Abstract: Provided are a computer program product, system, and method for supporting non-delivery notification between a switch and device in a network. A login with a switch is initiated including a test service parameter requesting a non-delivery notification service to cause the switch to return a non-delivery notification in response to a test path request indicating a destination node that is unavailable. Indication is made that the test service is available for the login in response to receiving a reply from the switch that the switch accepts the login with the non-delivery notification service. The test path request is sent to the switch to determine whether the destination node is available. The non-delivery notification is received from the switch in response to the switch determining that the destination node to which the test path request is directed is unavailable.

Abstract: A method for verifying an input/output (I/O) hardware configuration is provided. A verification command is processed. The verification command includes a software device address range associated with a logical control unit (LCU) of the I/O hardware. The LCU utilizes a first logical path. The software device address range utilizing the first logical path is compared with an existing software device address range utilizing at least one additional logical path. The verification command is accepted if the software device address range and the existing software device address range match.

Abstract: Provided are a computer program product, system, and method for supporting non-delivery notification between a switch and device in a network. A login with a switch is initiated including a test service parameter requesting a non-delivery notification service to cause the switch to return a non-delivery notification in response to a test path request indicating a destination node that is unavailable. Indication is made that the test service is available for the login in response to receiving a reply from the switch that the switch accepts the login with the non-delivery notification service. The test path request is sent to the switch to determine whether the destination node is available. The non-delivery notification is received from the switch in response to the switch determining that the destination node to which the test path request is directed is unavailable.

Abstract: Provided are a computer program product, system, and method for supporting non-delivery notification between a switch and device in a network. A login with a switch is initiated including a test service parameter requesting a non-delivery notification service to cause the switch to return a non-delivery notification in response to a test path request indicating a destination node that is unavailable. Indication is made that the test service is available for the login in response to receiving a reply from the switch that the switch accepts the login with the non-delivery notification service. The test path request is sent to the switch to determine whether the destination node is available in response to determining that the non-delivery notification service is available for the switch login. The non-delivery notification is received from the switch in response to the switch determining that the destination node to which the test path request is directed is unavailable.

Abstract: A method to minimize performance degradation during communication path failure in a data processing system, comprising a host computer, a storage controller, and a plurality of physical communication paths in communication with the host computer and the storage controller, where the method establishes a threshold communication path error rate, and determines an (i)th actual communication path error rate for an (i)th physical communication path, wherein that (i)th communication path is one of the plurality of physical communication paths. If the (i)th actual communication path error rate is greater than the threshold communication path error rate, the method discontinues use of the (i)th physical communication path.

Abstract: An apparatus for configuring a port in a multi-port communication adapter includes a quiesce module quiescing communications at one or more first I/O ports of a multi-port communication adapter while allowing communications at one or more second I/O ports of the multi-port communication adapter. A path module removes one or more logical paths between the one or more first I/O ports and one or more remote adapters in anticipation of taking the one or more first I/O ports offline. The offline module takes offline the one or more first I/O ports. The update module updates a port resource of the one or more first I/O ports while allowing a concurrent communication on the one or more second I/O ports of the multi-port communication adapter.

Abstract: A system and method for recovering from logical path failures is set forth. More specifically, when a host detects a logical path failure, the host enters a path discovery mode of operation. If the host continues to detect a logical path failure while operating in the logical path discovery mode of operation, the host removes the logical path from a logical path mask, and the host does not use the removed logical path again. Additionally, the system and method facilitates recovery of the failed logical paths by using a plurality of logical path masks. A first mask is referred to as an intermediate failure logical path mask and a second mask is referred to as a permanent failure logical path mask.

Abstract: Provided are a method, system, and article of manufacture, wherein a control unit receives a request to establish a relationship over a fiber channel connection, wherein a first indicator associated with the request indicates that the relationship supports persistent information unit pacing across a plurality of command chains. The control unit sends a response indicating an acceptance of the relationship, wherein a second indicator associated with the response indicates that the control unit supports persistent information unit pacing across the plurality of command chains. An information unit pacing parameter value is retained across the plurality of command chains, in response to determining that the second indicator indicates that the control unit supports persistent information unit pacing across the plurality of command chains.

Abstract: Provided are a method, system, and article of manufacture, in which a logical path is established between a control unit and a channel over a fiber channel connection. Code for persistent information unit pacing is loaded into the control unit and the channel. An indicator is set in node descriptors of the control unit and the channel to indicate concurrent enablement of persistent pacing while retaining the established logical path between the control unit and the channel.

Abstract: Provided are a method, system, and article of manufacture for credit depletion notification for transmitting frames between a port pair. Credits indicate a number of outstanding frames a first device may transmit to a second device. The credits are decremented in response to transmitting a frame to the second device. The credits are incremented in response to receiving a ready code from the second device indicating that the second device processed the transmitted frame. A determination is made as to whether additional credits are needed for communicating frames from the first device to the second device. A credit depletion notification is sent to the second device in response to determining that the additional credits are needed for communication with the second device.

Abstract: Provided are a system and article of manufacture for establishing and requesting status on a computational resource. An operation is performed to establish a computational resource, wherein the computational resource is not available until the establish operation is completed. A determination is made as to whether a status request to determine status of the computational resource is pending before the establish operation has completed. Indication is made to resubmit the status request if there is a status request for the computational resource pending before the establish operation has completed.

Abstract: A method for combining partial records into a single direct memory access (DMA) operation for a count key data (CKD) protocol in a computer environment is provided. In an initiator processor of the computer environment, a number of the partial records to be prefetched is determined by gathering a plurality of descriptor information for a command according to a predetermined algorithm having a plurality of assumptions for the command. The number of partial records is prefetched. At least one of record headers and record keys of the number of partial records are concatenated into the single DMA operation. The DMA operation is forwarded to a receiver process to be completed.

Abstract: A method to preserve a logical communication path in a data processing system, that includes a host computer, a storage controller that comprises a first logical control unit (“LCU”), and a logical communication path that is in communication with the host computer and the first LCU, comprising deleting the first LCU and setting a first status for same. The method then configures a second LCU, and establishes a second status for same, wherein the second LCU includes all or a portion of the first LCU, but is not the same as the first LCU. The deleting, setting, configuring, and establishing are performed while maintaining the logical communication path, which is in communication with the second LCU.

Abstract: Method, system and computer program product embodiments for, in an input/output (I/O) link handling complex instruction chains, a messaging scheme incorporating a method of error recovery between an initiator processor and a receiver processor, are provided. An operation initiation message is been sent from the initiator processor to the receiver processor for the receiver processor to begin work on an operation. If determined to be necessary, a terminate operation message is sent from the initiator processor to the receiver processor. The initiator processor withholds sending additional messages for the operation until a terminate operation response message is received. Once the terminate operation message is received, outstanding messages in process are flushed from the receiver processor. The receiver processor withholds sending additional messages to the initiator processor as the outstanding messages are completed.

Abstract: A method for facilitating input/output (I/O) communication for a processing operation is provided. An interrogate command is obtained by an I/O communications adapter. The interrogate command queries for status information of the processing operation to be provided in an interrogate response. A fixed number of resources and a time allocated to the interrogate command is throttled by pre-allocating the fixed number of resources needed for the interrogate command, and maintaining a timestamp for a interrogate message. The interrogate message is forwarded from the I/O communications adapter to a control unit. If the interrogate response is not received by the I/O communications adapter within a limited timeout period as measured by the timestamp, or if the interrogate message is received while the fixed number of pre-allocated resources are in use, the I/O communications adapter returns a busy response indicating the control unit is busy to prevent overrunning the control unit.

Abstract: Provided are a computer program product, system, and method for supporting non-delivery notification between a switch and device in a network. A login with a switch is initiated including a test service parameter requesting a non-delivery notification service to cause the switch to return a non-delivery notification in response to a test path request indicating a destination node that is unavailable. Indication is made that the test service is available for the login in response to receiving a reply from the switch that the switch accepts the login with the non-delivery notification service. The test path request is sent to the switch to determine whether the destination node is available in response to determining that the non-delivery notification service is available for the switch login. The non-delivery notification is received from the switch in response to the switch determining that the destination node to which the test path request is directed is unavailable.

Abstract: An apparatus, system, and method are disclosed for updating a code image for a communication adapter. The apparatus includes a save module, an update module, and a restore module. The save module saves configuration data associated with a connection at a communication adapter. The update module updates a code image on the communication adapter. The restore module restores the configuration data in response to the code image update. Advantageously, the apparatus eliminates the need for conventional host recovery, including relogin and reestablishment of paths and connections, after the code image update.

Abstract: Provided are a method, system, and program for managing communication between a first device and a second device and performing a recovery action at the second device in response to a credit depletion notification from the first device. The second device assigns credits indicating a number of outstanding frames the first device may transmit to the second device. The second device receives a first type or second type of credit depletion notification from the first device indicating that the first device needs additional credits to transmit further frames to the second device. The second device performs one of a plurality of recovery actions depending on whether the first type or second type of credit depletion notification was received.

Abstract: Provided is a system, deployment and program for resource allocation unit queuing in which an allocation unit associated with a task is classified. An allocation unit freed as the task ends is queued for use by another task in a queue at a selected location within the queue in accordance with the classification of said allocation unit. In one embodiment, an allocation unit is queued at a first end of the queue if classified in a first class and is queued at a second end of the queue if classified in said second class. Other embodiments are described and claimed.

Abstract: Provided are techniques for determining a link speed. When a link between two computing devices is operational, a link speed for use in communicating across the link is stored and a remembered indicator is set to TRUE. After any event occurs that causes the link to become inoperational, in response to determining that the remembered indicator is TRUE, the stored link speed is used when attempting to make the link become operational.