Abstract: A system and method for thresholding system power loss notifications in a data processing system are provided. Power loss detection modules are provided in a data processing system having one or more data processing devices, such as blades in an IBM BladeCenter® chassis. The power loss detection modules detect the type of infrastructure of the data processing system, a position of a corresponding data processing device within the data processing system, and a capability of the data processing system to provide power during a power loss scenario. The detection module detects various inputs identifying these types of data processing system and power system characteristics and provides logic for defining a set of behaviors during a power loss scenario, e.g., behaviors for sending system notifications of imminent power loss. The detection of the various inputs and the defining of a set of behaviors may be performed statically and/or dynamically.

Abstract: A data storage enclosure management system of a plurality of service processors is configured to communicate externally via a pair of FC-AL loops. Lead and subsidiary service processors are defined and lead service processors connect to ones of the FC-AL loops with an FC-AL address, and the lead and subsidiary service processors are connected by a secondary communication link. The lead service processor(s) employ an identifier unassociated with the FC-AL address to differentiate communications of the lead service processor from communications of an associated subsidiary service processor, the lead service processor serving as a proxy for the associated subsidiary service processor with respect to the FC-AL address and communicating with the associated subsidiary service processor via the secondary communication link.

Abstract: A mechanism is provided for selecting IDLE patterns based on data being transmitted on the different ports of a wide lane serial attached small computer system interface cable. The mechanism examines the frequency content of the data bearing lanes and selects a DWORD to transmit for an IDLE that has a different frequency content to reduce spikes in electromagnetic interference emissions at a given frequency.

Abstract: An apparatus, system, and method are disclosed for performing a storage device maintenance operation. A management module receives a command through an interconnection module configured as a non-blocking switch. The management module performs a maintenance operation on a storage device through the interconnection module in response to the command. In addition, the management module may receive queries on the status of the maintenance operation through the interconnection module and report the status of the maintenance operation through the interconnection module.

Abstract: A blade server system includes a plurality of blade slots, a management module, and a plurality of switch modules. The switch modules provide connectivity to a plurality of communications fabrics. At least one switch module includes an integrated redundant array of independent disks (RAID) controller. A storage enclosure may be connected to the switch with the integrated RAID controller without having to include a stand-alone RAID controller, such as in one of the blade slots, and without having to include a RAID controller within the storage enclosure.

Abstract: A method of configuring a blade enclosure is provided by the present invention in which, in a first step, slots are identified to whose SAS connectors SAS device blades are to be connected in a minimum capacity configuration. In a second step, slots are identified to whose SAS connectors SAS device blades are to be connected in a maximum capacity configuration. A path is then established from the SAS switch to the SAS connector of each slot identified in either the first step or the second step. Blade devices, such as RAID controller blades and disk enclosure blades are installed in the identified slots. Thus, the SAS switch within the enclosure selectively and efficiently interfaces with a predetermined number of blade slots rather than with all slots.

Abstract: An apparatus, system, and method are disclosed for selective cross communications between autonomous storage modules. A RAID controller communicates through a first cascading communications loop comprising a first storage module. The first storage module includes a plurality of storage devices and is disposed in an enclosure. The RAID controller also communicates through a second cascading communications loop comprising a second storage module. The second storage module also includes a plurality of storage devices and is disposed in the enclosure. An interface module transmits messages of the first loop through the second storage module. In one embodiment, the RAID controller communicates a cross communications command to the interface module through the second storage module to enable the interface module to transmit the messages of the first loop through the second storage module in response to a failure of the first loop upstream of the first storage module.

Abstract: An apparatus, system, and method are disclosed for providing a redundant array of inexpensive disks (“RAID”) storage subsystem within a processor blade enclosure. A first RAID controller blade is included and configured to fit in a processor blade enclosure. At least one processor in communication with the first RAID controller blade is included. A disk enclosure blade is provided that includes a plurality of hard disk drives. The disk enclosure blade is configured to fit in the processor blade enclosure and the hard disk drives are in communication with the first RAID controller blade.

Abstract: An apparatus, system, and method are disclosed for integrating a blade RAID controller and storage. A storage blade enclosure communicates with a blade chassis. The storage blade enclosure is mounted within the blade chassis. A RAID controller disposed in the storage blade enclosure receives a command through the storage blade enclosure. In one embodiment, the command is communicated through the blade chassis from a processor blade mounted in the blade chassis. The RAID controller redundantly stores data to or retrieves data from a storage module disposed in the storage blade enclosure in response to the command using a RAID redundancy methodology.

Abstract: A computing device comprising a plurality of devices and a plurality of visual indicators is disclosed. Each of the plurality of visual indicators is interconnected with a power source and is associated with a different one of the plurality of devices. None of the plurality of visual indicators comprises a capacitor.

Abstract: A radio frequency identifier (RFID) active/passive tag is provided to identify failed sub-CRU and location within a higher level CRU. When an error occurs on the base blade or within one of the sub-CRUs, the embedded processor writes failure information to the RFID. RFID tags may also contain data identifying the locations, of the sub-CRUs of the blade. Thus, when there is a failure, the RFID may report the failed component as well as the location of a failed sub-CRU. Sub-CRUs may also include an embedded processor and RFID tag. When a service action is initiated to repair or replace a blade, the RFID tag may be read by a RFID reader. The RFID reader device may then present failure information, including the identification of the failed sub-CRU and other associated information to the operator. The RFID reader device may also request associated information from a server computer.

Abstract: A high speed fabric is provided and is partitioned into sub-fabrics for host adapter traffic and device adapter traffic. A high-speed switch includes an expander for host adapter traffic and an expander for device adapter traffic. The high-speed switch also includes a plurality of connectors, where each connector is partitioned into dual interfaces. For each connector, one interface is connected to the host adapter traffic expander and the other interface is connected to the device adapter traffic expander. Blades are provided with one or more connectors, where each connector is partitioned into dual interfaces for host adapter traffic and device adapter traffic. The blades may be any combination of processor blades, boot drive enclosure blades, switched bunch of disks enclosure blades, and/or integrated RAID controller disk enclosure blades.

Abstract: A sector conversion device includes a small memory area that is used to save two sector's worth of data when power is lost during the sector conversion process. As part of the sector conversion process, the sector conversion device saves two sectors of data when a power loss event occurs. These two sectors of data are stored in the memory area within the sector conversion device itself. This sector memory within the sector conversion device is defined and partitioned separately from the main internal memory of the device. This sector memory is also powered by a separate voltage boundary from a hold up voltage source, which is connected to the sector conversion device via an independent set of voltage pins. The hold up voltage source enables the sector memory contents to be retained.

Abstract: The present invention increases the performance of storage subsystems having a single controller while keeping the cost lower than a dual controller storage subsystem. An interface card is positioned in an archetypal second storage controller position. The storage controller and the interface card are connected via a backend communication path which is configured as a data I/O path to facilitate communication between the two. Both the storage controller and the interface card can be connected to the same or different data trafficking devices. An expander chipset can be attached to the interface card to provide a second access port to a redundant array of independent disks. The addition of the interface card provides redundancy to at least one data trafficking device as well as the potential for dual ported access to the RAID. In this respect, the present invention enables dual controller capability at the cost of using only a single controller.

Abstract: A method to store, retrieve, and search information is disclosed. The method encodes information comprising a plurality of datasets in a holographic data storage medium to form an encoded holographic data storage medium, and encodes that same information to one or more of a plurality of non-holographic data storage media. The method then selects a dataset comprising a portion of the information, where that dataset is written to a dataset storage address on the non-holographic data storage medium, and illuminates the encoded holographic data storage medium with a dataset beam comprising that dataset to produce a dataset reference beam, such that the dataset reference beam strikes the optical detector at one or more dataset reference beam coordinates. The method then associates the dataset with the one or more dataset reference beam coordinates and with the dataset storage address.

Abstract: A method is disclosed to store, retrieve, and search both analog data and digital data. The method encodes information comprising a plurality of analog datasets in a holographic data storage medium to form an encoded holographic data storage medium, and further encodes digital data abstracted from the plurality of analog datasets to one or more of a plurality of non-holographic data storage media. The method then selects an analog dataset, wherein digital data abstracted from that analog dataset is written to a digital storage address on the one or more non-holographic data storage media, and illuminates the encoded holographic data storage medium with an analog dataset beam comprising the analog dataset. The encoded holographic data storage medium emits a dataset reference beam that strikes the second optical detector at one or more dataset reference beam coordinates. The method then associates the analog dataset with the dataset reference beam coordinate and with the digital storage address.

Abstract: An apparatus, system, and method are disclosed for limiting failures in redundant signals. A coordination module generates a power status signal for each of a plurality of power modules. An input module receives a source signal. A signal generation module generates a plurality of output signals from the source signal and at least one power status signal. The output signals are not asserted if at least one power supply is operational. If a device of the signal generation module malfunctions, no more than one output signal is erroneously asserted.

Abstract: An apparatus, system, and method are disclosed for integrating redundant array of independent disk (“RAID”) storage within a blade center. A plurality of mutually autonomous storage subsystems mount within the blade center through a switch. Each storage subsystem includes a storage module comprising a plurality of storage devices and a RAID controller. A server blade mounted within the blade center may access a first storage subsystem through a switch module. The switch module is a non-blocking, cross-point switch. In one embodiment, the switch module restricts the server blade's access to a second storage subsystem.

Abstract: An apparatus, system, and computer readable medium are disclosed for booting a server from a shared storage system. The present invention teaches at least one server having at least one processor, a storage system having a plurality of storage drives and at least one boot volume corresponding to the at least one server, and a switch fabric having at least one switch; the switch fabric isolates boot traffic form storage traffic and enables communication between the server and the boot volume of the storage system. In some embodiments the switch fabric includes one or more partitionable switches that isolate boot traffic from storage traffic. The boot volumes may be a redundant array of storage devices. In certain embodiments, the present invention also includes devices external to the server, switch fabric, and storage system.

Abstract: A mechanism is provided for unique identification of each endpoint in a storage area network interconnect that is bridged by a specialized cable. Each endpoint is capable of querying peer endpoints for a unique identification. Once a unique identifier is obtained for all peer connections to a given endpoint, the endpoint may perform a comparison to validate that the cable connection terminations are connected to valid endpoints. If all endpoints are valid, then the mechanism enables the ports connected to the cable.