International Business Machines Corporation

Compagnie Ibm France

Chung Man Fung

Beth Ann Peterson

Minh-Ngoc Le Huynh

Patricia Ching Lu

Lokesh M Gupta

James Chien-Chiung Chen

Matthew J Kalos

James C Chen

Dung Ngoc Dang

Kevin J Ash

Kyler A Anderson

Gail Andrea Spear

Richard Anthony Ripberger

Michael T Benhase

Susan Kay Candelaria

Christopher Michael Sansone

Dale Francis Riedy, Jr

Carol Santich Mellgren

Matthew John Ward

Warren Keith Stanley

Joseph S Hyde, Ii

Steven Edward Klein

Theodore Timothy Harris, Jr

John Richard Paveza

Matthew Richard Craig

William Henry Travis

Brian S Lee

Ronald E Bretschneider

Donald Prentiss Terry

Edwin K Scott

Patricia Chiung Lu

A computer-implemented method, according to one approach, includes: initiating an I/O request using a primary cache, where the I/O request includes supplemental information pertaining to an anticipated workload of the I/O request. Performance characteristics experienced by the primary cache while satisfying the I/O request are also evaluated. The supplemental information and the performance characteristics are further used to determine whether to satisfy a remainder of the I/O request using the secondary cache. In response to determining to satisfy a remainder of the I/O request using the secondary cache, the I/O request is demoted from the primary cache to the secondary cache, and a remainder of the I/O request is satisfied using the secondary cache. However, in response to determining to not satisfy a remainder of the I/O request using the secondary cache, a remainder of the I/O request is satisfied using the primary cache.

Using multi-tiered cache to satisfy input/output requests

Provided are a computer program product, system, and method for prefetching cache resources for a write request from a host to tracks in storage cached in a cache. Cache resources held for a plurality of tracks in a write set are released before expected writes are received for the tracks in the write set. Cache resources for tracks in the write set are obtained, following the release of the cache resources, to use for expected write requests to the tracks in the write set.

Obtaining cache resources for expected writes to tracks in a write set after the cache resources were released for the tracks in the write set

Provided are a computer program product, system, and method for providing track access reasons for track accesses resulting in the release of prefetched cache resources for the track. A first request for a track is received from a process for which prefetched cache resources to a cache are held for a second request for the track that is expected. A track access reason is provided for the first request specifying a reason for the first request. The prefetched cache resources are released before the second request to the track is received. Indication is made in an unexpected released track list of the track and the track access reason for the first request.

Providing track access reasons for track accesses resulting in the release of prefetched cache resources for the track

A computer-implemented method, according to one approach, includes: receiving an I/O request which includes supplemental information pertaining to an anticipated workload of the I/O request. The supplemental information is used to determine whether to satisfy the I/O request using a primary cache. In response to determining to satisfy the I/O request using the primary cache, the I/O request is initiated using the primary cache, and performance characteristics experienced by the primary cache while satisfying the I/O request are evaluated. The supplemental information and the performance characteristics are further used to determine whether to satisfy a remainder of the I/O request using the secondary cache. In response to determining to satisfy a remainder of the I/O request using the secondary cache, the I/O request is demoted from the primary cache to the secondary cache, and a remainder of the I/O request is satisfied using the secondary cache.

Provided are a method, system, and computer program product in which a storage controller receives a first write command with a first token over a first interface from a host computational device. In response to a failure of the first write command in the storage controller, the storage controller retains selected resources for reuse for a retry of the first write command, wherein the retry of the first write command is expected from the host computational device over a second interface that is a slower communication link than the first interface. In response to receiving, by the storage controller, a second write command with a second token over the second interface, wherein the second token is identical to the first token, the storage controller determines that the second write command is a retry of the first write command and reuses the retained selected resources for executing the second write command.

Reuse of resources in a storage controller for executing write commands over a plurality of interfaces

A host computational device transmits a first write command with a first token over a first interface to a storage controller. In response to receiving an indication by the host computational device that the first write command has failed in the storage controller, the host computational device transmits a second write command with a second token over a second interface to the storage controller, wherein the second write command is a retry of the first write command that failed, wherein the second token is identical to the first token, and wherein the second interface is a slower communication link than the first interface.

Token management for write commands transmitted by a host over a plurality of interfaces to a storage controller

Write transfer resource management in a data storage system in accordance with the present description includes overdue write transfer management logic which detects whether or not an established write set has become stale. In one embodiment, a determination is made as a function of whether a write transfer from a host and associated with an established write transfer set is overdue as measured by a time-out period of time. Upon determination that an established write transfer set has become stale, the stale write set is removed and the resources associated with the removed write set are freed for use by other write sets, significantly improving system performance. Other features and aspects may be realized, depending upon the particular application.

Write transfer resource management in a data storage system

A storage controller receives a plurality of synchronous writes from a host via a bus interface, wherein each of the synchronous writes is received for writing to a first node and a second node of the storage controller. For each record of a track written to the first node and the second node, an error detecting code is computed on writing the record. In response to determining that computed error detecting codes do not match for any corresponding records of the track in the first node and the second node, an indication of an error is transmitted from the storage controller to the host.

Checking of data difference for writes performed via a bus interface to a dual-server storage controller

Exemplary methods, computer systems, and computer program products for fabricating key fields by a processor device in a computer environment are provided. In one embodiment, the computer environment is configured for, as an alternative to reading Count-Key-Data (CKD) data in order to change the key field, providing a hint to fabricate a new key field, thereby overwriting a previous key field and updating the CKD data.

Fabricating key fields

System and computer program product are provided to configure a path between nodes through a fabric in a fibre channel storage area network (SAN). A node name is provided for a target node on the SAN and a port name is provided for each port in the target node. A relationship is established in a data structure between each port name and a slot in which each port is physically located in the target node. Prior to configuring a path between a source node and a port in the target node, the ports which are physically connected and logged in to the fabric are identified by port address. The port names corresponding to the port addresses are then identified. The port names are used to generate interface_ids of the ports corresponding to the physical slots in which the ports are located. A data structure is created to maintain the relationship between interface_ids and port names. To establish a path connection between a port in the source node and a selected port in the target node, the node name of the target node and the interface_id of the selected port are input to the data structure and the port name of the selected port is output. The port name is then used to obtain the address of the selected port and an I/O session path opened between the source and target nodes.

Configuration of fibre channel SAN path

A method for performing a data exchange between an initiator and a receiver in a fiber channel protocol (FCP) is provided. A control flag is set in a write command to indicate the presence of an identifier. The identifier is copied into a command descriptor block (CDB) of the write command and appended to a data frame. The write command and data frame, including the identifier, is sent from the initiator to the receiver.

FCP command-data matching for write operations

Provided are a method, system, and program monitoring paths between a first controller and second controller. A determination is made as to whether one path has been unavailable for a predetermined time period in response to detecting that the path is unavailable. Indication is made that the path is in a first failed state if the path has been unavailable for more than the predetermined time period and indication is made that the path is in a second failed state if the path has not been unavailable for the predetermined time period.

System and program for transmitting input/output requests from a first controller to a second controller

Disclosed is a technique for assigning priorities. A request to manipulate data is received. A type of the request is determined. A priority is assigned to the request based on the type of the request.

Assigning priorities

Methods, system and computer program product are provided to improve the efficiency of data transfers in a PPRC environment. Any or all of three features may be implemented, each of which reduces the number of round trips required for the exchange of handshaking, data and control information. A first feature includes disabling the 'transfer ready' acknowledgment which normally occurs between a primary storage controller and a secondary storage controller. A second feature includes pre-allocating payload and data buffers in the secondary storage controller. A third feature includes packaging write control information with a write command in an extended command descriptor block (CDB). Such a step eliminated the need for a separate transmission of the write control information. The CDB is transmitted along with a data block from the primary storage controller to the secondary storage controller and placed in the respective, pre-allocated buffers. Data may also be pipelined to the secondary. By decreasing the response time for data transfers, the distance separating the primary and secondary storage controllers may be increased.

Decreased response time for peer-to-peer remote copy write operation

Methods, system and computer program product are provided to configure a path between nodes through a fabric in a fibre channel storage area network (SAN). A node name is provided for a target node on the SAN and a port name is provided for each port in the target node. A relationship is established in a data structure between each port name and a slot in which each port is physically located in the target node. Prior to configuring a path between a source node and a port in the target node, the ports which are physically connected and logged in to the fabric are identified by port address. The port names corresponding to the port addresses are then identified. The port names are used to generate interface_ids of the ports corresponding to the physical slots in which the ports are located. A data structure is created to maintain the relationship between interface_ids and port names. To establish a path connection between a port in the source node and a selected port in the target node, the node name of the target node and the interface_id of the selected port are input to the data structure and the port name of the selected port is output. The port name is then used to obtain the address of the selected port and an I/O session path opened between the source and target nodes.

Growing community of inventors

San Francisco, CA, United States of America

Chung Man Fung