公开(公告)号：US10698607B2

公开(公告)日：2020-06-30

申请号：US14715745

申请日：2015-05-19

Applicant: NetApp Inc.

Inventor： Chinmoy Dey ,  Anoop Chakkalakkal Vijayan ,  Prasad Srinivas

IPC: G06F3/06 ,  G06F9/455

Abstract: One or more techniques and/or systems are provided for managing configuration updates used to replicate configuration of a primary storage virtual machine to a partner storage virtual machine. For example, the partner storage virtual machine may be configured to provide failover operation in place of the primary storage virtual machine in the event the primary storage virtual machine fails. Configuration updates are queued and replayed on the partner storage virtual machine to replicate objects of the primary storage virtual machine to the partner storage virtual machine (e.g., replay of create, modify, or delete object commands for synchronizing volumes, logical unit numbers, and/or other configuration objects of the primary storage virtual machine to the partner storage virtual machine). Configuration updates may be retained, modified, or discarded/removed based upon consolidation rules, which improves computing resource utilization by consolidating configuration updates and/or removing stale configuration updates while achieving a similar replication consistency result.

公开(公告)号：US10691553B2

公开(公告)日：2020-06-23

申请号：US14970611

申请日：2015-12-16

Applicant: NETAPP, INC.

Inventor： Amit Golander ,  Boaz Harrosh ,  Sagi Manole

IPC: G06F16/18 ,  G06F11/14

Abstract: A persistent memory based distributed-journal file system, comprising: 1) Direct mapped persistent memory unit hosting at least a subset of a file system which contains a plurality of files each associated with a metadata record and a self-journal record. 2) A memory storing a program code. 3) One or more processors coupled to the persistent memory unit and the memory for executing the program code which comprises: (a) Creating a resources dataset which maps characteristics of the file system by analyzing the files' metadata records. (b) Receiving an alteration request to alter altered file(s) of the plurality of files. (c) Determining if the alteration is an atomic alteration which is applied to the file system in an atomic operation. (d) Logging an indication of the alteration in the respective self-journal record of the altered file(s) for non-atomic alteration. (e) Applying the alteration in the file system.

公开(公告)号：US10684918B2

公开(公告)日：2020-06-16

申请号：US15071282

申请日：2016-03-16

Applicant: NetApp Inc.

Inventor： Krishna Murthy Chandraiah setty Narasingarayanapeta ,  Vijay Srinath ,  Rakesh Bhargava M R

IPC: G06F16/00 ,  G06F11/00 ,  G06F16/23 ,  G06F11/14

Abstract: One or more techniques and/or computing devices are provided for restarting a dump backup. For example, a phase offset table is used to track a directory transfer phase offset and a file transfer phase offset of phases of a dump backup. An offset map is used to map inodes, of data being backed up, to offsets within a backup image within which the data is being backed up. The phase offset table and/or the offset map are evaluated using a bytes written value to identify a phase during which the dump backup aborted and to identify a restart point. Accordingly, the dump backup is restarted at the restart point. In this way, the dump backup may be restarted during any phase and/or at any point using the bytes written value, the phase offset table, and the offset map without the need for additional information such as a file history.

公开(公告)号：US10664412B2

公开(公告)日：2020-05-26

申请号：US15796413

申请日：2017-10-27

Applicant: NETAPP, INC.

Inventor： Mahmoud K. Jibbe ,  Dean Lang ,  Scott Terrill ,  Matthew Buller ,  Jeffery Fowler

IPC: G06F12/12 ,  G06F12/128 ,  G06F12/0871

Abstract: Systems and methods that select a cache flushing algorithm are provided. A stripe that spans multiple storage devices and includes a plurality of segments is provided. The stripe also includes dirty data stored in a picket-fence pattern in at least a subset of segments in the plurality of segments. A memory cache that stores data separately from the plurality of storage devices and a metadata cache that stores metadata associated with the dirty data are also provided. A cache flushing algorithm is selected using the metadata. The selected cache flushing algorithm flushes data from the memory cache to the stripe.

公开(公告)号：US20200151144A1

公开(公告)日：2020-05-14

申请号：US16388984

申请日：2019-04-19

Applicant: NetApp Inc.

Inventor： Akhil KAUSHIK ,  Gaurav VERMA

IPC: G06F16/178 ,  G06F9/54

Abstract: Techniques are provided for synchronous replication for synchronous mirror copy guarantee. A file system dependent technique for synchronous mirror copy guarantee is provided by overriding default behavior of a persistent fence so that the persistent fence is activated to block operations targeting a storage object having a synchronous replication relationship based upon the synchronous replication relationship being out of sync. The default behavior of the persistent fence is overridden to allow operations to be executed upon the storage object based upon the synchronous replication relationship being in sync. A file system independent technique for synchronous mirror copy guarantee is provided by intercepting operations before the operations are received by a file system. The operations are selectively forwarded to the file system or not based upon a state of a synchronous replication relationship.

公开(公告)号：US20200151143A1

公开(公告)日：2020-05-14

申请号：US16269838

申请日：2019-02-07

Applicant: NetApp Inc.

Inventor： Akhil KAUSHIK ,  Gaurav Verma

IPC: G06F16/178 ,  G06F9/54

Abstract: Techniques are provided for synchronous replication for synchronous mirror copy guarantee. A file system dependent technique for synchronous mirror copy guarantee is provided by overriding default behavior of a persistent fence so that the persistent fence is activated to block operations targeting a storage object having a synchronous replication relationship based upon the synchronous replication relationship being out of sync. The default behavior of the persistent fence is overridden to allow operations to be executed upon the storage object based upon the synchronous replication relationship being in sync. A file system independent technique for synchronous mirror copy guarantee is provided by intercepting operations before the operations are received by a file system. The operations are selectively forwarded to the file system or not based upon a state of a synchronous replication relationship.

公开(公告)号：US20200089546A1

公开(公告)日：2020-03-19

申请号：US16690860

申请日：2019-11-21

Applicant: NetApp Inc.

Inventor： Rakshit Karnawat ,  Veena TS ,  Ganesh Marappa

IPC: G06F9/50 ,  G06F11/14 ,  G06F11/20

Abstract: Techniques for load balancing and fault tolerant service are described. An apparatus may comprise load balancing and fault tolerant component operative to execute a load balancing and fault tolerant service in a distributed data system. The load balancing and fault tolerant service distributes a load of a task to a first node in a cluster of nodes using a routing table. The load balancing and fault tolerant service stores information to indicate the first node from the cluster of nodes is assigned to perform the task. The load balancing and fault tolerant service detects a failure condition for the first node. The load balancing and fault tolerant service moves the task to a second node from the cluster of nodes to perform the task for the first node upon occurrence of the failure condition.

公开(公告)号：US10592464B2

公开(公告)日：2020-03-17

申请号：US16412794

申请日：2019-05-15

Applicant: NetApp, Inc.

Inventor： Peter Brown ,  Fan Yang ,  Andrew Boyer

IPC: G06F15/17 ,  G06F15/173 ,  H04L29/08 ,  H04L12/26

Abstract: Methods, non-transitory computer readable media and computing device that enabling direct memory access (DMA) capable devices for remote DMA (RDMA) are illustrated. With this technology, a first network message is inserted into a first location of a remote memory region of a computing device via DMA. The remote memory region is defined in an anchor record retrieved from a shared memory of the computing device. A local head pointer is synchronized, via DMA, with a remote head pointer stored by the computing device. The local and remote head pointers correspond to the first location of the remote memory region of the computing device. Following receipt of a DMA completion message, a notification message is sent, via DMA, to the computing device indicating that the network message has been transferred.

公开(公告)号：US20200081902A1

公开(公告)日：2020-03-12

申请号：US16682007

申请日：2019-11-13

Applicant: NetApp Inc.

Inventor： Yuedong Mu ,  Ching-Yuk Paul Ngan ,  Manoj V. Sundararajan

IPC: G06F16/27 ,  H04L29/08 ,  H04L12/911

Abstract: Synchronization metadata is read from non-volatile storage. The synchronization metadata comprises indications of one or more synchronization targets. A synchronization target is a node of a clustered storage system. A synchronization cache is populated with the synchronization metadata. After populating the synchronization cache with at least a portion of the synchronization metadata, a connection to a network is established. After the connection to the network is established, a connection to a first of the one or more synchronization targets is established.

公开(公告)号：US20200081807A1

公开(公告)日：2020-03-12

申请号：US16681979

申请日：2019-11-13

Applicant: NetApp Inc.

Inventor： Hrishikesh Keremane ,  Vijay Singh

IPC: G06F11/20 ,  G06F11/07

Abstract: One or more techniques and/or computing devices are provided for automatic switchover implementation. For example, a first storage controller, of a first storage cluster, may have a disaster recovery relationship with a second storage controller of a second storage cluster. In the event the first storage controller fails, the second storage controller may automatically switchover operation from the first storage controller to the second storage controller for providing clients with failover access to data previously accessible to the clients through the first storage controller. The second storage controller may detect, cross-cluster, a failure of the first storage controller utilizing remote direct memory access (RDMA) read operations to access heartbeat information, heartbeat information stored within a disk mailbox, and/or service processor traps. In this way, the second storage controller may efficiently detect failure of the first storage controller to trigger automatic switchover for non-disruptive client access to data.