Overview

IBM Spectrum Scale RAID integrates the functionality of an advanced storage controller into the GPFS NSD server. Unlike an external storage controller, where configuration, LUN definition, and maintenance are beyond the control of IBM Spectrum Scale, IBM Spectrum Scale RAID itself takes on the role of controlling, managing, and maintaining physical disks - hard disk drives (HDDs) and solid-state drives (SSDs).

Sophisticated data placement and error correction algorithms deliver high levels of storage reliability, availability, serviceability, and performance. IBM Spectrum Scale RAID provides a variation of the GPFS network shared disk (NSD) called a virtual disk, or vdisk. Standard NSD clients transparently access the vdisk NSDs of a file system using the conventional NSD protocol.

The features of IBM Spectrum Scale RAID include:
  • Software RAID

    IBM Spectrum Scale RAID, which runs on standard Serial Attached SCSI (SAS) disks in a dual-ported JBOD array, does not require external RAID storage controllers or other custom hardware RAID acceleration.

  • Declustering

    IBM Spectrum Scale RAID distributes client data, redundancy information, and spare space uniformly across all disks of a JBOD. This approach reduces the rebuild (disk failure recovery process) overhead and improves application performance compared to conventional RAID.

  • Pdisk-group fault tolerance

    In addition to declustering data across disks, IBM Spectrum Scale RAID can place data and parity information to protect against groups of disks that, based on characteristics of a disk enclosure and system, could possibly fail together due to a common fault. The data placement algorithm ensures that even if all members of a disk group fail, the error correction codes will still be capable of recovering erased data.

  • Checksum

    An end-to-end data integrity check, using checksums and version numbers, is maintained between the disk surface and NSD clients. The checksum algorithm uses version numbers to detect silent data corruption and lost disk writes.

  • Data redundancy

    IBM Spectrum Scale RAID supports highly reliable 2-fault-tolerant and 3-fault-tolerant Reed-Solomon-based parity codes and 3-way and 4-way replication.

  • Large cache

    A large cache improves read and write performance, particularly for small I/O operations.

  • Arbitrarily-sized disk arrays

    The number of disks is not restricted to a multiple of the RAID redundancy code width, which allows flexibility in the number of disks in the RAID array.

  • Multiple redundancy schemes

    One disk array can support vdisks with different redundancy schemes, for example Reed-Solomon and replication codes.

  • Disk hospital

    A disk hospital asynchronously diagnoses faulty disks and paths, and requests replacement of disks by using past health records.

  • Automatic recovery

    Seamlessly and automatically recovers from primary server failure.

  • Disk scrubbing

    A disk scrubber automatically detects and repairs latent sector errors in the background.

  • Familiar interface

    Standard IBM Spectrum Scale command syntax is used for all configuration commands, including maintaining and replacing failed disks.

  • Flexible hardware configuration

    Support of JBOD enclosures with multiple disks physically mounted together on removable carriers.

  • Journaling

    For improved performance and recovery after a node failure, internal configuration and small-write data are journaled to solid-state disks (SSDs) in the JBOD or to non-volatile random-access memory (NVRAM) that is internal to the IBM Spectrum Scale RAID servers.