Method and system for window-based churn handling in data cache

• US 10,496,290 B1
• Filed: 04/11/2017
• Issued: 12/03/2019
• Est. Priority Date: 04/11/2017
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: Visvanathan, Satish, Ugale, Rahul B.
• Primary Examiner(s): Yi, David
• Assistant Examiner(s): Goldschmidt, Craig S
• Application Number:
  US15/485,033
• Time in Patent Office: 966 Days
• Field of Search: None
• CPC Class Codes: G06F 11/1451 by selection of backup contents
• CPC Class Codes: G06F 12/0868 Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
• CPC Class Codes: G06F 12/0871 Allocation or management of cache space
• CPC Class Codes: G06F 12/0888 using selective caching, e.g. bypass
• CPC Class Codes: G06F 12/0891 using clearing, invalidating or resetting means
• CPC Class Codes: G06F 12/12 Replacement control
• CPC Class Codes: G06F 12/122 of the least frequently used [LFU] type, e.g. with individual count value
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/84 Using snapshots, i.e. a logical point-in-time copy of the data
• CPC Class Codes: G06F 2212/1024 Latency reduction
• CPC Class Codes: G06F 2212/1032 Reliability improvement, data loss prevention, degraded operation etc
• CPC Class Codes: G06F 2212/222 Non-volatile memory
• CPC Class Codes: G06F 2212/401 Compressed data
• CPC Class Codes: G06F 2212/463 File
• CPC Class Codes: G06F 2212/502 using adaptive policy
• CPC Class Codes: G06F 2212/60 Details of cache memory
• CPC Class Codes: G06F 2212/7205 Cleaning, compaction, garbage collection, erase control
• CPC Class Codes: G06F 2212/7211 Wear leveling
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0616 in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
• CPC Class Codes: G06F 3/0652 : Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket
• CPC Class Codes: G06F 3/0659 : Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0679 : Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]

Abstract

According to some embodiment, a backup storage system receives a request from a client for writing a data segment associated with a file object stored to a storage system. In response to the request, the system writes the data segment to one of a plurality of storage units of the storage system. The system determines whether an amount of access to a solid state device (SSD) operating as a cache memory device exceeds an access threshold based on a time window distribution. The system throttles access to the SSD for caching data in response to determining that the amount of access to the SSD has exceeded the access threshold.

Claims

1. A computer-implemented method for controlling access to a cache memory device, the method comprising:

receiving a request from a client for writing a data segment associated with a file object stored to a storage system;

in response to the request, writing the data segment to one of a plurality of storage units of the storage system;

determining, in the storage system, a hierarchy of file regions of the file object based on access frequency and access recency of the file regions of the file object, wherein a first portion of the hierarchy of file regions is designated as top hot file regions based on a first percentage;

calculating a miss rate of a solid state device (SSD) operating as a cache memory device based on a plurality of previous requests from the client;

automatically adjusting, based on the calculated miss rate of the SSD, the first percentage to a second percentage, the second percentage used to determine a second portion of the hierarchy of file regions as top hot file regions of the file object;

determining whether an amount of access to a solid state device (SSD) operating as a cache memory device exceeds an access threshold based on a time window distribution, wherein the access threshold is a desired average of writes per day (WPD) to the SSD over a predetermined period of time; and

throttling access to the SSD for caching data in response to determining that the amount of access to the SSD has exceeded the access threshold, including writing the data segment to the SSD in response to determining that the data segment is associated with a top hot file region in the second portion of the hierarchy of file regions, and discarding the data segment in response to determining that the data segment is not associated with a top hot file region in the second portion of the hierarchy of file regions.

2. The method of claim 1, wherein throttling access to the SSD for caching data comprises:

writing the data segment in a first of a plurality of write-evict units (WEUs) stored in the SSD for caching data in response to determining that the data segment is associated with the top hot file region.

3. The method of claim 1, wherein the time window distribution is a representation of a number of WPD associated with the SSD over the predetermined period of time.

4. The method of claim 1, wherein the access threshold is determined based on a ratio between a write bandwidth of the SSD and a capacity of the SSD.

5. The method of claim 4, wherein access to the SSD is effectively throttled such that a number of WPD for a particular day is less than or equal to the desired average of WPD.

6. The method of claim 1, wherein a write bandwidth of the SSD is determined based on the access threshold and a capacity of the SSD.

7. The method of claim 2, wherein the top hot file region is determined based on one or more histogram buckets corresponding to one or more file regions of the file object.

8. The method of claim 7, wherein each of the histogram buckets includes a timestamp and a type of access for a corresponding file region.

9. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for controlling access to a cache memory device, the operations comprising:

receiving a request from a client for writing a data segment associated with a file object stored to a storage system;

in response to the request, writing the data segment to one of a plurality of storage units of the storage system;

determining, in the storage system, a hierarchy of file regions of the file object based on access frequency and access recency of the file regions of the file object, wherein a first portion of the hierarchy of file regions is designated as top hot file regions based on a first percentage;

calculating a miss rate of a solid state device (SSD) operating as a cache memory device based on a plurality of previous requests from the client;

automatically adjusting, based on the calculated miss rate of the SSD, the first percentage to a second percentage, the second percentage used to determine a second portion of the hierarchy of file regions as top hot file regions of the file object;

determining whether an amount of access to a solid state device (SSD) operating as a cache memory device exceeds an access threshold based on a time window distribution, wherein the access threshold is a desired average of writes per day (WPD) to the SSD over a predetermined period of time; and

throttling access to the SSD for caching data in response to determining that the amount of access to the SSD has exceeded the access threshold, including writing the data segment to the SSD in response to determining that the data segment is associated with a top hot file region in the second portion of the hierarchy of file regions, and discarding the data segment in response to determining that the data segment is not associated with a top hot file region in the second portion of the hierarchy of file regions.

10. The non-transitory machine-readable medium of claim 9, wherein throttling access to the SSD for caching data comprises:

writing the data segment in a first of a plurality of write-evict units (WEUs) stored in the SSD for caching data in response to determining that the data segment is associated with the top hot file region.

11. The non-transitory machine-readable medium of claim 9, wherein the time window distribution is a representation of a number of WPD associated with the SSD over the predetermined period of time.

12. The non-transitory machine-readable medium of claim 9, wherein the access threshold is determined based on a ratio between a write bandwidth of the SSD and a capacity of the SSD.

13. The non-transitory machine-readable medium of claim 12, wherein access to the SSD is effectively throttled such that a number of WPD for a particular day is less than or equal to the desired average of WPD.

14. The non-transitory machine-readable medium of claim 9, wherein a write bandwidth of the SSD is determined based on the access threshold and a capacity of the SSD.

15. The non-transitory machine-readable medium of claim 10, wherein the top hot file region is determined based on one or more histogram buckets corresponding to one or more file regions of the file object.

16. The non-transitory machine-readable medium of claim 15, wherein each of the histogram buckets includes a timestamp and a type of access for a corresponding file region.

17. A data processing system, comprising:

a processor; and

a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations comprising;

receiving a request from a client for writing a data segment associated with a file object stored to a storage system;

in response to the request, writing the data segment to one of a plurality of storage units of the storage system;

determining, in the storage system, a hierarchy of file regions of the file object based on access frequency and access recency of the file regions of the file object, wherein a first portion of the hierarchy of file regions is designated as top hot file regions based on a first percentage;

calculating a miss rate of a solid state device (SSD) operating as a cache memory device based on a plurality of previous requests from the client;

automatically adjusting, based on the calculated miss rate of the SSD, the first percentage to a second percentage, the second percentage used to determine a second portion of the hierarchy of file regions as top hot file regions of the file object;

determining whether an amount of access to a solid state device (SSD) operating as a cache memory device exceeds an access threshold based on a time window distribution, wherein the access threshold is a desired average of writes per day (WPD) to the SSD over a predetermined period of time; and

throttling access to the SSD for caching data in response to determining that the amount of access to the SSD has exceeded the access threshold, including writing the data segment to the SSD in response to determining that the data segment is associated with a top hot file region in the second portion of the hierarchy of file regions, and discarding the data segment in response to determining that the data segment is not associated with a top hot file region in the second portion of the hierarchy of file regions.

18. The data processing system of claim 17, wherein throttling access to the SSD for caching data comprises:

writing the data segment in a first of a plurality of write-evict units (WEUs) stored in the SSD for caching data in response to determining that the data segment is associated with the top hot file region.

19. The data processing system of claim 17, wherein the time window distribution is a representation of a number of WPD associated with the SSD over the predetermined period of time.

20. The data processing system of claim 17, wherein the access threshold is determined based on a ratio between a write bandwidth of the SSD and a capacity of the SSD.

21. The data processing system of claim 18, wherein the top hot file region is determined based on one or more histogram buckets corresponding to one or more file regions of the file object.

22. The data processing system of claim 21, wherein each of the histogram buckets includes a timestamp and a type of access for a corresponding file region.