HP Galaxy Software Architecture on OpenVMS Alpha, Version 1.1 (12790)

HP Galaxy Software Architecture on OpenVMS Alpha, Version 1.1 SPD 70.44.09
Shared Memory Cluster Interconnect
The Shared Memory Cluster Interconnect (SMCI) is
a System Communications Services (SCS) port for
communications between Galaxy instances. When an
OpenVMS instance is booted as both a Galaxy and
as an OpenVMS Cluster member, the SMCI driver is
loaded. This SCS port driver communicates with other
cluster instances in the same Galaxy through shared
memory. This capability provides one of the major per-
formance benefits of the OpenVMS Galaxy Software Ar-
chitecture. The ability to communicate to another clus-
tered instance through shared memory provides dra-
matic performance benefits over traditional cluster in-
terconnects.
Local Area Network (LAN) Shared Memory Device
Driver
Local Area Network (LAN) communications between
OpenVMS Galaxy instances are supported by the Ether-
net LAN shared memory driver. This LAN driver commu-
nicates to other instances in the same OpenVMS Galaxy
system through shared memory. Communicating with
other instances through shared memory provides per-
formance benefits over traditional LANs.
RAMdisk in Shared Memory
In DECram for OpenVMS Alpha Version 3.0 or later,
DECram’s capability is extended to use OpenVMS
Galaxy shared memory to create an OpenVMS shared
memory disk. This allows users to take advantage of
OpenVMS Galaxy shared memory without modifications
to any of their applications.
Application Programming Interfaces
• Locks for synchronization
• Event notification
• Shared memory global sections
• Configuration information
• CPU management
For more information about OpenVMS Galaxy APIs, re-
fer to the HP OpenVMS Alpha Partitioning and Galaxy
Guide.
Single-Instance Galaxy Configuration
A single-instance Galaxy is for non-Galaxy platforms,
that is, those without a Galaxy console. Galaxy con-
figuration data, which is normally provided by console
firmware, is instead created in a file. By setting the sys-
tem parameter GALAXY to 1, SYSBOOT reads the file
into memory and the system boots as a single-instance
Galaxy, complete with shared memory, Galaxy system
services, and even self-reassignment of CPUs. This
can be done on any Alpha platform.
Single-instance Galaxy configurations will run on any
Alpha workstations or servers (even laptops) running
OpenVMS Version 7.2–1 or higher. This capability al-
lows early adopters to evaluate OpenVMS Galaxy fea-
tures and, most important, to develop and test Galaxy-
aware applications without incurring the expense of set-
ting up a full-scale Galaxy platform.
Because a single-instance Galaxy is not an emulator—
it is real Galaxy code—applications developed on a
single-instance Galaxy will run on multiple-instance con-
figurations.
SOFTWARE REQUIREMENTS
OpenVMS Galaxy configurations require OpenVMS
Alpha Version 7.2–1 or higher.
OpenVMS Galaxy console firmware for the supported
AlphaServers is located on the Alpha Systems Firmware
Update CD–ROM.
HARDWARE REQUIREMENTS
Configuring an OpenVMS Galaxy computing environ-
ment requires:
• One I/O module for each partition
• At least one processor module for each partition
• A dedicated serial console port for each partition
• Sufficient memory for operating system and required
applications
Optional Hardware
Customers might want to use the following optional
hardware:
• I/O expansion from an I/O module
• I/O adapters for network, storage, or traditional clus-
ter interconnects
• Additional CPUs for SMP instances
• Additional memory for Galaxy-wide global sections
GCU Hardware Requirements
Hewlett-Packard recommends an Alpha or VAX work-
station running DECwindows or a Windows NT work-
station with an X terminal emulator as a display device
for the OpenVMS Galaxy Configuration Utility.
3