Performance Information Reporting (PIR) gathers performance statistics from the server over a specified period, and then sends the results in text file logs to a specified email address. The PIR reports are initiated with the supervisor-level CLI command, performance-info-report. The gathered statistics are sent to a user-specified email address. The statistics can then be fed into a diagnostics portal that displays a report based on the contents of the PIR results. The diagnostics portal contains diagnostic files from the NAS server. By default the email sent out by 'performance-info-report' will include seven files.
Once initiated, PIR runs for ten minutes, however, an extended version called Continuous PIR runs until it is stopped. It also collates data in ten minute intervals, per each hour it is run. Once started by the user, Continuous PIRs can be used to gather results on at intervals, from the point a user starts it, until it is requested to stop. A user can catch unexpected issues as soon as they happen, rather than trying to predict them, or reacting once the interesting behaviour has already finished. Once the issue has been captured, continuous PIR can be switched off.
A specific file system of interest should be specified on the command line so that the performance statistics relate to the cluster node that is hosting that file system. If a file system is not specified on the command line (dev only option) then the statistics will relate to the cluster node which is running the 'performance-info-report' command.
See the Man pages for detailed information on the commands and options used to run a PIR.