Object storage is known by many for its ability to drive down the cost to store data through the use of commodity servers and high capacity hard drives. But object storage systems need flash and object storage system designers need to take full advantage of it. Object storage has the potential for rich metadata to be associated with each object, but the overhead of rich metadata does impact performance. Flash makes metadata processing much less of an issue. Second, there are workloads like Hadoop and Splunk that will access data directly on the object store, if a subset of their data is stored on flash then their time to results will be much faster.
In this ChalkTalk Video, George Crump of Storage Switzerland and CTO of Western Digital DCS Hal Woods, discuss the role of flash within an object storage system and some of the real-world use cases for object storage.
StorageSwiss.com - The Home of Storage Switzerland 
Well, a little breezy, but what can you do in 4 minutes to layout how SSDs will play in an object store. WD’s “Active Archive” is based on Amplidata’s Himalaya software which WD acquired not too long ago. Amplidata (WD/HGST), like Cleversafe (IBM), only uses erasure coding to protect data. The use of SSDs in an object store would certainly make it faster to retrieve data protected with erasure coding.
Let’s face it, flash is going to eventually permeate every aspect of data storage, including object. And now that Seagate has shown a 60TB SSD, you could have PB capacity on a single object-based storage cluster node or approx. 30PB of storage capacity in a 42U rack.