Attended ExecEvent’s first Next-Gen Object Storage Summit in Miami this past week. Learned a lot there and met a lot of the players and movers in this space. Here is a summary of what happened during the summit.
Spent most of the morning of the first day discussing some parameters of object storage in general. Janae got up and talked about 4 major adopters for object storage:
- Rapid Responders – these customer have data in long term storage and it just keeps building and needs to be stored in scaleable storage. They believe someday they will need access to it and have no idea when. But when they want it, they want it fast. Rapid responder adoption is based on the unpredictability of access. As such, having the data on scaleable disk object storage makes sense. Some examples include black operations sites with massive surveillance feeds which maybe needed fast sometime after initial analysis and medical archives.
- Distributed (content) Enterprises – geographically distributed enterprises with users around the globe that need shared access to data. Distributed enterprises often have 100 or so users sharing data access dispersed around the globe and want shared access to data. Object storage can dispurse the data to provide local caching across the world for better data and meta-data latency. Media and Entertainment are key customers in this space but design shops that follow the sun also have the problem.
- Private Cloud(y) – data centers adopt the cloud for a number of reasons but sometimes it’s just mandated. In these cases, direct control over cloud storage with the economics of major web service providers can be an alluring proposition. Some object storage solutions roll in with cloud like economics and on premises solutions and responsiveness, the best of all worlds. Enterprise IT forced to move to the cloud are in this category.
- Big Hadoop(ers) – lots of data to analyze but with no understanding of when it will be analyzed. Some Hadoopers can schedule analytics but most don’t know what they will want until they finish with the last analysis. In these cases, having direct access to all the data on an object store can cut setup time considerably.
There were other aspects of Janae’s session but these seemed of most interest. We spent the debating aspects of object storage rest of the morning getting an overview on Scality customers. At the end of the morning we debating aspects of object storage. I thought Jean-Luc from Data Direct Networks had the best view of this when he said object storage is at it’s core, data storage that has scalability, resilience, performance and distribution.
The afternoon sessions were deep dives with the sponsors of the Object Summit.
- Nexsan talked about there Assureon product line (EverTrust acquisition). SHA1 and MD5 hashes are made of every object then as objects are replicated to other sites, the hashes are both checked to insure the data hasn’t been corrupted and the are periodically checked (every 90 days) to see if the data is still correct. If it’s corrupted, other replica’s obtained and re-instated. In addition, Assureon has some unique immutable access logs that provide an almost “chain of custody” for objects in the system. Finally, Assureon uses a Microsoft Windows Agent that is Windows Certified and installs without disruption to allow any user (or administrator) to identify files, directories, or file systems to be migrated to the object store.
- Cleversafe was up next and talked about their market success with their distributed dsNet® object store and provided some proof points. [Full disclosure: I have recently been under contract with Cleversafe]. For instance, today they have under management over 15 billion objects and deployments with over 70PBs in production They have shipped over 170PB of dsNet storage to customers around the world. Cleversafe has many patents covering their information dispersal algorithms and performance optimization. Some of their sites are in the Federal government installations with a few web intensive clients as well, the most notable being Shutterfly, photo sharing site. Although dsNet is inherently geographical distributed all these “sites” could easily be configured over 1 to 3 locations or more for simpler DR-like support.
- Quantum talked about their Lattus product built ontop of Amplidata’s technology. Lattus uses 36TB storage nodes, controller nodes to provide erasure coding for geographical data integrity and NAS gateway nodes. The NAS gateway provides CIFS and NFS to objects. The Latus-C deployment is a forever disk archive for cloud like deployments. This system provides erasure coding for objects in the system which are then dispersed across up to 3 sites (today, with 4 site dispersal under test). Their roadmap Lattus-M is going to be a managed file system offering that operates in conjunction with their StorNext product with ILMlike policy management. Farther out, on the roadmap is a Lattus-H which offers object repository for Hadoop clusters that can gain rapid access to data for analysis.
- Scality talked about their success in major multi-tennant environments that need rock-solid reliability and great performance. Their big customers are major web providers that supply email services. Scality is a software product that builds a ring of object storage nodes that supplies the backend storage where the email data is held. Scality is priced on a per end-user capacity stored. Today the product supports RestFul interfaces, CDMI (think email storage interface), Scality File System (based on FUSE, a POSIX compliant Linux file system). NFS interface is coming early next year. With the Scality Ring, nodes can go down but the data is still available with rapid response time. Nodes can be replicated or spread across multiple locations
- Data Direct Networks (DDN) is coming at the problem from the High Performance Computing market and have an very interesting scaleable solution with extreme performance. DDN products are featured in many academic labs and large web 2.0 environments. The WOS object storage supports just about any interface you want Java, PHP, Python, RestFULL, NFS/CIFS, S3 and others. They claim very high performance something on the order of 350MB/sec read and 250MB/sec write (I think per node) of object data transfers. Nodes come in 240TB units and one can have up to 256 nodes in a WOS system. One customer uses a WOS node to land local sensor streams then ships it to other locations for analysis.
The next day was spent with Nexsan and DDN talking about their customer base and some of their success stories. We spent the remainder of the morning talking about the startup world which surrounds some object storage technology and the inhibiters to broader adoption of the technology.
In the end there’s a lot of education needed to jump start this market place. Education about both the customer problems that can be solved with object stores and the product differences that are out there today. I argued (forcefully) that what’s needed to accelerate adoption was some standard interface protocol that all object storage systems could utilize. Such a standard protocol would enable a more rapid ecosystem build out and ultimately more enterprise adoption.
One key surprise to me was that the problems their customers are seeing is something all IT customers will have some day. Jean-Luc called it the democratization of the HPC problems. Big Data is driving object storage requirements into the enterprise in a big way…