Data storage device for increasing lifetime and RAID system including the same
First Claim
Patent Images
1. A data storage device comprising:
- a nonvolatile memory arranged according to drives and stripes;
a buffer configured to store state information of each of the stripes; and
a memory controller comprising a redundant array of independent disks (RAID) controller configured to operate in a spare region mode and perform data recovery using garbage collection based on the state information,wherein the state information includes at least one of a first state indicating that none of the drives has malfunctioned, a second state indicating that a first drive among the drives has malfunctioned, and a third state indicating that data/parity stored in the first drive has been recovered,wherein upon detecting malfunction of the first drive, the RAID controller is further configured to change the state information from the first state to the second state, andwherein the RAID controller is further configured to recover the data/parity stored in the first drive to a spare region of the nonvolatile memory and change state information of a stripe among the stripes including the spare region from the second state to the third state, and to move the recovered data/parity while performing the garbage collection from the spare region to a predetermined drive, and change the state information of the stripe including the spare region from the third state to the first state.
1 Assignment
0 Petitions
Accused Products
Abstract
A data storage device includes a nonvolatile memory arranged in drives and stripes, a buffer storing state information for each of the stripes, and a memory controller including a redundant array of independent disks (RAID) controller that operates in a spare region mode and performs data recovery using garbage collection based on the state information. The state information includes a first state indicating that none of the drives has malfunctioned, a second state indicating one of the drives has malfunctioned, and a third state indicating that data/parity stored in a malfunctioning drive has been recovered.
18 Citations
15 Claims
-
1. A data storage device comprising:
-
a nonvolatile memory arranged according to drives and stripes; a buffer configured to store state information of each of the stripes; and a memory controller comprising a redundant array of independent disks (RAID) controller configured to operate in a spare region mode and perform data recovery using garbage collection based on the state information, wherein the state information includes at least one of a first state indicating that none of the drives has malfunctioned, a second state indicating that a first drive among the drives has malfunctioned, and a third state indicating that data/parity stored in the first drive has been recovered, wherein upon detecting malfunction of the first drive, the RAID controller is further configured to change the state information from the first state to the second state, and wherein the RAID controller is further configured to recover the data/parity stored in the first drive to a spare region of the nonvolatile memory and change state information of a stripe among the stripes including the spare region from the second state to the third state, and to move the recovered data/parity while performing the garbage collection from the spare region to a predetermined drive, and change the state information of the stripe including the spare region from the third state to the first state. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A redundant array of independent disks (RAID) system comprising:
-
a data storage device; and a host configured to communicate with the data storage device, wherein the data storage device comprises a nonvolatile memory arranged according to stripes and drives, a buffer configured to store state information of each of the stripes, and a memory controller comprising a redundant array of independent disks (RAID) controller configured to operate in a spare region mode and perform data recovery using garbage collection based on the state information, wherein the state information includes a first state indicating that none of the drives has malfunctioned, a second state indicating a first drive among the drives has malfunctioned, and a third state indicating that data/parity stored in the first drive has been recovered, and wherein upon receiving a request from the host directed to data stored in the first drive and state information for a stripe including the requested data indicates the second state, the data storage device is configured to perform an XOR operation on other data/parity in the stripe including the requested data to recover the requested data and output the recovered requested data to the host. - View Dependent Claims (9, 10, 11)
-
-
12. A method of operating a data storage device including a nonvolatile memory arranged according to stripes and drives, a buffer storing state information for each of the stripes, and a memory controller including a redundant array of independent disks (RAID) controller operating in a spare region mode and performing data recovery using garbage collection based on the state information, the method comprises:
-
setting the state information for each of the stripes to a first state indicating none of the drives has malfunctioned; upon determining that one drive among the drives has malfunctioned, changing the state information for each of the stripes from the first state to a second state indicating that a drive among the drives has malfunctioned; recovering data/parity of the one drive using spare regions distributed across other drives among the drives and changing the state information for each of the stripes from the second state to a third state indicating that the data/parity of the one drive has been recovered; and replacing the one drive with a replacement drive and designating regions of the replacement drive as new spare regions. - View Dependent Claims (13, 14, 15)
-
Specification