SVC - Cluster overview

This dashboard provides an overview of a Storwize or SVC cluster. The dashboard is called once for each server to be monitored. The dashboard displays information about server-side volumes at the top. The lower section displays information about the storage used.

  • The charts have thresholds that should not be exceeded.
  • If they are exceeded, you can use the existing data very quickly to start an analysis on the BVQ GUI or request an analysis with a BVQ expert.




Panels

  • Row 1: Front end related capacity and performance information

    • Virtual Capacity: Shows the sum of all volumes virtual capacites presented to the hosts
    • CPU %: Shows the max CPU utilization of all node CPUs for the last 24 hours
    • Node cache %: Shows the maximum usage of all node caches for the last 24 hours
    • FC port %: Shows the maximum port utilization of all node ports for the last 24 hours
    • FC Node DR: Shows the average port data rate of the last 24 hours between the nodes
    • FC Host DR: Shows the average port data rate of the last 24 hours from the storage to the host
  • Row 2: Front end Performance

    • Latency gauge for front end volumes: Shows max value for the last 24 hours
    • IO and Latency chart for front end volumes (VDisks): Shows aggregated average R&W IO rate and latency of all VDisks form the selected cluster
  • Row 3: Back end related capacity and performance information

    • Allocated: Shows the allocated capacity from the storage pools
    • Available: Shows the available capacity from the storage pools
    • Free %: Shows the free capacity in %
    • Cap. savings %: Shows the storage efficiency with thin provisioning and compression
    • Cap. coverage %: The over provisioned cap coverage % metric helps to monitor how much capacity is available to cover the over provisioned virtual capacity of the thin provisioned (space efficient) VDisks
    • FC Controller DR: Shows the average port data rate of the last 24 hours from the nodes to the backend controllers
  • Row 4: Backend Performance

    • Latency gauge for back end volumes: Shows max value for the last 24 hours
    • IO and Latency chart for backend storage Volumes (MDisks): Shows aggregated average R&W IO rate and latency of all MDisks form the selected cluster

Links to other dashboards:

  • SVC - All Cluster overview
  • SVC - Cluster capacity overview
  • Details
    • MDisk detail
    • Node detail
    • VDisk detail

Possible adjustments:

  • Especially the thresholds of the performance gauges and charts on lines 2 and 4 can be adjusted for the specific environment.
  • It may be helpfull to save the dashboard for special clusters multiple times. For these dashboards, the selection options for special clusters in the template can be set by filters.

Hints & restrictions:

  • Each Panel has it's own additional help text

Time range and interval settings

  • Time Range: It is recommended to use 24 hours or 12 hours time frames in monitoring mode
  • Interval: The interval corresponds to the fixed interval setting in the BVQ GUI. Increase the interval for longer time ranges.

Select options

  • Objects can only be selected using the drop downs


  • No labels