Pdisk paths

To the operating system, physical disks are made visible as block devices with device special file names, such as /dev/sdbc (on Linux®) or /dev/hdisk32 (on AIX®). Most pdisks that IBM Storage Scale RAID uses are located in JBOD arrays, except for the NVRAM pdisk that is used for the log tip vdisk. To achieve high availability and throughput, the physical disks of a JBOD array are connected to each server by multiple (usually two) interfaces in a configuration known as multipath (or dualpath). When two operating system block devices are visible for each physical disk, IBM Storage Scale RAID refers to them as the paths to the pdisk.

In normal operation, the paths to individual pdisks are discovered by IBM Storage Scale RAID automatically. There are only two instances when a pdisk must be referred to by its explicit block device path name: during recovery group creation using the mmcrrecoverygroup command, and when adding new pdisks to an existing recovery group with the mmaddpdisk command. In both of these cases, only one of the block device path names as seen on the active server needs to be specified; any other paths on the active and standby servers will be discovered automatically. For each pdisk, the nPathActive and nPathTotal stanza parameters can be used to specify the expected number of paths to that pdisk, from the active server and from all servers. This allows the disk hospital to verify that all expected paths are present and functioning.

The operating system could have the ability to internally merge multiple paths to a physical disk into a single block device. When IBM Storage Scale RAID is in use, the operating system multipath merge function must be disabled because IBM Storage Scale RAID itself manages the individual paths to the disk. For more information, see Configuring GNR recovery groups: a sample scenario.