International Business Machines Corporation

Frederic Lawrence Huss

Daniel Frank Moertl

Timothy J Schimke

Brian Eric Bakke

Brent Allen Carlson

Richard E Zelenski

Nancy M Schmucki

Paul Gary Reuland

Bruce Marshall Walk

Robert Edward Galbraith

Carl E Forhan

Todd Jason Youngman

Scott Alan Bauman

Jessica M Gisi

Russell Paul VanDuine

Laurel Scaife

Troy Evan Faber

Andrew J Kulich

Douglas David Prigge

An Input/Output (I/O) adapter for use with a second I/O adapter in a clustered configuration. The I/O adapter includes a dedicated communication link, such as a high-speed serial bus, that provides for communication between the I/O adapter and the second I/O adapter. The I/O adapter also includes a message passing circuit, coupled to the dedicated communication link, that allows for transferring of data between the I/O adapter and the second I/O adapter. The I/O adapter further includes a doorbell circuit, coupled to the message passing circuit, that generates interrupts to provide a low level communication between the I/O adapter and the second I/O adapter. A mirroring directory, coupled to the message passing circuit, is also included in the I/O adapter to provide for the mirroring of cache directory writes.

Dual storage adapters utilizing clustered adapters supporting fast write caches

A redundancy manager preferably in an I/O adapter has been disclosed to manage commands to peripheral devices in a computer system. These peripheral devices have multiple ports and may have a different bus associated with each port. The buses, referred to as independent pathways, moreover, need not have the same protocol. The redundancy manager determines the number of independent pathways connected to the peripheral device, presents only one logical device to the operating system and any device driver and any other command or device processing logic in the command path before the redundancy manager. For each incoming command, the redundancy manager determines which pathways are properly functioning and selects the best pathway for the command based on load balancing considerations and any ordering semantics that must be preserved in the incoming command and any outstanding commands and associated data that have not yet executed. The redundancy manager further reroutes the command to an alternate path and resets the device for the alternate path if the selected path failed. Thus, a dynamic mechanism and method to manage multiple pathways to I/O devices such as storage disks do not require the intervention of either the operating system of the computer or any device driver associated with the device or the interconnecting bus.

Transparent and dynamic management of redundant physical paths to peripheral devices

A storage area network (SAN) fibre channel arbitrated loop (FCAL) multiple system, multiple resource, storage enclosure and a method are provided for performing enclosure maintenance concurrent with device operations. The storage enclosure includes a plurality of storage resources or storage devices, a plurality of IO adapters (IOAs) coupled to the storage area network and a pair of enclosure services node cards. Each enclosure services node card includes loop connections for the plurality of storage resources. Each enclosure services node card includes a respective global bus connection and a loop connection to each of the plurality of IOAs. Each enclosure services node card is used concurrently by the multiple systems to manage the plurality of storage resources. In the method for performing enclosure maintenance concurrent with device operations, identical maintenance procedures are implemented for the enclosure services node cards and the storage devices. The enclosure services node cards are removable cards and contain active components including port bypass circuits (PBCs). Fibre channel (FC) connections for the plurality of storage resources provide redundant paths to each storage resource and allows access to data on the storage resources to continue when one of the pair of enclosure services node cards fails or is being maintained. Out of band communications to the enclosure services node cards are provided with the global buses, such as I2C buses, rather than FC loop. Multiple IOAs can concurrently use the same enclosure services node card without contention or collision.

Storage area network (SAN) fibre channel arbitrated loop (FCAL) multi-system multi-resource storage enclosure and method for performing enclosure maintenance concurrent with device operations

A method for maintaining data coherency in a dual Input/Output(I/O) adapter having primary and secondary adapters, wherein each of the primary and secondary adapters includes resident write cache data and directory storage devices. The method includes utilizing a split point to separate each of the cache data and directory storage devices into first and second regions, wherein the first regions contain the primary adapter cache data and directory information and the second regions contain the secondary adapter cache data and directory information. Information stored in the primary adapter cache data and directory storage devices is mirrored into the secondary adapter cache data and directory storage devices or, alternatively, information stored in the secondary adapter cache data and directory storage devices is mirrored into the primary adapter cache data and directory storage devices utilizing a dedicated communication link, such as a high-speed serial bus, between the primary and secondary adapters.

Method and system for maintaining data coherency in a dual input/output adapter utilizing clustered adapters

A method and apparatus are provided for adaptive localization of frequently accessed, randomly addressed data in a direct access storage device (DASD) to achieve improved system access performance. At selected sampling intervals, a DASD storage controller analyzes data access patterns based on frequency of access, identifies a remapping algorithm to remap the logical groups to physical groups, and moves the physical groups according to the identified remapping algorithm. The data reordering on the DASD provides frequently accessed data in close proximity so that seek time is minimized. The adaptive data localization method periodically performed by the storage controller is transparent to the host file system. The reordering of the data on the DASD is performed during periods of low system data transfer activity.

Method and apparatus for adaptive localization of frequently accessed,

Problem ownership and status propagation in a clustered system environment must be coordinated in a way that avoids redundant and/or conflicting recovery efforts. IOP managers which overcome these problems are disclosed. A primary IOP manager is one which has problem ownership for a particular IOP. There is only one primary IOP manager for each IOP. A secondary IOP manager is one which resides upon a computer system that shares the resources of a particular IOP or IOPs, but nevertheless does not have problem ownership for that particular IOP(s). There are one or more secondary IOP managers for a given IOP. When a primary IOP manager is informed of a problem in a device attached to a shared IOP, it updates resident system management information to indicate the new status of the subject device, informs its local system management of the problem so that corrective actions may be taken, and sends the status information to the secondary IOP managers via the IOP itself. When a secondary IOP manager is informed of a problem with a device attached to a shared IOP, it updates system management information to indicate the new status of the subject device and sends the status information to the primary IOP manager and other secondary IOP managers via the IOP itself. The secondary IOP manager does not, however, inform its local system management that corrective actions are required.

Distributed device status in a clustered system environment

A peer to peer connection authorizer is described. The connection authorizer involves three different entities: a system authorizer mechanism, a client connection manager, and a server connection manager. The system authorizer resides on the main or primary CPU while the client and server connection managers reside on individual IOPs. To obtain information required by a user and/or an application program, the client connection manager issues a request to the system authorizer. When the system authorizer receives the request, it first verifies that the client device is who it claims to be. If the system authorizer determines that the client device should be allowed to access the requested information, it then sends a token to the server device and a copy of the same token to the client device. Upon receipt of the token copy from the system authorizer, the client connection manager packages the token copy into a message that it sends to the server device. When the server connection manager receives the message from the client device, it compares the token copy to the token it received from the system authorizer. If the tokens match, the server connection manager responds to the client device and the connection is established.

Server entity that provides secure access to its resources through token

Connection authorizer for controlling access to system resources

Growing community of inventors

Rochester, MN, United States of America

Frederic Lawrence Huss