HP Data Protector Software Cell Manager Planning and Sizing

Memory
ProLiant servers use a variety of techniques to protect against memory errors. It is advisable to equip
the Cell Manager server with Fully-Buffered DIMM technology.
To improve memory protection even further, HP introduced Advanced ECC technology. Advanced
ECC technology is capable of correcting a multi-bit error that occurs within one dynamic random
access memory (DRAM) chip.
The ProLiant server online spare memory determines if an active DIMM (dual inline memory module)
exceeds a predefined error threshold. The error will be corrected and the data from the entire bank
that contains the failed DIMM will be copied to online spare memory. The failed bank is deactivated,
but the server will remain available until the failed DIMM is replaced during a scheduled shutdown.
Whereas online spare memory mode protects against single-bit errors and entire DRAM failure,
mirrored memory mode enables full protection against single-bit and multi-bit errors. In mirrored
memory mode, the same data is written to both system memory and mirrored memory banks, but data
is read only from the system memory banks. If a DIMM in the system memory banks experiences a
multi-bit error or reaches the pre-defined error threshold for single-bit errors, the roles of the system
and mirrored memory banks are reversed.
HP is one of the first companies to support hot plug RAID memory, which allows the memory
subsystem to operate almost continuously even in the event of a complete memory device failure. In
this context, RAID stands for Redundant Array of Industry-standard DIMMs.
Hot plug RAID memory generates parity for an entire cache line of data during write operations and
records the parity information on a dedicated parity cartridge. However, hot plug RAID memory does
not have the mechanical delays of seek time, rotational latency, and bottlenecks associated with disk
drive arrays.
To achieve maximum memory throughput, it is advisable to follow specific memory bank population rules.
Further information can be found in the White Paper “Fully-Buffered DIMM technology in
HP ProLiant servers”
(
http://bizsupport.austin.hp.com/bc/docs/support/SupportManual/c00913926/c00913926.pdf
).
Disk technology
It is advisable to use Enterprise class disc technology. Enterprise-class drives are designed for high
reliability, high performance, scalability, and error management under heavy 24x365 I/O
workloads. They are intended for mission-critical applications. Enterprise-class drives are the only
class of drives intended for unlimited I/O loads.
SAS-Serial attached SCSI is usually considered the most cost-effective solution for mission critical, high
I/O workload applications, such as business critical databases.
Further information can be found in the White Paper “Disk drive technology overview” at
http://bizsupport.austin.hp.com/bc/docs/support/SupportManual/c01071496/c01071496.pdf
HP was instrumental in developing the SAS standard. For a more detailed discussion of SAS, please
see the Technical Brief entitled, “Serial Attached SCSI technology” at
http://h20000.www2.hp.com/bc/docs/support/SupportManual/c00302340/c00302340.pdf
I/O subsystem
Advanced controllers (such as the HP Smart Array) decouple the logical disks seen by applications
from the physical devices used to implement the disk subsystem. A single logical disk (as seen by an
application) may be mapped onto an array of multiple physical disks. These controllers include both
hardware and software.
This approach provides greatly enhanced flexibility, expandability, maintainability, and performance.
Smart Array controllers are available for SAS, SATA, and SCSI interfaces.
29