Back to results
US 9,753,822 B1Granted
Automatic non-disruptive connection recovery of a fixed topology fabric in a data storage system
AssigneeEMC IP Holding Company LLC
InventorsAlesia Tringale, Sean Pollard, Julie Zhivich
Life of this patent
Estimating the term…
Abstract
Individual transport connections within a dual-star fabric connected multi-node storage system are disabled in response to associated failures due to faulty hardware or temporal congestion. Each configured IB transport connection is monitored for viability and, upon failure, removed from the pool of available resource. Following failure restoration the resource is tested to ensure proper functionality and then restored to the pool of resources. Mappings associated with the transport connections are maintained while the connections are disabled.
Claims20
An apparatus comprising:
- a data storage system comprising:
- a plurality of data storage devices;
- a plurality of storage nodes configured to access the data storage devices and communicate with another device;
- and
- a first switch and a second switch, each of which interconnects each pair of the storage nodes via at least one point-to-point link such that there are at least two point-to-point links between each pair of storage nodes;
- wherein each storage node includes at least one memory component and is configured to utilize the point-to-point links to access memory components associated with other storage nodes of the plurality of storage nodes, and in response to detection of a failure condition to route all communications associated with accessing memory components associated with other storage nodes of the plurality of storage nodes through the second switch while maintaining mapping information associated with all of the point-to-point links through the first switch.
3 more elements
A method comprising:
- in a data storage system comprising a plurality of data storage devices, a plurality of storage nodes configured to access the data storage devices and communicate with another device, and a first switch and a second switch, each of which interconnects each pair of the storage nodes via at least one point-to-point link such that there are at least two point-to-point links between each pair of storage nodes:
- utilizing, by each storage node, the point-to-point links to access memory components associated with other storage nodes of the plurality of storage nodes;
- and
- in response to detection of a failure condition, routing all communications associated with accessing memory components associated with other storage nodes of the plurality of storage nodes through the second switch while maintaining mapping information associated with all of the point-to-point links through the first switch.
1 more element
Dependencies are inferred from the claim text.