IP Library Granted Patent US 12,499,253
Granted Patent B2
US 12,499,253 · App. 18/697,415 · Granted Dec 16, 2025

Data stream processing method, storage control node, and nonvolatile readable storage medium

Inventor: Xueqing Zhang (Jiangsu, CN)
Assignee: SUZHOU METABRAIN INTELLIGENT TECHNOLOGY CO., LTD.
G06F21/606G06F21/602
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,499,253
App. No.
18/697,415
Granted
Dec 16, 2025
Kind
B2
Abstract

A data stream processing method, a storage control node, and a nonvolatile readable storage medium are provided. The storage control node includes a first Data Processing Unit (DPU) and a second DPU. The method includes: the first DPU receives an Input/Output interface (I/O) request, performs protocol offloading on the I/O request to obtain a data message, and stores the data message in a memory; and the second DPU acquires the data message from the memory and performs data processing on the acquired data message.

Claims (47)

1 . A data stream processing method, wherein a storage control node comprises a first Data Processing Unit (DPU) and a second DPU, and the data stream processing method comprises:

receiving, by the first DPU, an Input/Output interface (I/O) request, performing, by the first DPU, protocol offloading on the I/O request to obtain a data message, and storing, by the first DPU, the data message in a memory; and

acquiring, by the second DPU, the data message from the memory and performing, by the second DPU, data processing on the acquired data message, wherein

storing, by the first DPU, the data message in the memory comprises:

determining, by the first DPU, a type of data contained in the data message, and storing the data message in a corresponding memory according to the type of the data contained in the data message.

2 . The data stream processing method according to claim 1 , wherein storing, by the first DPU, the data message in the memory comprises:

storing, by the first DPU, the data message in the memory through a Peer-to-Peer (P2P) Direct Memory Access (DMA).

3 . The data stream processing method according to claim 1 , wherein acquiring, by the second DPU, the data message from the memory and performing, by the second DPU, the data processing on the acquired data message comprises:

performing, by the second DPU, hardware acceleration on the data processing in a hardware manner by using a built-in data stream acceleration engine.

4 . The data stream processing method according to claim 1 , wherein storing, by the first DPU, the data message in the corresponding memory according to the type of the data contained in the data message comprises:

selecting, by the first DPU according to storage reliability requirement corresponding to the type of the data contained in the data message, to store the data message in a Dynamic Random Access Memory (DRAM) or a Storage Class Memory (SCM), wherein storage reliability of the SCM is higher than storage reliability of the DRAM, and the memory comprises the DRAM or the SCM.

5 . The data stream processing method according to claim 1 , wherein determining, by the first DPU, the type of data contained in the data message comprises:

performing, by the first DPU, data fingerprint calculation on the data message to obtain a data fingerprint of the data message; and

determining, by the first DPU according to the data fingerprint, the type of the data contained in the data message.

6 . The data stream processing method according to claim 1 , wherein storing, by the first DPU, the data message in the memory comprises:

storing, by the first DPU, the data message in the memory through a high-speed interconnection bus.

7 . The data stream processing method according to claim 6 , wherein acquiring, by the second DPU, the data message from the memory and performing, by the second DPU, the data processing on the acquired data message comprises:

acquiring, by the second DPU, the data message from the memory through the high-speed interconnection bus, and performing, by the second DPU, at least one of erasure processing, encryption processing, compression processing, deduplication processing, and data consistency protection processing on the acquired data message.

8 . The data stream processing method according to claim 7 , wherein performing the compression processing on the acquired data message comprises:

performing, by the second DPU, the data compression by using a built-in acceleration module.

9 . The data stream processing method according to claim 7 , wherein performing the erasure processing on the acquired data message comprises:

performing, by the second DPU, data erasure by using a built-in acceleration module.

10 . The data stream processing method according to claim 7 , wherein performing, by the second DPU, at least one of the erasure processing, the encryption processing, the compression processing, the deduplication processing, and the data consistency protection processing on the acquired data message comprises:

performing the erasure processing, the encryption processing, the compression processing, the deduplication processing, and the data consistency protection processing by using one same second DPU.

11 . The data stream processing method according to claim 7 , wherein performing, by the second DPU, at least one of the erasure processing, the encryption processing, the compression processing, the deduplication processing, and the data consistency protection processing on the acquired data message comprises:

performing the encryption processing and the compression processing by using one same second DPU; and

performing the erasure processing, the deduplication processing, and the data consistency protection processing by using another second DPU.

12 . The data stream processing method according to claim 7 , wherein performing, by the second DPU, at least one of the erasure processing, the encryption processing, the compression processing, the deduplication processing, and the data consistency protection processing on the acquired data message comprises:

performing the erasure processing, the encryption processing, the compression processing, the deduplication processing, and the data consistency protection processing by respectively using different second DPUs.

13 . The data stream processing method according to claim 1 , further comprising:

performing, by a Central Processing Unit (CPU) in the storage control node, data forwarding control and storage management.

14 . The data stream processing method according to claim 1 , wherein performing, by the first DPU, the protocol offloading on the I/O request to obtain the data message comprises:

performing, by the first DPU, operations comprising at least one of unpacking, parsing and verification on a data packet corresponding to the I/O request so as to obtain the data message.

15 . A storage control node, comprising a first Data Processing Unit (DPU) and a second DPU, wherein

the first DPU is configured to receive an Input/Output interface (I/O) request, perform protocol offloading on the I/O request to obtain a data message, and store the data message in a memory;

the second DPU is configured to acquire the data message from the memory and perform data processing on the acquired data message; and

the first DPU is configured to determine a type of data contained in the data message, and store the data message in a corresponding memory according to the type of the data contained in the data message.

16 . The storage control node according to claim 15 , wherein the first DPU is configured to perform data fingerprint calculation on the data message to obtain a data fingerprint of the data message; and determine, based on the data fingerprint, the type of the data contained in the data message.

17 . The storage control node according to claim 15 , wherein the first DPU is configured to store the data message in the memory through a high-speed interconnection bus.

18 . The storage control node according to claim 15 , wherein the second DPU is configured to acquire the data message from the memory through a high-speed interconnection bus, and perform at least one of erasure processing, encryption processing, compression processing, deduplication processing, and data consistency protection processing on the acquired data message.

19 . The storage control node according to claim 15 , further comprising a CPU, wherein

the CPU is configured to perform data forwarding control and storage management.

20 . A nonvolatile readable storage medium, wherein the nonvolatile readable storage medium stores a computer program, and the computer program, when being executed by a processor, causes the processor to implement the following operations:

receiving, by a first Data Processing Unit (DPU) in a storage control node, an Input/Output interface (I/O) request, performing protocol offloading on the I/O request to obtain a data message, and storing the data message in a memory; and

acquiring, by a second DPU in the storage control node, the data message from the memory and performing data processing on the acquired data message, wherein

storing, by the first DPU, the data message in the memory comprises:

determining, by the first DPU, a type of data contained in the data message, and storing the data message in a corresponding memory according to the type of the data contained in the data message.

Assignments (2)
LICENSE Recorded Jun 30, 2026
From: IEIT SYSTEMS CO., LTD
To: AIVRES SYSTEMS INC.
Reel/Frame 075857/0939 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 2, 2024
From: ZHANG, XUEQING
To: SUZHOU METABRAIN INTELLIGENT TECHNOLOGY CO., LTD.
Reel/Frame 066977/0108 →
Priority Claims (1)
CN 202210144052.0 · Feb 17, 2022 · national
Continuity (1)
Related Publication 20240403455A1 · Dec 5, 2024
References Cited (20)
US 12218923B1 · Shetty · 2025 [cited by examiner]
US 20030117652A1 · Lapstun · 2003 [cited by applicant]
US 20190163493A1 · Dubeyko et al. · 2019 [cited by applicant]
US 20210250285A1 · Noureddine et al. · 2021 [cited by applicant]
CN 101101699A · 2008 [cited by applicant]
CN 101730145A · 2010 [cited by applicant]
CN 103973581A · 2014 [cited by applicant]
CN 108009119A · 2018 [cited by applicant]
CN 110892380A · 2020 [cited by examiner]
CN 111083070A · 2020 [cited by applicant]
CN 112565919A · 2021 [cited by applicant]
CN 113113068A · 2021 [cited by applicant]
CN 113703843A · 2021 [cited by applicant]
CN 114201421A · 2022 [cited by applicant]
EP 1156422A2 · 2001 [cited by examiner]
TW 201816619A · 2018 [cited by applicant]
WO 2013136857A1 · 2013 [cited by applicant]
Chinese Search Report for Chinese Patent Application No. 20221014052.0 dated Mar. 22, 2022. [cited by applicant]
Chinese Search Report for Chinese Patent Application No. 20221014052.0 dated Apr. 12, 2022. [cited by applicant]
International Search Report and Written Opinion for International Patent Application No. PCT/CN2022/134124 mailed Feb. 16, 2023. [cited by applicant]