Back to results
US 2015/0317283 A1Published application
Correlation coefficient calculation method, computer-readable recording medium, and correlation coefficient calculation device
AssigneeFujitsu Limited
InventorsYasuhiko Kanemasa, Atsushi Kubota
Life of this patent
Estimating the term…
Abstract
A performance diagnostic server acquires time series data that indicates the number of executions per time from a multi-tier system and calculates, on the basis of the time series data, a correlation coefficient of processing types that are executed by a server in each tier. The performance diagnostic server calculates, from a correlation coefficient of processing types, a partial correlation coefficient by removing the effect of the trend of the entire multi tiers and updates the correlation coefficient of the processing types on the basis of the calculated partial correlation coefficient.
Claims12
A correlation coefficient calculation method executed by a computer, the correlation coefficient calculation method comprising:
- calculating time series data on the number of requests for processes in tiers in a system that is made up of multiple tiers and time series data on a total number of requests for each tier;
- calculating a first correlation coefficient of time series data on a first process in a first tier and time series data on a second process in a second tier;
- calculating a second correlation coefficient of time series data on a total number of requests in the first tier and the time series data on the first process;
- calculating a third correlation coefficient of time series data on the total number of requests in the first tier and time series data on a total number of requests in the second tier;
- calculating a fourth correlation coefficient of time series data on the total number of requests in the second tier and the time series data on the second process;
- calculating a fifth correlation coefficient of the time series data on the total number of requests in the first tier and the time series data on the second process;
- calculating a sixth correlation coefficient of the time series data on the total number of requests in the second tier and the time series data on the first process;
- calculating a sixth partial correlation coefficient by removing the effect of all requests in the first tier on the sixth correlation coefficient, using the second correlation coefficient and the third correlation coefficient;
- calculating a fourth partial correlation coefficient by removing the effect of all requests in the first tier on the fourth correlation coefficient, using the third correlation coefficient and the fifth correlation coefficient;
- calculating a first partial correlation coefficient by removing the effect of all requests in the first tier on the first correlation coefficient, using the second correlation coefficient and the fifth correlation coefficient;
- and
- calculating a correlation coefficient as a correlation coefficient of the first process and the second process, the correlation coefficient being obtained by removing the effect of all requests in the second tier on the first partial correlation coefficient, using the sixth partial correlation coefficient and the fourth partial correlation coefficient.
9 more elements
A non-transitory computer-readable recording medium having stored therein a correlation coefficient calculating program causing a computer to execute a process comprising:
- calculating time series data on the number of requests for processes in tiers in a system that is made up of multiple tiers and time series data on a total number of requests for each tier;
- calculating a first correlation coefficient of time series data on a first process in a first tier and time series data on a second process in a second tier;
- calculating a second correlation coefficient of time series data on a total number of requests in the first tier and the time series data on the first process;
- calculating a third correlation coefficient of time series data on the total number of requests in the first tier and time series data on a total number of requests in the second tier;
- calculating a fourth correlation coefficient of time series data on the total number of requests in the second tier and the time series data on the second process;
- calculating a fifth correlation coefficient of time series data on the total number of requests in the first tier and the time series data on the second process;
- calculating a sixth correlation coefficient of the time series data on the total number of requests in the second tier and the time series data on the first process;
- calculating a sixth partial correlation coefficient by removing the effect of all requests in the first tier on the sixth correlation coefficient, using the second correlation coefficient and the third correlation coefficient;
- calculating a fourth partial correlation coefficient by removing the effect of all requests in the first tier on the fourth correlation coefficient, using the third correlation coefficient and the fifth correlation coefficient;
- calculating a first partial correlation coefficient by removing the effect of all requests in the first tier on the first correlation coefficient, using the second correlation coefficient and the fifth correlation coefficient;
- and
- calculating a correlation coefficient as a correlation coefficient of the first process and the second process, the correlation coefficient being obtained by removing the effect of all requests in the second tier on the first partial correlation coefficient, using the sixth partial correlation coefficient and the fourth partial correlation coefficient.
9 more elements
A correlation coefficient calculation device comprising:
- a memory;
- and
- a processor coupled to the memory, wherein the processor executes a process comprising:
- calculating time series data on the number of requests for processes in tiers in a system that is made up of multiple tiers and time series data on a total number of requests for each tier;
- calculating a first correlation coefficient of time series data on a first process in a first tier and time series data on a second process in a second tier;
- calculating a second correlation coefficient of time series data on a total number of requests in the first tier and the time series data on the first process;
- calculating a third correlation coefficient of time series data on the total number of requests in the first tier and time series data on a total number of requests in the second tier;
- calculating a fourth correlation coefficient of time series data on the total number of requests in the second tier and the time series data on the second process;
- calculating a fifth correlation coefficient of the time series data on the total number of requests in the first tier and the time series data on the second process;
- calculating a sixth correlation coefficient of the time series data on the total number of requests in the second tier and the time series data on the first process;
- calculating a sixth partial correlation coefficient by removing the effect of all requests in the first tier on the sixth correlation coefficient, using the second correlation coefficient and the third correlation coefficient;
- calculating a fourth partial correlation coefficient by removing the effect of all requests in the first tier on the fourth correlation coefficient, using the third correlation coefficient and the fifth correlation coefficient;
- calculating a first partial correlation coefficient by removing the effect of all requests in the first tier on the first correlation coefficient, using the second correlation coefficient and the fifth correlation coefficient;
- and
- calculating a correlation coefficient as a correlation coefficient of the first process and the second process, the correlation coefficient being obtained by removing the effect of all requests in the second tier on the first partial correlation coefficient, using the sixth partial correlation coefficient and the fourth partial correlation coefficient.
12 more elements
Dependencies are inferred from the claim text.