Sanmina Corporation

Emc Corporation

Saratoga Speed, Inc.

Chris Youngworth

Sharad Mehrotra

Paul Sweere

Jon Livesey

Jack Mills

Tim Lieber

Uday K Gupta

Richard P Ruef

Julian Ratcliffe

Julian Ratcliff

A system can comprise an I/O circuitry, a processor, reconfigurable circuitry, an array of flash storage devices, and a serial interconnect network that is coupled to transfer data between the I/O circuitry, the processor, the reconfigurable circuitry and the flash storage devices. The processor can be configured to designate an interconnect address space for use in communication over the interconnect network among the I/O circuitry, the processor, the reconfigurable circuitry and the flash storage devices. The reconfigurable circuitry can be configured to translate data addresses during transfers of data between the I/O circuitry and the array of flash storage devices. A method to access an array of flash storage devices that are coupled to I/O circuitry over a serial interconnect network can comprise using reconfigurable circuitry to capture data during transfers of data over the serial interconnect network.

Network storage system using flash storage

The present disclosure describes methods and system configurations for failover of cluster computing system resources, for a cluster computing system including a plurality of cluster nodes. In some examples, operations are performed to monitor an abstracted resource and reconfigure the abstracted resource, to enable fail-over processing for component members of the abstracted resource. In further examples, a hierarchy of resource dependencies is defined to enable enhanced fail-over processing for the failure of abstracted resources that cause the failure of services within the cluster computing system that are dependent upon the abstracted resources.

High availability management techniques for cluster resources

A method of storing a file in a storage system that includes a plurality of memory-storage hosts includes: providing unique chunk identifiers for memory chunks included in the file; using a hash mapping to identify one or more storage locations for each chunk identifier, each storage location corresponding to a portion of a memory-storage host; and storing each memory chuck at the corresponding one or more storage locations identified by the hash mapping.

Network system to distribute chunks across multiple physical nodes

In a synchronous remote mirroring system, as a host computer writes data to primary storage in a primary data storage system, remote copy data is transferred from the primary data storage system to a secondary storage system in which secondary storage is maintained as a remote mirror of the primary storage. The primary data storage system performs data reduction upon the remote copy data prior to transmitting the remote copy data in a reduced to the secondary data storage system. The secondary data storage system returns an acknowledgement of receipt of the remote copy data upon receipt of the remote copy data in the reduced form, and later reverses the data reduction upon the remote copy data in the reduced form to produce data written to the secondary storage to maintain the secondary storage as the remote mirror of the primary storage.

Continuous data reduction for highly available synchronous mirrors

Growing community of inventors

San Jose, CA, United States of America

Chris Youngworth