HP BCDVideo BCD108, Руководство пользователя

Страница: 48 / 162

Hardware options installation 48
Advanced ECC memory configuration
Advanced ECC memory is the default memory protection mode for this server. Standard ECC can correct
single-bit memory errors and detect multi-bit memory errors. When multi-bit errors are detected using
Standard ECC, the error is signaled to the server and causes the server to halt.
Advanced ECC protects the server against some multi-bit memory errors. Advanced ECC can correct
both single-bit memory errors and 4-bit memory errors if all failed bits are on the same DRAM device on
the DIMM.
Advanced ECC provides additional protection over Standard ECC because it is possible to correct certain
memory errors that would otherwise be uncorrected and result in a server failure. Using HPE Advanced
Memory Error Detection technology, the server provides notification when a DIMM is degrading and has a
higher probability of uncorrectable memory error.
Online Spare memory configuration
Online spare memory provides protection against degraded DIMMs by reducing the likelihood of
uncorrected memory errors. This protection is available without any operating system support.
Online spare memory protection dedicates one rank of each memory channel for use as spare memory.
The remaining ranks are available for OS and application use. If correctable memory errors occur at a rate
higher than a specific threshold on any of the non-spare ranks, the server automatically copies the
memory contents of the degraded rank to the online spare rank. The server then deactivates the failing
rank and automatically switches over to the online spare rank.
Mirrored memory configuration
Mirroring provides protection against uncorrected memory errors that would otherwise result in server
downtime. Mirroring is performed at the channel level to one memory channel pair that can be either:
•
Channel 1 data being mirrored in channel 2
•
Channel 3 data being mirrored in channel 4
If an uncorrectable error is detected in the active memory channel, data is retrieved from the mirror
channel. This channel becomes the new active channel, and the system disables the channel with the
failed DIMM.
General DIMM and NVDIMM-N slot population guidelines
Population requirements
•
Do not mix RDIMMs, UDIMMs, and LRDIMMs.
•
When NVDIMM-Ns are installed in this server, install at least one regular RDIMM in a DIMM slot
associated with the first processor installed.
•
Install DIMMs only if the corresponding processor is installed.
•
When mixing regular DIMMs and NVDIMM-Ns in a channel, install the regular DIMMs first and then
install the NVDIMM-Ns in the channel.
•
When installing NVDIMM-Ns in this server and using the HPE 96W Smart Storage Battery, install a
maximum of 16 NVDIMM-Ns in the server.
•
When single-rank, dual-rank, and quad-rank DIMMs are populated for two DIMMs per channel or
three DIMMs per channel, install the higher numbered rank DIMM first in the channel (starting from
the farthest DIMM slot). For example, install the quad-rank DIMM first, the dual-rank DIMM next, and
the single-rank DIMM last.
Population recommendations