Metering computing power in memory subsystems
A scanner is used to generate a set of processing power consumption metrics for a memory subsystem. From the set of processing power consumption metrics, a number of in-memory computations is determined. From the number of in-memory computations, a total computing score is determined. A user is notified of the total computing score.
1. A system for metering computing power, comprising:
a scanner configured to discover and monitor one or more data processing units to obtain information related to a number of in-memory computations performed over a period of time, and at least one processing power consumption metric;
a central server configured to receive from the scanner the number of in-memory computations and the at least one processing power consumption metric, and to determine a total computing score for the time period based upon the received information from the scanner; and
a processor configured to generate a consumption report for the one or more data processing units, the consumption report including the computed total computing score, the consumption report indicative of a total amount of computing resources consumed by the one or more data processing units.
2. The system of claim 1 wherein the central server is configured to receive additional information related to resource consumption of the one or more data processing units.
3. The system of claim 1 wherein the scanner is configured to poll via an application programming interface (API) the one or more data processing units.
4. The system of claim 1 wherein the scanner is local to a hypervisor associated with the one or more data processing units.
5. The system of claim 1 wherein the number of in-memory computations includes processing occurring in the memory system without communication with a central processing unit.
6. A method for metering computing power, comprising:
discovering, by a scanner, one or more data processing units
monitoring, by the scanner, the one or more data processing units;
obtaining information related to a number of in-memory computations performed over a period of time, and at least one processing power consumption metric;
receiving from the scanner at a central server the number of in-memory computations and the at least one processing power consumption metric,
determining, by the central server, a total computing score for the time period based upon the information received from the scanner; and
generating, by a processor, a consumption report for the one or more data processing units, the consumption report including the computed total computing score, the consumption report indicative of a total amount of computing resources consumed by the one or more data processing units.
7. The method of claim 6 further comprising:
receiving, by the central server, additional information related to resource consumption of the one or more data processing units.
8. The method of claim 6 further comprising:
polling, by the scanner via an application programming interface (API), the one or more data processing units.
9. The method of claim 6 wherein the scanner is local to a hypervisor associated with the one or more data processing units.
10. The method of claim 6 wherein the number of in-memory computations includes processing occurring in the memory system without communication with a central processing unit.