System and method for analyzing input/output activity on local attached storage

• US 20040024921A1
• Filed: 02/21/2003
• Published: 02/05/2004
• Est. Priority Date: 02/21/2002
• Status: Active Grant

• Current Assignee: Precise Software Solutions, Inc. (Idera, Inc.)
• Original Assignee: Precise Software Solutions, Inc. (Idera, Inc.)
• Inventors: Kyler, Daniel B., Peake, William Jr., McLaughlin, Colleen
• Granted Patent: US 7,275,097 B2
• Time in Patent Office: Days
• US Class Current: 710/1
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: Y10S 707/99931 Database or file accessing

Abstract

A system, method and computer program product for analyzing file I/O activity on local attached storage devices within a computer network is provided. In an embodiment, a software agent executes on one or more servers within the network, and monitors the I/O activity on the network'"'"'s local attached storage (e.g., SAN, NAS, and IDE and SCSI disks). A management interface is also provided for monitoring I/O activity-related data and for receiving reports on such I/O activity. In an embodiment, collected I/O-related data and any predefined I/O metrics are stored in a central repository (e.g., a relational database). The system, method and computer program product provide accurate metrics to assists system administrators in deciding, justifying and validating resource purchases for and allocations within the network.

Claims

1. A method for analyzing input/output (I/O) activity on local attached storage within a computer network, comprising the steps of:

storing a list of plurality of managed objects to be monitored within the network;

storing a plurality of thresholds, each corresponding to one of said plurality of managed objects, and each establishing a limit related to at least one I/O metric for each corresponding managed object;

storing a plurality of threshold actions, each corresponding to one of said plurality of thresholds;

collecting, for a pre-determined time interval, said at least one I/O metric for each of said plurality of managed objects;

determining, after said pre-determined time interval, whether any of said plurality of thresholds has been exceeded for any of said plurality of managed objects; and

causing the appropriate one of said plurality of threshold actions to be executed when the result of said determining step is positive.

2. The method of claim 1, wherein said at least one I/O metric collected for each of said plurality of managed objects is one of:

(i) a file I/O metric;

(ii) a physical disk read I/O metric;

(iii) a physical disk write I/O metric.

3. The method of claim 1, wherein said plurality of managed objects includes at least one of:

(i) a server;

(ii) a partition;

(iii) a directory;

(iv) a file;

(v) a process;

(vi) an end-user.

4. The method of claim 1, wherein the local attached storage is one of:

(i) a storage area network (SAN);

(ii) a network attached storage (NAS);

(iii) a Small Computer Interface System (SCSI) disk;

(iv) an Integrated Drive Electronics (IDE) disk.

5. The method of claim 1, further comprising the step of:

causing a report to be generated, when the result of said determining step is positive, wherein said report identifies which of said plurality of thresholds has been exceeded during said pre-determined time interval.

6. The method of claim 1, wherein said determining step comprises the steps of:

performing a calculation involving the value of said at least one I/O metric collected during said a pre-determined time interval for each of said plurality of managed objects; and

comparing the result of said calculation to a numerical limit value for each of said plurality of managed objects.

7. A method for providing an administrator with an analysis of input/output (I/O) activity on local attached storage within a computer network, comprising the steps of:

receiving a first input indicative of a managed object to be monitored within the network;

receiving a second input defining a threshold related to at least one I/O metric associated with said managed object;

receiving a third input indicative of a threshold action associated with said threshold;

collecting, for a pre-determined time interval, said at least one I/O metric;

determining, after said pre-determined time interval, whether said threshold has been exceeded; and

causing said threshold action to be executed when the result of said determining step is positive.

8. The method of claim 7, wherein said at least one I/O metric collected for said managed object is one of:

(i) a file I/O metric;

(ii) a physical disk read I/O metric;

(iii) a physical disk write I/O metric.

9. The method of claim 7, wherein said managed object is one of:

(i) a server;

(ii) a partition;

(iii) a directory;

(iv) a file;

(v) a process;

(vi) an end-user.

10. The method of claim 7, wherein the local attached storage is one of:

(i) a storage area network (SAN);

(ii) a network attached storage (NAS);

(iii) a Small Computer Interface System (SCSI) disk;

(iv) an Integrated Drive Electronics (IDE) disk.

11. The method of claim 7, further comprising the step of:

causing a report to be generated, when the result of said determining step is positive, wherein said report identifies said threshold, said managed object, and the value of said at least I/O metric collected during said pre-determined time interval.

12. The method of claim 7, wherein said second input includes a numerical limit value.

13. The method of claim 12, wherein said determining step comprises the steps of:

performing a calculation involving the value of said at least one I/O metric collected during said a pre-determined time interval; and

comparing the result of said calculation to said numerical limit value.

14. A system for analyzing input/output (I/O) activity on local attached storage within a computer network, comprising:

a repository for storing;

a list of plurality of managed objects to be monitored within the network;

a plurality of thresholds, each corresponding to one of said plurality of managed objects, and each establishing a limit related to at least one I/O metric for each corresponding managed object; and

a plurality of threshold actions, each corresponding to one of said plurality of thresholds;

a collector engine capable of collecting, for a pre-determined time interval, said at least one I/O metric for each of said plurality of managed objects; and

a service process capable of;

determining, after said pre-determined time interval, whether any of said plurality of thresholds has been exceeded for any of said plurality of managed objects; and

causing the appropriate one of said plurality of threshold actions to be executed when any of said plurality of thresholds has been exceeded.

15. The system of claim 14, wherein said at least one I/O metric collected for each of said plurality of managed objects is one of:

(i) a file I/O metric;

(ii) a physical disk read I/O metric;

(iii) a physical disk write I/O metric.

16. The system of claim 14, wherein said plurality of managed objects includes at least one of:

(i) a server;

(ii) a partition;

(iii) a directory;

(iv) a file;

(v) a process;

(vi) an end-user.

17. The system of claim 14, wherein the local attached storage is one of:

(i) a storage area network (SAN);

(ii) a network attached storage (NAS);

(iii) a Small Computer Interface System (SCSI) disk;

(iv) an Integrated Drive Electronics (IDE) disk.

18. The system of claim 14, further comprising:

a graphical user interface capable of displaying a report wherein said report identifies any of said plurality of thresholds which have been exceeded during said pre-determined time interval.

19. The system of claim 14, wherein said collector engine comprises a plurality of I/O filter drivers that layer on the local attached storage.

20. A computer program product comprising a computer usable medium having control logic stored therein for causing a computer to analyze input/output (I/O) activity on local attached storage within a network, said control logic comprising:

first computer readable program code means for causing the computer to store a list of plurality of managed objects to be monitored within the network;

second computer readable program code means for causing the computer to store a plurality of thresholds, each corresponding to one of said plurality of managed objects, and each establishing a limit related to at least one I/O metric for each corresponding managed object;

third computer readable program code means for causing the computer to store a plurality of threshold actions, each corresponding to one of said plurality of thresholds;

fourth computer readable program code means for causing the computer to collect, for a pre-determined time interval, said at least one I/O metric for each of said plurality of managed objects;

fifth computer readable program code means for causing the computer to determine, after said pre-determined time interval, whether any of said plurality of thresholds has been exceeded for any of said plurality of managed objects; and

sixth computer readable program code means for causing the computer to execute the appropriate one of said plurality of threshold actions when the result of said fifth computer readable program code means is positive.

21. The computer program product of claim 20, further comprising:

seventh computer readable program code means for causing the computer to generate a report, when the determination of said fifth computer readable program code means is positive, wherein said report identifies which of said plurality of thresholds has been exceeded during said pre-determined time interval.

22. The computer program product of claim 20, wherein said fifth computer readable program code means comprises:

seventh computer readable program code means for causing the computer to perform a calculation involving the value of said at least one I/O metric collected during said a pre-determined time interval for each of said plurality of managed objects; and

eighth computer readable program code means for causing the computer to compare the result of said calculation to a numerical limit value for each of said plurality of managed objects.