Server Fault is a question and answer site for system and network administrators. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

It's my understanding that auto-tiering is storage optimization based on cost-savings. You put the most-used data on the most expensive devices and the least-accessed data on the least expensive devices.

Auto load balancing is storage optimization based on putting data where you have space evenly across devices.

Is this a correct differentiation of the functionality/processes? If one storage virtualization solution claims to have storage load balancing and another claims to have auto-tiering are these the same or different functionalities?

share|improve this question

Auto-Tiering is used by many arrays to move data across different tiers of disk. Typically Tiers are set up in a similar fashion to this, but may vary:

  • Tier 1 - SSD or SAS/FC Drives with SSD Cache
  • Tier 2 - SAS/FC 10k-15k drives
  • Tier 3 - SATA, 7200 rpm drives

When auto-tiering is enabled, the array will moved data accross the different drive types/pools/tiers based on access patterns, etc. Primary purpose is generally to increase performance and reduce the resources of attmepting to do this manually.

It attempts to move data to the faster tiers when it needs to be accessed. Data that is mostly inactive is moved to slower storage.

Load balancing is generally for your paths. This is set by a policy such as round robin, where your data is "balanced" accross the available ports/paths. This is for balancing your SAN traffic across different switch ports and front end ports on the array.

SAN storage arrays require continual redesign and tuning to ensure that I/O is load balanced across all storage array paths. To meet this requirement, distribute the paths to the LUNs among all the SPs to provide optimal load balancing. Close monitoring indicates when it is necessary to manually rebalance the LUN distribution. Some vendors will also "auto load balance" between controllers for individual luns.

Terminology can vary slightly from Vendor to Vendor. Is there a particular array that you are inquiring about? I can update my reponse to be more detailed towards to particular product/vendor.

share|improve this answer
Excellent answer. – longneck Nov 15 '12 at 17:40
Thanks so much for your help! This is a great explanation and much appreciated! I'm researching several storage virt solutions including DataCore SANsymphony-V, Hitachi VSP and FalconStor NSS. – Stephanie Nov 15 '12 at 17:49
Glad I could help. Thanks for cleaning up my response longneck. – x50 Nov 15 '12 at 18:58
Be aware of load balancing for paths- each vendor will have a best practices guide that should be followed, and sometimes have limitations on the supported configurations. If you decided to put all your hosts across all your ports on, for example, a VSP, you'd be limited to 2000 volumes. Each port can only support 2000 unique LDEVs. That said, every additional port you provide is an additional SCSI queue that can be used by the host which may increase performance. – Basil Nov 15 '12 at 21:39

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.