Manualshelf

VERITAS Volume Manager 3.5 Administrator's Guide (September 2004)

ManualsBrandsHP ManualsSoftwareHP-UX 11i Volume Management (LVM/VxVM) Software
371372373374375376377378379380
Administering Cluster Functionality
Cluster Initialization and Configuration
Chapter 10 351
running on the same node; it does not attempt to connect with
vxconfigd daemons on other nodes. During cluster startup, the kernel
prompts vxconfigd to begin cluster operation and indicates whether it is
a master node or a slave node.
When a node is initialized for cluster operation, the vxconfigd daemon
is notified that the node is about to join the cluster and is provided with
the following information from the cluster monitor configuration
database:
• cluster ID
• node IDs
• master node ID
• role of the node
• network address of the vxconfigd daemon on each node
On the master node, the vxconfigd daemon sets up the shared
configuration by importing shared disk groups, and informs the
vxclustd daemon when it is ready for the slave nodes to join the cluster.
On slave nodes, the vxconfigd daemon is notified when the slave node
can join the cluster. When the slave node joins the cluster, the vxconfigd
daemon and the VxVM kernel communicate with their counterparts on
the master node to set up the shared configuration.
When a node leaves the cluster, the vxclustd daemon notifies the kernel
on all the other nodes. The master node then performs any necessary
cleanup. If the master node leaves the cluster, the kernels choose a new
master node and the vxconfigd daemons on all nodes are notified of the
choice.
The vxconfigd daemon also participates in volume reconfiguration as
described in “Volume Reconfiguration” on page 349.
vxconfigd Daemon Recovery
In a cluster, the vxconfigd daemons on the slave nodes are always
connected to the vxconfigd daemon on the master node. If the vxconfigd
daemon is stopped, volume reconfiguration cannot take place and other
nodes cannot join the cluster until it is restarted. If a cluster monitor is
enabled, it may try to fail over VxVM to another node in the cluster. It is
therefore inadvisable to stop the vxconfigd daemon on any cluster node.