International Business Machines Corporation

Agustin Mena, Iii

Renato John Recio

William Todd Boyd

Madeline Vega

John Lewis Hufferd

Andrew Dunshea

Jos Manuel Accapadi

Mark Elliott Hack

Herman Dietrich Dierks

Dirk Michel

Mathew Accapadi

Vinit Jain

Bret Ronald Olszewski

Venkat Venkatsubra

Rohith Kottamangalam Ashok

Mysore Sathyanaranyana Srinivas

Mysore Sathyanarayana Srinivas

Vandana Mallempati

Thuy B Nguyen

Diane Garza Flemming

Octavian Florin Herescu

Jean-Philippe Sugarbroad

Matthew Accapadi

Jean-Philipe Sugerbroad

Described herein is a system and method for associating process priority with I/O queuing. The system can receive a first I/O request from a first process; store the first I/O request in an I/O queue; receive a second I/O request from a second process; store the second I/O request in the I/O queue; and sort the I/O queue based, at least in part, on a first priority of the first process and a second priority of the second process.

Associating process priority with I/O queuing

Input/output (I/O) requests generated by processes are typically stored in I/O queues. Because the queued I/O requests may not be associated with the processes that generated them, changing a process' priority may not affect the priority of the I/O requests generated by the process. Therefore, after the process' priority has been increased, it may be forced to wait for an I/O handler to service its I/O request, which may be stuck behind an I/O request generated by a lower priority process. Functionality can be implemented to associate the processes' priorities with the I/O requests generated by the processes. Also, reordering the queued I/O requests to reflect changes in the processes' priorities can ensure that the I/O requests from high priority processes are serviced before the I/O requests from low priority processes. This can ensure efficient processing and lower wait times for high priority processes.

Automated techniques ensure that system central processing unit ('CPU') power is not a bottleneck when migrating logical partitions from one system to another system or systems (e.g., in the event of a system evacuation). CPU resources needed to fully drive available bandwidth during the migration are computed. CPU resources of the system are then adjusted for the migration, which may comprise scaling down the CPU resources that are guaranteed for the executing partitions and/or adjusting relative partition variable weights to limit the amount of excess capacity that can be allocated to a partition.

System and program product to allocate and reallocate CPU resources needed to utilize full available network adapter bandwidth capacity for logical partition migration

Allocate and reallocate CPU resources needed to utilize full available network adapter bandwidth capacity for logical partition migration

A computer program product for scheduling threads in a multiprocessor computer comprises computer program instructions configured to select a thread in a ready queue to be dispatched to a processor and determine whether an interrupt mask flag is set in a thread control block associated with the thread. If the interrupt mask flag is set in the thread control block associated with the thread, the computer program instructions are configured to select a processor, set a current processor priority register of the selected processor to least favored, and dispatch the thread from the ready queue to the selected processor.

Computer program product for scheduling ready threads in a multiprocessor computer based on an interrupt mask flag value associated with a thread and a current processor priority register value

Methods, systems, and computer program products are provided for scheduling threads in a multiprocessor computer. Embodiments include selecting a thread in a ready queue to be dispatched to a processor and determining whether an interrupt mask flag is set in a thread control block associated with the thread. If the interrupt mask flag is set in the thread control block associated with the thread, embodiments typically include selecting a processor, setting a current processor priority register of the selected processor to least favored, and dispatching the thread from the ready queue to the selected processor. In some embodiments, setting the current processor priority register of the selected processor to least favored is carried out by storing a value associated with the highest interrupt priority in the current processor priority register.

Scheduling threads in a multiprocessor computer

An apparatus and method for an improved bulk read socket call are provided. With the apparatus and method, a new field, so_rcvlen, is added to the socket structure that identifies the bulk read size requested by the user. The kernel of the prior art recv( ) function is also modified so that it sets the so_rcvlen to the size requested by the user prior to the recv( ) function going to sleep and waiting for the full data size requested by the user. A new flag, SP_MSGWAITALL, is also provided in the socket structure. In the TCP input processing, when data is received for a particular socket, the current setting of the SP_MSGWAITALL is checked. If the SP_MSGWAITALL flag is set, it is determined whether the amount of data stored in the socket receive buffer is less than the value of so_rcvlen. If not, the TCP input processing does not wake up the recv( ) thread. However, for every alternate segment, the TCP input processing sends back an acknowledgment (ACK). In the TCP output processing, when the SP_MSGWAITALL flag is set and the amount of data in the socket receive buffer is less than so_rcvlen, the full window is advertised. Once the TCP input processing determines that there is at least an amount of data in the socket receive buffer equal to the value of so_rcvlen, the TCP input processing will wake up the recv( ) thread and the SP_MSGWAITALL flag is reset.

Method and apparatus for an improved bulk read socket call

The present invention provides mechanisms that enable application instances to pass block mode storage requests directly to a physical I/O adapter without run-time involvement from the local operating system or hypervisor. In one aspect of the present invention, a mechanism is provided for handling user space creation and deletion operations for creating and deleting allocations of linear block addresses of a physical storage device to application instances. For creation, it is determined if there are sufficient available resources for creation of the allocation. For deletion, it is determined if there are any I/O transactions active on the allocation before performing the deletion. Allocation may be performed only if there are sufficient available resources and deletion may be performed only if there are no active I/O transactions on the allocation being deleted.

Mechanisms for creation/deletion of linear block address table entries for direct I/O

A computer implemented method, apparatus, and computer usable code for receiving data from a sender across a network connection for the data transfer. An expected size for a congestion window for the sender is identified. An amount of the data received from the sender is tracked. An acknowledgment is sent in response to the amount of data received from the sender meet in the expected size of the congestion window for the sender.

Acknowledging packet receipt based on expected size of sender's congestion window

A mechanism is provided that enables user space middleware or applications to pass file name based storage requests directly to a physical I/O Adapter without run-time involvement from the local Operating System (OS). A mechanism is provided for using a file protection table (FPT) data structure, which may include a file name protection table (FNPT) and file extension protection table (FEPT), to control user space and out of user space Input/Output (I/O) operations. In addition, a mechanism is provided for managing the FPT based on user space operations to create, query, modify and delete entries in the FPT.

Processing user space operations directly between an application instance and an I/O adapter

Enabling user space middleware or applications to pass file name based storage requests directly to a physical I/O Adapter without run-time involvement from the local Operating System (OS)is provided. A mechanism is provided for using a file protection table (FPT) data structure, which may include a file name protection table (FNPT) and file extension protection table (FEPT), to control user space and out of user space Input/Output (I/O) operations. The FNPT has an entry for each file managed by the OS' file system and points to a segment of the FEPT. Each entry in the FEPT may include a protection domain, along with other protection table context information, against which I/O requests may be checked to determine if an application instance that submitted the I/O requests may access the file identified in the I/O requests.

Out of user space I/O directly between a host system and a physical adapter using file based linear block address translation

The present invention provides a method that enables application instances to pass block mode storage requests directly to a physical I/O adapter without run-time involvement from either the local operating system or hypervisor. In one aspect of the present invention, a mechanism is provided for determining whether a user space operation is a resource management operation of a work processing operation. If the user space operation is a resource management operation, appropriate functions are performed to either query, create, modify or destroy resource allocations in the I/O adapter. If the user space operation is a work processing operation, appropriate functions are performed to create work queue entries and inform the I/O adapter of the work queue entries and to retrieve completion queue entries for work queue entries whose processing has been completed by the I/O adapter.

Method for user space operations for direct I/O between an application instance and an I/O adapter

A computer implemented method for receiving data from a sender across a network connection for the data transfer. An expected size for a congestion window for the sender is identified. An amount of the data received from the sender is tracked. An acknowledgment is sent in response to the amount of data received from the sender meet in the expected size of the congestion window for the sender.

TCP/IP method FPR determining the expected size of conjestion windows

The present invention provides a method that enables application instances to pass block mode storage requests directly to a physical I/O adapter without run-time involvement from the local operating system or hypervisor. Specifically, a mechanism for providing and using a linear block address (LBA) translation protection table (TPT) to control out of user space I/O operations is provided. In one aspect of the present invention, the LBATPT includes an adapter protection table that has entries for each portion of a storage device. Entries include access control values which identify whether the entry is valid and what access type operations may be performed on a corresponding portion of a storage device. I/O requests may be checked against these access control values to determine if an application instance that submitted the I/O requests may access the LBAs identified in the I/O requests in the manner requested.

Growing community of inventors

Austin, TX, United States of America

Agustin Mena, Iii