IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0529199
(2012-06-21)
|
등록번호 |
US-8516112
(2013-08-20)
|
발명자
/ 주소 |
- Moehler, Gregor
- Scherzinger, Stefanie
- Steinbach, Torsten
|
출원인 / 주소 |
- International Business Machines Corporation
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
3 인용 특허 :
3 |
초록
▼
A method, computer program product, and system for performance monitoring of a computer resource utilized by a user community. The computer resource is monitored, and sets of performance metrics characterizing a state of the computer resource are collected and analyzed to detect performance incident
A method, computer program product, and system for performance monitoring of a computer resource utilized by a user community. The computer resource is monitored, and sets of performance metrics characterizing a state of the computer resource are collected and analyzed to detect performance incidents. External information such as contextual information and user annotations are also collected and analyzed. If a performance incident is detected, its set of performance metrics and associated external information are used to search a data repository of past performance incidents for related incidents, in order to identify critical performance incidents, determine recommended solutions for the performance incidents, and determine performance forecasts for the computer resource.
대표청구항
▼
1. A computer-implemented method for performance monitoring of a computer resource in a computer system utilized by a user community, comprising: collecting a first set of performance metrics that characterize a state of a computer resource in a computer system utilized by a user community;receiving
1. A computer-implemented method for performance monitoring of a computer resource in a computer system utilized by a user community, comprising: collecting a first set of performance metrics that characterize a state of a computer resource in a computer system utilized by a user community;receiving first external information related to the first set of performance metrics from a source other than the computer resource, wherein the first external information comprises one or both of contextual information and user-provided annotation information;designating the first set of performance metrics as representing a first performance incident;storing a first incident record for the first performance incident in a data repository comprising a plurality of stored incident records stored therein, wherein the first incident record comprises the first set of performance metrics and the first external information, and wherein each stored incident record in the plurality comprises a stored set of performance metrics that characterize a past state of the computer resource and represent a past performance incident, and stored external information related to the past performance incident;searching the data repository using both the first performance metrics and the first external information to identify stored incident records that are related to the first performance incident, by determining the similarity of the first set of performance metrics to the stored sets of performance metrics and to the stored external information, and determining the similarity of the first external information to the stored sets of performance metrics and to the stored external information, wherein if a stored set of performance metrics is similar to the first set of performance metrics or the first external information, or if stored external information is similar to the first set of performance metrics or the first external information, then the stored incident record comprising the similar performance metrics or similar external information is identified as a related incident record; andif any of the plurality of stored incident records are identified as related to the first incident record, communicating an alert to at least one member of the user community. 2. The method of claim 1, wherein: said receiving first external information further comprises receiving at least some of the first external information in an unstructured format and converting the unstructured format into a structured format to produce structured first external information; andsaid storing further comprises storing the structured first external information in the first incident record. 3. The method of claim 2, wherein the first external information is user-provided annotation information received from at least one member of the user community. 4. The method of claim 1, wherein said receiving first external information further comprises receiving contextual information from a data feed, and wherein the source other than the computer resource is a feed source. 5. The method of claim 1, wherein similarity is determined using a distance metric. 6. The method of claim 1, further comprising: receiving a user designation of one or more performance metrics in the first set of performance metrics as key metrics, wherein the key metrics are assigned a higher weight in the determination of similarity than the performance metrics that have not been designated. 7. The method of claim 1, wherein said designation of the first set of performance metrics as representing the first performance incident is a user designation received from a user. 8. The method of claim 1, wherein said designation of the first set of performance metrics as representing the first performance incident is an automatically generated designation based on pre-determined incident criteria. 9. The method of claim 1, wherein, for one or more of the related stored incident records, the external information comprises user-provided annotation information related to a solution of the past performance incident, the method further comprising: determining, using the user-provided annotation information related to the solution of the past performance incident, one or both of a performance forecast for the first performance incident and a recommended solution for the first performance incident; andcommunicating the performance forecast, if it was determined, and the recommended solution, if it was determined, to at least one member of the user community. 10. The method of claim 1, wherein said collection of the first set of performance metrics comprises deriving at least some of the performance metrics from measurable metrics of the computer resource. 11. The method of claim 1, further comprising: communicating the related stored incident records to at least one member of the user community. 12. The method of claim 1, wherein the computer resource is a database system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.