IBM 2013Jun10 Easy Tier enhancements announcement

In Data storage, DS8000, DS8800, DS8870, IBM by AdministratorLeave a Comment

IBM® has recently enhanced their Easy Tier® automated storage tiering functionality.

IBM Easy Tier software functionality

Last year IBM announced a statement of direction (SoD) to offer an API for more application control over Easy Tier functionality.  At IBM Edge 2013 conference this month they rolled out Easy Tier Application, a new application-programing interface (API) that enables software developers to supply hints and help manage Easy Tier data placement on DS8870 and other IBM System Storage® storage. With Easy Tier Application volume pinning customers can assign application data into flash or any tier of storage. Pinned volumes allow a combination of manual allocation for some information while at the same time providing automated storage tiering for all the rest of the data in a storage pool.

Easy Tier Server uses server-side flash on IBM Power Series® servers with automated storage tiering across a host and storage system to copy the hottest data to server flash to be accessed directly. Having this data available on the host avoids any SAN or storage system overhead for all subsequent reads. Easy Tier Server also offers the native data protection, high availability and other advanced functionality of sophisticated storage arrays because all the data continues to reside on shared IBM System Storage. IBM showed a performance boost for an AIX server, with Easy Tier Server and an AIX Power 770 server with an EXP30 Ultra SSD I/O drawer running OLTP type activity had a 5.3X performance increase over just using a disk only DS8870 storage system. Easy Tier Server currently supports AIX.

Easy Tier Heat Map Transfer extends the performance boost of automated storage tiering to secondary mirrors of data on remote systems. With this feature, Easy Tier transfers data placement information (heat maps) from the primary system to a secondary system. As a result, the remote storage can duplicate any tiering activity that occurs on the local system. In the event of an outage, then, replicated data can have the same high I/O performance provided by the primary system.

Announcement Significance

Storage auto-tiering has become a frequently asked for option as SSDs have become more ubiquitous in enterprise storage. Server side flash has take more time to be incorporated into this auto-tiering frameworks but just about every vendor has announced or released something here as well. IBM has responded fairly quickly to the Server side flash opportunity with its control over server hardware, AIX software and storage.  The application API is more of a differentiator but there are a couple of other alternatives to address this side of the problem.  Again, IBM’s control of the O/S and key applications has helped it respond faster but it’s just a start. I would be surprised if Vmware vSphere and Windows Server don’t incorporate something similar in the very near future for all storage vendors to use.

~~~~

[This announcement summary dispatch was originally sent out to our newsletter subscribers in June of 2013.  If you would like to receive this information via email please consider signing up for our free monthly newsletter (see subscription request, above right) and we will send our current issue along with download instructions for this and other reports. Dispatches are posted to our website at least a quarter or more after they are sent to our subscribers, so if you are interested in current results you will need to signup for our newsletter.]  

Silverton Consulting, Inc. is a Storage, Strategy & Systems consulting services company, based in the USA offering products and services to the data storage community.

 

 

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.