HP ProLiant DL380p ISS Technology Focus, Number 11 - Page 2
The future: HP Advanced Memory Error Detection Technology
View all HP ProLiant DL380p manuals
Add to My Manuals
Save this manual to your list of manuals |
Page 2 highlights
• In 1999, HP introduced the Pre-Failure Alert notification system to monitor the status of critical components (hard drives, system memory, and power supplies) and notify IT administrators if the components have an increased probability of failure. • In 2002, HP introduced Hot-Plug Mirrored Memory, which protects against uncorrectable memory errors that would otherwise result in a server failure. Hot-Plug Mirrored memory lets administrators hotreplace failed DIMMS and hot-add new DIMMs, all without taking down the server. • In 2003, HP introduced Hot Plug RAID memory in ProLiant DL760 G2 servers to protect against uncorrectable memory errors that would otherwise result in a server failure. Hot Plug RAID memory lets administrators hot-replace failed DIMMs and hot-add new DIMMs, all without taking down the server. Hot Plug RAID memory has the advantage of providing similar levels of protection against errors as Hot-Plug Mirrored Memory without reserving as much of the installed memory for redundancy. The future: HP Advanced Memory Error Detection Technology The higher occurrence of memory errors has increased the number of error-event counts reported by the current threshold algorithm. Of these events, the most critical errors are the ones that allow the algorithm to predict DRAM defects warranting memory replacement. As memory densities have increased and servers now contain up to 18 trillion memory cells, the current algorithm is no longer optimal for distinguishing the most critical errors. Therefore, we are again enhancing the HP Pre-failure alert algorithm to include HP Advanced Memory Error Detection Technology. This innovation seeks out specific defects that either cause performance degradation or significantly increase the probability of exposing the system to an uncorrectable (non-recoverable) memory condition. HP Advanced Memory Error Detection Technology analyzes multiple parameters of correctable memory error events and intelligently detects when the system is at increased probability of non-recoverable memory conditions. This technology will increase server uptime by more accurately determining when a server administrator should schedule planned maintenance to replace degraded DIMMs. The technology also ensures that the algorithm alerts the server administrator only when necessary. Meet the Expert-Melvin Benedict Name: Melvin Benedict Title: Master Engineer-ISS Years at HP: 14+ University/Degree: Sacramento City College/AAEE Marist College/BS Physics University of Arizona/MSEE U.S. Patents: 4 Melvin Benedict is a Master Engineer in HP Industry Standard Servers (ISS), and he is the technical liaison between HP and AMD for server