System and method for prioritizing and preventing backup failures
Techniques described herein relate to a method for forecasting backup failures. Such techniques may include: obtaining data items associated with backup jobs; writing entries in a time series database, the entries comprising successful backup jobs and failed backup jobs; performing a first analysis to predict future failed backup jobs based on the entries in the time series database to obtain a future backup job failure predictions; performing a second analysis to determine a confidence prediction for each of the future backup job failure predictions; ranking the future backup job failure predictions based on the second analysis; performing a third analysis to determine at least one variable leading to each of the future backup job failure predictions; and sending results of the second analysis and the third analysis to an administrator of a data domain.
1. A method for forecasting backup failures, the method comprising:
obtaining a plurality of data items associated with a plurality of backup jobs;
writing a plurality of entries in a time series database, the plurality of entries comprising successful backup jobs and failed backup jobs;
performing a first analysis to predict a plurality of future backup job failures based on the plurality of entries in the time series database to obtain a plurality of future backup job failure predictions;
performing a second analysis to determine a confidence prediction for each of the predicted plurality of future backup job failures, wherein the second analysis comprises a transductive confidence machine analysis;
ranking the predicted plurality of future backup job failures based on the second analysis;
performing a third analysis to determine at least one variable leading to each of the predicted plurality of future backup job failures, wherein the third analysis comprises an exchangeability test; and
sending results of the second analysis and the third analysis to an administrator of a data domain.
2. The method of claim 1 , wherein a first portion of the plurality of data items is associated with a client device and a second portion of the plurality of data items is associated with a backup storage device of the data domain.
3. The method of claim 1 , wherein the plurality of entries in the time series database comprises a chronological series of entries for each of a series of backup jobs associated with a client device.
4. The method of claim 1 , wherein the failed backup jobs of the plurality of entries comprise information prior to a time window configured by administrator.
5. The method of claim 1 , wherein the first analysis comprises a nearest neighbor analysis.
6. The method of claim 1 , wherein the exchangeability test comprises an analysis using martingales.
7. The method of claim 6 , wherein, when the third analysis yields a result over a threshold, the at least one variable is selected.
8. The method of claim 1 , wherein the results comprise a client identifier, a job identifier, a ranking among predicted failures, and the at least one variable.
9. The method of claim 1 , wherein, in response to receiving the results, the administrator initiates a remedial action.
10. The method of claim 9 , wherein the remedial action prevents a future backup job failure before a failure occurs.
11. The method of claim 9 , wherein the remedial action comprises a set of actions to prevent a plurality of future backup job failures.
12. The method of claim 1 , further comprising displaying the results in a graphical user interface (GUI) to an administrator, wherein the GUI enables the administrator to select a first backup job of the plurality of backup jobs for which to perform a remedial action.
13. A non-transitory computer readable medium comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a method for forecasting backup failures, the method comprising:
obtaining a plurality of data items associated with a plurality of backup jobs;
writing a plurality of entries in a time series database, the plurality of entries comprising successful backup jobs and failed backup jobs;
performing a first analysis to predict a plurality of future backup job failures based on the plurality of entries in the time series database to obtain a plurality of future backup job failure predictions;
performing a second analysis to determine a confidence prediction for each of the predicted plurality of future backup job failures, wherein the second analysis comprises a transductive confidence machine analysis;
ranking the predicted plurality of future backup job failures based on the second analysis;
performing a third analysis to determine at least one variable leading to each of the predicted plurality of future backup job failures, wherein the third analysis comprises an exchangeability test; and
sending results of the second analysis and the third analysis to an administrator of a data domain.
14. The non-transitory computer readable medium of claim 13 , wherein a first portion of the plurality of data items is associated with a client device and a second portion of the plurality of data items is associated with a backup storage device of the data domain.
15. The non-transitory computer readable medium of claim 13 , wherein the plurality of entries in the time series database comprises a chronological series of entries for each of a series of backup jobs associated with a client device.
16. The non-transitory computer readable medium of claim 13 , wherein the first analysis comprises a nearest neighbor analysis.
17. The non-transitory computer readable medium of claim 13 , further comprising displaying the results in a graphical user interface (GUI) to an administrator, wherein the GUI enables the administrator to select a first backup job of the plurality of backup jobs for which to perform a remedial action.
18. A system for forecasting backup failures, the system comprising:
a plurality of client devices each comprising a processor, a memory, and a persistent storage device;
a plurality of storage devices; and
a data domain management controller operatively connected to the plurality of client devices and the plurality of storage devices, and configured to:
obtain a plurality of data items associated with a plurality of backup jobs;
write a plurality of entries in a time series database, the plurality of entries comprising successful backup jobs and failed backup jobs;
perform a first analysis to predict a plurality of future backup job failures based on the plurality of entries in the time series database to obtain a plurality of future backup job failure predictions;
perform a second analysis to determine a confidence prediction for each of the predicted plurality of future backup job failures, wherein the second analysis comprises a transductive confidence machine analysis;
rank the predicted plurality of future backup job failures based on the second analysis;
perform a third analysis to determine at least one variable leading to each of the predicted plurality of future backup job failures, wherein the third analysis comprises an exchangeability test; and
send results of the second analysis and the third analysis to an administrator of a data domain.