International Business Machines Corporation

International Busniss Machines Coporation

Ealan Abraham Henis

David Breitgand

Onn Menahem Shehory

Maayan Goldstein

John Michael Lake

Simona Cohen

Yaron Weinsberg

Kenneth Nagin

John Michael Marberg

Edya Ladan-Mozes

Shahar Ronen

Elena Yerushalmi

Machines, systems and methods for dynamically implementing storlets in a storage data path. The method comprises receiving a request to perform a storage-related function on data stored on a first data storage medium in a data storage system; verifying the request by way of an authentication and authorization mechanism to prevent unauthorized access to data stored on the first data storage medium in the data storage system; and utilizing a storlet to service the request, wherein the storlet is dynamically deployed on a node in the data storage system such that the node has sufficient resources to support the storlet to service the request.

Dynamic storlets in storage system data path

A method for maximizing a utility of a service contract by optimizing target response time for a performance service level objective is provided. A set of criteria are provided to ensure that performance requirements for the service are met. The method comprises determining one or more usage windows for providing a service, wherein each usage window is associated with a performance requirement and a time period; extracting usage patterns for each usage window based on historical data provided from monitoring requests for service in each usage window; extracting response time per transaction associated with said requests based on historical data provided from monitoring responses provided to said requests in each usage window; and calculating optimal probability for breach in each usage window (Pi) and determining the associated target response time, based on the usage pattern for each window and the response time per transaction.

Automated derivation of response time service level objectives

Methods for generating a characterizing summary and generating a collection of relevant preservation objects in a preservation system are provided. A characterizing summary is generated by collecting first information about a preservation object; collecting second information about other preservation objects or other metadata; generating a characterizing summary according to the first information and the second information; and adding the characterizing summary to the preservation object. A collection of relevant preservation objects is generated by accessing one or more preservation objects by way of one or more metadata included in a target preservation object constructed for content data; determining whether each of the accessed preservation objects is relevant to the target preservation object; adding each relevant preservation object to a list of relevant preservation objects; and generating the collection of relevant preservation objects according to the list of relevant preservation objects.

Preservation of digital content

A method for managing a computer system includes monitoring first violations of a service level objective (SLO) of a service running on the computer system so as to determine a first statistical behavior of the first violations. Second violations of a component performance threshold of a component of the computer system are monitored so as to determine a second statistical behavior of the second violations. A model that predicts the second statistical behavior based on the first statistical behavior is produced. The component performance threshold is automatically adjusted responsively to the model, so as to improve a prediction of the first violations by the second violations.

Automated and adaptive threshold setting

Managing a computer system including automatically adjusting two separate component thresholds (a component threshold pair) based on a statistical model. Specifically, a first component threshold is modeled to predict violations of an SLO based on a violation of the first component threshold and a second, separate component threshold is modeled to predict a non-violation (compliance) of an SLO based on a non-violation of the second component threshold. Over time, the values of the component thresholds may change and one component threshold may be greater than the other component threshold at one time, and vice versa at another time. A component metric reading between the first and second component thresholds indicates that a prediction of an SLO violation or compliance is less certain, and a warning may be issued rather than an alert.

System and method for automated and adaptive threshold setting to separately control false positive and false negative performance prediction errors

Systems and methods for optimizing performance in a computing environment are provided. The system comprises means for monitoring execution of annotated logic code associated with a software component to determine whether a condition has been satisfied, wherein annotations in the logic code provide one or more details about the software component, the details being useful to a healing agent to correct a problem associated with said condition during the execution of the logic code.

Self-healing system and method for code optimization in a computing environment

Systems and methods for optimizing memory management in a runtime environment are provided. The method comprises monitoring one or more objects loaded into primary memory of a computing system to determine if at least a first object can be removed from the primary memory; instantiating a proxy object to replace the first object in the primary memory; removing the first object from the primary memory; and monitoring calls to the proxy object to determine whether the first object is invoked by a process.

Managing memory resident objects to optimize a runtime environment

A method for diagnosing network performance problems includes providing a graph representing a topology of a network including first nodes that are classified as providers of a resource, second nodes that are classified as consumers of the resource, and third nodes that are classified as mediators intervening between the providers and the consumers. Responsively to a report of a performance problem encountered by a given consumer in the network, at least one input/output (I/O) path is traced through the graph connecting the given consumer to one or more of the providers. One or more problematic nodes are identified along the at least one I/O path as possible causes of the performance problem.

Growing community of inventors

Rehovot, Israel

Ealan Abraham Henis