International Business Machines Corporation

Deepavali M Bhagwat

Wayne A Sawdon

Frank Bernhard Schmuck

Dean Hildebrand

Marc M Eshel

Joseph W Dain

Renu Tewari

Manoj Premanand Naik

Nilesh Prabhakar Bhosale

James Hewitt

Constantine Arnold

Owen Theodore Anderson

Lukas Rupprecht

Marc Adam Kaplan

Felipe Knop

D Scott Guthridge

Enci Zhong

Dimitrios Skourtis

Hai Zhong Zhou

Gregory Tad Kishi

John Thomas Olson

John Lewars

James C Davis

Frank N Lee

M Corneliu Constantinescu

Sven Oehme

Shekhar Amlekar

Jacob Morris Tick

Shashank Gugnani

Luis Teran

April Brown

A method for executing operation requests includes formatting one or more storage devices and selecting one or more labeled replicas and one or more distinguished replicas, receiving an operation request with respect to a set of data blocks, identifying a preferred replica corresponding to the received operation request, determining whether the replication-pending bits for the preferred replica are set, and executing the received operation request with respect to the corresponding distinguished replica. A method for executing a write operation request additionally includes setting replication-pending bits with respect to the labeled replica, wherein the replication-pending bits indicate an incomplete write request, writing data to both a labeled replica and a distinguished replica, and clearing the replication-pending bits with respect to the labeled replica to indicate the completion of the write operation. A method for executing a read operation additionally includes identifying a preferred replica with respect to the received read request.

Interrupted replicated write recognition

A method and a computer system for asymmetric replication of data are provided. Storage of a set of data is organized as a first copy and as a second copy in non-volatile storage. The second copy is reliable and stored so as to be readable at a speed slower than for the first copy. A read instruction regarding the set of data is received and performed preferentially via the first copy such that the asymmetric replication achieves enhanced performance speed. A request to execute a write operation is received. The write operation is executed to the first copy and to the second copy. In response to determining that the write operation to the first copy was unsuccessful, a label for the first copy is set as stale.

Efficient use of optional fast replicas via asymmetric replication

A computer-implemented method includes monitoring file access activity and generating an audit log based on the file access activity. The method also includes collecting samples of file usage activity, running a pattern recognition algorithm on the samples of the file usage activity for detecting malware activity, and, in response to detecting malware activity, restoring at least one file based on the audit log. A computer program product includes one or more computer readable storage media and program instructions collectively stored on the one or more computer readable storage media. The program instructions include program instructions to perform the foregoing method. A system includes a processor and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. The logic is configured to perform the foregoing method.

Detection of encrypting malware attacks

A dataset formatted in a first format is generated, wherein the dataset formatted in the first format includes at least a plurality of data elements that comprise data. A selection is made of machine learning framework, wherein the machine learning framework operates on datasets formatted in a second format that is different from the first format. The dataset is converted from the first format to the second format and links are generated from the converted dataset formatted in the second format to the plurality of data elements of the dataset formatted in the first format to avoid creating additional copies of the plurality of data elements.

Generation of a dataset in the format of a machine learning framework

A computer-implemented method according to one embodiment includes monitoring for occurrence of trigger events corresponding to creation of metadata in a computing environment, and detecting occurrence of a trigger event. The method further includes loading a rule that is associated with the detected trigger event in response to detecting occurrence of the trigger event. The rule includes a condition and an action, and the action defines a subset of metadata associated with processing a job in the computing environment. The method further includes collecting the defined subset of metadata in accordance with the action in response to the condition of the rule being met, and storing the collected subset of metadata. A system according to another embodiment includes a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. The logic is configured to perform the foregoing method.

Rule-based collections of subset(s) of metadata in response to a trigger event occurring

Embodiments include a method for fault tolerance in the delivery of event information within a file system cluster. One or more processors to determine event information associated with file system activity performed by a node of the cluster. The one or more processors add the event information to an event log buffer in memory. The one or more processors receive a first log sequence number (LSN) associated with flushing of recovery information from a recovery log buffer. The one or more processors determine the event information in the event log buffer having a log sequence number less than or equal to the first log sequence number, and determining the event information includes log sequence numbers less than or equal to the first log sequence number, the one or more processors flush the corresponding event information from the event log buffer to disk storage.

Reliable delivery of event notifications from a distributed file system

Embodiments for storage resource utilization analytics using metadata tags by a processor. Storage capacity utilization in the plurality of heterogeneous storage systems may be determined using one or more events indexed into a centralized search index.

Storage resource utilization analytics in a heterogeneous storage system environment using metadata tags

A computer-implemented method includes using a cache replacement algorithm to forcefully evict target data from a cache. Using the cache replacement algorithm includes selectively accessing data in the cache. A computer program product includes one or more computer readable storage media and program instructions collectively stored on the one or more computer readable storage media. The program instructions include program instructions to perform the foregoing method. A system includes a processor and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor. The logic is configured to perform the foregoing method.

Fine-grained forced cache eviction

One embodiment provides a method for storage management in a hierarchical file system that includes creating a structure for the hierarchical file system including a top-file system and sub-file systems that each include files and directories. Directories for the sub-file systems of the hierarchical file system are tracked. A request for creation of a unique directory in the hierarchical file system is received. Upon a request by a particular sub-file system for more inodes without any inodes available, inode numbers are revoked from at least one other sub-file system having unused inodes.

Global namespace for a hierarchical set of file systems

One embodiment provides a method for optimizing data read-ahead for machine learning applications including obtaining, by a processor, next file information from a workflow scheduler for next input files for a next processing stage that are to be accessed by a machine learning application. Data for the next processing stage for the machine learning application and at least one system job is prefetched. The next input files are prefetched as the prefetching data reaches an end of current inputs. A schedule is caused to chain the next input files for the next processing stage to current input files of a current processing stage.

Prefetch chaining for optimizing data read-ahead for workflow and analytics

A computer-implemented method according to one embodiment includes obtaining, at an untrusted environment, encrypted data from a storage location, initiating, within the untrusted environment, a performance of one or more secure computations on the encrypted data, and providing, within the untrusted environment, results of performing the one or more secure computations on the encrypted data.

Providing differential privacy in an untrusted environment

In one embodiment, a computer-implemented method for namespace and content manipulation within a storage system includes: defining policy rule(s), each policy rule dictating: how namespaces within the storage system may be transformed; and/or how content stored within the storage system may be transformed; receiving a request for access to a particular data set stored within the storage system; parsing the request to determine one or more transformations requested therein and/or required thereby; determining whether the particular data set is compliant with the one or more transformations; in response to determining the particular data set is compliant with the one or more transformations, providing access to the particular data set; and in response to determining the particular data set is not compliant with the one or more transformations, performing the one or more transformations to generate a transformed data set, and providing access to the transformed data set.

Dynamic, transparent manipulation of content and/or namespaces within data storage systems

Embodiments for namespace management between storage systems by a processor. Events, containing metadata associated with an operation, from a plurality of heterogeneous storage systems may be received such that the events are indexed into a common repository according to the metadata to maintain a single namespace for data in the plurality of heterogeneous storage systems.

Global namespace in a heterogeneous storage system environment

A computer-implemented method according to one embodiment includes identifying an event associated with a high speed storage tier of a data storage system, determining a policy rule that is triggered in response to the event, and implementing one or more data management actions associated with the high speed storage tier according to the policy rule.

Dynamically managing a high speed storage tier of a data storage system

One embodiment provides a method for optimizing data read-ahead for workflow and analytics applications including obtaining, by a processor, next file information from a workflow scheduler for next files for a next processing stage that are to be accessed by a process. Data for the next processing stage for at least one application and at least one system job is prefetched. The next files are prefetched as the prefetching data reaches an end of current inputs.

Growing community of inventors

Cupertino, CA, United States of America

Deepavali M Bhagwat