CN108282516B - Distributed storage cluster load balancing method and device based on iSCSI - Google Patents
Distributed storage cluster load balancing method and device based on iSCSI Download PDFInfo
- Publication number
- CN108282516B CN108282516B CN201711388538.4A CN201711388538A CN108282516B CN 108282516 B CN108282516 B CN 108282516B CN 201711388538 A CN201711388538 A CN 201711388538A CN 108282516 B CN108282516 B CN 108282516B
- Authority
- CN
- China
- Prior art keywords
- iscsi
- target
- target node
- read
- write
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a load balancing method and a load balancing device for a distributed storage cluster based on iSCSI, wherein all nodes in the distributed storage cluster are configured with iSCSI Target service, and each node is used as an iSCSI Target node to map distributed block equipment created by the distributed storage cluster out by the iSCSI block equipment; the method comprises the following steps: the iSCSI client side is mounted to the distributed block equipment through each iSCSI Target node; when the iSCSI client needs to read/write the distributed block equipment, at least one Target iSCSI Target node is determined according to the read/write information, and the distributed block equipment is read/written through the at least one Target iSCSI Target node. The invention can solve the problems of single point of failure and performance bottleneck existing in the traditional distributed storage iSCSI realization method.
Description
Technical Field
The invention relates to the technical field of distributed storage, in particular to a load balancing method and device of a distributed storage cluster based on iSCSI.
Background
Internet Small Computer System Interface (iSCSI) is a TCP/IP-based protocol used to establish and manage interconnections between IP storage devices, hosts, clients, etc., and to create a Storage Area Network (SAN). SANs enable the SCSI protocol to be applied to high-speed data transfer networks, with such transfers occurring at block-level across multiple data storage networks.
The traditional iSCSI implementation method for distributed storage is as follows: the distributed storage provides a large storage space, a distributed block device is established in the distributed storage cluster, an iSCSI Target service is configured on a node in the distributed storage cluster, the node is used as an iSCSI Target node to map the distributed block device in an iSCSI block device mode, an iSCSI client side is mounted to the iSCSI block device through the iSCSI Target node, and the iSCSI block device is subjected to read-write operation through the iSCSI Target node.
The traditional distributed storage iSCSI implementation method has the following defects:
1. a single node provides iSCSI Target services and if the node fails, traffic is interrupted.
2. The single node provides iSCSI Target service, all iSCSI data streams of the iSCSI client end can read and write distributed block equipment through the iSCSI Target service provided by the node, and the iSCSI Target service distributes read/write tasks to each node in the distributed storage cluster according to the self principle of distributed storage, so that the node is the performance bottleneck of the iSCSI data streams.
Disclosure of Invention
In view of this, an object of the present invention is to provide a distributed storage cluster load balancing method and apparatus based on iSCSI, which can solve the problems of single point of failure and performance bottleneck existing in the conventional distributed storage iSCSI implementation method.
In order to achieve the purpose, the invention provides the following technical scheme:
a load balancing method for a distributed storage cluster based on iSCSI is disclosed, wherein all nodes in the distributed storage cluster are configured with iSCSI Target service, and each node is used as an iSCSI Target node to map out distributed block equipment created by the distributed storage cluster by the iSCSI block equipment; the method comprises the following steps:
the iSCSI client side is mounted to the distributed block equipment through each iSCSI Target node;
when the iSCSI client needs to read/write the distributed block equipment, at least one Target iSCSI Target node is determined according to the read/write information, and the distributed block equipment is read/written through the at least one Target iSCSI Target node.
A load balancing device of a distributed storage cluster based on iSCSI is disclosed, wherein all nodes in the distributed storage cluster are configured with iSCSI Target service, and each node is used as an iSCSI Target node to map out distributed block equipment created by the distributed storage cluster by the iSCSI block equipment; the device is applied to an iSCSI client and comprises:
the mounting unit is used for mounting the distributed block equipment through each iSCSI Target node;
and the read-write unit is used for determining at least one Target iSCSI Target node according to read/write information when the distributed block equipment needs to be read/written, and performing read/write operation on the distributed block equipment through the at least one Target iSCSI Target node.
According to the technical scheme, the iSCSI Target service is configured on all the nodes in the distributed storage cluster, and each node is used as the iSCSI Target node to map out the distributed block equipment created by the distributed storage cluster in an iSCSI block equipment mode, so that an iSCSI client can access the distributed block equipment through a plurality of iSCSI Target nodes at the same time. The method of the scheme can not only avoid the problem of single point of failure, but also solve the problem of performance bottleneck caused by adopting a single node to provide iSCSI Target service because the distributed block equipment can be accessed concurrently.
Drawings
FIG. 1 is a flowchart of a method for load balancing of iSCSI-based distributed storage clusters;
fig. 2 is a schematic structural diagram of an iSCSI-based distributed storage cluster load balancing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention are described in detail below with reference to the accompanying drawings according to embodiments.
In the invention, the iSCSI Target service is configured on all nodes of the distributed storage cluster based on iSCSI, so that all nodes are used as iSCSI Target nodes, and each iSCSI Target node maps the distributed block devices created by the cluster in an iSCSI block device mode. Thus, from the iSCSI client perspective, there are multiple iSCSI block devices in the cluster that are accessible, but these iSCSI block devices all actually point to (represent) the same distributed block device, i.e., the distributed block device created by the cluster.
Referring to fig. 1, fig. 1 is a flowchart of an iSCSI-based distributed storage cluster load balancing method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
and step 101, the iSCSI client side mounts the data to the distributed block equipment through each iSCSI Target node.
The premise of the step is that: all nodes in the distributed storage cluster are configured with iSCSI Target service, and each node is used as an iSCSI Target node to map out distributed block equipment created by the cluster in an iSCSI block equipment mode.
After each iSCSI Target node maps out the distributed block equipment created by the cluster in an iSCSI block equipment mode, for an iSCSI client, the mapped iSCSI block equipment is an independent iSCSI block equipment which can be accessed, and the iSCSI client can be mounted to the iSCSI block equipment through the iSCSI Target node and accesses the iSCSI block equipment through the iSCSI Target node.
As mentioned above, iSCSI block devices mapped out through different iSCSI Target nodes appear to iSCSI clients as different iSCSI block devices, but these iSCSI block devices are still actually distributed block devices created by the cluster. In order to concurrently access distributed block devices, it is necessary to distinguish the iSCSI block devices and assign storage spaces to different iSCSI block devices, so that when an iSCSI client accesses the iSCSI block devices through an iSCSI Target node, only the storage space corresponding to the iSCSI block device can be accessed.
For this purpose, after executing step 101, the method further includes:
taking the distributed block equipment mounted by each iSCSI Target node as iSCSI block equipment corresponding to the iSCSI Target node;
numbering the iSCSI block devices corresponding to all iSCSI Target nodes from 1 to n, and assigning a storage space for each iSCSI block device based on the size of the storage space of the distributed block devices, wherein n is the number of the iSCSI block devices.
For example,
suppose there are 10 nodes in the cluster, where 10 nodes are all configured with iSCSI Target service, and each node is used as an iSCSI Target node to map out the distributed block devices created by the cluster in an iSCSI block device manner. The iSCSI client is mounted to the distributed block devices through 10 nodes, the iSCSI block device number corresponding to the distributed block device mounted through the 1 st node as the 1 st node is 1 (the iSCSI block device is denoted as client _ block1), the iSCSI block device number corresponding to the distributed block device mounted through the 2 nd node as the 2 nd node is 2 (the iSCSI block device is denoted as client _ block2), and so on. And finally obtaining client _ block1, client _ block2, … … and client _ block 10.
Assuming that the distributed block devices have 1000 data blocks in total, the 1000 data blocks may be divided into 10 storage spaces according to the number 10 of iSCSI Target nodes (equivalent to the number of iSCSI block devices), and one of the storage spaces is specified for each iSCSI block device, for example, the 1 st to 100 th data blocks are divided into storage space of client _ block1, the 101 st to 200 th data blocks are divided into storage space of client _ block2, … … th to 100 th data blocks are divided into storage space of client _ block 10.
In the embodiment of the invention, the read/write information at least comprises a starting position and a length; the starting position is a read/write starting position from the distributed block device, when the read/write information is read information, the starting position is the read starting position, the length is the length of data to be read from the distributed block device, when the read/write information is write information, the starting position is the write starting position, and the length is the length of data to be written into the distributed block device. In addition, when the read/write information is write information, the read/write information should also include data content to be written.
In this embodiment of the present invention, the method for determining at least one Target iSCSI Target node according to read/write information and performing read/write operation on the distributed block device through the at least one Target iSCSI Target node may specifically be:
determining a read/write target storage space according to the read/write information;
determining at least one iSCSI block device covering a read/write Target storage space according to the storage space of each iSCSI block device, and determining an iSCSI Target node corresponding to each iSCSI block device in the at least one iSCSI block device as a Target iSCSI Target node;
and aiming at each Target iSCSI Target node, determining a Target read/write storage space corresponding to the Target iSCSI Target node according to the read/write Target storage space and the storage space of the iSCSI block device corresponding to the Target iSCSI Target node, and performing read/write operation based on the Target read/write storage space corresponding to the Target iSCSI Target node on the distributed device through the Target iSCSI Target node.
For example, assume that the data content of 150 data blocks needs to be read out to the distributed block device, and the read-out start position is the start position of the 460 th data block. The above method is performed as follows:
a. the target storage space for reading/writing is determined.
The read/write information includes a read start position and a read data length, wherein the read start position is a start position of 460 th data blocks, and the read data length is 150 data blocks. Therefore, the target storage space for reading/writing is 460 th and 610 th data blocks.
b. And determining a Target iSCSI Target node.
Since the client _ block4 (the storage space is data block 401-.
c. And determining a Target read/write storage space corresponding to each Target iSCSI Target node, and performing read operation.
The storage space of the client _ block4 is data block 401-. Therefore, the iSCSI client will read the data content in data block 460 and 500 from the distributed block device through the 4 th iSCSI Target node.
The storage space of the client _ block5 is data block 501-. Therefore, the iSCSI client will read the data content in data block 501 and 600 from the distributed block device through the 5 th iSCSI Target node.
The storage space of the client _ block6 is data block 601-. Therefore, the iSCSI client will read the data content in data block 601 and 610 from the distributed block device through the 6 th iSCSI Target node.
In practical applications, there may be a case where an iSCSI Target node fails, which may result in a failure of a read/write operation if a distributed block device is read/written through the iSCSI Target node.
In order to solve the above problem, in the present application, a proxy iSCSI Target node is selected for the failed iSCSI Target node, and read/write operations are performed through the proxy iSCSI Target node.
Therefore, when the read/write operation of the Target read/write storage space corresponding to the Target iSCSI Target node to the distributed device through a certain Target iSCSI Target node fails, a proxy iSCSI Target node of the Target iSCSI Target node may be further determined, and the read/write operation of the Target read/write storage space corresponding to the Target iSCSI Target node to the distributed device is performed through the proxy iSCSI Target node.
In the embodiment of the present invention, one possible method for determining the proxy iSCSI Target node of the Target iSCSI Target node is as follows:
determining the number x of the iSCSI block device corresponding to the Target iSCSI Target node, updating the value of x by adopting the formula x being (x + 1)% n,
and determining the iSCSI block equipment with the number of the updated x value, and determining the iSCSI Target node corresponding to the iSCSI block equipment as a proxy iSCSI Target node of the Target iSCSI Target node.
The iSCSI-based distributed storage cluster load balancing method is described in detail above, and the present invention also provides an iSCSI-based distributed storage cluster load balancing apparatus, which is described in detail below with reference to fig. 2.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a load balancing apparatus for a distributed storage cluster based on iSCSI in an embodiment of the present invention, where all nodes in the distributed storage cluster configure an iSCSI Target service, and each of the nodes serves as an iSCSI Target node to map out distributed block devices created by the distributed storage cluster as iSCSI block devices; the device is applied to an iSCSI client and comprises:
a mounting unit 201, configured to mount to the distributed block device through each iSCSI Target node;
the read-write unit 202 is configured to, when the distributed block device needs to be read/written, determine at least one Target iSCSI Target node according to the read/write information, and perform read/write operation on the distributed block device through the at least one Target iSCSI Target node.
In the device shown in figure 2 of the drawings,
the mount unit 201, after being mounted to the distributed block device through each iSCSI Target node, is further configured to:
taking the distributed block equipment mounted by each iSCSI Target node as iSCSI block equipment corresponding to the iSCSI Target node;
numbering iSCSI block devices corresponding to all iSCSI Target nodes from 1 to n, and assigning a storage space for each iSCSI block device based on the size of the storage space of the distributed block devices, wherein n is the number of the iSCSI Target nodes.
In the device shown in figure 2 of the drawings,
the read/write information comprises a starting position and a length;
the read-write unit 202, determining at least one Target iSCSI Target node according to the read/write information, and when performing a read/write operation on the distributed block device through the at least one Target iSCSI Target node, is configured to:
determining a read/write target storage space according to the read/write information;
determining at least one iSCSI block device covering a read/write Target storage space according to the storage space of each iSCSI block device, and determining an iSCSI Target node corresponding to each iSCSI block device in the at least one iSCSI block device as a Target iSCSI Target node;
and aiming at each Target iSCSI Target node, determining a Target read/write storage space corresponding to the Target iSCSI Target node according to the read/write Target storage space and the storage space of the iSCSI block device corresponding to the Target iSCSI Target node, and performing read/write operation based on the Target read/write storage space corresponding to the Target iSCSI Target node on the distributed device through the Target iSCSI Target node.
In the device shown in figure 2 of the drawings,
the read-write unit 202 further determines a proxy iSCSI Target node of the Target iSCSI Target node when the Target iSCSI Target node fails to perform read/write operation on the distributed device based on the Target read/write storage space corresponding to the Target iSCSI Target node, and performs read/write operation on the distributed device based on the Target read/write storage space corresponding to the Target iSCSI Target node through the proxy iSCSI Target node.
In the device shown in figure 2 of the drawings,
the read-write unit 202, when determining the proxy iSCSI Target node of the Target iSCSI Target node, is configured to:
determining the number x of the iSCSI block device corresponding to the Target iSCSI Target node, and updating the value of x by adopting a formula x ═ x + 1)% n:
and determining the iSCSI block equipment with the number of the updated x value, and determining the iSCSI Target node corresponding to the iSCSI block equipment as a proxy iSCSI Target node of the Target iSCSI Target node.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (6)
1. A load balancing method of a distributed storage cluster based on iSCSI is characterized in that all nodes in the distributed storage cluster are configured with iSCSI Target service, and each node is used as an iSCSI Target node to map distributed block equipment created by the distributed storage cluster out by the iSCSI block equipment; the method comprises the following steps:
the iSCSI client side is mounted to the distributed block equipment through each iSCSI Target node;
when the iSCSI client needs to read/write the distributed block equipment, determining at least one Target iSCSI Target node according to read/write information, and performing read/write operation on the distributed block equipment through the at least one Target iSCSI Target node;
wherein, after the iSCSI client is mounted to the distributed block device through each iSCSI target node, the method further includes:
taking the distributed block equipment mounted by each iSCSI Target node as iSCSI block equipment corresponding to the iSCSI Target node;
numbering iSCSI block devices corresponding to all iSCSI SITarget nodes from 1 to n, and assigning a storage space for each iSCSI block device based on the size of the storage space of the distributed block devices, wherein n is the number of the iSCSI block devices;
the read/write information comprises a starting position and a length;
the method for determining at least one Target iSCSI Target node according to the read/write information and performing read/write operation on the distributed block device through the at least one Target iSCSI Target node comprises the following steps:
determining a read/write target storage space according to the read/write information;
determining at least one iSCSI block device covering a read/write Target storage space according to the storage space of each iSCSI block device, and determining an iSCSI Target node corresponding to each iSCSI block device in the at least one iSCSI block device as a Target iSCSI Target node;
and aiming at each Target iSCSI Target node, determining a Target read/write storage space corresponding to the Target iSCSI Target node according to the read/write Target storage space and the storage space of iSCSI block equipment corresponding to the Target iSCSI Target node, and performing read/write operation based on the Target read/write storage space corresponding to the Target iSCSI Target node on the distributed block equipment through the Target iSCSI Target node.
2. The method of claim 1,
when the Target iSCSI Target node fails to perform read/write operation on the distributed block equipment based on the Target read/write storage space corresponding to the Target iSCSI Target node, further determining a proxy iSCSI Target node of the Target iSCSI Target node, and performing read/write operation on the distributed block equipment based on the Target read/write storage space corresponding to the Target iSCSI Target node through the proxy iSCSI Target node.
3. The method of claim 2,
the method for determining the proxy iSCSI Target node of the Target iSCSI Target node comprises the following steps:
determining the number x of the iSCSI block device corresponding to the Target iSCSI Target node, and updating the value of x by adopting a formula x ═ x + 1)% n:
and determining the iSCSI block equipment with the number of the updated x value, and determining the iSCSI Target node corresponding to the iSCSI block equipment as a proxy iSCSI Target node of the Target iSCSI Target node.
4. A load balancing device of a distributed storage cluster based on iSCSI is characterized in that all nodes in the distributed storage cluster are configured with iSCSI Target service, and each node is used as an iSCSI Target node to map distributed block equipment created by the distributed storage cluster out by the iSCSI block equipment; the device is applied to an iSCSI client and comprises:
the mounting unit is used for mounting the distributed block equipment through each iSCSI Target node;
the reading and writing unit is used for determining at least one Target iSCSI Target node according to the reading/writing information when the distributed block equipment needs to be read/written, and performing reading/writing operation on the distributed block equipment through the at least one Target iSCSI Target node;
wherein, the mount unit, after being mounted to the distributed block device through each iSCSI Target node, is further configured to:
taking the distributed block equipment mounted by each iSCSI Target node as iSCSI block equipment corresponding to the iSCSI Target node;
numbering iSCSI block devices corresponding to all iSCSI Target nodes from 1 to n, and assigning a storage space for each iSCSI block device based on the size of the storage space of the distributed block devices, wherein n is the number of iSCSI Target nodes;
the read/write information comprises a starting position and a length;
the read-write unit is configured to determine at least one Target iSCSI Target node according to read/write information, and when performing read/write operation on the distributed block device through the at least one Target iSCSI Target node, configured to:
determining a read/write target storage space according to the read/write information;
determining at least one iSCSI block device covering a read/write Target storage space according to the storage space of each iSCSI block device, and determining an iSCSI Target node corresponding to each iSCSI block device in the at least one iSCSI block device as a Target iSCSI Target node;
and aiming at each Target iSCSI Target node, determining a Target read/write storage space corresponding to the Target iSCSI Target node according to the read/write Target storage space and the storage space of iSCSI block equipment corresponding to the Target iSCSI Target node, and performing read/write operation based on the Target read/write storage space corresponding to the Target iSCSI Target node on the distributed block equipment through the Target iSCSI Target node.
5. The apparatus of claim 4,
and the read-write unit is used for further determining a proxy iSCSI Target node of the Target iSCSI Target node when the read/write operation of the Target read/write storage space corresponding to the Target iSCSI Target node on the distributed block equipment through the Target iSCSI Target node fails, and the read/write operation of the Target read/write storage space corresponding to the Target iSCSI Target node on the distributed block equipment is carried out through the proxy iSCSI Target node.
6. The apparatus of claim 5,
the read-write unit, when determining the proxy iSCSI Target node of the Target iSCSI Target node, is configured to:
determining the number x of the iSCSI block device corresponding to the Target iSCSI Target node, and updating the value of x by adopting a formula x ═ x + 1)% n:
and determining the iSCSI block equipment with the number of the updated x value, and determining the iSCSI Target node corresponding to the iSCSI block equipment as a proxy iSCSI Target node of the Target iSCSI Target node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711388538.4A CN108282516B (en) | 2017-12-21 | 2017-12-21 | Distributed storage cluster load balancing method and device based on iSCSI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711388538.4A CN108282516B (en) | 2017-12-21 | 2017-12-21 | Distributed storage cluster load balancing method and device based on iSCSI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108282516A CN108282516A (en) | 2018-07-13 |
| CN108282516B true CN108282516B (en) | 2021-09-10 |
Family
ID=62801972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711388538.4A Active CN108282516B (en) | 2017-12-21 | 2017-12-21 | Distributed storage cluster load balancing method and device based on iSCSI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108282516B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110784515B (en) * | 2019-09-19 | 2022-11-22 | 平安科技（深圳）有限公司 | Data storage method based on distributed cluster and related equipment thereof |
| CN112261079B (en) * | 2020-09-11 | 2022-05-10 | 苏州浪潮智能科技有限公司 | Distributed block storage service link management method and system based on iSCSI |
| CN114265702B (en) * | 2022-03-02 | 2022-05-31 | 苏州浪潮智能科技有限公司 | iSCSI service load balancing method, device, equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101702115A (en) * | 2009-11-27 | 2010-05-05 | 浪潮电子信息产业股份有限公司 | Method for realizing block protocol interface based on cluster storage system |
| CN103188345A (en) * | 2013-03-01 | 2013-07-03 | 北京邮电大学 | Distributive dynamic load management system and distributive dynamic load management method |
| CN106354436A (en) * | 2016-09-20 | 2017-01-25 | 郑州云海信息技术有限公司 | Storage system based on distributed IPSAN |
-
2017
- 2017-12-21 CN CN201711388538.4A patent/CN108282516B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101702115A (en) * | 2009-11-27 | 2010-05-05 | 浪潮电子信息产业股份有限公司 | Method for realizing block protocol interface based on cluster storage system |
| CN103188345A (en) * | 2013-03-01 | 2013-07-03 | 北京邮电大学 | Distributive dynamic load management system and distributive dynamic load management method |
| CN106354436A (en) * | 2016-09-20 | 2017-01-25 | 郑州云海信息技术有限公司 | Storage system based on distributed IPSAN |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108282516A (en) | 2018-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11775569B2 (en) | Object-backed block-based distributed storage | |
| CN105408880B (en) | Direct access to the long-time memory of sharing and storing device | |
| US10769024B2 (en) | Incremental transfer with unused data block reclamation | |
| JP6607783B2 (en) | Distributed cache cluster management | |
| US10466935B2 (en) | Methods for sharing NVM SSD across a cluster group and devices thereof | |
| US10554520B2 (en) | Data path monitoring in a distributed storage network | |
| US11036393B2 (en) | Migrating data between volumes using virtual copy operation | |
| JP2018509695A (en) | Computer program, system, and method for managing data in storage | |
| JP2014525073A (en) | Deduplication in extent-based architecture | |
| CN108282516B (en) | Distributed storage cluster load balancing method and device based on iSCSI | |
| JP6293086B2 (en) | Deduplication of receiver-side data in data systems | |
| US20070156763A1 (en) | Storage management system and method thereof | |
| US9158714B2 (en) | Method and system for multi-layer differential load balancing in tightly coupled clusters | |
| US10523753B2 (en) | Broadcast data operations in distributed file systems | |
| US10579597B1 (en) | Data-tiering service with multiple cold tier quality of service levels | |
| US20170097941A1 (en) | Highly available network filer super cluster | |
| US20150106468A1 (en) | Storage system and data access method | |
| CN111316251A (en) | Scalable storage system | |
| JPWO2015118865A1 (en) | Information processing apparatus, information processing system, and data access method | |
| US11343308B2 (en) | Reduction of adjacent rack traffic in multi-rack distributed object storage systems | |
| KR20230088215A (en) | Distributed storage system | |
| CN106649141A (en) | Storage interaction device and storage system based on ceph | |
| US7698424B1 (en) | Techniques for presenting multiple data storage arrays to iSCSI clients as a single aggregated network array | |
| JP6260088B2 (en) | Virtual file access system, virtual file access method, and virtual file access program | |
| KR100785774B1 (en) | Obeject based file system and method for inputting and outputting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518057 Shenzhen Software Park, No. 9, 501, 502, Science and Technology Middle Road, Nanshan District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Innovation Technology Co., Ltd. Address before: 518057 Shenzhen Software Park, No. 9, 501, 502, Science and Technology Middle Road, Nanshan District, Shenzhen City, Guangdong Province Applicant before: UIT Storage Technology (Shenzhen) Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |