Classifying snapshot image processing

Patent metadata

Field	Value
Publication number	US-11416343-B2
Application number	US-202017071267-A
Country	US
Kind code	B2
Filing date	Oct 15, 2020
Priority date	Jul 31, 2019
Publication date	Aug 16, 2022
Grant date	Aug 16, 2022

Abstract

Systems, methods, and machine-storage medium for classifying snapshot image processing are described. The system receives read requests to read snapshot information. Each read request includes an offset identifying a storage location and a length. The snapshot information includes snapshots including a full snapshot and at least one incremental snapshot. The read requests include a first read request to read data from the snapshot information. The system generates a first plurality of read events including a second plurality of read events that are generated by processing the first read request. The second plurality of read events includes first and a second read events. The system identifies whether utilizing a cache optimizes the job based on the first plurality of read events.

First claim

The invention claimed is:

1. A system comprising:
at least one processor and memory having instructions executable by the at least one processor to cause the system to:
receive a plurality of read requests to read snapshot information, the plurality of read requests being received from a job that is repeatedly executed, each of the plurality of read requests including an offset and a length, the offset identifying a storage location, the length being added to the storage location to identify a range of one or more storage locations, the snapshot information including a plurality of snapshots including a full snapshot and at least one incremental snapshot of a production machine;
generate a count of one or more duplicate reads of data from the one or more storage locations based on the plurality of read requests; and
identify whether utilizing a cache optimizes the job based on the count of the one or more duplicate reads of data.

2. The system of claim 1 , wherein:
the offset identifies the storage location,
the one or more storage locations including at least one storage location,
the full snapshot is of the production machine,
the plurality of read requests include a first read request to read data from the snapshot information, and
the instructions are further executable by the at least one processor to cause the system to:
generate a first plurality of read events based on the plurality of read requests, the first plurality of read events including a second plurality of read events, the second plurality of read events being generated by processing the first read request, the second plurality of read events including at least two read events including a first read event and a second read event, the first read event corresponds to a reading a first portion of the data from a first snapshot of the plurality of snapshots, the second read event corresponds to reading a second portion of the data from a second snapshot of the plurality of snapshots, the first snapshot and the second snapshot being different snapshots;
identify duplicate read events based on the first plurality of read events; and
aggregate the duplicate read events to generate at least one count of aggregated duplicate read events for the plurality of snapshots, wherein identifying whether utilizing the cache optimizes the job based on the first plurality of read events includes identifying the cache optimizes the job based on the at least one count of aggregated duplicate read events for the plurality of snapshots.

3. The system of claim 2 , wherein the plurality of snapshots includes snapshots that respectively correspond to snapshot levels and snapshot level identifiers.

4. The system of claim 2 , wherein the at least one count of aggregated duplicate read events for the plurality of snapshots includes a count of aggregated duplicate read events for a base snapshot.

5. The system of claim 2 , wherein the at least one count of aggregated duplicate read events for the plurality of snapshots includes a count of aggregated duplicate read events for an incremental snapshot.

6. The system of claim 2 , wherein, to identify whether utilizing a cache optimizes the job based on the first plurality of read events, the instructions are further executable by the at least one processor to cause the system to:
compare a percentage of duplicate reads with a predetermined threshold.

7. The system of claim 6 , wherein, to compare the percentage of duplicate reads with the predetermined threshold, the instructions are further executable by the at least one processor to cause the system to:
utilize a bloom filter.

8. The system of claim 2 , wherein, to identify whether utilizing a cache optimizes the job based on the first plurality of read events, the instructions are further executable by the at least one processor to cause the system to:
compare a percentage of early reads with a predetermined threshold.

9. The system of claim 2 , wherein the first read request includes a first offset and a first length and wherein the first read event includes the first offset and a second length and wherein the second read event includes a third offset and a third length.

10. A method comprising:
receiving a plurality of read requests to read snapshot information, the plurality of read requests being received from a job that is repeatedly executed, each of the plurality of read requests including an offset and a length, the offset identifying a storage location, the length being added to the storage location to identify a range of one or more storage locations, the snapshot information including a plurality of snapshots including a full snapshot and at least one incremental snapshot of a production machine;
generating a count of one or more duplicate reads of data from the one or more storage locations based on the plurality of read requests; and
identifying whether utilizing a cache optimizes the job based on the count of the one or more duplicate reads of data.

11. The method of claim 10 , wherein:
the offset identifies the storage location,
the one or more storage locations including at least one storage location,
the full snapshot is of the production machine,
the plurality of read requests include a first read request to read data from the snapshot information, and
the method further comprises:
generating a first plurality of read events based on the plurality of read requests, the first plurality of read events including a second plurality of read events, the second plurality of read events being generated by processing the first read request, the second plurality of read events including at least two read events including a first read event and a second read event, the first read event corresponds to a reading a first portion of the data from a first snapshot of the plurality of snapshots, the second read event corresponds to reading a second portion of the data from a second snapshot of the plurality of snapshots, the first snapshot and the second snapshot being different snapshots;
identifying duplicate read events based on the first plurality of read events; and
aggregating the duplicate read events to generate at least one count of aggregated duplicate read events for the plurality of snapshots, wherein identifying whether utilizing the cache optimizes the job based on the first plurality of read events includes identifying the cache optimizes the job based on the at least one count of aggregated duplicate read events for the plurality of snapshots.

12. The method of claim 11 , wherein the plurality of snapshots includes snapshots that respectively correspond to snapshot levels and snapshot level identifiers.

13. The method of claim 11 , wherein the at least one count of aggregated duplicate read events for the plurality of snapshots includes a count of aggregated duplicate read events for a base snapshot.

14. The method of claim 11 , wherein the at least one count of aggregated duplicate read events for the plurality of snapshots includes a count of aggregated duplicate read events for an incremental snapshot.

15. The method of claim 11 , wherein identifying whether utilizing a cache optimizes the job based on the first plurality of read events includes comparing a percentage of duplicate reads with a predetermined threshold.

16. The method of claim 15 , wherein comparing the percentage of duplicate reads with the predetermined threshold includes utilizing a bloom filter.

17. The method of claim 11 , wherein identifying whether utilizing a cache optimizes the job based on the first plurality of re

Assignees

• Rubrik Inc

Inventors

• Joo Jonathan Youngha
• Gee Adam
• Jain Vivek Sanjay
• Lee Junyong

Classifications

• G06F11/301

  where the computing system is a virtual computing platform, e.g. logically partitioned systems (virtual machines G06F9/45533; logical partitioning of resources G06F9/5077) · CPC title

• G06F11/1451 Primary

  by selection of backup contents · CPC title

• G06F3/0614

  Improving the reliability of storage systems · CPC title

• G06F2201/84

  Using snapshots, i.e. a logical point-in-time copy of the data · CPC title

• G06F3/0656

  Data buffering arrangements · CPC title