Emc IP Holding Company LLC

Anil Kumar Koluguri

Dmitry Nikolayevich Tylik

Matthew H Long

Vinod Rajasekaran

Yuri Alexandrovich Stotski

Avitan Gefen

Alan Lee Taylor

Shaul Dar

William C Whitney

Michael Zeldich

Arun Joseph

Jean Marie Schiff

Somchai Pitchayanonnetr

William S Burney

David Sydow

A method, computer program product, and computing system for processing historical input/output (IO) performance data associated with one or more storage objects of a storage system. A plurality of IO modeling systems may be trained using the historical IO performance data. Modeling performance information may be determined for the plurality of IO modeling systems across the historical IO performance data. A forecast score may be determined for each IO modeling system based on the modeling performance information for the plurality of IO modeling systems. A subset of the plurality of IO modeling systems may be selected based upon the forecast score for each IO modeling system. The at least one IO modeling system may be trained using the historical IO performance data. IO performance data may be forecasted using the at least one trained IO modeling system from the subset of the plurality of IO modeling systems.

System and method for modeling and forecasting input/output (IO) performance using adaptable machine learning

A virtual volume is initially provided from a first storage appliance within a cluster of storage appliances by providing access to the virtual volume over a data path between a host computer and a protocol endpoint hosted on the first storage appliance, based on an initial binding between the virtual volume and the protocol endpoint hosted on the first storage appliance. A rebind request is conveyed to the host computer, and in response to receiving a bind request for the virtual volume, a new binding is created between the virtual volume and a protocol endpoint hosted by the second storage appliance. The virtual volume is subsequently provided from the second storage appliance by providing the host computer with access to the virtual volume over a data path between the host computer and the protocol endpoint hosted on the second storage appliance based on the newly created binding.

Non-disruptive migration of a virtual volume in a clustered data storage system

During preparation for migration of a logical volume from a source data storage appliance to a destination data storage appliance, a determination is made as to whether at least one host that accesses a copy of the logical volume contained in the source data storage appliance is managed by a host administration server. In response to determining that at least one host that accesses the copy of the logical volume contained in the source data storage appliance is managed by the administration server, a rescan request is transmitted to the administration server. The rescan request causes the host administration server to instruct each host that is managed by the host administration server that accesses the copy of the logical volume contained in the source data storage appliance to perform a rescan operation to discover at least one new path to the logical volume.

Host rescan for logical volume migration

At the start of an I/O cutover process that changes host computer access to a logical volume from a source data storage appliance to a destination data storage appliance, and during which processing of host I/O operations directed to the logical volume is frozen, at least one I/O freeze timer is set. In response to expiration of the I/O freeze timer, and prior to completion of the I/O cutover process, processing of host I/O operations directed to the logical volume is resumed.

Limiting the time that I/O to a logical volume is frozen

Data storage systems of a cluster associate virtual volumes (VVols) with protocol endpoints (PEs) organized into host-specific initiator groups. From the perspective of the hosts, the PEs are specialized SCSI LUNs that aggregate the VVols bound thereto. In operation, a host directs VVol access requests to the host-specific PEs, and a data storage system processes the VVol requests as received via the corresponding PEs.

Data storage system binding virtual volumes to host-specific protocol endpoints

A technique for managing data storage for virtual machines in a data storage system includes receiving, from a virtual machine administrative program, a request to operate a virtual machine disk (VMD) at a different service level from one at which the data storage system is currently operating the VMD. In response to receiving the request, the data storage system migrates the VMD from a first set of storage extents providing a first service level to a second set of storage extents providing a second service level.

Growing community of inventors

Raleigh, NC, United States of America

Anil Kumar Koluguri