Evaluation for rebuilding performance of redundant arrays of independent disks
Embodiments of the present disclosure provide a solution of evaluating a rebuilding performance of a redundant array of independent disks. In some embodiments, there is provided a computer-implemented method, comprising: simulating, based on a first group of redundant arrays of independent disks, a rebuilding process for a second group of redundant arrays of independent disks; obtaining a first performance metric of the simulated rebuilding process; and identifying a factor associated with the rebuilding performance of the second group of redundant arrays of independent disks based on the first performance metric.
1. A computer-implemented method, comprising:
simulating, based on a first group of redundant arrays of independent disks (RAID), a rebuilding process for a second group of redundant arrays of independent disks, wherein the first group and the second group of redundant arrays of independent disks each include, respectively, a plurality of sub-RAID groups (sub-RGs);
obtaining a first performance metric, of a plurality of performance metrics, of the simulated rebuilding process, wherein during the simulated rebuilding process, a pre-reading operation is directed to at least one of a respective group of redundant arrays of independent disks and a respective sub-RAID group of the plurality of sub-RAID groups; and
identifying, based on the first performance metric, a factor associated with rebuilding performance of the second group of redundant arrays of independent disks.
2. The method according to claim 1 , wherein the first group of redundant arrays of independent disks includes a group of conventional redundant arrays of independent disks, and the second group of redundant arrays of independent disks includes a group of mapped redundant arrays of independent disks.
3. The method according to claim 1 , wherein simulating the rebuilding process for the second group of redundant arrays of independent disks comprises:
disabling a disk in the first group of redundant arrays of independent disks and disabling rebuilding of the first group of redundant arrays of independent disks;
initiating, via an input output generator, a read request for data in the disabled disk concurrently, such that a read IO load is identical to a simulated mapped redundant array of independent disks; and
in response to receiving the requested data, writing the requested data concurrently into a spare disk via the input output generator such that a written IO load is identical to the simulated mapped redundant arrays of independent disks.
4. The method according to claim 3 , wherein the input output generator includes a common input output generator or a private input output generator.
5. The method according to claim 3 , wherein the input output generator is used for initiating at least one of a read request and a write request for at least one of the following: a volume, a logic unit number, a group of redundant arrays of independent disks, and a disk.
6. The method according to claim 1 , wherein simulating the rebuilding process for the second group of redundant arrays of independent disks comprises:
disabling a plurality of disks in one or more first groups of redundant arrays of independent disks;
disabling rebuilding of the one or more first groups of redundant arrays of independent disks;
initiating, via a plurality of input output generators, a plurality of read requests for a plurality of data in the plurality of disabled disks concurrently; and
in response to receiving the requested plurality of data, writing the requested plurality of data concurrently into one or more spare disks via the plurality of input output generators.
7. The method according to claim 6 , further comprising:
re-simulating the rebuilding process for the second group of redundant arrays of independent disks by changing at least one of the following: the number of the plurality of input output generators, and the number of the one or more spare disks.
8. The method according to claim 1 , wherein obtaining the first performance metric of the simulated rebuilding process comprises:
obtaining at least one of the following performance metrics of the simulated rebuilding process: rebuilding rate, usage of a central processing unit, and usage of memory.
9. The method according to claim 7 , wherein obtaining the first performance metric of the simulated rebuilding process comprises:
obtaining a second performance metric of the re-simulated rebuilding process.
10. The method according to claim 9 , wherein identifying the factor comprises:
identifying the factor associated with the rebuilding performance of the second group of redundant arrays of independent disks by comparing the first and second performance metrics.
11. An electronic device, comprising:
at least one processing unit; and
at least one memory coupled to the at least one processing unit with instructions being stored thereon, the instructions, when executed by the at least one processing unit, performing actions including:
simulating, based on a first group of redundant arrays of independent disks (RAID), a rebuilding process for a second group of redundant arrays of independent disks, wherein the first group and the second group of redundant arrays of independent disks each include, respectively, a plurality of sub-RAID groups (sub-RGs);
obtaining a first performance metric, of a plurality of performance metrics, of the simulated rebuilding process, wherein during the simulated rebuilding process, a pre-reading operation is directed to at least one of a respective group of redundant arrays of independent disks and a respective sub-RAID group of the plurality of sub-RAID groups configuration; and
identifying, based on the first performance metric, a factor associated with rebuilding performance of the second group of redundant arrays of independent disks.
12. The device according to claim 11 , wherein the first group of redundant arrays of independent disks includes a group of conventional redundant arrays of independent disks, and the second group of redundant arrays of independent disks includes a group of mapped redundant arrays of independent disks.
13. The device according to claim 11 , wherein simulating the rebuilding process for the second group of redundant arrays of independent disks comprises:
disabling a disk in the first group of redundant arrays of independent disks and disabling rebuilding of the first group of redundant arrays of independent disks;
initiating, via an input output generator, a read request for data in the disabled disk concurrently, such that a read TO load is identical to a simulated mapped redundant array of independent disks; and
in response to receiving the requested data, writing the requested data concurrently into a spare disk via the input output generator such that a written TO load is identical to the simulated mapped redundant arrays of independent disks.
14. The device according to claim 13 , wherein the input output generator includes a common input output generator or a private input output generator.
15. The device according to claim 13 , wherein the input output generator is used for initiating at least one of a read request and a write request for at least one of the following: a volume, a logic unit number, a group of redundant arrays of independent disks, and a disk.
16. The device according to claim 11 , wherein simulating the rebuilding process for the second group of redundant arrays of independent disks further comprises:
disabling a plurality of disks in one or more first groups of redundant arrays of independent disks, and disabling rebuilding of the one or more first groups of redundant arrays of independent disks;
initiating, via a plurality of input output generators, a plurality of read requests for a plurality of data in the plurality of disabled disks concurrently; and
in response to receiving the requested plurality of data, writing the requested plurality of data concurrently into one or more spare disks via the plurality of input output generators.
17. The device according to claim 16 , wherein the actions further include:
re-simulating the rebuilding process for the second group of redundant arrays of independent disks by changing at least one of the following: the number of the plurality of input output generators, and the number of the one or more spare disks.
18. The device according to claim 11 , wherein obtaining the first performance metric of the simulated rebuilding process comprises:
obtaining at least one of the following performance metrics of the simulated rebuilding process: rebuilding rate, usage of a central processing unit, and usage of memory.
19. The device according to claim 17 , wherein obtaining the first performance metric of the simulated rebuilding process comprises:
obtaining a second performance metric of the re-simulated rebuilding process.
20. The device according to claim 19 , wherein identifying the factor comprises:
identifying the factor associated with the rebuilding performance of the second group of redundant arrays of independent disks by comparing the first and second performance metrics.