Displaying and changing the file system manager node
In general, GPFS™ performs the same functions on all nodes. There are also cases where one node provides a more global function that affects the operation of multiple nodes. For example, each file system is assigned a node that functions as a file system manager.
For a more detailed discussion on the role of the file system manager node, see Special management functions.
The node that is the file system manager can also be used for applications. In some cases involving very large clusters or applications that place a high stress on metadata operations, it may be useful to specify which nodes are used as file system managers. Applications that place a high stress on metadata operations are usually those that involve large numbers of very small files, or that do very fine-grain parallel write-sharing among multiple nodes.
mmlsmgr fs1
The output shows the device
name of the file system and the file system manager's node number
and name: file system manager node [from 19.134.68.69 (k164n05)]
---------------- ------------------
fs1 19.134.68.70 (k164n06)
For complete usage information, see mmlsmgr command.
mmchmgr fs1 k145n32
GPFS: 6027-628 Sending migrate request to current manager node 19.134.68.69 (k145n30).
GPFS: 6027-629 [N] Node 19.134.68.69 (k145n30) resigned as manager for fs1.
GPFS: 6027-630 [N] Node 19.134.68.70 (k145n32) appointed as manager for fs1.
For complete usage information, see mmchmgr command.