Emc Corporation

Emc IP Holding Company LLC

Ajith Balakrishnan

Arieh Don

Helen S Raizen

Srikanth Venkataraman

Alexandr Veprinsky

Felix Shvaiger

Nitin Chhabra

Sumit Basu Mallick

Vinay G Rao

Sanjib Mallick

Peng Wu

Rong Yu

Erik P Smith

Zvi Gabriel Benhanokh

Mark C Lippitt

Santhosh Venkatesh Kudva

Bradley Allen Bowlin

Ankur Dixit

Brad Bowlin

Nihar R Panda

Raghuram Adabala

Eitan Ben-Amos

Nithin Surendran

Savitha Susan Bijoy

Rajesh Parameswaran

Prakash Chanderia

Example embodiments relate to a method, a system, and a computer program product for load balancing for port selection. The method includes determining a processing load for each storage port in a plurality of storage ports having variable processing power and calculating a delay characteristic for each storage port of the plurality of storage ports according to its processing load. A command then may be sent to a selected storage port of the plurality of storage ports according to the delay characteristics and a policy.

Method and apparatus for cost-based load balancing for port selection

Described herein are methods and systems by which certain servicing and maintenance of a device coupled to a computer network can be performed remotely. The system receives an event associated with the operation of the device and compares the event to a set of rules to identify if the event is a false positive event. The system generates a notification when the event is not the false positive event and transmits the notification to a service agent.

Dial home optimizer

Example embodiments of the present disclosure relate to a method, computer program product, and system for an upgrade of an array specific module in a multipath application comprising suspending all input/output operations associated with the array specific module; and upgrading the array specific module without disrupting any input/output operations associated with the array specific module.

Storage system upgrade

Techniques are presented for event-based host registration. Continuously performed standard path testing operations are able to cause an event signal upon detection of a newly-available path, and upon receiving such an event signal, a host is able to perform host registration along the newly-available path, obviating the need to periodically send out registration commands while simultaneously minimizing latency.

Event-based in-band host registration

Example embodiments of the present invention relate to methods, systems, and computer program products for reducing I/O latency in a storage system. The method include polling a storage system for values related to caching of I/Os in global memory for subsequent destaging to disk. The host then may determine respective write delay values for I/Os to be sent from a host communicatively coupled with the storage system according to the values related to caching of I/Os. The write delay values then may be applied to the I/Os at the host to delay sending of the I/Os by respective delay times from the host to the storage system.

Method and system for machine learning for write command selection based on technology feedback

In one aspect, a method includes migrating a first device on a first array to a second device on a second storage array. The migrating includes instructing an asset to scan the first array and the second array for the first device and the second device, reading a work buffer on the second array, sending a request to the work buffer for a chunk of the first device to copy to the second device, reading assigned chunk from the first device, copying the assigned chunk to the second device and notifying the work buffer that the copying of the assigned chunk was successful.

Migrating data using multiple assets

A technique manages operation of a host computer having access to a storage volume on a storage system via two or more distinct paths. The technique involves operating a multipathing driver within the host computer, the multipathing driver controlling path access from the host computer to the storage volume. The technique further involves operating a host bus adaptor (HBA) driver within the host computer to interface the host computer to a fabric connecting the host computer to the storage system. The technique further involves conveying fabric topology state change event information from the HBA driver to the multipathing driver to enable the multipathing driver to take action in response to fabric topology state change events. In some arrangements, an event monitoring handler receives fabric event information from registered state change notifications (RSCNs) containing fabric event information from the HBA driver, and forwards that information on to the multipathing driver.

Notifying a multipathing driver of fabric events and performing multipathing management operations in response to such fabric events

Described are techniques for achieving service level objectives. A first service level objective for a first tenant of a data storage system may be received. The first tenant may have data stored in a first set of devices of the data storage system. The first service level objective may include a first value for a first metric. The first tenant may be located on a first host and may issue I/O operations directed to the first set of devices. A first calculated value for the first metric may be determined using one or more measured values obtained at the first host. It may be determined, using the first calculated value for the first metric, whether the first service level objective for the first tenant is violated. Responsive to determining the first service level objective for the first tenant is violated, first processing may be performed to selects a remediation action.

Techniques for improved service level objective fulfillment

A method of registering a host bus port (HBP) of a host computer (host) at a storage bus port (SBP) of a data storage array over a storage network includes (a) acquiring a configuration instruction directing the host to process registration messages from an event processing engine, (b) receiving a registration message from the event processing engine indicating that the HBP needs to be registered with the SBP, the registration message having been generated by the event processing engine in response to receiving an event notification message indicating that a data path across the storage network between the HBP and the SBP is available, and (c) in response to receiving the registration message, processing the registration message by registering the HBP with the SBP by sending a registration command from the HBP to the SBP across the storage network, the registration command including registration information associated with the HBP.

In one aspect, a method includes measuring performance parameters for each path, determining classifications of each path based on a service level objective and sending I/Os using load balancing by the classifications determined. In another aspect, an apparatus includes electronic hardware circuitry configured to measure performance parameters for each path, determine classifications of each path based on a service level objective and send I/Os using load balancing by the classifications determined. In a further aspect, an article includes a non-transitory computer-readable medium that stores computer-executable instructions. The instructions cause a machine to measure performance parameters for each path, determine classifications of each path based on a service level objective and send I/Os using load balancing by the classifications determined.

Path selection using a service level objective

Example embodiments of the present invention relate to a method, an apparatus, and a computer program product for sending an I/O over a preferred path. The method includes determining a preferred path to an address range of a virtual storage unit striped across a plurality of disks of a data storage system and sending an I/O for data comprising the address range over the preferred path.

Method and apparatus for dynamic path-selection for improving I/O performance in virtual provisioned storage arrays with data striping

Described are techniques for parameter selection. First processing is performed that migrates data of a first device from an origin to a destination data storage system. The first processing includes cutover processing. After cutover processing is performed, requests to the first device are serviced by the destination data storage system rather than the origin data storage system. During first processing, occurrence of cutover processing is detected. Responsive to detecting the occurrence of cutover processing, second processing is performed to update one or more parameters each having a value that varies in accordance with a type of physical data storage system. Prior to second processing, the parameters have values determined in accordance with a type of physical data storage system of the origin data storage system, and after second processing, the parameters have values determined in accordance with a type of physical data storage system of the destination data storage system.

Automated updating of parameters and metadata in a federated storage environment

A technique for verifying the safety of tenant data in a data center includes creating a topological map of storage constructs used for storing the tenant data within the data center. The topological map includes a logical storage device, a physical storage device, and a set of hardware structures disposed between the logical and physical storage devices. The constructs of the topological map are evaluated to generate an individual assessment of fault tolerance of each construct, and a set of rules are applied to generate an overall assessment of the safety of the tenant data. In an example, an administrator may operate this technique on a tenant application and generate a report for the tenant summarizing the results.

Verifying application data protection

Designing a test bed for testing a computer product includes (1) obtaining customer configuration data describing different system configurations in which the computer product is used, (2) preprocessing the customer configuration data to generate structured customer configuration, (3) applying a classification to the structured customer configuration data to separate the distinct system configurations into groupings according to similarity in one or more of the system attributes among members of each group, and (4) for each grouping, identifying a representative system configuration to be used for testing and generating a corresponding set of test bed definition data describing the representative system configuration to enable implementation. The classification may employ clustering analysis, and supplementary and/or backup techniques may be included.

Growing community of inventors

Bengaluru, India

Ajith Balakrishnan