CLARiiON and VNX
Storage Pool does not have enough free space for FAST VP to relocate slices.
When a Virtual Provisioning Pool runs out of space, new slices cannot be allocated and host writes cannot written to the Pool LUN.
FAST Virtual Provisioning requires 10% of the slices to be free on the drives/tier it would use to relocate the data to. If there is not sufficient free space on that tier, no relocations can be done into that tier; however, if other tiers have sufficient free space, then relocations away from the tier with minimal free space can still succeed.
For FAST auto-tiering to work effectively, there should be at least 10% free capacity in a pool. This is because 10% of each Tier's capacity is reserved for new allocations; relocations into that tier will fail if it has under 10% of unallocated capacity. Therefore, as the total free space for the Pool drops to near 10%, the proportion of failed relocations will increase.
Adding further drives to the Pool or freeing up space will fix this issue. Adding drives of just one type will only add capacity to one Tier. However, as the migrations progress, auto-tiering will move data from other tiers onto the new drives, thus freeing up capacity on other tiers as well.
After increasing the free space in the pool, the events to watch for are:
PEService 71660400 Relocation completed for Storage Pool ...
These should be in the SP event logs after each time the FAST schedule runs. The amount of failed relocations should fall, as the free space becomes distributed over all three tiers (if drives are added initially nearly all free space will be on that Tier).
In FAST, the capacity scheduled to be relocated should start to fall as well.
For more information please refer to Primus article “emc274840 “.