Mount options specific to IBM Spectrum Scale

Mount options specific to IBM Spectrum Scale™ can be specified with the -o parameter on the mmchfs, mmremotefs, mmmount and mount commands. Options specified with the mmchfs and mmremotefs commands are recorded in the GPFS™ configuration files and are passed as default options to subsequent mount commands on all nodes in the cluster. Options specified with the mmmount or mount commands override the existing default settings and are not persistent.

All of the mount options can be specified using the -o parameter. Multiple options should be separated only by a comma. If an option is specified multiple times, the last instance is the one that takes effect. Certain options can also be set with specifically designated command flags. Unless otherwise stated, mount options can be specified as:

option or option=1 or option=yes - to enable the option

nooption or option=0 or option=no - to disable the option

The option={1 | 0 | yes | no} syntax should be used for options that can be intercepted by the mount command and not passed through to GPFS. An example is the atime option in the Linux environment.

The GPFS-specific mount options are:

atime

Update inode access time for each access. This option can also be controlled with the -S option of the mmcrfs and mmchfs commands.

mtime

Always return accurate file modification times. This is the default. This option can also be controlled with the -E option on the mmcrfs and mmchfs commands.

noatime

Do not update inode access times on this file system. This option can also be controlled with the -S option on the mmcrfs and mmchfs commands.

nomtime

Update file modification times only periodically. This option can also be controlled with the -E option on the mmcrfs and mmchfs commands.

norelatime

Update inode access time for each access. This option is the default if minReleaseLevel is less than 5.0.0 when the file system is created. This option can also be controlled with the -S option of the mmcrfs and mmchfs commands. For more information, see atime values.

nosyncnfs

Do not commit metadata changes coming from the NFS daemon synchronously. Normal file system synchronization semantics apply. On AIX® nodes, nosyncnfs is the default. On Linux nodes, syncnfs is the default.

relatime

Allow the update of inode access time only if one of the following is true:

The existing access time is older than 24 hours. Access time is user configurable through the atimeDeferredSeconds configuration attribute.
The existing file modification time is greater than the existing access time.

This option is the default if minReleaseLevel is 5.0.0 or greater when the file system is created. This option can also be controlled with the -S option of the mmcrfs and mmchfs commands. For more information, see atime values.

syncnfs

Synchronously commit metadata changes coming from the NFS daemon. On Linux nodes, syncnfs is the default. On AIX nodes, nosyncnfs is the default.

useNSDserver={always | asfound | asneeded | never}

Controls the initial disk discovery and failover semantics for NSD disks. The possible values are:

always: Always access the disk using the NSD server. Local dynamic disk discovery is disabled.
asfound: Access the disk as found (the first time the disk was accessed). No change of disk access from local to NSD server, or the other way around, is performed by GPFS.
asneeded: Access the disk any way possible. This is the default.
never: Always use local disk access.