Classifications

• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
  • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
  • G06F3/0601—Interfaces specially adapted for storage systems
  • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
  • G06F3/0604—Improving or facilitating administration, e.g. storage management
  • G06F3/0607—Improving or facilitating administration, e.g. storage management by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F11/00—Error detection; Error correction; Monitoring
  • G06F11/006—Identification
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
  • G06F13/38—Information transfer, e.g. on bus
  • G06F13/40—Bus structure
  • G06F13/4063—Device-to-bus coupling
  • G06F13/4068—Electrical coupling
  • G06F13/4081—Live connection to bus, e.g. hot-plugging
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
  • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
  • G06F3/0601—Interfaces specially adapted for storage systems
  • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
  • G06F3/0629—Configuration or reconfiguration of storage systems
  • G06F3/0632—Configuration or reconfiguration of storage systems by initialisation or re-initialisation of storage systems
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
  • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
  • G06F3/0601—Interfaces specially adapted for storage systems
  • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
  • G06F3/0671—In-line storage system
  • G06F3/0683—Plurality of storage devices
  • G06F3/0689—Disk arrays, e.g. RAID, JBOD

Definitions

• This invention relates to a "plug and play", high speed, microcomputer based, Fibre Channel compatible and fault tolerant mass storage information server system.
• the present invention relates to a device and method for providing an enterprise-wide information server system which incorporates a dual loop arbitrated, Fibre Channel capable, multiple-fault tolerant, hot-swappable disk array requiring no host computer.
• the disk array subsystem is configured with various types of operating system software to create duplicate and multiple copies of the data stored on the information server system across various different combinations of the physical and logical disk drives.
• Any of a large array of fault tolerant disk array architectures are typically employed including, for example, various implementations of what is known the trade as the redundant array of independent disks or "RAID" topologies and protocols.
• the operating system software program Upon detection of a complete or partial failure of a particular disk storage device, the operating system software program notifies the server of the failure, marks the portion of the disk which failed or logically removes the completely failed disk storage device from the disk array. Next, the operating system typically reallocates the remaining available physical disk space into a modified configuration of logical disk drives.
• the operating system reconstructs new duplicate, multiple copies of the data stored on the server system within the constraints of the newly reduced amount of free disk space.
• the server system also alerts the server system administrator that a failure has occurred so that corrective action may be taken. Depending on the exact nature of the failure, the necessary corrective action can include removal and replacement of the completely or partially failed disk storage device.
• the remove and replace system maintenance operation requires, in many systems, that the entire server system be taken off-line and powered down before the physical replacement operation can be performed. Some information server systems permit removal and replacement of the defective disk storage device while the server system remains on-line and powered on. This process is commonly referred to by the trade as "hot-swapping" of devices.
• the process of logical reintegration requires a significant portion of the server system central processing unit and memory resources. These resources are needed to accomplish the reallocation of the newly available free disk space into the logical disk configuration of the server and the redistribution of the multiple, duplicate copies of the information stored on the server across the new and remaining physical and logical disk drives. This need for server system resources, although temporary, results in a severe decrease in the performance of the information server system.
• users of presently available information server technology have generally two types of information server system options available. The first type of server system is completely unavailable for the duration of the system maintenance operation. The second type of system is, in effect, unavailable to the users due to the seriously degraded performance experienced by the information server system during the system maintenance operation.
• Patents which are hereby incorporated by reference in their entirety, appear to disclose various types and components of the above described information server systems: 5,402,428; 5,471 ,099; 5,479,653; 5,502,836; 5,517,632; 5,518,418; 5,522,031; 5,530,831; 5,544,339; 5,548,712; 5,615,352; 5,651,132; 5,659,677; 5,664,119; 5,666,337; 5,680,538; 5,694,581; and 5,701,406.
• the present invention is an information server system with a "plug and play", scalable, modular, fault tolerant, multi-loop, hot swappable architecture incorporating a central processing unit, a storage device controller connected to the central processing unit for controlling at least one storage device array and a communications interface system connected to the central processing unit for communicating with other systems. More particularly, the invention represents a plug and play storage system for information storage and retrieval applications and incorporates an on board computer server for the storage system, thus eliminating the requirement for resources from a host computer.
• the computer controls and communicates with a storage device controller and a communications interface with other systems external to the storage system.
• the storage device operates via a high speed interface to control an array of storage devices through their individual hot swap interface cards.
• the invention provides a self contained plug and play information server system which incorporates a high speed, microcomputer based, server running industry standard operating system software enhanced to include functionality directed to operation of an array controller for a storage device such as a magnetic disk array, optical device array, solid state memory or the like, and which controls the physically independent or integral storage device array, and a communications interface.
• the array controller subsystem controls and communicates with the storage device array with a Fibre Channel protocol and topology compatible 1.0625 gigabit per second copper compact PCI and/or a fibre optic interface bus and an Intelligent Input/Output, "I 2 O" bus for control of and communication with the disk storage device array.
• the storage device array incorporates a plurality of storage devices with a corresponding number of bypass, or "bridging", interface cards configured to facilitate the on-line addition, removal and replacement of storage devices.
• the storage device array further incorporates a physically independent Fibre Channel compatible optical bus for high speed communication between storage device array subsystem components, including the internal storage devices, independent from the information server.
• the present invention accordingly provides for an information server system with a scalable, modular, fault tolerant, hot swappable architecture, that comprises a central processing unit; an array controller subsystem connected to the central processing unit for controlling at least one storage device array; and a communications interface subsystem connected to the central processing unit for communicating with other subsystems of the information server and for controlling the array controller subsystem.
• the information server system further comprises a midplane connector for connecting interface cards for components.
• each disk storage device array comprises a plurality of disk storage devices and a corresponding number of bypass interface cards, all of which communicate with one another and the information server.
• each disk storage device array comprises a predetermined number of bypass interface cards which populate the entire information server system, . whether or not the entire information server system is fully populated with a corresponding number of disk devices.
• Each disk storage device is preferably hot-swappable, and each disk storage device is mounted on a bypass interface card that connects to the midplane connector.
• the disk array controller subsystem controls and communicates with one or more disk storage device arrays with an arbitrated dual channel Fibre Channel system, and each of the disk storage devices are connected to the arbitrated dual channel Fibre Channel architecture, whereby each disk storage device may perform simultaneous reads and writes of data in response to any requests from the outside world through the information server.
• the disk storage devices include electronic device registration devices, and the disk array controller subsystem monitors identification numbers of the electronic device registration devices. The disk array controller subsystem can thus monitor when a component in the information server system is removed or added.
• the electronic device registration devices are preferably integrated into an electronic circuitry of each of the disk devices such that engagement or disengagement of each disk storage device with the disk storage device array causes a triggering of the electronic device registration devices to generate and transmit a unique identifying serial number signal unique to each disk storage device to the disk array controller subsystem.
• a triggering of the electronic device registration devices preferably causes the electronic device registration devices to generate and transmit a unique identifying serial number signal unique to each disk device to the disk array controller subsystem, and upon receiving the signal, the disk array controller subsystem then immediately either initiates logical connection or disconnection of the disk device to or from the array, depending on whether the disk device has been engaged or disengaged, respectively.
• the disk array controller subsystem can thus accomplish the electrical and logical connection and disconnection of the disk device by control of the bypass interface cards.
• the bypass interface cards comprise an independent but logically integrated optical bus for communication within the Fibre Channel topology and protocol between disk drives.
• the disk array controller subsystem is adapted to configure one or more of the disk storage devices for a configuration selected from the group consisting of RAID 0, RAID 1 , RAID 3, RAID 5, RAID 10 and an XOR RAID configuration.
• an operator may activate a so-called "hot button” which will disable the write function to the array, 8
• the present invention provides a novel, plug and play, high speed scalable and modular fault tolerant information server architecture which offers many benefits over prior art systems.
• Other features and advantages of the present invention will become apparent from the following detailed description of the invention, taken in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of the invention.
• FIG. 1 is a diagrammatic representation of the Information Server System of the present invention
• FIG. 2 is a diagrammatic representation of the Disk Array Controller subsystem of the Information Server System of FIG. 1;
• FIG. 3 is a is a diagrammatic representation of the Fault Tolerant, Fibre Channel Arbitrated Dual Loop, Hot-Swappable Disk Array subsystem of the Information Server System of FIG. 1.
• the information server system of the present invention incorporates two primary subsystems, including an information server 200 and a disk storage device array 300 connected through its integral Fibre Channel architecture compatible, high speed physical and virtual backplane bus and Intelligent Input/Output, "I2O" bus to the integral and or independent and external bus 150.
• bus 150 is a Gigabit compact PCI/Fibre Channel interface and I 2 O
• the information server further incorporates secondary subsystems including, but not limited to, a communications interface subsystem 210, a disk array controller subsystem 230, and single board high speed computer 280 running a computer industry standard operating system software program such as, for example, Windows NT available from Microsoft Corporation.
• secondary subsystems including, but not limited to, a communications interface subsystem 210, a disk array controller subsystem 230, and single board high speed computer 280 running a computer industry standard operating system software program such as, for example, Windows NT available from Microsoft Corporation.
• the computer further communicates with a display 282, such as a touch screen display, and a storage device 284 such as a hard disk.
• the operating system software incorporates enhancements adding additional functionality directed to control of the communications interface 210, disk array controller 230 and single board computer 280.
• the single board computer (“SBC") 280 can include any of a wide number of suitable devices including, but not limited to, the Compact PCI CPU Board with Pentium Processor, Model No. ZT 5510, available from Ziatech Corporation.
• Modifications to enhance performance of the ZT 5510 can include an onboard 40 MB flash memory card for permanent storage of the non-reconfigurable portions of the Windows NT operating system software and an onboard, removable, PCMCIA 40 Mb flash memory card, "D2 FlashDisk” available from Sandisk Corporation for read/writeable storage of the reconfigurable portions of the Windows NT software.
• the respective manufacturer, Fibre Channel Consortium and I 2 O Special Interest Group reference design data sheets and materials describing the detailed operating capabilities and specifications of each of these components are hereby incorporated by reference in their entirety.
• the communications interface subsystem 210 communicates with 10
• DSU digital subscriber unit
• T-l communications compatible DSUs such as the Model
• the communications boards incorporate, among other components, multi-channel communications processors which can include, for example, the 4-channel "Quick-Chip" communications processor from Motorola Corp.
• the communications circuit board also includes onboard buffer memory and a high speed, Fibre Channel compatible, optical bus for intra-server-component high speed data communications as well as Fibre Channel compatible, compact PCI bridge circuitry such as the bridge chip set available from Tundra. Additionally, for improved communications diagnostic, status and health monitoring capabilities, the communications board incorporates a bit error rate tester chip set, such as the device available as Model No. DS2172 from Dallas Semiconductor, configured for communication with the SBC 280 and operating system software, via the I2O bus.
• the communications interface subsystems 210 have been described with reference to well known T-l communications architecture, the subsystems are adaptable for compatibility with nearly all other network and telecommunications architectures, protocols and topologies including, but not limited to, T-3, DS-3, OC-3C, OC-12C, OC-192C, FDDI, SONET, SCSI, TCP/TP, HiPPI and ATM.
• T-3, DS-3, OC-3C, OC-12C, OC-192C, FDDI, SONET, SCSI, TCP/TP, HiPPI and ATM The respective manufacturer, consortium, industry association and organization reference design data sheets and materials describing the detailed operating capabilities and specifications of each of these components are hereby incorporated by reference in their entirety.
• the disk array controller subsystem 230 further incorporates a high speed chip set, such as the ISP2100 Intelligent Fibre Channel Processor available from Qlogic Corp., which includes a reduced instruction set chip (“RISC”) processor 235, a compact PCI 11
• RISC reduced instruction set chip
• This controller 230 communicates data stored on the disk array or to be stored thereon through the communications interface subsystem 210 between the disk array 300 and the outside world.
• the controller 230 is fully Fibre Channel compliant and is capable of controlling up to 126 disk storage devices in the disk array 300.
• the controller 230 is adapted to configure the disk array 300 for fault tolerant, data redundancy protocols including, but not limited to, RAID 0, 1 , 3, 5, 10 (1 & 0) and the new XOR RAID configuration.
• the respective manufacturer, consortium, industry association and organization reference design data sheets and materials describing the detailed operating capabilities and specifications of each of these components are hereby incorporated by reference in their entirety.
• the fault tolerant, Fibre Channel capable, arbitrated dual loop, hot-swappable disk storage device array subsystem 300 further includes an enclosure having a front bay of slots for receipt of disk devices 340 and a rear bay for receipt of bypass / bridging interface cards 370.
• the midplane of the enclosure incorporates a backbone Fibre Channel compact PCI bus in addition to physically independent, but logically integrated (within the Fibre Channel topology and protocol) I2O and optical buses.
• the disk array 300 also incorporates a plurality of disk storage devices and a corresponding number of bypass interface cards 370, all of which communicate with one another and the information server 200 though any one or combination of the above described buses.
• Each disk array 300 preferably incorporates a predetermined number of bypass interface cards 370 which populate the entire enclosure of the array 300 whether or not the entire enclosure is fully populated with a corresponding disk devices 340.
• the bypass cards 370 maintain the logical and electrical integrity of the backbone buses of the array subsystem 300 regardless of the number of empty disk device 340 slots.
• Each of the disk storage devices 340 may include any number of different storage media types including, but not limited to, optical, magnetic disk, 12
• each of the disk storage devices 340 includes a physical interlock system, not shown in the drawings, which is adapted to physically engage and disengage the disk storage device 340 to and from aphysical enclosure which contains the disk array 300.
• Such devices can specifically include, for example, any one or combination of 4.3 Gb, 9.1 Gb and 18 Gb magnetic disk drives available from Seagate Technologies.
• Each of the disk devices 340 fully implement the arbitrated dual channel Fibre Channel architecture such that every disk device 340 may perform simultaneous reads and writes of data in response to any requests from the outside world through the information server 200.
• All of such devices of the present invention include, among other components, data carriers known to the trade as electronic device registration devices.
• the data carrier device preferably incorporates a 64-bit ROM with a factory specified, unique 48-bit serial number. This capability enables unique identification of each and every physical disk device 340 manufactured for use with the present invention by any number of manufacturers, industry-wide for the foreseeable future.
• the data carrier device is integrated into the electronic circuitry of each of the disk devices 340 so that as the physical interlock of each disk device 340 is actuated to either engage or disengage the disk device 340 from the disk array 300, the interlock also triggers the data carrier device.
• This triggering of the data carrier generates and transmits a unique identifying serial number signal unique to each disk device 340 which is transmitted, for example, over the I 2 O bus to the disk controller 230.
• the controller 230 Upon receiving the signal, the controller 230 then immediately either initiates logical connection or disconnection of the disk device 340 to or from the array 300 depending on whether the disk device 340 has been engaged or disengaged, respectively.
• the controller accomplishes the electrical and logical connection and disconnection of the disk device 340 by control of the bypass interface card 13
• disk device 340 connection or disconnection can be accomplished either physically by a system administrator or remotely by error monitoring software functions of either the controller 230 or operating system running on the SBC 280.
• data carrier devices are readily available from a variety of manufacturers including the "iButton" available from Dallas Semiconductor as Part No. DS1990A.
• the bypass/bridging interface cards 370 which populate the rear bay accept signals from the controller 230 to communicate via the Fibre Channel interface 150 and protocol between the storage devices, the diagnostics and the diagnostics and control system, and interfacing with the storage devices via the 310 connectors to the storage devices.
• each storage device can simultaneously perform multiple reads and writes within the arbitrated dual channel Fibre Channel topology and protocol capability previously described above.
• This capability allows remote software control to automatically detect insertion of new disk devices 340 into the disk array 300, and is thus hot swappable.
• automatic testing, formatting, and logical integration can occur without any intervention of administrator personnel, beyond physical insertion of a new bypass card 370 and/or disk device 340.
• bypass interface cards 370 typically incorporate any one of a number of Fibre Channel compatible bypass chip sets including, but not limited to, those available from Motorola Corp. as Part No. 10SX1189 and Vitesse Semiconductor Corp. as Part Nos. VSC7121 and VSC7122 Bypass Circuits. 14
• the respective manufacturer, consortium, industry association and organization reference design data sheets and materials describing the detailed operating capabilities and specifications of each of these components are hereby incorporated by reference in their entirety.
• the method of the invention embodies the control of hot swappable interface cards and associated storage devices arranged in an array and controlled via a high speed interface with a diagnostic and control system containing a communications interface and a storage device controller.
• a high speed computer dedicated to system control and operation interfaces with both the communications interface and the storage device controller to sense and manage the condition of the various elements of the storage device array.
• the information server can be in continuous operation without the necessity of taking the system down to add storage capacity. From the above, it will be appreciated that the present invention represents a new and novel arrangement for an information server system serving a computer information system.
• the system and method of the invention provide a plug and play, truly hot swappable storage device system that does not require an external host computer.
• the system of the invention can be directly connected to Fibre Channel networks or Ethernet connections.
• the system provides both hot swappability and hot expandability for storage device addition and repair without powering down or additional diagnostic activities external to the system. Because of the scalability and modularity of the architecture, the system can be adapted to virtually any capacity. While particular forms of the invention have been illustrated and described, it will also be apparent that various modifications can be made without departing from the spirit and scope of the invention. Accordingly, it is not intended that the invention be limited, except as by the appended claims.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• General Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Human Computer Interaction (AREA)
• Computer Hardware Design (AREA)
• Quality & Reliability (AREA)
• Signal Processing For Digital Recording And Reproducing (AREA)

Applications Claiming Priority (3)

Publications (1)

Family

ID=22139245

Family Applications (1)

Country Status (4)

Families Citing this family (9)

Family Cites Families (7)

• 1999
  • 1999-03-10 EP EP99912372A patent/EP1062567A1/en not_active Withdrawn
  • 1999-03-10 WO PCT/US1999/005231 patent/WO1999046671A1/en active Application Filing
  • 1999-03-10 JP JP2000535989A patent/JP2002507019A/ja active Pending
  • 1999-03-10 AU AU30758/99A patent/AU3075899A/en not_active Abandoned
• 2007
  • 2007-07-04 JP JP2007176292A patent/JP2007305150A/ja active Pending

Non-Patent Citations (1)

Also Published As

Similar Documents

Legal Events