摘要:
A method for acquiring the node identifier of a node in a data processing input/output (I/O) system having a plurality of nodes. This procedure is part of the initialization of each node in the I/O system and may be used to establish the configuration of the I/O system such that if a connection breaks or a fault occurs between nodes, the configuration can be confirmed after the break or fault is corrected. This prevents data from being sent to the wrong device if lines were connected in a different configuration during the correction of a fault. The node identifier is a worldwide-unique identifier such that only one node is identified by a node identifier. The node identifier contains a validity code that specifies if the node identifier is valid. Also disclosed is a retry procedure for retrying the acquisition of a node identifier if the acquired node identifier is not valid, and a deferral procedure which defers the retry procedure if a link is not available.
摘要:
The utilization of various individual components of a channel is determined in order to learn which portion of a channel is busy and to what extent that portion is busy. The determination of a component's utilization is dependent on the type of component, as well as the operational characteristics of that component.
摘要:
A queuing method and apparatus for transfer or incoming and outgoing data in a network environment having a main storage is presented. A plurality of queue sets are provided in the main storage with at least one or more sets being dedicated for input and output. The queues can share access to a plurality of devices in the network across a plurality of communication stacks. Various network resources are mapped to the queues in order to facilitate resource allocation and dynamic configuration by providing initialization of a plurality of configuration parameters. In this way dynamic expanding and contracting of the number of queues in each set as dictated by traffic patterns and feedback indicators is provided.
摘要:
A method of providing direct data processing access in a network computing system environment. The system environment has a main storage which can be connected to one or more application servers and is in processing communication with an interface element. The interface element has at least one adapter and can be connected to one or more application user(s). One or more queues are established in the main storage that can handle data without causing interrupts in the running programs. Incoming data is received using the adapter and as data is received or modified, the status of the network computing system will be updated to reflect the new data or change. Data is then processed in the main storage after interrogating the multiple existing queues in the main storage and forwarding them in turn to their appropriate destination or application server after a determination has been made by interrogating these queues.
摘要:
In a computer I/O system including a plurality of link-level facilities and a dynamic switch having a plurality of ports, each link-level facility being attached to an individual one of the ports, a mechanism and method for assigning a unique link level address to each of the link-level facilities. As each of the link-level facilities comes on line, it sends an acquire link address (ALA) frame and waits for a response (ACK) frame. The ALA frame may be addressed to a general to-whom-it-may-concern address and have a source address of who-am-I. Only a dynamic switch normally assigns link addresses. When receiving an ALA frame, the dynamic switch returns an ACK frame having a unique link address assigned to the sender of the ALA frame. Provision is made for determining if there is a dynamic switch present, or, if the link-level facilities are connected together by a static connection through the dynamic switch, for the link-level facility of a channel to assign the unique link addresses.
摘要:
A large data processing system includes a channel path management program that is periodically executed during operation of the system to gather control unit and subchannel utilization statistics and to monitor such statistics. If the degree of utilization of a channel path or an I/O device exceeds a predetermined threshold value, one or more change(s) is(are) dynamically made in the channel path configuration.
摘要:
For a CPU I/O request, the disclosed methods find a physical channel path within a logical channel (LCH) likely to be connectable to a requested device by using channel path count (CAT count) fields. The CAT counts respectively indicate the current number of uncompleted requests accepted by the respective physical channels in the data processing system. An available physical channel in the LCH with the smallest CAT count is found as the candidate channel path for a connection attempt to the requested device. If the lowest CAT count is equal for plural available channel paths, any of these plural channel paths may be selected as the candidate channel path. The CAT count for a channel path is incremented for each successful connection of any device to that channel path. The CAT count for a channel path is decremented upon receiving a signal indicating that a successfully connected I/O device has completed the operation for a request. CAT counts indicate the current load on each physical channel across all LCHs in which the physical channels may be contained. The CAT counts indicate the relative likelihood of the physical channels within a LCH being non-busy relative to each other in order to find the channel path most likely to be non-busy and thereby avoid a RPS miss when a requested DASD record is reached during disk rotation. Choosing the channel paths with the lowest available CAT counts balances the load among the physical channels across all LCHs containing the same physical channel.
摘要:
An input/output subsystem is configured as a plurality of input/output subsystem images, each of which appears to a program as an independent input/output subsystem. An input/output subsystem image is identified by an input/output subsystem image identifier, which is used by various programs to designate the particular input/output subsystem image for which an I/O operation is to be performed. An input/output subsystem image includes, for instance, one or more input/output paths. An input/output path of an input/output subsystem image is identified by an input/output path identifier, as well as a physical input/output path identifier.
摘要:
Asynchronous requests, such as input/output (I/O) requests, within a coprocessor of a computing environment are managed. The management of the asynchronous requests is based on priorities associated with the asynchronous requests. This management includes, for instance, selecting an asynchronous request to be processed using a priority scheme, and/or affording resources to the asynchronous requests using a priority scheme.
摘要:
Execution of input/output operations is controlled by one or more suspend and/or resume mechanisms. Suspension of an input/output operation is accomplished by one of a number of mechanisms including, for instance, a START SUBCHANNEL instruction with execution limits, a SUSPEND SUBCHANNEL instruction with or without a suspension time limit, or a suspend subchannel channel command word with or without a suspension time limit. Subsequent to suspending execution of a channel program, execution can be resumed automatically or by issuing a RESUME SUBCHANNEL instruction with limits or a resume subchannel channel command word with limits.