IP Library Granted Patent US 11,334,508
Granted Patent B2
US 11,334,508 · App. 17/169,775 · Granted May 17, 2022

Storage system, data management method, and data management program

Inventors: Yuto Kamo (Tokyo, JP); Ryosuke Tatsumi (Tokyo, JP); Tomohiro Yoshihara (Tokyo, JP); Takashi Nagao (Tokyo, JP)
Assignee: Hitachi, Ltd.
G06F13/28G06F12/0868G06F2212/1024
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 11,334,508
App. No.
17/169,775
Granted
May 17, 2022
Kind
B2
Abstract

An object of the present invention is to properly secure the consistency of data while suppressing a processing load of a controller on a processor. A storage system includes a plurality of controllers and an HCA that can directly access a memory and can communicate with the controllers. The controller includes a CPU, and a memory having a buffer region into which data is temporarily stored and a cache region into which data is cached. In the case where new data according to a write request is stored into the buffer region, the CPU of the controller sequentially transfers the new data to the cache regions using the HCA without passing through the other buffer regions.

Claims (31)

1. A storage system comprising:

a plurality of controllers;

a storage device unit into which data can be stored; and

wherein the controller includes:

a processor unit; and

a memory,

wherein in the case where new data according to a write request is stored into a first memory of a first controller, the first controller transfers the new data from the first memory storing the new data corresponding to the write request to a second memory of a second controller and transfers the data to a third memory of a third controller,

wherein in the case where a state of old data of the second memory and the third memory related to new data according to the write request is dirty, transfer is performed separately on the second memory and the third memory and the old data is overwritten, and

in the case where a state of old data of the second memory and the third memory is not dirty, transfer is performed in parallel on the second memory and the third memory and the old data is overwritten.

2. The storage system according to claim 1 ,

wherein in the case where the transfer is performed separately, after success of another transfer to the second memory is confirmed, transfer to the third memory is performed and a process is performed, in the case where a problem occurs at the time of the transfer, by use of the new data or old data that is not damaged due to the problem.

3. The storage system according to claim 2 ,

wherein in the case where a problem occurs at the time of the transfer,

when either of transfer of the second memory or the third memory is performed normally, normally transferred new data is destaged in the storage device unit, and

when either of transfer of the second memory or the third memory is not performed normally, old data already stored in the second memory or the third memory is destaged in the storage device unit and data of the second memory or the third memory is not made to be dirty.

4. The storage system according to claim 1 ,

wherein the first controller is directly accessible to the second memory of the second controller and the third memory of the third controller.

5. The storage system according to claim 4 ,

wherein the transfer is performed by Direct Memory Access (DMA) of the first controller.

6. A data management method conducted by a storage system comprising:

a plurality of controllers;

a storage device unit into which data can be stored; and

wherein each of the controllers includes:

a processor unit; and

a memory,

wherein the method comprises the steps of:

storing new data according to a write request into a first memory of a first controller;

transferring, by the first controller, the new data from the first memory storing the new data corresponding to the write request to a second memory of a second controller; and

after completion of transfer to the second memory, transfers the data to a third memory of a third controller,

wherein in the case where a state of old data of the second memory and the third memory related to new data according to the write request is dirty, transfer is performed separately on the second memory and the third memory and the old data is overwritten, and

in the case where a state of old data of the second memory and the third memory is not dirty, transfer is performed in parallel on the second memory and the third memory and the old data is overwritten.

Assignments (1)
COMPANY SPLIT Recorded Aug 20, 2024
From: HITACHI, LTD.
To: HITACHI VANTARA, LTD.
Reel/Frame 069518/0761 →
Priority Claims (1)
JP 2018-210691 · Nov 8, 2018 · national
Continuity (2)
Continuation 16546356 · Aug 21, 2019
Related Publication 20210165753A1 · Jun 3, 2021