collection is disabled. If --protocol smb,nfs is provided to gpfs.snap, only NFS and SMB information is gathered and no CES or Authentication data is collected. To disable all protocol data collection, use the argument --protocol none.