Storage Systems with Peer Data Recovery

Patent metadata

Field	Value
Publication number	US-2020042390-A1
Application number	US-201816054989-A
Country	US
Kind code	A1
Filing date	Aug 3, 2018
Priority date	Aug 3, 2018
Publication date	Feb 6, 2020
Grant date	—

Abstract

Example peer storage systems, storage devices, and methods provide peer data recovery across a peer communication channel. Peer storage devices establish peer communication channels that communicate data among the peer storage devices. A storage device may identify storage media segments from their storage medium for recovery of failed data units. A peer storage device may be identified that contains recovery data for the failed data units. The recovery data may be received over the peer communication channel and the storage media segments may be recovered using the recovery data.

First claim

What is claimed is:

1 . A storage device, comprising:
a processor; a memory; at least one storage medium; an interface configured to communicate with a plurality of peer storage devices over a peer communication channel; and a self-healing module stored in the memory and executable by the processor to perform operations comprising:
identifying a first storage media segment from the at least one storage medium for recovery to a second storage media segment, wherein the first storage media segment includes a failed data unit;
identifying at least one peer storage device identifier for at least one peer storage device from the plurality of peer storage devices, wherein the at least one peer storage device contains recovery data for the failed data unit;
receiving the recovery data for the failed data unit from the at least one peer storage device over the peer communication channel; and
recovering the first storage media segment to the second storage media segment using the recovery data.

2 . The storage device of claim 1 , wherein the peer communication channel bypasses a storage control plane for managing the storage device.

3 . The storage device of claim 1 , further comprising:
a device error detector stored in the memory and executable by the processor to perform operations comprising:
detecting an unrecoverable error in the failed data unit stored on the at least one storage medium; and
initiating the self-healing module to identify the first storage media segment that includes the failed data unit in response to detecting the unrecoverable error.

4 . The storage device of claim 3 , wherein the device error detector is further executable by the processor to perform operations comprising:
detecting a failing media location from the at least one storage medium in response to exceeding an endurance threshold for the failing media location; and initiating the self-healing module to identify the first storage media segment, wherein the first storage media segment includes the failing media location and the failing media location includes the failed data unit.

5 . The storage device of claim 3 , wherein the device error detector is further executable by the processor to perform operations comprising:
identifying a storage media device from the at least one storage medium, wherein the storage media device includes a plurality of data units; and executing a media scan of the storage media device to detect errors in the plurality of data units, wherein the plurality of data units includes the failed data unit and the first storage media segment includes the storage media device.

6 . The storage device of claim 3 , wherein the device error detector is further executable by the processor to perform operations comprising:
identifying a logical data group from the at least one storage medium, wherein the logical data group includes a plurality of data units; and executing a media scan of the logical data group to detect errors in the plurality of data units, wherein the plurality of data units includes the failed data unit.

7 . The storage device of claim 1 , wherein:
the at least one peer storage device includes a peer parity storage device and the recovery data includes a parity data set for the failed data unit; and recovering the first storage media segment includes using the parity data set to calculate the failed data unit using an erasure coding engine.

8 . The storage device of claim 1 , wherein:
the at least one peer storage device includes a peer mirror storage device; the recovery data includes a duplicate data set for the failed data unit; and recovering the first storage media segment includes using the duplicate data set to write the failed data unit to the second storage media segment.

9 . The storage device of claim 1 , wherein the self-healing module is further executable by the processor to perform operations comprising:
sending a peer query to the at least one peer storage device over the peer communication channel using the at least one peer storage device identifier, wherein receiving the recovery data for the failed data unit is in response to the peer query.

10 . The storage device of claim 1 , wherein:
the second storage media segment is in a peer offload storage device selected from the plurality of peer storage devices; and recovering the first storage media segment to the second storage media segment includes a peer data transfer to the peer offload storage device over the peer communication channel.

11 . A computer-implemented method, comprising:
storing storage device identifiers for a plurality of peer storage devices in a first storage device; establishing a peer communication channel with at least one of the plurality of peer storage devices from the first storage device, wherein the peer communication channel bypasses a storage control plane for managing the first storage device; identifying a first storage media segment in the first storage device for recovery to a second storage media segment, wherein the first storage media segment includes a failed data unit; identifying at least one peer storage device identifier for at least one peer storage device from the plurality of peer storage devices, wherein the at least one peer storage device contains recovery data for the failed data unit and is not the first storage device; receiving the recovery data for the failed data unit from the at least one peer storage device over the peer communication channel; and recovering the first storage media segment to the second storage media segment using the recovery data.

12 . The computer-implemented method of claim 11 , further comprising:
detecting an unrecoverable error in the failed data unit stored in the first storage device, wherein identifying the first storage media segment is in response to detecting the unrecoverable error.

13 . The computer-implemented method of claim 11 , further comprising:
detecting a failing media location in the first storage device in response to exceeding an endurance threshold for the failing media location, wherein:
identifying the first storage media segment is in response to detecting the failing media location; and
the first storage media segment includes the failing media location and the failing media location includes the failed data unit.

14 . The computer-implemented method of claim 11 , further comprising:
executing a media scan of a storage media device in the first storage device to detect at least one media error, wherein:
the storage media device includes a plurality of data units;
the plurality of data units includes the failed data unit;
the at least one media error relates to the failed data unit;
the first storage media segment includes the storage media device; and
identifying the first storage media segment is in response to detecting the at least one media error in the media scan.

15 . The computer-implemented method of claim 11 , further comprising:
executing a media scan of a logical data group in the first storage device to detect at least one media error in at least one logical data unit, wherein:
the logical data group includes a plurality of logical data units;
the plurality of logical data units includes the failed data unit;
the at least one media error relates to the failed data unit; and
identifying the first storage media segment is in response to detecting the at least one media error in the media scan.

16 . The computer-implemented method of claim 11 , wherein:
the at least one peer storage device incl

Assignees

• Western Digital Tech Inc

Inventors

• Roberts Adam

Classifications

• G06F11/1076

  Parity data used in redundant arrays of independent storages, e.g. in RAID systems · CPC title

• G11C29/52 Primary

  Protection of memory contents; Detection of errors in memory contents · CPC title

• G11C2029/0411

  Online error correction · CPC title

• G06F11/1464

  for networked environments · CPC title

• G06F11/2094

  Redundant storage or storage space (G06F11/2056 takes precedence) · CPC title