Kodak is going to use Sun's Honeycomb, aka Sun StorageTek 5800, in its CARESTREAM medical information system. Sun has not announced Honeycomb as a product but says Kodak will be using it with 2007 availability.
The details here have been hurriedly obtained from a Sun release, release notes and administration guide for the product. These suggest that it is related to EMC's Centera product in several ways. However Sun is not presenting it as a fixed reference data, content-addressed storage device. But it initially seems to me, on the basis of the details that follow, that that is exactly what it is.
From Sun's release
"By making its Versatile Intelligent Patient Archive (VIParchive) software available with the StorageTek 5800 system, Kodak's CARESTREAM Solution will offer radiologists and healthcare IT managers a new storage option that improves reliability and performance, while helping to lower costs."
"As the world's first Application-Aware Programmable Storage solution, the StorageTek 5800 system, formerly known as Project Honeycomb, blurs the lines between application server and storage, giving application developers new flexibility in the way their applications are deployed. By off-loading selected data services from the application server, the system can help improve the overall application price/performance while helping to lower cost and complexity."
"Examples of these services include metadata management, database queries, and custom services such as image resizing. By moving portions of the application to the data, rather than moving data to the application, picture archive and communication system (PACS) providers can deliver a more flexible, higher reliability solution."
We learn more about Honeycomb from the product's release notes and administration guide.
From the product's release notes
The Sun StorageTek 5800 system is an online storage appliance featuring a fully integrated hardware and software architecture in which the disk-based storage nodes are arranged in a symmetric cluster. The clustered and redundant design provides high availability, good performance, and exceptional data integrity.
The Sun StorageTek 5800 system provides the following features:
. Storage control, data, and metadata path operations distributed across the cluster to provide reliability and performance scaling
. Total symmetry in both hardware and software
. No single point of failure, with non-disruptive serviceability that includes fail-in-place components for deferred maintenance
. Optional storage of metadata associated with all data for easy reference and parallel search capability against an in-memory metadata index
. Automated integrity and placement algorithms that eliminate redundant array of inexpensive disks (RAID) configuration and volume management
. Fully integrated load and capacity balancing technology
. A virtual-view file system interface for auxiliary archive access using the Web-based Distributed Authoring and Versioning (WebDAV) protocol
. A Software Developers Kit (SDK) with Application Programming Interfaces (APIs), documentation, and an emulator
(From the admin guide) The Sun StorageTek 5800 system is an online storage appliance featuring a fully integrated hardware and software architecture in which the disk-based storage nodes are arranged in a symmetric cluster. Data can be associated with metadata for easy reference as discussed in “Metadata”.
Both data and metadata are distributed across disks and nodes. There is no dedicated metadata server or master node, and the system presents a simple, single image for client and administrator access. The clustered and redundant design provides high availability, good performance, and exceptional data integrity.
The Sun StorageTek 5800 system is a rack-mounted system designed to have no single point of failure and to be serviceable without disruption. Each 1U Sun StorageTek 5800 system server node runs the Solaris OS and consists of a 1U socket 939 AMD Opteron processor, a server management board, and 4 Serial ATA (SATA), 3.5 inch (8.89 cm) drives.
A pair of Load Balancers provide for failover and load spreading across nodes. Because the system features a fail-in-place self-healing design, much of the urgency normally associated with switch, disk, Network Interface Card (NIC), Central Processing Unit (CPU), or other hardware failures is removed.
The minimum system configuration consists of a half-cell of eight storage nodes with four SATA 500-gigabyte (GB) drives per node (meaning 2TB per node and 16TB total), two Load Balancers, and one Sun Fire™ x2100 server acting as the service node.
The maximum configuration consists of one cell of 16 storage nodes with four SATA 500-GB drives per node (meaning 32TB total), two Load Balancers, and one Sun Fire x2100 server acting as the service node
The Sun StorageTek 5800 system is a unique product that combines servers, storage, networking, and distributed-systems software in a single solution.
There are two main types of metadata in the Sun StorageTek 5800 system: system and user, or extended, metadata. The systemmetadata includes a unique identifier for each stored object, called the object ID or OID, as well as information on creation time (ctime), data length, and data hash.
The Sun StorageTek 5800 system’s user or extended metadata provides the ability to store application-level attributes associated with data objects. User metadata also allows you to arbitrarily define a schema(using the EXtensible Markup Language (XML). Typically, user queries are executed against application-stored, user metadata. Optionally, they can be issued against system metadata as well.
You can define a set of metadata attributes associated with your stored objects. For example, in an application that stores medical records, the metadata attributes include things like patient name, doctor’s name, reason for visit, deductible, medical record number and insurance company. You can then run a query to retrieve the record using these fields, or combine the query to retrieve all records for a given doctor or insurance company on a particular date. Extensible metadata provides unlimited scope when designing the application.
You access data in Sun StorageTek 5800 system storage in one of two ways:
. Through an API (Java and C client libraries)
. Through a file system view with WebDAV
File system views
The Sun StorageTek 5800 system contains no internal hierarchical path structure. Virtual views are queries against metadata that are expressed externally as file system paths and file names. A virtual file system view is defined using the metadata attributes defined in the schema.
For example, using a medical record schema ... you can define a view that is organized at the top level directory by doctor name, then by patient name at the second level, and so on. Opening the top-level view for a given doctor shows a list of patients for that doctor
Which leaves us ...
Which leaves us at the point that Honeycomb on its own cannot be used. It needs an OEM partner of Sun to decide that it is better to use Honeycomb instead of force-fitting an inappropriate file system into an application. Kodak has to have been persuaded that the 5800 with metadata organised by Kodak is much better for its end users than whatever native file system/server combination it used before.
EMC's Centera is used in PACS applications. Soon then, it will be possible to have a pretty direct comparison between Centera and Honeycomb.
That will be interesting.