Determining Flash Pool candidacy and optimal cache size

Before converting an existing aggregate to a Flash Pool aggregate, you can determine whether the aggregate is I/O bound, and what would be the best Flash Pool cache size for your workload and budget. You can also check whether the cache of an existing Flash Pool aggregate is sized correctly.

Before you begin

You should know approximately when the aggregate you are analyzing experiences its peak load.

Procedure

  1. Enter advanced mode: set advanced
  2. If you need to determine whether an existing aggregate would be a good candidate for conversion to a Flash Pool aggregate, determine how busy the disks in the aggregate are during a period of peak load, and how that is affecting latency: statistics show-periodic -object disk:raid_group -instance raid_group_name -counter disk_busy|user_read_latency -interval 1 -iterations 60
    You can decide whether reducing latency by adding Flash Pool cache makes sense for this aggregate.
    The following command shows the statistics for the first RAID group of the aggregate aggr1: statistics show-periodic -object disk:raid_group -instance /aggr1/plex0/rg0 -counter disk_busy|user_read_latency -interval 1 -iterations 60
  3. Start Automated Workload Analyzer (AWA): storage automated-working-set-analyzer start -nodenode_name -aggregate aggr_name
    AWA begins collecting workload data for the volumes associated with the specified aggregate.
  4. Exit advanced mode: set admin
    Allow AWA to run until one or more intervals of peak load have occurred. AWA collects workload statistics for the volumes associated with the specified aggregate, and analyzes data for up to one rolling week in duration. Running AWA for more than one week will report only on data collected from the most recent week. Cache size estimates are based on the highest loads seen during the data collection period; the load does not need to be high for the entire data collection period.
  5. Enter advanced mode: set advanced
  6. Display the workload analysis: storage automated-working-set-analyzer show -node node_name
  7. Stop AWA: storage automated-working-set-analyzer stop node_name
    All workload data is flushed and is no longer available for analysis.
  8. Exit advanced mode: set admin