Optimized storage device sizing through customer workload analysis

A system, comprising:

• a memory;
• and
• at least one processor that is operatively coupled to the memory, the at least one processor being configured to perform the operations of:
• retrieving telemetry data that is reported by a plurality of onboard controllers, each onboard controller being part of a different one of a plurality of first SSDs, each onboard controller being configured to perform wear leveling or garbage collection of the first SSD of which the onboard controller is part;
• detecting whether the telemetry data satisfies a condition that evaluates whether the plurality of first SSDs are subjected to wear that would cause a predetermined SSD type to fail before an end of a given period;
• generating, based on whether the condition is satisfied, a recommendation regarding a usage of the predetermined SSD type in a storage system configuration, wherein, when the condition is satisfied, the recommendation provides that the predetermined SSD type is prohibited from being used in the storage system configuration, and when the condition is not satisfied, the recommendation provides that the predetermined SSD type is allowed to be used in the storage system configuration, and
• generating the storage system configuration based on the recommendation, wherein the storage system configuration identifies second SSDs to be included in a second storage system that is being defined, such that the second SSDs belong to the predetermined SSD type if and only if the recommendation indicates that the predetermined SSD type is allowed to be used in the storage system configuration,
• wherein the telemetry data includes a plurality of frames, each of the plurality of frames includes at least two different types of telemetry data, each of the plurality of frames includes telemetry data that is reported by at least two different first SSDs, and detecting whether the condition is satisfied includes evaluating a machine learning model based on the plurality of frames to calculate a composite metric and comparing the composite metric to a threshold.

A non-transitory computer readable medium storing one or more processor-executable instructions, which when executed by at least one processor, cause the at least one processor to perform the operations of:

• retrieving telemetry data that is reported by a plurality of onboard controllers, each onboard controller being part of a different one of a plurality of first SSDs, each onboard controller being configured to perform wear leveling or garbage collection of the first SSD of which the onboard controller is part;
• detecting whether the telemetry data satisfies a condition that evaluates whether the plurality of first SSDs are subjected to wear that would cause a predetermined SSD type to fail before an end of a given period;
• generating, based on whether the condition is satisfied, a recommendation regarding a usage of the predetermined SSD type in a storage system configuration, wherein, when the condition is satisfied, the recommendation provides that the predetermined SSD type is prohibited from being used in the storage system configuration, and when the condition is not satisfied, the recommendation provides that the predetermined SSD type is allowed to be used in the storage system configuration, and
• generating the storage system configuration based on the recommendation, wherein the storage system configuration identifies second SSDs to be included in a second storage system that is being defined, such that the second SSDs belong to the predetermined SSD type if and only if the recommendation indicates that the predetermined SSD type is allowed to be used in the storage system configuration,
• wherein the telemetry data includes a plurality of frames, each of the plurality of frames includes at least two different types of telemetry data, each of the plurality of frames includes telemetry data that is reported by at least two different first SSDs, and detecting whether the condition is satisfied includes evaluating a machine learning model based on the plurality of frames to calculate a composite metric and comparing the composite metric to a threshold.