Computing estimated performance of a software application in a target system
First Claim
Patent Images
1. A method comprising:
- receiving, by one or more processors, user input regarding a target system on which a software application is to be deployed;
matching, by the one or more processors, a benchmark system from plural candidate benchmark systems to the target system, wherein the matching is based on comparing each of the candidate benchmark systems to the target system that includes at least one of;
comparing a processor type of each candidate benchmark system with a processor type of the target system;
comparing a processor speed of each candidate benchmark system with a processor speed of the target system;
comparing a number of CPUs per node of each candidate benchmark system with a number of CPUs per node of the target system; and
comparing a number of nodes of each candidate benchmark system with a number of nodes of the target system; and
computing, by the one or more processors, an estimated performance of the software application on the target system based on scaling of performance of the matched benchmark system to the target system, wherein computing the estimated performance of the software application on the target system is further based on an application complexity factor, wherein the application complexity factor is based on a relationship of at least one of workload complexity and source code efficiency of the software application to a benchmark software application.
1 Assignment
0 Petitions
Accused Products
Abstract
User input regarding a target system on which a software application is to be deployed is received. A benchmark system from plural candidate benchmark systems is matched to the target system. An estimated performance of the software application on the target system or an estimated utilization of resources of the target system by the software application is computed based on information relating to the matched benchmark system.
43 Citations
25 Claims
-
1. A method comprising:
-
receiving, by one or more processors, user input regarding a target system on which a software application is to be deployed; matching, by the one or more processors, a benchmark system from plural candidate benchmark systems to the target system, wherein the matching is based on comparing each of the candidate benchmark systems to the target system that includes at least one of; comparing a processor type of each candidate benchmark system with a processor type of the target system; comparing a processor speed of each candidate benchmark system with a processor speed of the target system; comparing a number of CPUs per node of each candidate benchmark system with a number of CPUs per node of the target system; and comparing a number of nodes of each candidate benchmark system with a number of nodes of the target system; and computing, by the one or more processors, an estimated performance of the software application on the target system based on scaling of performance of the matched benchmark system to the target system, wherein computing the estimated performance of the software application on the target system is further based on an application complexity factor, wherein the application complexity factor is based on a relationship of at least one of workload complexity and source code efficiency of the software application to a benchmark software application. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An article comprising at least one storage medium containing instructions that when executed cause a system to:
-
receive user input regarding a target system on which a software application is to be deployed; access a database containing information relating to plural candidate benchmark systems; select a benchmark system from the plural candidate benchmark systems, the selected benchmark system resembling the target system, wherein selecting the benchmark system is based on comparing each of the candidate benchmark systems to the target system that includes at least one of; comparing a processor type of each candidate benchmark system with a processor type of the target system; comparing a processor speed of each candidate benchmark system with a processor speed of the target system; comparing a number of CPUs per node of each candidate benchmark system with a number of CPUs per node of the target system; and comparing a number of nodes of each candidate benchmark system with a number of nodes of the target system; and compute an estimated performance of the software application on the target system based on scaling of performance of the selected benchmark system to the target system, wherein computing the estimated performance of the software application on the target system is further based on an application complexity factor, wherein the application complexity factor is based on a relationship of at least one of workload complexity and source code efficiency of the software application to a benchmark software application. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16, 17)
-
-
18. A system comprising:
-
a benchmark database containing information pertaining to plural candidate benchmark systems; and one or more processors configured to; receive user input regarding a target system on which a software application is to be deployed; select a benchmark system from among the plural benchmark systems in the benchmark database that most closely resembles the target system, wherein selecting the benchmark system is based on comparing each of the candidate benchmark systems to the target system that includes at least one of; comparing a processor type of each candidate benchmark system with a processor type of the target system; comparing a processor speed of each candidate benchmark system with a processor speed of the target system; comparing a number of CPUs per node of each candidate benchmark system with a number of CPUs per node of the target system; and comparing a number of nodes of each candidate benchmark system with a number of nodes of the target system; and calculate an estimated performance of the software application on the target system based on scaling performance of the selected benchmark system to the target system, wherein calculating the estimated performance of the software application on the target system is further based on an application complexity factor, wherein the application complexity factor is based on a relationship of at least one of workload complexity and source code efficiency of the software application to a benchmark software application. - View Dependent Claims (19, 20, 21, 22, 23, 24)
-
-
25. A method comprising:
-
receiving, by one or more processors, user input regarding a target system on which a first software application is to be deployed, wherein the target system is a shared system on which the first software application and at least another software application is executable; accessing, by the one or more processors, a database containing information relating to plural candidate benchmark systems; selecting, by the one or more processors, a benchmark system from the plural candidate benchmark systems by comparing each of the candidate benchmark systems to the target system that includes at least one of; comparing a processor type of each candidate benchmark system with a processor type of the target system; comparing a processor speed of each candidate benchmark system with a processor speed of the target system; comparing a number of CPUs per node of each candidate benchmark system with a number of CPUs per node of the target system; and comparing a number of nodes of each candidate benchmark system with a number of nodes of the target system; and computing an estimated performance of the first software application on the target system based on scaling of the performance of the selected benchmark system to the target system, wherein computing the estimated performance of the first software application on the target system is further based on an application complexity factor, wherein the application complexity factor is based on a relationship of at least one of workload complexity and source code efficiency of the first software application to a benchmark software application.
-
Specification