IP Library Granted Patent US 10,579,275
Granted Patent B2
US 10,579,275 · App. 15/579,893 · Granted Mar 3, 2020

Storage system and storage control method

Inventors: Akihiko Araki (Tokyo, JP); Yusuke Nonaka (Tokyo, JP); Noboru Morishita (Tokyo, JP)
Assignee: HITACHI, LTD.
G06F3/0613G06F3/061G06F3/0604G06F3/0607G06F3/0635G06F3/0643G06F3/0659G06F3/0661G06F3/0662G06F3/0664G06F3/0689G06F16/176G06F16/182H04L67/1097H04L69/08
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 10,579,275
App. No.
15/579,893
Granted
Mar 3, 2020
Kind
B2
Abstract

This storage system comprises a block interface, a block control unit, a file control unit, and shared memory. The file control unit and block control unit are coupled via a first memory-through path structured to pass through a first area of the shared memory, and via a second memory-through path structured to pass through a second area of the shared memory. The block control unit has a protocol control unit and a virtual driver; exchanges control information for the file control unit with the file control unit via the first memory-through path; uses the virtual driver to convert an I/O request passed from the file control unit via the second memory-through path and processes the result with a protocol processing unit; and bypasses the virtual driver and uses the protocol processing unit to process a block I/O request transferred from the block interface via a physical path.

Claims (57)

1. A storage system comprising:

a block I/F configured to receive a block I/O request from a host computer;

a block control unit coupled to the block I/F by a physical path so as to control the block I/O request received by the block I/F;

a file control unit configured to provide a file server to the host computer; and

a first shared memory shared by the block control unit and the file control unit, wherein

the file control unit and the block control unit are coupled by:

a first memory-through path structured so as to pass through a first area of the first shared memory; and

a second memory-through path structured so as to pass through a second area of the first shared memory,

the block control unit includes:

a protocol processing unit configured to process a protocol associated with transfer of data via the physical path; and

a virtual driver configured to convert exchange of data via the first or second memory-through path to a protocol that can be processed by the protocol processing unit, and

the block control unit is configured to:

exchange control information on control of the file control unit with the file control unit via the first memory-through path;

use the virtual driver to convert an I/O request passed from the file control unit via the second memory-through path, and process the result using the protocol processing unit; and

bypass the virtual driver and use the protocol processing unit to process a block I/O request transferred from the block I/F via the physical path.

2. The storage system according to claim 1 , further comprising:

a plurality of clusters each including a file control unit and a block control unit; and

a second shared memory that can be accessed from the block control units of the plurality of clusters, wherein

the second shared memory has a health area in which health information of the file control unit of each cluster is stored, and

in each cluster,

the block control unit is configured to, upon receiving an I/O request for the health information from the file control unit, perform exclusive control with respect to the health area and return an execution result of the I/O request for the health information with respect to the health area to the file control unit via the first memory-through path, and

the file control unit is configured to determine the health of the file control unit of another cluster on the basis of the execution result of the I/O request for the health information returned from the block control unit.

3. The storage system according to claim 1 , further comprising:

a file I/F configured to receive a file I/O request from the host computer, wherein

the file I/F is coupled to the block control unit by a physical path that is faster than the first and second memory-through paths, and

the file I/F is configured to convert the file I/O request received from the host computer to a block I/O request, and transfer the converted block I/O request to the block control unit via the physical path.

4. The storage system according to claim 3 , wherein

the block control unit is configured to manage whether the type of paths coupled to the block control unit is the physical path or the first or second memory-through path, and perform different processes depending on the type of the path.

5. The storage system according to claim 4 , wherein

the second memory-through path is faster than the first memory-through path.

6. The storage system according to claim 1 , wherein

the file control unit is configured to monitor the health of the block control unit via the first memory-through path, and stop execution of the file control unit when it cannot be confirmed that the block control unit is active.

7. The storage system according to claim 1 , wherein

the second area has a larger capacity than the first area.

8. The storage system according to claim 1 , wherein

a polling interval of the block control unit with respect to the second area is shorter than a polling interval thereof with respect to the first area.

9. The storage system according to claim 1 , further comprising:

a file I/F configured to receive a file I/O request from the host computer, wherein

the file I/F is coupled to the file I/F by a physical path that is faster than the first and second memory-through paths,

the file control unit and the block control unit are coupled by a third memory-through path structured so as to pass through a third area of the first shared memory, the third memory-through path being faster than the first and second memory-through paths,

the file I/F is configured to transfer the file I/O request received from the host computer to the file control unit via the physical path, and

the file control unit is configured to convert the file I/O request transferred from the file I/F to a block I/O request, and pass the converted block I/F request to the block control unit via the third memory-through path.

10. A storage control method in a storage system comprising:

a block I/F that receives a block I/O request from a host computer;

a block control unit that is coupled to the block I/F by a physical path so as to control the block I/O request received by the block I/F;

a file control unit that provides a file server to the host computer; and

a shared memory that is shared by the block control unit and the file control unit, wherein

the file control unit and the block control unit are coupled by:

a first memory-through path structured so as to pass through a first area of the shared memory; and

a second memory-through path structured so as to pass through a second area of the first shared memory,

the block control unit includes:

a protocol processing unit that processes a protocol associated with transfer of data via the physical path; and

a virtual driver that converts exchange of data via the first or second memory-through path to a protocol that can be processed by the protocol processing unit, and

the block control unit:

exchanges control information on control of the file control unit with the file control unit via the first memory-through path;

uses the virtual driver to convert an I/O request passed from the file control unit via the second memory-through path, and processes the result using the protocol processing unit; and

bypasses the virtual driver and uses the protocol processing unit to process a block I/O request transferred from the block I/F via the physical path.

Assignments (2)
COMPANY SPLIT Recorded Aug 20, 2024
From: HITACHI, LTD.
To: HITACHI VANTARA, LTD.
Reel/Frame 069518/0761 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 5, 2017
From: ARAKI, AKIHIKO; NONAKA, YUSUKE; MORISHITA, NOBORU
To: HITACHI, LTD.
Reel/Frame 044304/0640 →
Continuity (1)
Related Publication 20180173721A1 · Jun 21, 2018
Cited By (1)
US 12,554,525