How We are Unique

Zetta Enterprise Storage On-demand is more than just “storage in the cloud.” The underpinning technology has been designed from the ground up to deliver enterprise-class (and better) availability, transparent access, and flexible, dynamic scaling. Significant innovations that deliver these capabilities include:

 

• Best-in-Market Data Integrity Protection
• Strong Consistency Model
• Protocol Translation
• Grid-Like, Scale-Up/Out Virtualization with Multi-Tenancy
• Multi-tenancy with Performance Guarantees
• At-rest Data Encryption

 

Best-In-Market Data Integrity Protection

The Zetta data integrity solution exceeds anything on the market today, and has four key components:

 

• RAIN-6 — We call our RAID implementation “RAIN,” because we do more than stripe data across independent disks to ensure integrity, we stripe them across independent computers (“nodes”), guaranteeing availability and integrity even in the event of complete node failure from any cause, whether network, power supply, memory, or disk failure.
  
  
• N+3 — While most of the industry uses an N+2 RAID scheme, we use an N+3 scheme, ensuring availability and integrity even if three entire nodes in our 8+3 sets are offline at one time. And not only do we stripe data using an N+3 method, we also offer N+3 throughout the Zetta system architecture— including the Logical Controller and Network levels.
  
  
• Hashing at multiple file system layers — Zetta cryptographically hashes each file upon ingest, and compares the inbound hash to the outbound hash before returning the file upon a read request, checking to make sure that no corruption has occurred while in our possession (note that these write receipts can be distributed back to the customer as well, validating that data Zetta receives matches data sent by the customer). Additionally, Zetta creates additional hashes for each individual data chunk that is placed on disk, and then continually compares that hash with the actual data chunks stored, enabling us to detect any errors or anomalies and auto-correct them from the parity stripes while the data is idle reducing the performance impact of data recovery during critical read operations.
  
  
• Replication — in addition to these extensive data integrity checks and balances, we also offer optional replication to alternative geo-diverse Zetta sites, ensuring data integrity even in the event of an entire site disaster.
  
  

Zetta RAIN-6 in an 8+3 configuration has 3 parities that insure data availability and accessibility even in the event of 3 simultaneous failures of any kind including drives, network links or even entire storage nodes.

 

For more information, read Jeff Whitehead's blog entry on Data Integrity in the Cloud.

 

Strong Consistency Model

Zetta is a POSIX-compatible solution, which means that it behaves in ways that existing application infrastructures expect, including having a strong consistency model. Many Web 2.0 Cloud Storage providers rely on the eventual consistency model today.

 

What this means is that when a customer application calls sync() or closes a file, the Zetta system will not acknowledge the request until the data is synchronized down to the disk level (i.e., the data is in non-volatile format and redundantly encoded across nodes in N+3 fashion). This strong consistency model ensures that reads always get the most current, accurate data— there is no possibility of getting inaccurate or out-of-date data using this system.

 

Additionally, when a file is received, we make these hashes available to the customer, allowing the application to independently verify that the data on the Zetta storage solution is the data that was sent by the application.

 

Protocol Translation

Existing cloud storage solutions require the use of proprietary Web APIs, despite the fact that enterprise applications and IT architectures work with open standards to interconnect and communicate with storage resources. In contrast, Zetta remains committed to the existing standards and interfaces used by today's enterprise applications, offering POSIX compliant storage accessed via industry standard storage access technologies including CIFS, NFS, FTP, sFTP, WebDAV and rsync. And Zetta was built to adopt emerging standards in the future, ensuring your data is never stuck behind a customized, unsupported or stale interface technology.

 

Grid-Like, Scale-Up and Scale-Out Virtualization

Most storage virtualization functions by taking a monolithic storage array and sub-compartmentalizing it into multiple smaller logical compartments to use it for multiple applications simultaneously.

 

The Zetta solution is effectively the inverse of this. Zetta aggregates a myriad of smaller nodes and logically combines them into a very large virtual array, enabling far more dynamic scale-out capabilities for space and performance, and greatly increasing the fault-tolerance of the overall system.

 

Then Zetta leverages this entire scalable storage grid to backstop the Zetta File System. The Zetta File System is a true multi-tenant solution, leveraging virtualization at the customer access layer with per-volume encryption to ensure that all customer data is kept completely private and logically partitioned.

 

Multi-tenancy with Performance Guarantees

Zetta provisions scalable virtual volumes and also guarantees the performance of each individual virtual volume, regardless of the number of other customers or workloads accessing the storage service at the same time, by leveraging the very high degree of parallelism available in our distributed computing infrastructure. With strict service level agreements wrapped around availability, integrity and performance we are ensuring our customers receive the expected performance at ALL times.

 

At-Rest Encryption

Zetta provides a comprehensive, highly secure data storage solution without the complexity, additional expense and associated management overhead needed to deploy secure storage within traditional storage products. In many cases Zetta's storage already meets or exceeds the compliance requirements customers face for their data storage.

 

All information stored on the Zetta system is encrypted “at rest” at all times using a full public Key infrastructure (PKI) including unique customer keys for every volume— keys that are protected with government-grade, FIPS 140-2 certified hardware security modules.

 

In addition, the Zetta architecture— while fully multi-tenant— provides logical separation of customer data; this, combined with our “encryption key-per-volume” practices, provides a highly secure, truly private data security solution.