ºÝºÝߣ

Editor's Notes

• #10: The HP Storage Portfolio.HP makes it easy to build the exact storage infrastructure you need. We're committed to giving you the tools, resources, and services you need ¡ª regardless of your storage experience.Throughout the lifecycle of your data, we can help you Store it on best-in-class platforms that fit into your environment, be it SAN, NAS, dedicated to a server, or even archived off your main platform.Protect it with both tape- and disk-based backup targets, encryption and key management, and integrated backup software.Optimize it to get the most out of what you have, including virtualizing at the array or network level, helping to reduce backup volumes with Deduplication, or buy only the drives you need with Thin ProvisioningManage it with our Storage Essentials resource management, full-featured device management, and data management of documents & records with TRIM software.And we offer end-to-end Storage Services, from design and installation, to optimization, to mission-critical support.
• #15: PREMA Architecture for the DL980 G7HP¡¯s PREMA Architecture represents a technology direction for scalable, resilient, x86 server designs. The PREMA Architecture is the design foundation for x86 servers that need to deliver more scalability, resiliency, and efficiency to meet the needs of customers using scale-up x86 servers in most demanding, data intensive workload environments such as business processing, business intelligence, and large scale consolidation and virtualization.HP scale-up x86 servers utilizing the PREMA Architecture are designed to take full advantage of processor technology such as Intel¡¯s latest Nehalem-EX processors with QPI (Quick Path Interconnect). Building on top of the performance and resiliency enhancements provided by the underlying processor technology, and leveraging the alignment with industry standard operating environments such as Microsoft Windows Server and Linux, HP scale-up ProLiant servers such as the DL980 G7 deliver the robustness needed for more demanding and data intensive workloads.In addition to the scaling and advanced reliability functionalities delivered by HP, Intel, and operating system partners with the Nehalem-EX environment, the DL980 G7 includes a node controller to further improve the attributes associated with the PREMA Architecture, especially focused on customer requirements around scalability and resiliency. When a system scales to a larger numbers of inter-connected processors, the communication and coordination between the processors grows at an accelerated (exponential) rate. The node controller is an HP developed technology leveraging the mission critical computing expertise ro reduce this communication and coordination overhead between the processors. The node controller groups processors into island of two processors to minimize inter-processor communication and enable rapid access to local memory. There are 4 node controllers in a DL980. Each node controller caches information about all the processors which reduces the overhead of requesting and receiving updates from all other processors. This functionality is called smart CPU caching.In addition, the node controllers and processors in a DL980 are connected through a high bandwidth interconnect fabric called redundant system fabric. The redundant system fabric extends the advanced reliability of the Intel Nehalem-EX processor by providing more interconnect capacity, lower data error rates and dynamic traffic routing for improved reliability. HP ProLiant DL980 G7 with the PREMA Architecture delivers on the key HP scale-up x86 server value proposition of balanced scaling; self-healing resiliency and breakthrough efficiency. Balanced scaling with smart CPU cachingSmart CPU caching functionality enabled by the node controller can offer up to 20% better system performance on DL980 G7 than competitive 8 socket systems for a diverse set of workloads. It enables 30% faster local memory access enabling performance boost to workloads with?affinity to local memory to. For example, Virtual Machines, SAP and High Performance Computing. Some of the key features include:Balanced and fully connected QPI?fabric. The 980 system fabric has the equivalent of 6 QPI links while most of the competitive 8 socket systems without a node controller only have 4 QPI links to connect the processorsDynamic balancing of QPI fabric traffic to eliminate performance bottlenecks. If some of the QPI links are overused by a processors then the excess traffic is dynamically routed through an alternate pathEnables higher inter-socket link bandwidth and frees up memory bandwidth of the burden from IO traffic for balanced scaling since the node controller stores DMA tags and eliminates DMA tag writes to the processors and memory.Self-healing resiliency via redundant system fabric Redundant system fabric is the interconnect fabric between the processors and the node controllers in DL980 G7 that provides additional resiliency features in addition to the Intel Nehalem-EX processor's advanced reliability functionalities.Some of the key features include:50% more interconnect capacity of the DL980 system fabric and dynamic routing of traffic in case of a failed link via an alternate link improves system reliability Improved reliability of the fabric since the lower fabric link rates (4.8 Gpbs.) leads to greater margin, lower risk, and lower error rates in comparison to systems without node controller running standard QPI link rate of (6.4 Gbps ).Enhanced error containment that stops the bad data to spill out of the I/O subsystem to storage or network resulting in substantially increased?data integrity for business applications.Improved error logging and diagnostics information so that OS and virtual machines can attempt error recovery or corrective actions can be taken by administrators easily. DL980 warm resets after fatal errors and captures error logs instead of a hard reset and losing the error log data.In addition to the balanced scaling and self healing resiliency enabled by HP PREMA Architecture, the HP DL980 G7, with help common ProLiant innovations like iLO3, Insight software and Thermal Logic, delivers breakthrough efficiency enableing customers to reduce their datacenter footprint by a consolidation ratio up to 197 to 1. Delivering a payback in as little as 60 days.
• #16: BladeSystem are modular, converged infrastructure designed for any workload with the range of offerings spanning:Client Virtualization: announced in Feb 2009, the new HP BladeSystem bc2800 Blade PC and HP BladeSystem bc2200 Blade PC, are combined with Citrix XenDesktop 3 to provide a high-definition user experience and centralized desktop management. The combined offering leverages the power of both the data center and endpoint devices to significantly reduce desktop total cost of ownership.Small and Remote site: BladeSystem c3000 is an all-in-one infrastructure built just for small sites with big compute and storage needs. Now, you can mix and match storage, servers and network in one box, to integrate solutions with less effort - including the new All-in-One storage blade.Enterprise Data Center: BladeSystem c7000 enclosure is ideal for larger data centers with more dynamic data center environments Supports up to 16 half-height 2 socket Intel? Xeon? and AMD Opteron? blades for maximum performance and density Over 40% power savings and 47% less airflow when compared to competitors rack mount servers Redundant and flexible I/O configurations with HP BladeSystem Interconnect technology Full power redundancy with N+N hot-plug power supplies and the flexibility of N+1 redundancyThe HP BladeSystem c7000 carrier grade model uses -48V DC power supply and is NEBS certified. Massive Scale Out and HPC: The new?HP ProLiant BL2x220c has been designed from the ground up for the unique demands of massive scale-out and cloud data centers.? The world¡¯s first 2 in 1 blade server, the BL2x220c has 2 independent servers in 1 blade enclosure, essentially doubling compute performance without increasing the size of the data center, and coupled with the HP StorageWorks 9100 Extreme Data Storage System, provides a scale-out storage infrastructure built for the next generation of massive scale-out and cloud-enabled data centers.Mission Critical: The new Integrity NonStop BladeSystem?doubles the performance in half the footprint while providing the same trusted 24/7 NonStop availability, scalability, and data integrity.