Determination of storage configuration for enterprise distributed environment
A method comprises collecting data from a computing environment comprising one or more storage devices, wherein the data comprises information identifying assignments of the one or more storage devices to one or more servers in the computing environment. In the method, the data is analyzed using one or more machine learning algorithms, wherein the analyzing comprises predicting whether a given configuration of the one or more storage devices in combination with the one or more servers is a specified configuration. The method also includes generating a storage configuration recommendation for a user based on the analysis, and transmitting the storage configuration recommendation to the user.
1. A method, comprising:
collecting data from a computing environment comprising one or more storage devices, wherein the data comprises information identifying assignments of the one or more storage devices to one or more servers in the computing environment;
analyzing the data using one or more machine learning algorithms, wherein the analyzing comprises predicting whether a given configuration of the one or more storage devices in combination with the one or more servers is a specified configuration;
generating a storage configuration recommendation for a user based on the analysis;
transmitting the storage configuration recommendation to the user;
training one or more machine learning models used in connection with generating storage device and server configurations with training data, wherein the training data comprises a plurality of specified storage configurations and system state data corresponding to one or more alerts generated in connection with operation of the one or more storage devices and the one or more servers; and
retraining the one or more machine learning models with additional training data comprising a determination of whether the given configuration is the specified configuration;
wherein predicting whether the given configuration is the specified configuration comprises:
determining whether the given configuration one of meets and exceeds a probability threshold corresponding to the specified configuration;
identifying at least one change to the given configuration; and
re-determining whether the given configuration one of meets and exceeds the probability threshold based on the at least one change, wherein the at least one change comprises a removal of the one or more storage devices from the computing environment; and
wherein the steps of the method are executed by a processing device operatively coupled to a memory.
2. The method of claim 1 , wherein:
the one or more machine learning algorithms utilize a probabilistic machine learning classifier; and
predicting whether the given configuration is the specified configuration comprises inputting the data to the probabilistic machine learning classifier to determine and re-determine whether the given configuration one of meets and exceeds the probability threshold.
3. The method of claim 2 , wherein the probabilistic machine learning classifier comprises a Naïve Bayes classifier.
4. The method of claim 1 , wherein the data further comprises one or more runtime workload patterns of the one or more servers.
5. The method of claim 4 , wherein the generating of the storage configuration recommendation comprises recommending one or more storage device types to correspond with the one or more runtime workload patterns of the one or more servers.
6. The method of claim 5 , wherein the one or more runtime workload patterns comprise one of a sequential workload pattern and a random workload pattern.
7. The method of claim 1 , wherein the data further comprises at least one of serial attached small computer system interface controller data and storage controller data.
8. The method of claim 1 , wherein the data further comprises at least one of error data, warning data, activity log data and technical support ticket data.
9. The method of claim 8 , wherein the training data further comprises at least one of the error data, warning data, activity log data and technical support ticket data.
10. The method of claim 1 , wherein:
the data further comprises at least one of redundant array of independent disks (RAID) level data, sector size data and storage device type data; and
the method further comprises categorizing the one or more storage devices according to at least one of RAID level, sector size and storage device type.
11. The method of claim 1 , wherein the data is collected from a chassis management controller over a communication path between a chassis and the one or more servers.
12. The method of claim 1 , further comprising determining that the given configuration is not the specified configuration.
13. The method of claim 12 , further comprising generating an additional configuration of the one or more storage devices in combination with the one or more servers responsive to the determination that the given configuration is not the specified configuration, wherein the generation of the additional configuration is performed using the one or more machine learning models.
14. The method of claim 13 , further comprising using the one or more machine learning algorithms to predict whether the additional configuration is the specified configuration.
15. The method of claim 13 , further comprising dynamically updating the one or more machine learning models with at least one of error data, warning data, activity log data and technical support ticket data of the computing environment.
16. An apparatus comprising:
a processing device operatively coupled to a memory and configured to:
collect data from a computing environment comprising one or more storage devices, wherein the data comprises information identifying assignments of the one or more storage devices to one or more servers in the computing environment;
analyze the data using one or more machine learning algorithms, wherein the analyzing comprises predicting whether a given configuration of the one or more storage devices in combination with the one or more servers is a specified configuration;
generate a storage configuration recommendation for a user based on the analysis;
transmit the storage configuration recommendation to the user;
train one or more machine learning models used in connection with generating storage device and server configurations with training data, wherein the training data comprises a plurality of specified storage configurations and system state data corresponding to one or more alerts generated in connection with operation of the one or more storage devices and the one or more servers; and
retrain the one or more machine learning models with additional training data comprising a determination of whether the given configuration is the specified configuration;
wherein, in predicting whether the given configuration is the specified configuration, the processing device is configured to:
determine whether the given configuration one of meets and exceeds a probability threshold corresponding to the specified configuration;
identify at least one change to the given configuration; and
re-determine whether the given configuration one of meets and exceeds the probability threshold based on the at least one change, wherein the at least one change comprises a removal of the one or more storage devices from the computing environment.
17. The apparatus of claim 16 , wherein:
the one or more machine learning algorithms utilize a probabilistic machine learning classifier; and
in predicting whether the given configuration is the specified configuration, the processing device is configured to input the data to the probabilistic machine learning classifier to determine and re-determine whether the given configuration one of meets and exceeds the probability threshold.
18. The apparatus of claim 17 , wherein the processing device is further configured to:
determine that the given configuration is not the specified configuration; and
generate an additional configuration of the one or more storage devices in combination with the one or more servers responsive to the determination that the given configuration is not the specified configuration, wherein the generation of the additional configuration is performed using the one or more machine learning models.
19. An article of manufacture comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device to perform the steps of:
collecting data from a computing environment comprising one or more storage devices, wherein the data comprises information identifying assignments of the one or more storage devices to one or more servers in the computing environment;
analyzing the data using one or more machine learning algorithms, wherein the analyzing comprises predicting whether a given configuration of the one or more storage devices in combination with the one or more servers is a specified configuration;
generating a storage configuration recommendation for a user based on the analysis;
transmitting the storage configuration recommendation to the user;
training one or more machine learning models used in connection with generating storage device and server configurations with training data, wherein the training data comprises a plurality of specified storage configurations and system state data corresponding to one or more alerts generated in connection with operation of the one or more storage devices and the one or more servers; and
retraining the one or more machine learning models with additional training data comprising a determination of whether the given configuration is the specified configuration;
wherein, in predicting whether the given configuration is the specified configuration, the program code further causes said at least one processing device to perform the steps of:
determining whether the given configuration one of meets and exceeds a probability threshold corresponding to the specified configuration;
identifying at least one change to the given configuration; and
re-determining whether the given configuration one of meets and exceeds the probability threshold based on the at least one change, wherein the at least one change comprises a removal of the one or more storage devices from the computing environment.
20. The article of manufacture of claim 19 , wherein:
the one or more machine learning algorithms utilize a probabilistic machine learning classifier; and
in predicting whether the given configuration is the specified configuration, the program code further causes said at least one processing device to perform the step of inputting the data to the probabilistic machine learning classifier to determine and re-determine whether the given configuration one of meets and exceeds the probability threshold.