MODELING WORKLOAD INFORMATION FOR A PRIMARY STORAGE AND A SECONDARY STORAGE

• US 20150277762A1
• Filed: 03/27/2014
• Published: 10/01/2015
• Est. Priority Date: 03/27/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Guo, Yong, Xu, Yan, Li, Jun Tao
• Granted Patent: US 9,304,689 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays

Abstract

Provided are a computer program product, system, and method for modeling workload information for a primary storage and a secondary storage. A determination is made of: a first type and second type of Input/Output (I/O) operations with respect to extents configured in the primary storage; a cumulative I/O workload for the primary storage based on a first type and a second type of I/O operations at different cumulative storage amounts of the primary storage indicating a concentration of the I/O workload on the primary storage; and cumulative I/O workload for the secondary storage based on the first type and the second type of I/O operations at different storage amounts indicating a concentration of the I/O workload of the first type of I/O operations on the secondary storage. A performance gap is determined based on the cumulative I/O workloads for the primary and secondary storages at one of the storage amounts.

Claims

1. A computer program product for generating storage information on a storage environment having a primary storage and a secondary storage, the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that when executed performs operations, the operations comprising:

determining a first type and second type of Input/Output (I/O) operations with respect to extents configured in the primary storage;

determining cumulative I/O workload for the primary storage based on the first type and the second type of I/O operations at different cumulative storage amounts of the primary storage indicating a concentration of the I/O workload on the primary storage, wherein the primary storage includes multiple storage tiers;

determining cumulative I/O workload for the secondary storage based on the first and second types of I/O operations at different storage amounts indicating a concentration of the I/O workload on the secondary storage, wherein the secondary storage includes multiple storage tiers;

determining a performance gap based on the cumulative I/O workloads for the primary and secondary storages at one of the storage amounts; and

generating information on the determined performance gap.

2. The computer program product of claim 1, wherein the first type of I/O operation comprises a write operation and the second type of I/O operation comprises a read operation, and wherein writes to the primary storage are written to the secondary storage.

3. The computer program product of claim 1, wherein there are at least two storage tiers, a first storage tier comprising a higher performance tier than a second storage tier, wherein the operations further comprise:

using the information on the determined performance gap to determine an amount of the first storage tier to add to the secondary storage to maintain performance in an event that read and write operations at the primary storage are redirected to the secondary storage due to a failure of the primary storage.

4. The computer program product of claim 1, wherein generating the information comprises generating in a computer renderable file a chart having a first line showing the cumulative I/O workload for the primary storage for different cumulative amounts of storage at the primary storage and having a second line showing the I/O cumulative workload for the secondary storage for different cumulative amounts of storage at the secondary storage, wherein gaps between the first line and the second line at different storage amounts indicates performance gaps for those storage amount if the I/O workload of the primary storage were transferred to the secondary storages.

5. The computer program product of claim 4, wherein the chart rendered in the computer renderable file shows that the cumulative I/O workload for the primary storage are higher than the cumulative I/O workload for the secondary storage at different storage cumulative exceeding a specified storage amount at which the cumulative I/O workloads for the primary and secondary storages are substantially similar.

6. The computer program product of claim 1, wherein the operations further comprise:

determining a primary extent activity ranking for extents in the primary storage based on the I/O activity of the first and second types of I/O operations with respect to the extents in the primary storage, wherein the I/O workload percentages are based on I/O operations to extents ordered in the primary extent activity ranking from a highest activity ranking to a lowest activity ranking; and

determining a secondary extent activity ranking for extents in the secondary storage based on the I/O activity of only the first type of I/O operation with respect to the extents in the primary storage, wherein the I/O workload percentages are based on I/O operations to extents ordered in the secondary extent activity ranking from a highest activity ranking to a lowest activity ranking.

7. The computer program product of claim 6, wherein the primary extent activity ranking of extents differs from the secondary extent activity ranking of extents resulting in different cumulative I/O workload for the cumulative storage amounts for the primary and secondary storages.

8. The computer program product of claim 6, wherein the operations further comprise:

assigning extents in the primary storage to storage tiers based on the primary extent activity ranking, wherein higher ranked extents are stored on relatively higher performing storage tiers; and

assigning extents in the secondary storage to storage tiers based on the secondary extent activity ranking, wherein higher ranked extents are stored on relatively higher performing storage tiers.

9. A system for generating storage information on a storage environment having a primary storage and a secondary storage, comprising:

a processor; and

a computer readable storage medium having computer readable program code embodied therein that when executed by the processor performs operations, the operations comprising;

determining a first type and second type of Input/Output (I/O) operations with respect to extents configured in the primary storage;

determining cumulative I/O workload for the primary storage based on the first type and the second type of I/O operations at different cumulative storage amounts of the primary storage indicating a concentration of the I/O workload on the primary storage, wherein the primary storage includes multiple storage tiers;

determining cumulative I/O workload for the secondary storage based on the first type and second type of I/O operations at different storage amounts indicating a concentration of the I/O workload on the secondary storage, wherein the secondary storage includes multiple storage tiers;

determining a performance gap based on the cumulative I/O workloads for the primary and secondary storages at one of the storage amounts; and

generating information on the determined performance gap.

10. The system of claim 9, wherein the first type of I/O operation comprises a write operation and the second type of I/O operation comprises a read operation, and wherein writes to the primary storage are written to the secondary storage.

11. The system of claim 9, wherein there are at least two storage tiers, a first storage tier comprising a higher performance tier than a second storage tier, wherein the operations further comprise:

using the information on the determined performance gap to determine an amount of the first storage tier to add to the secondary storage to maintain performance in an event that read and write operations at the primary storage are redirected to the secondary storage due to a failure of the primary storage.

12. The system of claim 9, wherein generating the information comprises generating in a computer renderable file a chart having a first line showing the cumulative I/O workload for the primary storage for different cumulative amounts of storage at the primary storage and having a second line showing the I/O cumulative workload for the secondary storage for different cumulative amounts of storage at the secondary storage, wherein gaps between the first line and the second line at different storage amounts indicates performance gaps for those storage amount if the I/O workload of the primary storage were transferred to the secondary storages.

13. The system of claim 12, wherein the chart rendered in the computer renderable file shows that the cumulative I/O workload for the primary storage are higher than the cumulative I/O workload for the secondary storage at different storage cumulative exceeding a specified storage amount at which the cumulative I/O workloads for the primary and secondary storages are substantially similar.

14. The system of claim 9, wherein the operations further comprise:

determining a primary extent activity ranking for extents in the primary storage based on the I/O activity of the first and second types of I/O operations with respect to the extents in the primary storage, wherein the I/O workload percentages are based on I/O operations to extents ordered in the primary extent activity ranking from a highest activity ranking to a lowest activity ranking; and

determining a secondary extent activity ranking for extents in the secondary storage based on the I/O activity of only the first type of I/O operation with respect to the extents in the primary storage, wherein the I/O workload percentages are based on I/O operations to extents ordered in the secondary extent activity ranking from a highest activity ranking to a lowest activity ranking.

15. A method for generating storage information on a storage environment having a primary storage and a secondary storage, comprising:

determining a first type and second type of Input/Output (I/O) operations with respect to extents configured in the primary storage;

determining cumulative I/O workload for the primary storage based on the first type and the second type of I/O operations at different cumulative storage amounts of the primary storage indicating a concentration of the I/O workload on the primary storage, wherein the primary storage includes multiple storage tiers;

determining cumulative I/O workload for the secondary storage based on the first type and the second type of I/O operations at different storage amounts indicating a concentration of the I/O workload on the secondary storage, wherein the secondary storage includes multiple storage tiers;

determining a performance gap based on the cumulative I/O workloads for the primary and secondary storages at one of the storage amounts; and

generating information on the determined performance gap.

16. The method of claim 15, wherein the first type of I/O operation comprises a write operation and the second type of I/O operation comprises a read operation, and wherein writes to the primary storage are written to the secondary storage.

17. The method of claim 15, wherein there are at least two storage tiers, a first storage tier comprising a higher performance tier than a second storage tier, further comprising:

using the information on the determined performance gap to determine an amount of the first storage tier to add to the secondary storage to maintain performance in an event that read and write operations at the primary storage are redirected to the secondary storage due to a failure of the primary storage.

18. The method of claim 15, wherein generating the information comprises generating in a computer renderable file a chart having a first line showing the cumulative I/O workload for the primary storage for different cumulative amounts of storage at the primary storage and having a second line showing the I/O cumulative workload for the secondary storage for different cumulative amounts of storage at the secondary storage, wherein gaps between the first line and the second line at different storage amounts indicates performance gaps for those storage amount if the I/O workload of the primary storage were transferred to the secondary storages.

19. The method of claim 18, wherein the chart rendered in the computer renderable file shows that the cumulative I/O workload for the primary storage are higher than the cumulative I/O workload for the secondary storage at different storage cumulative exceeding a specified storage amount at which the cumulative I/O workloads for the primary and secondary storages are substantially similar.

20. The method of claim 15, further comprising:

determining a primary activity ranking for extents in the primary storage based on the I/O activity of the first and second types of I/O operations with respect to the extents in the primary storage, wherein the I/O workload percentages are based on I/O operations to extents ordered in the primary extent activity ranking, from a highest activity ranking to a lowest activity ranking; and

determining a secondary activity ranking for extents in the secondary storage based on the I/O activity of only the first type of I/O operation with respect to the extents in the primary storage, wherein the I/O workload percentages are based on I/O operations to extents ordered according to the secondary extent activity ranking, from a highest activity ranking to a lowest activity ranking.