Dynamic DASD data management and partitioning based on access frequency utilization and capacity

• US 6,324,620 B1
• Filed: 07/23/1998
• Issued: 11/27/2001
• Est. Priority Date: 07/23/1998
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Nelson, Glen Warren, Mullins, Timothy John, Christenson, Patrick James, Corrigan, Michael Joseph, Walk, Bruce Marshall, McDermott, Michael James, Crowley, Thomas Richard, Faunce, Michael Steven, VanDuine, Russell Paul
• Primary Examiner(s): Smith, Matthew
• Assistant Examiner(s): Speight, Jibreel
• Application Number:
  US09/121,449
• Time in Patent Office: 1,223 Days
• Field of Search: 707/205, 711/112, 711/122, 711/117, 375/341, 710/74, 712/37, 705/1
• US Class Current: 711/112
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0674 Disk device

Abstract

Method and apparatus for managing data on DASD units to improve system performance comprises monitoring portions of data on a plurality of DASD units to determine the times the data is accessed within a given time period, and characterizing accessed data portions of a DASD unit as HOT and COLD data. The DASD units are monitored to determine the number of times each unit is accessed within a time period to develop utilization factors reflective of the number of times the DASD unit is accessed during the time period. HOT and COLD data is moved between DASD units based on the utilization factors of the DASD units.

Claims

1. A method of managing data on DASD units to improve system performance comprising:

monitoring portions of data on a plurality of DASD units and determining the number of times that portions of data on the DASD units are accessed within a given time period;

characterizing frequently accessed data portions of a DASD unit as HOT data and characterizing less frequently accessed data portions of the DASD unit as COLD data;

monitoring the DASD units to determine the number of times each unit is accessed within a time period and assigning utilization factors to the DASD units which are reflective of the number of times each DASD unit is accessed during the time period;

moving HOT and COLD data between DASD units based on the utilization factors of the DASD units.

2. The method of claim 1 further comprising determining the capacities of DASD units and moving COLD data between DASD units based on said capacities.

3. The method of claim 2 further comprising moving COLD data to a DASD unit with available capacity.

4. The method of claim 1 further comprising moving HOT data to a DASD unit with a low utilization factor.

5. The method of claim 1 further comprising:

partitioning the DASD units to have HOT partitions and COLD partitions; and

moving HOT data to a HOT partition and COLD data to a COLD partition of a DASD unit.

6. The method of claim 5 further comprising:

determining an average utilization factor for the DASD units being monitored;

expanding the HOT partition of a DASD unit having a utilization factor below the average utilization factor by a utilization threshold amount.

7. The method of claim 6 further comprising reducing the HOT partition of a DASD unit having a utilization factor exceeding the average utilization factor by a utilization threshold amount.

8. The method of claim 5 wherein said HOT partition of a DASD unit is smaller than the COLD partition.

9. The method of claim 1 further comprising adjusting the utilization factors of the respective DASD units as the data is moved between the devices.

10. The method of claim 9 wherein the utilization factor of a DASD unit receiving data is increased.

11. The method of claim 9 wherein the utilization factor of a DASD unit sending data is decreased.

12. The method of claim 1 further comprising:

determining an average utilization factor for the DASD units being monitored;

if the utilization factor of a DASD unit exceeds the average utilization factor by an upper threshold amount, categorizing the DASD unit as highly utilized with a high utilization factor; and

if the utilization factor of a DASD unit is below the average utilization factor by a lower threshold amount, categorizing the DASD unit as under utilized with a low utilization factor.

13. The method of claim 1 further comprising:

determining an average frequency of access within the time period for portions of data;

characterizing a frequently accessed data portion of a DASD unit as HOT data if the frequency of access of the portion exceeds the average frequency of access by an upper frequency threshold; and

characterizing a less frequently accessed data portion of a DASD unit as COLD data if the frequency of access of the portion is below the average frequency of access by a lower frequency threshold.

14. The method of claim 1 further comprising, upon creation of data on a DASD, designating the data as one of HOT and COLD data.

15. A method of managing data on DASD units to improve system performance comprising:

monitoring portions of data on a DASD unit and determining the number of times that the portions of data on the DASD unit are accessed within a given time period;

characterizing frequently accessed data portions of a DASD unit as HOT data and characterizing less frequently accessed data portions of the DASD unit as COLD data;

partitioning the DASD unit to have a HOT partition and a COLD partition; and

on the DASD unit, moving HOT data to a HOT partition and COLD data to a COLD partition.

16. The method of claim 15 further comprising:

monitoring DASD units to determine the number of times each unit is accessed within a time period and assigning a utilization factor to a DASD unit which is reflective of the number of times the DASD unit is accessed during the time period;

determining an average utilization factor for the DASD units being monitored;

expanding the HOT partition of a DASD unit having a utilization factor below the average utilization factor by a utilization threshold amount.

17. The method of claim 16 further comprising reducing the HOT partition of a DASD unit having a utilization factor exceeding the average utilization factor by a utilization threshold amount.

18. The method of claim 16 further comprising forming the HOT partition of the DASD unit close to other HOT data on the DASD unit.

19. The method of claim 16 further comprising, upon creation of data on a DASD, designating the data as one of HOT and COLD data.

20. The method of claim 16 further comprising:

determining an average frequency of access within the time period for portions of data;

characterizing a frequently accessed data portion of a DASD unit as HOT data if the frequency of access of the portion exceeds the average frequency of access by an upper frequency threshold; and

characterizing a less frequently accessed data portion of a DASD unit as COLD data if the frequency of access of the portion is below the average frequency of access by a lower frequency threshold.

21. An apparatus for managing data on DASD units to improve system performance comprising:

a memory;

a program resident in memory and configured to characterize frequently accessed data portions of a DASD unit as HOT data and less frequently accessed data portions of the DASD unit as COLD data, the program further configured to assign utilization factors to the DASD units which are reflective of the number of times each DASD unit is accessed during a time period and to move HOT and COLD data between DASD units based on the utilization factors of the DASD units.

22. The apparatus of claim 21 wherein the program is further configured to determine the capacities of DASD units and to move COLD data between DASD units based on said capacities.

23. The apparatus of claim 22 wherein the program is further configured to move COLD data to a DASD unit with available capacity.

24. The apparatus of claim 21 wherein the program is further configured to move HOT data to a DASD unit with a low utilization factor.

25. The apparatus of claim 21 wherein the program is further configured to partition the DASD units to have HOT partitions and COLD partitions and to move HOT data to a HOT partition and COLD data to a COLD partition of a DASD unit.

26. The apparatus of claim 25 wherein the program is further configured to make said HOT partition of a DASD unit smaller than the COLD partition.

27. The apparatus of claim 21 wherein the program is further configured to determine an average utilization factor for the DASD units being monitored and to expand the HOT partition of a DASD unit having a utilization factor below the average utilization factor by a utilization threshold amount.

28. The apparatus of claim 21 wherein the program is further configured to reduce the HOT partition of a DASD unit having a utilization factor exceeding the average utilization factor by a utilization threshold amount.

29. The apparatus of claim 21 wherein the program is further configured to adjust the utilization factors of the respective DASD units as the data is moved between the devices.

30. The apparatus of claim 29 wherein the program is further configured to increase the utilization factor of a DASD unit receiving data.

31. The apparatus of claim 29 wherein the program is further configured to decrease the utilization factor of a DASD unit sending data.

32. The apparatus of claim 21 wherein the program is further configured to determine an average utilization factor for the DASD units being monitored, and if the utilization factor of a DASD unit exceeds the average utilization factor by an upper threshold amount, to categorize the DASD unit as highly utilized with a high utilization factor;

and

if the utilization factor of a DASD unit is below the average utilization factor by a lower threshold amount, to categorize the DASD unit as under utilized with a low utilization factor.

33. The apparatus of claim 21 wherein the program is further configured to determine an average frequency of access within the time period for portions of data and to characterize a frequently accessed data portion of a DASD unit as HOT data if the frequency of access of the portion exceeds the average frequency of access by an upper frequency threshold, and to characterize a less frequently accessed data portion of a DASD unit as COLD data if the frequency of access of the portion is below the average frequency of access by a lower frequency threshold.

34. The apparatus of claim 21 wherein the program is further configured, upon creation of data on a DASD, to designate the data as one of HOT and COLD data.

35. An apparatus for managing data on DASD units to improve system performance comprising:

a memory;

a program resident in memory and configured to characterize frequently accessed data portions of a DASD unit as HOT data and less frequently accessed data portions of the DASD unit as COLD data, the program further configured to partition the DASD unit to have a HOT partition and a COLD partition and, on the DASD unit, to move HOT data to a HOT partition and COLD data to a COLD partition.

36. The apparatus of claim 35 wherein the program is further configured to monitor DASD units for determining the number of times each unit is accessed within a time period and to assign a utilization factor to a DASD unit which is reflective of the number of times the DASD unit is accessed during the time period, the program further configured to determine an average utilization factor for the DASD units being monitored and to expand the HOT partition of a DASD unit having a utilization factor below the average utilization factor by a utilization threshold amount.

37. The apparatus of claim 36 wherein the program is further configured to reduce the HOT partition of a DASD unit having a utilization factor exceeding the average utilization factor by a utilization threshold amount.

38. The apparatus of claim 36 wherein the program is further configured to form the HOT partition of the DASD unit close to other HOT data on the DASD unit.

39. The apparatus of claim 36 wherein the program is further configured, upon creation of data on a DASD, to designate the data as one of HOT and COLD data.

40. The apparatus of claim 36 wherein the program is further configured to determine an average frequency of access within the time period for portions of data and to characterize a frequently accessed data portion of a DASD unit as HOT data if the frequency of access of the portion exceeds the average frequency of access by an upper frequency threshold, and to characterize a less frequently accessed data portion of a DASD unit as COLD data if the frequency of access of the portion is below the average frequency of access by a lower frequency threshold.

41. A program product for managing data on DASD units to improve system performance, the program product comprising:

a program configured to characterize frequently accessed data portions of a DASD unit as HOT data and less frequently accessed data portions of the DASD unit as COLD data, the program further configured to assign utilization factors to the DASD units which are reflective of the number of times each DASD unit is accessed during a time period and to move HOT and COLD data between DASD units based on the utilization factors of the DASD units;

a signal bearing media bearing the program.

42. The program product of claim 41 wherein the signal bearing media is a transmission media.

43. The program product of claim 41 wherein the signal bearing media is recordable media.

44. A program product for managing data on DASD units to improve system performance, the program product comprising:

a program configured to characterize frequently accessed data portions of a DASD unit as HOT data and less frequently accessed data portions of the DASD unit as COLD data, the program further configured to partition the DASD unit to have a HOT partition and a COLD partition and, on the DASD unit, to move HOT data to a HOT partition and COLD data to a COLD partition;

a signal bearing media bearing the program.

45. The program product of claim 44 wherein the signal bearing media is a transmission media.

46. The program product of claim 44 wherein the signal bearing media is recordable media.

47. A method of managing data on DASD units to improve system performance comprising:

monitoring portions of data on a plurality of DASD units for determining the number of times that the portions of data are accessed within a predetermined time period;

characterizing less frequently accessed data as COLD data;

monitoring the utilization of individual DASD units of a plurality of DASD units to determine under-utilized units and over-utilized units;

moving the COLD data to DASD units that are over-utilized.

48. The method of claim 47 wherein the COLD data being moved is from a DASD unit which is under-utilized.

49. The method of claim 47 wherein said less frequently accessed data has not been accessed within said predetermined time period.

50. The method of claim 47 wherein said monitoring includes counting the number of I/O operations for portions of data to determine the number of times that the data portions are accessed in the predetermined time period.