Measuring data access activity

• US 8,566,483 B1
• Filed: 12/17/2009
• Issued: 10/22/2013
• Est. Priority Date: 12/17/2009
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Chen, Xiangping, Can, Khang, Madhukar, Manish, Harvey, David W., Throop, Dean D., Ku, Mark K.
• Primary Examiner(s): PORTKA, GARY J
• Application Number:
  US12/640,254
• Time in Patent Office: 1,405 Days
• Field of Search: None
• US Class Current: 710/18
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 2201/88 Monitoring involving counting
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

A method is used in measuring data access activity. I/O data is analyzed that describes I/O activity for a slice of a logical volume. Based on the I/O data, a first value of data access activity is determined for the slice corresponding to a first time period, and a second value of data access activity is determined corresponding to a second time period. From the first and second values, an exponential moving average of data access activity is derived for the slice.

Claims

1. A method for use in measuring data access activity in a data storage system, wherein the data storage system comprises data storage devices in a RAID group, the method comprising:

capturing I/O data describing I/O activity for slices in the RAID group, wherein the I/O data describes I/O response time for the slices in the RAID group;

based on the I/O data, determining a first value of data access activity for a first slice in the RAID group, wherein the first value of data access activity describes a first I/O response time corresponding to a first time period;

based on the I/O data, determining a first average I/O response time for the RAID group comprising the first slice, wherein the first average I/O response time corresponds to the first time period;

based on the first I/O response time and the first average I/O response time, determining a normalized first I/O response time;

based on the I/O data, determining a second value of data access activity for the first slice in the RAID group, wherein the second value of data access activity describes a second I/O response time corresponding to a second time period;

based on the I/O data, determining a second average I/O response time for the RAID group comprising the first slice, wherein the second average I/O response time corresponds to the second time period;

based on the second I/O response time and the second average I/O response time, determining a normalized second I/O response time; and

deriving, from the normalized first and second I/O response times, an exponential moving average of data access activity for the first slice.

2. The method of claim 1, further comprising:

using a policy engine to derive the exponential moving average.

3. The method of claim 1, wherein the exponential moving average is further derived from a smoothing factor.

4. The method of claim 1, wherein the exponential moving average is further derived from slice I/O raw statistics.

5. The method of claim 1, wherein how the exponential moving average is derived is based on a system I/O traffic pattern.

6. The method of claim 1, wherein the exponential moving average is derived from normalized total response time which is normalized based on performance capability.

7. The method of claim 1, wherein the exponential moving average is further derived from a variable sampling period.

8. A system for use in measuring data access activity in a data storage system, wherein the data storage system comprises data storage devices in a RAID group, the system comprising:

first logic capturing I/O data describing I/O activity for slices in the RAID group, wherein the I/O data describes I/O response times for the slices in the RAID group;

second logic determining, based on the I/O data, a first value of data access activity for a first slice in the RAID group, wherein the first value of data access activity describes a first I/O response time corresponding to a first time period;

third logic determining, based on the I/O data, a first average I/O response time for the RAID group comprising the first slice, wherein the first average I/O response time corresponds to the first time period;

fourth logic determining, based on the first I/O response time and the first average I/O response time, a normalized first I/O response time;

fifth logic determining, based on the I/O data, a second value of data access activity for the first slice in the RAID group, wherein the second value of data access activity describes a second I/O response time corresponding to a second time period;

sixth logic determining, based on the I/O data, a second average I/O response time for the RAID group comprising the first slice, wherein the second average I/O response time corresponds to the second time period;

seventh logic determining, based on the second I/O response time and the second average I/O response time, a normalized second I/O response time; and

eighth logic, from the normalized first and second I/O response times, an exponential moving average of data access activity for the first slice.

9. The system of claim 8, further comprising:

ninth logic using a policy engine to derive the exponential moving average.

10. The system of claim 8, wherein the exponential moving average is further derived from a smoothing factor.

11. The system of claim 8, wherein the exponential moving average is further derived from slice I/O raw statistics.

12. The system of claim 8, wherein how the exponential moving average is derived is based on a system I/O traffic pattern.

13. The system of claim 8, wherein the exponential moving average is derived from normalized total response time which is normalized based on performance capability.

14. The system of claim 8, wherein the exponential moving average is further derived from a variable sampling period.