Home > Storage > PowerScale (Isilon) > Product Documentation > Storage (general) > PowerScale OneFS Operating System > Data protection
As traditional storage systems scale, techniques that were appropriate at a small size become inadequate at a larger size, and there is no better example of this than RAID. RAID can be effective only if the data can be reconstructed before another failure can occur. However, as the amount of data increases, the speed to access that data does not and the probability of additional failures continues to increase. OneFS does not depend on hardware-based RAID technologies to provide data protection. Instead, OneFS includes a core technology, FlexProtect, which is built on solid mathematical constructs and uses Reed-Solomon encodings to provide redundancy and availability. FlexProtect provides protection for up to four simultaneous failures of either full nodes or individual drives. As the cluster scales in size, FlexProtect delivers on the need to ensure minimal reconstruction time for an individual failure.
FlexProtect is a key innovation in OneFS and takes a file-specific approach toward data protection, storing protection information for each file independently. This independent protection allows protection data to be dispersed throughout the cluster (see 0) along with the file data—dramatically increasing the potential parallelism for access and reconstruction when required. When there is a failure of a node or drive in a cluster, FlexProtect can identify which portions of files are affected by the failure. It then employs multiple nodes to participate in the reconstruction of only the affected files. Since the Autobalance feature in OneFS spreads files out across the cluster, the number of spindles and CPUs available for reconstruction exceeds what is found in a typical hardware RAID implementation. Also, FlexProtect does not need to reconstruct data back to a single spare drive (which with RAID, creates an unavoidable bottleneck). Instead, the file data is reconstructed in available space, providing a virtual hot spare.
OneFS constantly monitors the health of all files and disks within the cluster. If components are at risk, the file system automatically flags the problem components for replacement, transparently reallocating those files to healthy components. OneFS also ensures data integrity if the file system has an unexpected failure during a write operation. Each write operation is transactionally committed to a mirrored file system journal to protect against node or cluster failure. In the case of a write failure, the journal enables a node to rejoin the cluster quickly, without the need for a file system consistency check. With no single point of failure, the file system is also transactionally safe in the event of a journal failure.
Since the FlexProtect feature in OneFS is file-aware, it also provides file-specific protection capabilities. An individual file (or more typically, a directory) can be given a specific protection level. Also, different portions of the file system can be protected at levels aligned to the importance of the data or workflow. Critical data can be protected at a higher level whereas less critical data can be protected at a lower level. This provides storage administrators with a very granular protection or capacity trade-off that can be adjusted dynamically as a cluster scales and a workflow ages.
To effectively protect a file system that is hundreds of terabytes or petabytes in size, an extensive use of multiple data availability and data protection technologies is required. OneFS incorporates several strategies for data protection including data replication, synchronization, and snapshot capabilities.
OneFS Snapshots are highly scalable and typically take less than one second to create. They create little performance overhead, regardless of the level of activity of the file system, the size of the file system, or the size of the directory being copied. Also, only the changed blocks of a file are stored when updating the snapshots, thereby ensuring highly efficient snapshot storage utilization.
OneFS, combined with OneFS SnapshotIQ software, can be used to create up to 20,000 snapshots on a cluster. This ability provides a substantial benefit over most other snapshot implementations because the snapshot intervals can be far more granular and thereby offer significantly improved recovery point objectives (RPO) time frames. OneFS also provides near-immediate restoration of snapshot data backups to recover data quickly. With OneFS, snapshot restores are fast, efficient, and simple.
OneFS writable snapshots enable the creation and management of space and time efficient, modifiable copies of a regular read-only snapshot. As such, they present a writable copy of a source snapshot. This copy is accessible at a directory path within the /ifs namespace, which can be accessed and edited through any of the cluster’s file and object protocols, including NFS, SMB, and S3.
While snapshots provide an ideal solution for infrequent or smaller-scale data loss occurrences, when it comes to catastrophic failures or natural disasters, a second, geographically separate copy of a dataset is clearly beneficial.
OneFS and SyncIQ software combine to deliver high-performance, asynchronous replication of data to address a broad range of RPO and recovery time objectives (RTO). They are easily optimized for either LAN or WAN connectivity to replicate over short or long distances, providing protection from both site-specific and regional disasters. SyncIQ also offers encryption for secure replication across untrusted networks.
Complementary to the manual and scheduled replication policies, SyncIQ also offers a continuous mode, or replicate on change, option. SyncIQ will continuously monitor the replication dataset and automatically replicate any changes to the target cluster.
OneFS further simplifies and accelerates disaster recovery and business continuity at scale with integrated, push-button simple failover and failback. With faster, easier failover and failback capabilities, most workflows will realize dramatic improvements in synchronization times. The same workflow will also be able to perform multiple syncs in the same time for ‘fresher’ target data.
OneFS also enables performing large-scale backup and restore functions across massive, single-volume datasets—while using an enterprise’s existing, SAN-based tape and VTL infrastructure. This ability is enabled by a Fibre Channel backup accelerator card, in concert with OneFS NDMP support and SnapshotIQ.
OneFS is certified with a wide range of leading enterprise backup applications, including:
Each of the OneFS enhanced data protection capabilities – FlexProtect, SmartLock, SnapshotIQ, SyncIQ, NDMP will help enterprises reduce both RPO and RTO for mission critical applications and big data environments.