Building Stable Storage Area Networks For Compute Clusters
First Claim
1. A method comprising:
- aggregating volumes in a plurality of volumes into a transfer set according to system characteristics;
discontinuing I/O requests to volumes in the transfer set;
transferring ownership of volumes in the transfer set to one or more storage controllers that have not owned the volumes in the transfer set; and
reinstating the I/O requests to the volumes in the transfer set.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems and methods that result in a stable storage system are provided. In the storage system, the latency spikes may be reduced when multiple volumes are aggregated into transfer sets according to system characteristics. The storage system transfers ownership of volumes in each transfer set as a single transaction. In the storage system, connectivity between the host and the storage controller is re-established based on the connectivity in a physical transport layer and a single path. In the storage system, pre-mature failback is also avoided when ownership of volumes is transferred back to a preferred storage controller when the same number of paths existed between the host and the preferred storage controller before and after a failover operation. Further, the storage system generates connectivity reports that display connectivity paths between hosts, storage controllers, and volumes.
-
Citations
20 Claims
-
1. A method comprising:
-
aggregating volumes in a plurality of volumes into a transfer set according to system characteristics; discontinuing I/O requests to volumes in the transfer set; transferring ownership of volumes in the transfer set to one or more storage controllers that have not owned the volumes in the transfer set; and reinstating the I/O requests to the volumes in the transfer set. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A computing device comprising:
-
a memory containing machine readable medium comprising machine executable code having stored thereon instructions for performing a method of transferring ownership of volumes; and a processor coupled to the memory, the processor configured to execute the machine executable code to cause the processor to; aggregate a subset of volumes in a plurality of volumes into a transfer set; change a caching model for at least one cache that stores data associated with the subset of volumes to a write-thru model; flush the data in the at least one cache to underlying one or more storage devices; discontinue I/O requests to the subset of volumes; transfer ownership of the subset of the volumes in the transfer set; and reinstate the I/O requests to the subset of volumes. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
-
17. A non-transitory machine readable medium having stored thereon instructions for performing a method comprising machine executable code which when executed by at least one machine, causes the machine to:
-
determine a number of paths between a host and a preferred storage controller, wherein the preferred storage controller has ownership of a volume; perform a failover operation, wherein the failover operation transfers ownership of the volume from the preferred storage controller to a non-preferred storage controller; determine a number of paths between the host and the preferred storage controller subsequent to the failover operation; compare the number of paths before the failover operation to the number of paths subsequent to the failover operation; and transfer the ownership of the volume from the non-preferred storage controller to the preferred storage controller based on comparing the number of paths. - View Dependent Claims (18, 19, 20)
-
Specification