International Business Machines Corporation

Nikhil Hegde

Rashmi Narasimhan

Adekunle Bello

Aruna Yedavilli

Kavitha Vittal Murthy Baratakke

Sivakumar Krishnasamy

Prashant Anant Paranjape

Radhika Chirra

Bruce Gerard Mealey

Mark D Rogers

Vishal Ramachandra Mansur

Omar Cardona

Andrew Dunshea

Jos Manuel Accapadi

Keerthi B Kumar

Rajarshi Das

Ajay Kumar Mahajan

Shailaja Mallya

Anis M Abdul

Juan M Casas, Jr

Vishal R Mansur

Kavitha V M Baratakke

Paul Henry Hernandez

Kavitha V Baratakke

Fred Allison Bower, Iii

Gregory Joseph McKnight

Shaival Jagdishbhai Chokshi

Pramod Achyut Bhandiwad

Peter Morjan

Sandhya Kapoor

Uma M Chandolu

Jason M Heim

Prithvi Srihari

Richard Jamie Knight

Puneet Mahajan

Sivarami R Chaganti

G Shantala

Jagdish C Gopalakrishnan

Varun Sethi

Deepak W Elias

Tony W Offer

Sophia Jacob

Arnab Tah

Maria J Frederic

A method, programmed medium and system are provided for preventing the denial of file system access to a plurality of clients accessing a NFS server. In one example, an NFS server is configured to listen on a server port. The server runs a separate daemon which 'watches' client requests as they are received at the NFS server. The server processing system tracks the number of times a client sends consecutive TCP zero-window packets in response to a data packet from the server. If the number of zero-window packets crosses a user-defined threshold, then a routine is called to stop responding to that client using a backoff algorithm. When the server reaches a point where the number of available threads or any other relevant resource dips below a user-defined threshold, the server process starts terminating connections to the clients starting from the ones with the oldest entry in the table.

Server access processing system

A system and computer program product are provided for optimized timer placement. A request to apply a new timer in a computer system is received and an interrupt time for the new timer is extracted from the new timer. A timer list is accessed for each processor in the system responsive to the received request. A range for placement of the new timer is established with respect to each of the accessed timer lists. A timer expiry delay is calculated between proximal processor interrupts and the extracted interrupt time based on the established range placement. Proximity of the extracted interrupt time within the existing processor interrupts is determined and one of the processors is selected based on the calculation and the determined proximity. The new timer is placed on the selected processor.

Timer placement optimization

A method is provided for optimized timer placement. A request to apply a new timer in a computer system is received and an interrupt time for the new timer is extracted from the new timer. A timer list is accessed for each processor in the system responsive to the received request. A range for placement of the new timer is established with respect to each of the accessed timer lists. A timer expiry delay is calculated between proximal processor interrupts and the extracted interrupt time based on the established range placement. Proximity of the extracted interrupt time within the existing processor interrupts is determined and one of the processors is selected based on the calculation and the determined proximity. The new timer is placed on the selected processor.

A method for zeroing memory in computing systems where access to memory is non-uniform includes receiving, via a system call, a request to delete a memory region, forwarding the request to an intermediate software thread, and using the intermediate software thread to perform the request as a background process. The method further includes, upon receiving a message from the intermediate software thread, returning to a system caller, while performing the request, via the intermediate software thread, continues in the background.

Off-line affinity-aware parallel zeroing of memory in non-uniform memory access (NUMA) servers

A method for zeroing memory in computing systems where access to memory is non-uniform includes receiving, via a system call, a request for a pool of memory, determining a size of the requested pool of memory, and creating a dummy memory segment. The size of the dummy memory segment is larger than the size of the requested pool of memory. The dummy memory segment is filled with one or more pages, based on the determined size of the requested pool of memory, and the dummy memory segment is deleted.

Affinity aware parallel zeroing of memory in non-uniform memory access (NUMA) servers

A system includes a processor and a memory storing a program, and a computer readable medium includes a program for performing an operation for zeroing memory in computing systems where access to memory is non-uniform. The operation includes receiving, via a system call, a request to delete a memory region. The operation also includes sorting, after receiving the request, one or more pages of the memory region according to each associated affinity domain of each page. The operation further includes sending requests to zero the sorted one or more pages to one or more zeroing threads that are attached to the respective affinity domain. The operation further yet includes waiting, after sending the requests, to return to the system caller until a message is received, from the zeroing threads in each affinity domain, indicating that all the page zeroing requests have been processed.

Affinity-aware parallel zeroing of pages in non-uniform memory access (NUMA) servers

According to one aspect of the present disclosure, a method and technique for dynamic reconfiguration of network devices for outage prediction is disclosed. The method includes: aggregating a plurality of network devices to form an input/output (I/O) link bundle; identifying a quality of service level of data throughput needed by at least one workload utilizing the I/O link bundle; monitoring a parameter of each of the network devices of the I/O link bundle; determining whether the monitored parameter indicates a predicted data throughout quality of service level decrease by a network device being utilized by the workload below the quality of service level for the workload; and responsive to determining that the monitored parameter indicates a predicted quality of service level decrease by the respective network device, dynamically reconfiguring the link bundle to maintain the quality of service level for the workload utilizing the I/O link bundle.

Dynamic reconfiguration of network devices for outage prediction

A method includes receiving, into a target machine communicatively coupled to a first subnetwork, data for migration of a virtual partition from a source machine communicatively coupled to a second subnetwork. The virtual partition has a source network address defined by network addressing of the second subnetwork. The method includes initiating restart of the virtual partition on the target machine, wherein the initiating comprises determining a socket connection providing network communication between the virtual partition and a host and transmitting, through a network tunnel communication from the target machine to the host, a communication providing a target network address that is assigned to the virtual partition after the virtual partition is migrated to the target machine. The method includes routing a packet, from a process executing in the virtual partition of the target machine, to the host based on the virtual partition having the target network address.

Migration of logical partitions between two devices

A system and technique for dynamic reconfiguration of network devices for outage prediction is disclosed. The system includes a host and a plurality of network devices aggregated to form a link bundle; and wherein the host comprises a configuration manager operable to: identify a quality of service level of data throughput needed by at least one workload utilizing the link bundle; monitor a parameter of each of the network devices of the link bundle; determine whether the monitored parameter indicates a predicted data throughout quality of service level decrease by a network device being utilized by the workload below the quality of service level for the workload; and responsive to determining that the monitored parameter indicates a predicted quality of service level decrease by the respective network device, dynamically reconfigure the link bundle to maintain the quality of service level for the workload utilizing the link bundle.

In a method for regulating network bandwidth in a virtualized computer environment, a computer having a hypervisor program receives a request from a first virtual client to transmit data. In response, the computer transfers the data from a memory of the first virtual client to a memory of a virtual server. The computer receives an error notification from a shared virtual network adapter of the virtual server, indicative of insufficient network bandwidth available to transmit the data. In response, the computer notifies the first virtual client that insufficient network bandwidth is available to transmit the data.

Regulating network bandwidth in a virtualized environment

A service module that provides for discovery of one or more network interfaces connecting a prospective remote procedure call (RPC) client, facilitates the provision of RPC programs in a network including multi-horned systems. When a request for a network address to an RPC application providing an RPC program is received from the RPC client, the RPC bind daemon discovers from the module, using the client response address, over which interface(s) the client is accessible. The daemon then selects an address of a network path to the RPC application that the prospective client can access and returns the corresponding network address. The service module monitors the network stack for RPC get address requests and builds tables of client address entries with corresponding network interface identifiers. The entries are retired according to an aging policy.

Remote procedure call (RPC) bind service with physical interface query and selection

Provided is reporting session information for a session upstream from a server. A data processing system receives a session handshake from a first client for a session between the server and the first client. The system receives a session-descriptor for a session between a second client and the first client before handling a nested session. The system determines whether a user has made an upstream session request. The system obtains session data from an upstream data structure, responsive to a determination that the user has made an upstream session request. The system renders the session data based on the upstream session request.

Remote session management

A method identifies a network socket on a machine by assigning a non-IP address socket anchor and a port number to the network socket. A socket anchor may comprise a globally unique number. In some embodiments, a socket anchor comprises a number having a preselected number of bits. The number having the preselected number of bits may comprise a selected number associated with the machine concatenated with a number of randomly generated bits. The number of bits of the selected number plus the number of randomly generated bits is equal to the preselected number of bits. In some embodiments, the selected number associated with the machine is a Media Access Control (MAC) address of a network interface associated with the machine.

Transport layer connection

Growing community of inventors

Round Rock, TX, United States of America

Nikhil Hegde