Autonomous I/O ingestion and data flushing among nodes in storage systems

Patent metadata

Field	Value
Publication number	US-12210755-B2
Application number	US-202318496283-A
Country	US
Kind code	B2
Filing date	Oct 27, 2023
Priority date	Jan 26, 2022
Publication date	Jan 28, 2025
Grant date	Jan 28, 2025

Abstract

Nodes in a storage system can autonomously ingest I/O requests and flush data to storage. First and second nodes determine a sequence separator, the sequence separator corresponding to an entry in a page descriptor ring that separates two flushing work sets (FWS). The first node receives an input/output (I/O) request and allocates a sequence identification (ID) number to the I/O request. The first node determines a FWS for the I/O request based on the sequence separator and the sequence ID number, and commits the I/O request using the sequence ID number. The I/O request and the sequence ID number are sent to the second node.

First claim

What is claimed is:

1. A method for nodes in a storage system to autonomously ingest I/O requests, the method comprising:
communicating, by a first node, with a second node to determine a sequence separator, the sequence separator corresponding to an entry in a page descriptor ring that separates two flushing work sets (FWS);
receiving, by the first node, an input/output (I/O) request;
allocating, by the first node, a sequence identification (ID) number to the I/O request;
determining, by the first node, a FWS for the I/O request based on the sequence separator and the sequence ID number;
committing, by the first node, the I/O request using the sequence ID number; and
sending, by the first node, the I/O request and the sequence ID number to the second node.

2. The method of claim 1 , further comprising:
causing, by the first node, the second node to determine another sequence separator that separates one of the two FWSs from a third FWS by adding a predetermined value to the sequence separator.

3. The method of claim 1 , further comprising:
causing, by the first node, the second node to compare the sequence ID number received from the first node to the sequence separator; and
causing, by the first node, the second node to identify an FWS for the I/O request based on the comparison.

4. The method of claim 3 , further comprising:
causing, by the first node, the second node to determine whether the sequence ID number has been allocated on the second node.

5. The method of claim 4 , further comprising:
if the sequence ID number has not been allocated on the second node, causing, by the first node, the second node to allocate the sequence ID number on the second node to the I/O request.

6. A storage system with nodes that autonomously ingest I/O requests, the system including a processor configured to:
communicate, by a first node, with a second node to determine a sequence separator, the sequence separator corresponding to an entry in a page descriptor ring that separates two flushing work sets (FWS);
receive, at the first node, an input/output (I/O) request;
allocate, at the first node, a sequence identification (ID) number to the I/O request;
determine, at the first node, a FWS for the I/O request based on the sequence separator and the sequence ID number;
commit, at the first node, the I/O request using the sequence ID number; and
send, by the first node, the I/O request and the sequence ID number to the second node.

7. The storage system of claim 6 , the processor further configured to:
cause, by the first node, the second node to determine another sequence separator that separates one of the two FWSs from a third FWS by adding a predetermined value to the sequence separator.

8. The storage system of claim 6 , the processor further configured to:
cause, by the first node, the second node to compare the sequence ID number received from the first node to the sequence separator; and
cause, by the first node, the second node to identify an FWS for the I/O request based on the comparison.

9. The storage system of claim 8 , the processor further configured to:
cause, by the first node, the second node to determine whether the sequence ID number has been allocated on the second node.

10. The storage system of claim 9 , the processor further configured to:
if the sequence ID number has not been allocated on the second node, cause, by the first node, the second node to allocate the sequence ID number on the second node to the I/O request.

11. A non-transitory processor-readable storage medium having stored thereon program code of one or more software programs for nodes in a storage system to autonomously ingest I/O requests, wherein the program code when executed by at least one processing device causes the at least one processing device to perform the following steps:
communicating, by a first node, with a second node to determine a sequence separator, the sequence separator corresponding to an entry in a page descriptor ring that separates two flushing work sets (FWS);
receiving, by the first node, an input/output (I/O) request;
allocating, by the first node, a sequence identification (ID) number to the I/O request;
determining, by the first node, a FWS for the I/O request based on the sequence separator and the sequence ID number;
committing, by the first node, the I/O request using the sequence ID number; and
sending, by the first node, the I/O request and the sequence ID number to the second node.

12. The non-transitory processor-readable storage medium of claim 11 , wherein the program code when executed by the at least one processing device causes the at least one processing device to perform the following additional steps:
determining, by the first node, another sequence separator that separates one of the two FWSs from a third FWS by adding a predetermined value to the sequence separator.

13. The non-transitory processor-readable storage medium of claim 12 , wherein the program code when executed by at least one processing device causes the at least one processing device to perform the following additional steps:
after committing the I/O request using the sequence ID number, decrementing, by the first node, the counter for pending I/O requests for the FWS.

14. The non-transitory processor-readable storage medium of claim 11 , wherein the program code when executed by at least one processing device causes the at least one processing device to perform the following additional steps:
causing, by the first node, the second node to determine another sequence separator that separates one of the two FWSs from a third FWS by adding a predetermined value to the sequence separator.

15. The non-transitory processor-readable storage medium of claim 11 , wherein the program code when executed by at least one processing device causes the at least one processing device to perform the following additional steps:
after determining the FWS for the I/O request, incrementing, by the first node, a counter for pending I/O requests for the FWS.

16. The non-transitory processor-readable storage medium of claim 11 , wherein the program code when executed by the at least one processing device causes the at least one processing device to perform the following additional steps:
comparing a counter for pending I/O requests for the FWS to zero (0); and
flushing data associated with the FWS to storage if the counter is equal to 0.

17. The non-transitory processor-readable storage medium of claim 11 , wherein the program code when executed by the at least one processing device causes the at least one processing device to perform the following additional steps:
causing, by the first node, the second node to compare the sequence ID number received from the first node to the sequence separator; and
causing, by the first node, the second node to identify an FWS for the I/O request based on the comparison.

18. The non-transitory processor-readable storage medium of claim 17 , wherein the program code when executed by the at least one processing device causes the at least one processing device to perform the following additional steps:
causing, by the first node, the second node to determine whether the sequence ID number has been allocated on the second node.

19. The non-transitory processor-readable storage medium of claim 18 , wherein the program code when executed by the at least one processing device causes the at least one processing device to perform the following additional steps:
if the sequence ID numb

Assignees

• Dell Products Lp

Inventors

• Shveidel Vladimir
• Han Geng
• Liu Yousheng

Classifications

• G06F3/0659

  Command handling arrangements, e.g. command buffers, queues, command scheduling · CPC title

• G06F3/0611

  in relation to response time · CPC title

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title

• G06F3/0652

  Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket · CPC title

• G06F3/0689

  Disk arrays, e.g. RAID, JBOD · CPC title