Battery learn cycle management
In one aspect, an example methodology implementing the disclosed techniques includes, by a disk controller of a plurality of disks of a data storage system, collecting usage telemetry from the plurality of disks and initiating determination of one or more candidate time slots for performing a battery learn cycle using a machine learning model. The machine learning model is trained using the usage telemetry from the plurality of disks. The method also includes, by the disk controller, presenting one or more of the one or more candidate time slots for performing a battery learn cycle.
1. A computer implemented method to determine candidate time slots for performing a battery learn cycle, the method comprising:
collecting, by a disk controller of a plurality of disks of a data storage system, disk usage telemetry from the plurality of disks;
initiating, by the disk controller, prediction of one or more candidate time slots for performing a battery learn cycle using a machine learning model, wherein the machine learning model is trained using the disk usage telemetry from the plurality of disks;
presenting, by the disk controller, one or more of the one or more candidate time slots for performing a battery learn cycle; and
performing the battery learn cycle according to the one or more candidate time slots.
2. The method of claim 1 , wherein the collection of the disk usage telemetry is from a time the disk controller is installed.
3. The method of claim 1 , wherein the collection of the disk usage telemetry is from a time a firmware of the disk controller is updated.
4. The method of claim 1 , wherein the disk usage telemetry includes percentage (%) idle time information.
5. The method of claim 4 , wherein the % idle time information is an average % idle time across the plurality of disks.
6. The method of claim 1 , wherein the machine learning model is a time series machine learning model.
7. The method of claim 1 , wherein the presented one or more of the one or more candidate time slots include time slots prior to a due date for performing an automatic battery learn cycle.
8. The method of claim 1 , wherein the presented one or more of the one or more candidate time slots include time slots subsequent to a due date for performing an automatic battery learn cycle.
9. The method of claim 1 , wherein the presented one or more of the one or more candidate time slots include time slots subsequent to a reminder date for performing a battery learn cycle.
10. The method of claim 1 , wherein the prediction of the one or more candidate time slots for performing a battery learn cycle using the machine learning model is based on an estimation of a time needed to perform the battery learn cycle.
11. A system comprising:
one or more non-transitory machine-readable mediums configured to store instructions; and
one or more processors configured to execute the instructions stored on the one or more non-transitory machine-readable mediums, wherein execution of the instructions causes the one or more processors to,
collect disk usage telemetry from a plurality of disks of a data storage system;
initiate prediction of one or more candidate time slots for performing a battery learn cycle by use of a machine learning model, wherein the machine learning model is trained using the disk usage telemetry from the plurality of disks;
present one or more of the one or more candidate time slots for performing a battery learn cycle;
perform the battery learn cycle according to the one or more candidate time slots.
12. The system of claim 11 , wherein to collect the disk usage telemetry is from a time the disk controller is installed or a firmware of the disk controller is updated.
13. The system of claim 11 , wherein the disk usage telemetry includes percentage (%) idle time across the plurality of disks.
14. The system of claim 11 , wherein the machine learning model is a time series machine learning model.
15. The system of claim 11 , wherein the one or more of the one or more candidate time slots include time slots prior to a due date for performing an automatic battery learn cycle.
16. The system of claim 11 , wherein the one or more of the one or more candidate time slots include time slots subsequent to a due date for performing an automatic battery learn cycle.
17. The system of claim 11 , wherein the one or more of the one or more candidate time slots include time slots subsequent to a reminder date for performing a battery learn cycle.
18. The system of claim 11 , wherein the determination-prediction of the one or more candidate time slots for performing a battery learn cycle by use of the machine learning model is based on an estimation of a time to perform the battery learn cycle.
19. The system of claim 11 , wherein the plurality of disks includes a redundant array of inexpensive disks (RAID).
20. A computer program product including one or more non-transitory machine-readable mediums encoding instructions that when executed by one or more processors cause a process to be carried out to determine candidate time slots for performing a battery learn cycle, the process comprising:
collecting disk idle time telemetry from a plurality of disks of a data storage system;
initiating prediction of one or more candidate time slots for performing a battery learn cycle using a machine learning model, wherein the machine learning model is trained using the disk idle time telemetry from the plurality of disks;
presenting one or more of the one or more candidate time slots for performing a battery learn cycle;
performing the battery learn cycle according to the one or more candidate time slots.