Forwarding incoming IO to SCM namespaces

Patent metadata

Field	Value
Publication number	US-12259828-B2
Application number	US-202318528058-A
Country	US
Kind code	B2
Filing date	Dec 4, 2023
Priority date	May 27, 2021
Publication date	Mar 25, 2025
Grant date	Mar 25, 2025

Abstract

Techniques for intelligently routing IO to a storage class memory (SCM) namespace are disclosed. A configuration for a namespace is determined, where the configuration indicates a type of IO that the namespace is structured to handle. Details about the configuration of the namespace are stored in a repository. A forwarding rule is generated based on the namespace's stored configuration. When incoming IO having attributes similar to that type is received, implementation of the forwarding rule causes the incoming IO to be directed to the namespace. Attributes of a particular incoming IO are determined. As a result of the attributes satisfying a similarity threshold relative to the type, the forwarding rule is implemented such that the particular incoming IO is directed to the namespace.

First claim

What is claimed is:

1. A method for forwarding, in real-time, input/output (IO) to storage class memory (SCM) namespaces that are optimized to handle IO having different attributes, the method comprising:
determining, by a processor, namespace attributes for each SCM namespace included in a set of SCM namespaces;
storing, by the processor, the namespace attributes for each of the SCM namespaces in a database;
in response to receiving network IO from a remote source, selecting an SCM namespace that is a best fit for the network IO by comparing attributes of the network IO with the namespace attributes; and
redirecting, by the processor, the network IO to the selected SCM namespace.

2. The method of claim 1 , wherein the processor determines IO attributes for the network IO.

3. The method of claim 1 , wherein selecting the SCM namespace that is the best fit for the network IO is further performed based on a query to a database using the SCM namespace as a query parameter.

4. The method of claim 1 , wherein the SCM namespace supports a memory mode.

5. The method of claim 1 , wherein the SCM namespace supports a storage mode.

6. The method of claim 1 , wherein the SCM namespace supports an app-direct mode.

7. The method of claim 1 , wherein the selected SCM namespace is selected based on an identified workload pattern associated with a client application that provided the network IO.

8. The method of claim 1 , wherein the namespace attributes include a bandwidth for the SCM namespace.

9. The method of claim 1 , wherein the namespace attributes include a persistent memory input/output operations per second (IOPS) for the SCM namespace.

10. The method of claim 1 , wherein the namespace attributes include a latency for the SCM namespace.

11. A computer system that forwards, in real-time, input/output (IO) to storage class memory (SCM) namespaces that are optimized to handle IO having different attributes, the computer system comprising:
one or more processors; and
one or more hardware storage devices that store instructions that are executable by the one or more processors to cause the computer system to:
determine namespace attributes for each SCM namespace included in a set of SCM namespaces;
store the namespace attributes for each of the SCM namespaces in a database;
in response to receiving network IO from a remote source, select an SCM namespace that is a best fit for the network IO by comparing attributes of the network IO with the namespace attributes; and
redirect the network IO to the selected SCM namespace.

12. The computer system of claim 11 , wherein the namespace attributes include a bandwidth for the SCM namespace.

13. The computer system of claim 11 , wherein the attributes for the network IO are identified using a machine learning algorithm.

14. The computer system of claim 13 , wherein the machine learning algorithm is a Markov transition state machine learning algorithm.

15. The computer system of claim 11 , wherein the SCM namespace is associated with a first device node and a second SCM namespace is associated with a second device node, and wherein the first device node is mounted at a different file system location than a file system location where the second device node is mounted.

16. The computer system of claim 11 , wherein selecting the SCM namespace is based on client application behavior for a client application that transmitted the network IO.

17. The computer system of claim 11 , wherein the SCM namespace supports a memory mode or a storage mode.

18. The computer system of claim 11 , wherein the SCM namespace supports a memory mode, a storage mode, or an app-direct mode.

19. The computer system of claim 18 , wherein the SCM namespace supports all of the memory mode, the storage mode, and the app-direct mode.

20. One or more non-transitory hardware storage devices that store instructions that are executable by one or more processors to cause the one or more processors system to:
determine namespace attributes for each SCM namespace included in a set of SCM namespaces;
store the namespace attributes for each of the SCM namespaces in a database;
in response to receiving network IO from a remote source, select an SCM namespace that is a best fit for the network IO by comparing attributes of the network IO with the namespace attributes; and
redirect the network IO to the selected SCM namespace.

Assignees

• Emc Ip Holding Co Llc

Inventors

• Liu Bing
• Prasad Parmeshwr
• Vishwakarma Rahul Deo

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/245

  Query processing · CPC title

• G06F13/1668 Primary

  Details of memory controller · CPC title