公开(公告)号：US11372544B2

公开(公告)日：2022-06-28

申请号：US17031461

申请日：2020-09-24

Applicant: NetApp, Inc.

Inventor： Ankit Kumar ,  Christopher Cason ,  Daniel David McCarthy

IPC: G06F3/06

Abstract: A technique manages bandwidth allocated among input/output operations, such as reads and writes, to storage devices coupled to storage nodes of a cluster. The technique balances the writes in a manner that reduces latency of reads, while allowing the writes to complete in a desired amount of time. The writes include write types, such as client writes, data migration writes, block transfer writes, and recycling writes, which are defined by differing characteristics and relative priorities. To ensure timely completion of the write types, the technique provides periodic time intervals over which the writes may be balanced and allocated sufficient bandwidth to access the storage devices. The time intervals may include shuffle intervals within a larger distribution interval. In addition, the technique throttles certain write types at the storage device level to maintain consistent read performance. Throttling is based on a credit system that allocates bandwidth as “credits” based on write type.

公开(公告)号：US20210232314A1

公开(公告)日：2021-07-29

申请号：US16752001

申请日：2020-01-24

Applicant: NetApp, Inc.

Inventor： James Philip Wittig ,  Forrest Trimbell ,  Daniel David McCarthy ,  Jared Cantwell ,  Mark Olson ,  Christopher Cason

IPC: G06F3/06

Abstract: A technique is configured to maintain multiple copies of data served by storage nodes of a cluster during upgrade of a storage node to ensure continuous protection of the data served by the nodes. The data is logically organized as one or more volumes on storage devices of the cluster and includes metadata that describe the data of each volume. A data protection system may be configured to maintain at least two copies of the data in the cluster during upgrade to a storage node that is assigned to host one of the copies of the data but that is taken offline during the upgrade. As a result, an original slice service of the node may be rendered unavailable during the upgrade. In response, the technique redirects replicated data targeted to the original slice service to a standby pool of slice services in accordance with a degraded redundant metadata service of the cluster. In the event the standby slice service itself subsequently becomes unavailable, another standby slice service from the standby pool is activated to receive the subsequent data. In this manner, cascading failure of secondary slice slices is handled.

公开(公告)号：US20200097374A1

公开(公告)日：2020-03-26

申请号：US16394642

申请日：2019-04-25

Applicant: NetApp, Inc.

Inventor： Christopher Cason

IPC: G06F11/14 ,  G06F16/18

Abstract: A technique is configured to log and update metadata in a log-structured file system to facilitate recovery and restart in response to failure of a storage node of a cluster. A block identifier (ID) is used to identify a block of data serviced by the storage node. Metadata embodied as mappings between block IDs and locations of data blocks in the cluster are illustratively maintained in “active” and “frozen” map fragments. An active map fragment refers to a map fragment that has space available to store a mapping, whereas a frozen map fragment refers to a map fragment that no available space for storing a mapping. The active map fragments are maintained in memory as “in-core” data structures, whereas the frozen map fragments are paged-out and stored on storage devices of the cluster as “on-disk” map fragment structures. Each frozen map fragment written to a segment includes a pointer to a last written frozen map fragment to form a chain (e.g., linked-list) of on-disk frozen map fragments. Each time a data block is persisted on a segment of the storage devices, an active map fragment is populated in-core and a metadata write marker is recorded on the segment (on-disk) indicating the location of the data block that was written to the segment. If a storage node crashes when the active map fragment is only partially populated, the metadata write markers facilitate rebuild of the active map fragment upon recovery and restart of a storage service of the node.