Abstract: An embodiment of a method of predicting response time for a storage request begins with a first step of a computing entity storing a training data set. The training data set comprises past performance observations for past storage requests of a storage array. Each past performance observation comprises an observed response time and a feature vector for a particular past storage request. The feature vector includes characteristics that are available external to the storage array. In a second step, the computing entity forms a response time forecaster from the training data set. In the third step, the computing entity applies the response time forecaster to a pending feature vector for a pending storage request to obtain a predicted response time for the pending storage request.

Abstract: An embodiment of a method of estimating overall storage system cost begins with a first step of modeling a storage system design in operation under a workload to determine location of retrieval points. The retrieval points provide sources for primary storage recovery for a plurality of failure scenarios. The method continues with a second step of finding a most recent retrieval point relative to a target recovery time that is available for recovery for a particular failure scenario. A third step determines a difference between the target recovery time and a retrieval point creation time for the most recent retrieval point, which indicates a data loss time period. A fourth step determines a recovery time for propagation of the most recent retrieval point to primary storage. In a fifth step, a storage system cost comprising outlay costs and penalty costs is determined.

Abstract: An embodiment of a method of estimating storage system reliability begins with a first step of modeling a storage system design in operation under a workload to determine location of retrieval points. The retrieval points provide sources for primary storage recovery for a plurality of failure scenarios. The method continues with a second step of finding a most recent retrieval point relative to a target recovery time that is available for recovery for a particular failure scenario. In a third step, a difference between the target recovery time and a retrieval point creation time for the most recent retrieval point is determined. The difference indicates a data loss time period.