Storage systems including a plurality of solid state drives and management methods thereof
Methods of operating storage systems that include a plurality of solid state drives, and the storage systems, are described. For example, a method may include, configuring the plurality of solid state drives into an erasure coding set for applying erasure coding, monitoring a reliability status of each of the plurality of solid state drives, selecting at least one solid state drive whose reliability status is lower than a reference value from among the plurality of solid state drives to exclude the at least one solid state drive from the erasure coding set, and constructing a replication set for applying data protection of a replication method by using the at least one solid state drive excluded from the erasure coding set.
1. A method of operating a storage system, the storage system including a plurality of solid state drives, and the method comprising:
configuring the plurality of solid state drives into an erasure coding set and applying erasure coding to the erasure coding set;
monitoring a reliability status of each of the plurality of solid state drives;
selecting, from among the plurality of solid state drives of the erasure coding set, at least one solid state drive having a reliability status that is lower than a threshold value, the reliability status being lower than the threshold value indicating that the at least one solid state drive has degraded reliability;
excluding the at least one solid state drive from the erasure coding set based on the reliability status of the at least one solid state drive being lower than the threshold value;
reconfiguring the erasure coding set by replacing the at least one solid state drive excluded from the erasure coding set with a different solid state drive;
constructing a replication set that includes the at least one solid state drive excluded from the erasure coding set and applying a replication method of data protection to the replication set, and
mapping the erasure coding set and the replication set into a valid stripe associated with the erasure coding and a replication stripe associated with the replication method, wherein the valid stripe comprises a first portion of the erasure coding set and a first portion of the replication set, and wherein the replication stripe comprises only a second portion of the replication set.
2. The method of claim 1 , wherein the reliability status of each of the plurality of solid state drives corresponds to a respective read latency of each of the plurality of solid state drives.
3. The method of claim 1 , wherein the reliability status of each of the plurality of solid state drives corresponds to a respective number of read failures of each of the plurality of solid state drives.
4. The method of claim 1 , wherein the constructing of the replication set is performed subsequently to a number of solid state drives that are excluded from the erasure coding set reaching a predetermined number.
5. The method of claim 4 , wherein the constructing the replication set comprises:
storing original data in a memory unit of a first solid state drive of the replication set, and storing copy data of the original data in a memory unit of a second solid state drive of the replication set.
6. The method of claim 1 , wherein the different solid state drive is taken from an over-provisioning area.
7. The method of claim 1 , wherein the different solid state drive is taken from a different erasure coding set.
8. A storage system, comprising:
a plurality of solid state drives; and
a system controller configured to group the plurality of solid state drives in sets and apply data protection to the sets, the sets including a first set in which an erasure coding method is applied to the solid state drives of the first set, and a second set in which a replication method is applied to the solid state drives of the second set,
wherein the system controller is configured to monitor a reliability status of each of the plurality of solid state drives, and is configured to select at least one of the solid state drives of the first set having a reliability status that is lower than a reference value, exclude the selected at least one solid state drive from the first set, and allocate the selected at least one solid state drive to the second set,
wherein the system controller is further configured to reconfigure the erasure coding set by replacing the at least one solid state drive excluded from the erasure coding set with a different solid state drive,
wherein the reliability status of the selected at least one solid state drive of the first set being lower than the reference value indicates that the selected at least one solid state drive has degraded reliability, and
wherein the system controller comprises a mapper configured to map the first set and the second set into a valid stripe associated with the erasure coding method and a replication stripe associated with the replication method, wherein the valid stripe comprises a first portion of the first set and a first portion of the second set, and wherein the replication stripe comprises only a second portion of the second set.
9. The storage system of claim 8 , wherein the system controller is configured to detect a respective read latency of each of the plurality of solid state drives as part of being configured to monitor the reliability status.
10. The storage system of claim 8 , wherein the system controller is configured to detect a respective number of read failures of each of the plurality of solid state drives as part of being configured to monitor the reliability status.
11. The storage system of claim 8 , wherein the system controller comprises:
a device status monitor configured to monitor the reliability status of each of the plurality of solid state drives.
12. The storage system of claim 11 , wherein the system controller comprises:
an erasure coding engine configured to perform the erasure coding method on at least one solid state drive mapped to the first set; and
a replication engine configured to perform the replication method on at least one solid state drive mapped to the second set.
13. The storage system of claim 12 , wherein the system controller comprises a network interface card configured to communicate with an external network.
14. A method of operating a storage system comprising:
configuring a plurality of solid state drives into a first set and applying an erasure coding data protection policy to the first set, the erasure coding data protection policy applied as a default data protection policy;
monitoring a reliability status of each of the plurality of solid state drives of the first set;
selecting, from among the plurality of solid state drives of the first set, at least one solid state drive having a reliability status that is lower than a threshold value, and excluding the selected at least one solid state drive from the first set, wherein the reliability status of the at least one solid state drive of the first set being lower than the threshold value indicates that the at least one solid state drive has degraded reliability;
reconfiguring the erasure coding set by replacing the at least one solid state drive excluded from the first set with a different solid state drive;
configuring a second set that includes the selected at least one solid state drive excluded from the first set and applying a replication data protection policy to the second set; and
mapping the first set and the second set into a valid stripe associated with the erasure coding data protection policy and a replication stripe associated with the replication data protection policy, wherein the valid stripe comprises a first portion of the first set and a first portion of the second set, and wherein the replication stripe comprises only a second portion of the second set.
15. The method of claim 14 , wherein the reliability status of each of the plurality of solid state drives corresponds to a respective read latency of each of the plurality of solid state drives.
16. The method of claim 14 , wherein the reliability status of each of the plurality of solid state drives corresponds to a respective number of read failures of each of the plurality of solid state drives.