Apparatus and method for cache provisioning, configuration for optimal application performance

• US 10,656,839 B2
• Filed: 11/19/2018
• Issued: 05/19/2020
• Est. Priority Date: 03/17/2014
• Status: Active Grant

• Current Assignee: PrimaryIO, Inc.
• Original Assignee: PrimaryIO, Inc.
• Inventors: Nagaraj, Murali
• Primary Examiner(s): Birkhimer, Christopher D
• Application Number:
  US16/195,697
• Publication Number:
  US 20190087092A1
• Time in Patent Office: 547 Days
• CPC Class Codes: G06F 12/08 in hierarchically structured memory systems, e.g. virtual memory systems
• 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 2212/1024 Latency reduction
• CPC Class Codes: G06F 2212/261 Storage comprising a plurality of storage devices
• 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 3/0676 Magnetic disk device
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

In an embodiment of the invention, a method comprises: recording application-level heuristics and IO-level (input/output-level) heuristics; correlating and analyzing the application-level heuristics and IO-level heuristics; and based on an analysis and correlation of the application-level heuristics and IO-level heuristics, generating a policy for achieving optimal application performance. In another embodiment of the invention, an apparatus comprises: a system configured to record application-level heuristics and IO-level heuristics, to correlate and analyze the application-level heuristics and IO-level heuristics, and based on an analysis and correlation of the application-level heuristics and IO-level heuristics, to generate a policy for achieving optimal application performance.

Claims

1. A method, comprising:

monitoring an input/output (IO) stream between an application and at least one storage device with an IO monitor;

recording application-level heuristics that include information pertaining to a plurality of characteristics associated with the application;

recording IO-level heuristics in IO requests including information pertaining to a plurality of characteristics associated with the IO stream between the application and the at least one storage device;

correlating the recorded IO-level heuristics with the recorded application-level heuristics to determine at least one optimizable cache parameter for a performance increase corresponding to the IO stream;

generating a caching policy based on the at least one optimizable cache parameter;

selecting cache settings based on the caching policy; and

configuring a cache unit based on the selected cache settings.

2. The method of claim 1, wherein the at least one storage device includes either or both a hard disk drive (HDD) and a solid state device (SSD).

3. The method of claim 2, further comprising sending a portion of the IO stream designated as being important to the SSD.

4. The method of claim 2, further comprising sending a portion of the IO stream designated as being unimportant to the HDD.

5. The method of claim 1, further comprising generating an acceleration policy including the at least one optimizable cache parameter.

6. The method of claim 5, wherein the acceleration policy further includes either or both cache provisioning hints and an acceleration strategy.

7. The method of claim 1, wherein the characteristics associated with the stream are selected from a group consisting of the following:

shape/distribution;

burstiness;

distribution of the size;

predominance of reads/writes;

whether the 10 stream is sequential or random;

sizes and rates; and

whether the 10 stream is exhibiting a locality of reference or a great amount of randomness.

8. The method of claim 1, wherein the characteristics associated with the application include characteristics of at least one selected from the following group:

a database, an index, a collection, and a table.

9. The method of claim 1, wherein the at least one optimizable cache parameter is selected from the following group:

cache unit size;

cache capacity;

read cache size;

write cache size;

regions of the at least one storage device designated as being important; and

regions of the at least one storage device designated as being unimportant.

10. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1.

11. A system, comprising:

at least one storage device;

an input/output (IO) monitor configured to interact with an application, to collect information pertaining to a plurality of characteristics associated with the application, and to collect information pertaining to a plurality of characteristics associated with an IO stream between the application and the storage device;

an IO stream analyzer coupled with the IO monitor and configured to determine at least one optimizable cache parameter for a particular performance boost corresponding to the IO stream based on the plurality of characteristics associated with the application and the plurality of characteristics associated with the IO stream; and

a caching engine configured to interact with a storage stack to perform caching operations with the at least one storage device based on the at least one optimizable cache parameter determined by the IO stream analyzer.

12. The system of claim 11, wherein the at least one storage device includes either or both a hard disk drive (HDD) and a solid state device (SSD).

13. The system of claim 12, wherein the caching engine is further configured to direct the storage stack to send a portion of the IO stream designated as being important to the SSD.

14. The system of claim 12, wherein the caching engine is further configured to direct the storage stack to send a portion of the IO stream designated as being unimportant to the HDD.

15. The system of claim 11, wherein the IO stream analyzer is configured to generate an acceleration policy including the at least one optimizable cache parameter.

16. The system of claim 15, wherein the acceleration policy further includes either or both cache provisioning hints and an acceleration strategy.

17. The system of claim 11, wherein the characteristics associated with the IO stream are selected from a group consisting of the following:

shape/distribution;

burstiness;

distribution of the IO size;

predominance of reads/writes;

whether the IO stream is sequential or random;

sizes and rates; and

whether the IO stream is exhibiting a locality of reference or a great amount of randomness.

18. The system of claim 11, wherein the characteristics associated with the application include characteristics of at least one selected from the following group:

a database, an index, a collection, and a table.

19. The system of claim 11, wherein the at least one optimizable cache parameter is selected from the following group:

cache unit size;

cache capacity;

read cache size;

write cache size;

regions of the at least one storage device designated as being important; and

regions of the at least one storage device designated as being unimportant.

20. The system of claim 11, wherein the application is running on either a UNIX operating system or a Linux operating system.