Articles
The Benefits of In-line, Real-Time Data Compression
August 12, 2009
Written by: By Peter Smails, SVP of marketing, Storwize
Today, the amount of mission-critical information to which enterprise must have ready access continues to escalate dramatically. According to research from the Enterprise Strategy Group, file capacity is projected to increase from just more than 10,000 PB in 2008 to more than 62,000 PB 2012 (55% CAGR). Together, economic pressures and that file data growth are driving adoption of data reduction technologies. While deduplication has captured much of the market’s attention for backup solutions, businesses are also looking to real-time compression technology to create savings for online data, and throughout the entire data lifecycle from primary through backup.To understand why it’s important first to briefly understand the difference in the technologies and where they fit in the overall data reduction landscape:
Real-Time Compression is designed to sit transparently in front of network attached storage (NAS) devices and reduce the size of every file created up to 10x depending upon file type. Applications have random, read-write access to compressed data while the physical capacity required to store a file, or copies and permutations of a file is significantly reduced throughout the entire lifecycle, including backup. Because less data is written to disk, overall network and storage performance and utilization can also be significantly enhanced.
Deduplication is designed to reduce the physical storage required to store redundant data. In the deduplication process, duplicate data is deleted, leaving only one copy of the data to be stored, which is why it is well suited for backup data where you typically have multiple data sets (daily/weekly) of mostly redundant data and access is primarily sequential (e.g., restore). The more copies of redundant data you have the higher your effective deduplication rate.
Though several vendors offer data compression technology and position their solutions as appropriate for online data, only an in-line, real-time compression appliance delivers on all the key requirements for online data reduction, mainly:
Significant Data Reduction or Online Data
Real-time compression is the best technology for non-backup, random access, data sets, delivering the highest real-time data reduction across multiple online data types. Savings are instantaneous as soon as you start writing or reading files.
Complete Transparency
Real-time compression transparently supports all applications including high-performance databases. Real-time compression does not require any client software or changes to clients, servers, applications, or workflow.
Enhanced Storage Performance and Efficiency
With real-time compression there is no storage performance impact, and in most cases there is a performance improvement even with high-performance applications
Benefits Throughout the Lifecycle
By reducing data payload in real-time at primary storage, real-time compression creates financial and operational savings at every storage tier throughout the entire data lifecycle. Because there is less data, time and cost are reduced for all downstream operations including migration, replication, archiving, and backup. Plus, real-time compression is the only technology that is complementary with deduplication providing the highest levels of data reduction from primary thru backup.
Faced with lower sales due to frozen or reduced IT budgets, real-time compression solutions represent a tremendous opportunity for resellers to offer their customers a compelling alternative to the traditional model of simply expanding their infrastructure. Real-time compression offers an immediate ROI and has a positive impact on storage infrastructure by enabling businesses to get more from their current IT investment while reducing capital expenditures and operating costs.
By Peter Smails, SVP of marketing, Storwize



