CN111049669A - Distributed storage system and method for realizing flow control - Google Patents
Distributed storage system and method for realizing flow control Download PDFInfo
- Publication number
- CN111049669A CN111049669A CN201911046664.0A CN201911046664A CN111049669A CN 111049669 A CN111049669 A CN 111049669A CN 201911046664 A CN201911046664 A CN 201911046664A CN 111049669 A CN111049669 A CN 111049669A
- Authority
- CN
- China
- Prior art keywords
- control
- client
- network management
- distributed storage
- management device
- 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.)
- Withdrawn
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a distributed storage system and a method for realizing flow control, wherein the system comprises a distributed storage cluster, at least one network management device and a plurality of clients; the uplink data output port of each client is configured with a first control queue, and each first control queue corresponds to one network management device; when a client writes data into a storage cluster, the first control queue performs flow control on the write data sent to the corresponding network management equipment by the client; a downlink data output port of each network management device is configured with a second control queue, and each second control queue corresponds to one client; when the client reads data from the storage cluster, the second control queue controls the flow of the read data sent to the corresponding client by the network management equipment; the invention can meet the storage bandwidth control of the client without independently realizing a complex storage flow control function on the distributed storage cluster, effectively improves the network service quality, and has simple and easy operation.
Description
Technical Field
The present invention belongs to the field of distributed storage technology, and more particularly, to a distributed storage system and method for implementing flow control.
Background
A distributed storage system is used for storing data on a plurality of independent devices in a distributed mode. The traditional network storage system adopts a centralized storage server to store all data, the storage server becomes the bottleneck of the system performance, is also the focus of reliability and safety, and cannot meet the requirement of large-scale storage application. The distributed network storage system adopts an expandable system structure, utilizes a plurality of storage servers to share the storage load, and utilizes the position server to position the storage information, thereby not only improving the reliability, the availability and the access efficiency of the system, but also being easy to expand.
In distributed storage, a storage system generally provides a standard block storage interface iSCSI, and a client can access a back-end storage cluster through an iSCSI protocol; therefore, a block storage gateway can exist in the distributed storage system, and the block storage gateway provides a server side of an iSCSI protocol, is responsible for resolving the protocol and forwards a read-write request to a back-end storage cluster; wherein: the client serves as a client of the storage system and is also an initiator in an iSCSI protocol and provides a storage volume for an application program to use; the iSCSI gateway is used as a server side in the iSCSI protocol, analyzes the iSCSI protocol, converts a standard iSCSI read-write request into a private interface of distributed storage, and transmits data to the rear end of the storage cluster through a storage client; the back-end storage cluster is used as a server side of distributed storage and is responsible for storing data, ensuring reliability and availability and the like.
The Client, the block storage gateway and the back-end storage cluster are communicated through a network. The iSCSI gateway can be configured with a plurality of gateways, a client generally accesses data through a fixed gateway, and one gateway can provide services for one or more clients. When a plurality of clients access the back-end storage cluster, some clients occupy high bandwidth and some clients occupy low bandwidth, and when the total bandwidth of all the clients exceeds the maximum bandwidth which can be provided by the back-end storage cluster, the performance of all the clients is reduced, under the condition, the network bandwidth of the clients needs to be limited, so that the limitation on the storage bandwidth is further achieved.
Typically, memory flow control is a high level function in memory that is not yet provided by part of the software. Although flow control can also be realized in the back-end storage cluster, the control algorithm is relatively complex and the realization difficulty is relatively high.
Disclosure of Invention
Aiming at least one defect or improvement requirement in the prior art, the invention provides a distributed storage system and a method for realizing flow control, which can meet the storage bandwidth control of a client without realizing a complex storage flow control function on a distributed storage cluster by respectively configuring flow control strategies at an uplink data output port of each client and a downlink data output port of a network management device.
To achieve the above object, according to an aspect of the present invention, there is provided a distributed storage system for implementing flow control, including a distributed storage cluster, at least one network management device, and a plurality of clients; the client accesses the distributed storage cluster through the network management equipment;
the uplink data output port of each client is configured with at least one first control queue, and each first control queue corresponds to a network management device connected with the client;
when a client writes data into the distributed storage cluster, the first control queue performs flow control on the write data sent to the corresponding network management equipment by the client according to a first control strategy configured in advance;
at least one second control queue is configured at a downlink data output port of each network management device, and each second control queue corresponds to a client connected with the network management device;
and when the client reads data from the distributed storage cluster, the second control queue controls the flow of the read data sent to the corresponding client by the network management equipment according to a second control strategy configured in advance.
Preferably, in the distributed storage system, each first control queue has a first mapping identifier pointing to a corresponding network management device, where the first mapping identifier is an IP address of the network management device.
Preferably, in the distributed storage system, each second control queue has a second mapping identifier pointing to a corresponding client, where the second mapping identifier is a client IP address.
Preferably, in the distributed storage system, the first control policy is a preconfigured storage bandwidth;
the sum of the storage bandwidths corresponding to the first control strategy pointing to the network control equipment on the client connected with each network control equipment is less than the maximum bandwidth of the equipment.
Preferably, in the distributed storage system, the second control policy is a preconfigured storage bandwidth;
and the sum of the storage bandwidths corresponding to all the second control strategies on each network control device is less than the maximum bandwidth of the device.
According to another aspect of the present invention, there is also provided a distributed storage method for implementing flow control, the method including the steps of:
s1: configuring at least one first control queue at an uplink data output port of each client, wherein each first control queue corresponds to a network management device connected with the client;
s2: when a client writes data into the distributed storage cluster, flow control is carried out on the write data sent to the corresponding network management equipment by the client according to a first control strategy pre-configured in the first control queue;
s3: configuring at least one second control queue at a downlink data output port of each network management device, wherein each second control queue corresponds to a client connected with the network management device;
s4: and when the client reads data from the distributed storage cluster, controlling the flow of the read data sent to the corresponding client by the network management equipment according to a second control strategy pre-configured in the second control queue.
Preferably, in the distributed storage method, each first control queue has a first mapping identifier pointing to a corresponding network management device, where the first mapping identifier is an IP address of the network management device.
Preferably, in the distributed storage method, each second control queue has a second mapping identifier pointing to a corresponding client, where the second mapping identifier is a client IP address.
Preferably, in the distributed storage method, the first control policy is a pre-configured storage bandwidth;
the sum of the storage bandwidths corresponding to the first control strategy pointing to the network control equipment on the client connected with each network control equipment is less than the maximum bandwidth of the equipment.
Preferably, in the distributed storage method, the second control policy is a pre-configured storage bandwidth;
and the sum of the storage bandwidths corresponding to all the second control strategies on each network control device is less than the maximum bandwidth of the device.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
(1) the invention provides a distributed storage system and a method for realizing flow control.A first control queue is configured at an uplink data output port of each client, and when the client writes data into a distributed storage cluster, the first control queue controls the flow of the write-in data sent to corresponding network management equipment by the client; configuring a second control queue at a downlink data output port of each network management device, and controlling the flow of read data sent to a corresponding client by the network management device through the second control queue when the client reads data from the distributed storage cluster; the invention can meet the storage bandwidth control of the client without independently realizing the complex storage flow control function on the distributed storage cluster by respectively configuring the flow control strategy at the uplink data output port of each client and the downlink data output port of the network management equipment, and performs the corresponding flow control according to the bandwidth requirements of different clients, thereby effectively improving the network service quality, and the method is simple and easy to operate.
(2) The invention provides a distributed storage system and a method for realizing flow control, wherein the configuration process of a first control queue and a second control queue is flexible and simple, and the flow rate of each client is configured at any time; the storage bandwidth can be adjusted on line, and the service is not interrupted in the adjustment process.
Drawings
Fig. 1 is a schematic structural diagram of a distributed storage system implementing flow control according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a bandwidth control process when a client writes data according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a bandwidth control process when a client reads data 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 present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Fig. 1 is a schematic structural diagram of a distributed storage system for implementing flow control according to this embodiment, and referring to fig. 1, the distributed storage system includes a distributed storage cluster, at least one network management device, and a plurality of clients; the client accesses the distributed storage cluster through the network management equipment; the network management device may be a gateway, an Access Controller (AC), a router, or the like, and the embodiment employs an iSCSI gateway.
When a client writes data into the distributed storage cluster, the data is output from an uplink data output port of the client and reaches the network management equipment, the network management equipment analyzes the data content according to the iSCSI protocol, blocks the data to be written according to a fixed size after the analysis is finished and sends the blocked data to the distributed storage cluster, and the distributed storage cluster stores the data on a local hard disk.
The uplink data output port of each client is configured with at least one first control queue, and each first control queue corresponds to a network management device connected with the client; when the client writes data into the distributed storage cluster, the first control queue performs flow control on the write data sent by the client to the corresponding network management equipment according to a first control strategy configured in advance.
In this embodiment, each first control queue has a first mapping identifier pointing to a corresponding network management device, where the first mapping identifier is an IP address of the network management device.
The first control strategy is a preset storage bandwidth; the sum of the storage bandwidths corresponding to the first control strategy pointing to the network control equipment on the client connected with each network control equipment is smaller than the maximum bandwidth of the network control equipment.
Fig. 2 is a schematic diagram of a bandwidth control process when a client writes data according to an embodiment of the present invention; referring to fig. 2, when the client writes data, the data first goes from the upstream data output gateway (eth0) of the client to the upstream data input gateway of the network management device, then goes out through the upstream data output gateway to the back-end storage server, and finally the data is stored on the hard disk of the storage server.
In this embodiment, a first control queue is established on an upstream data output network port (eth0) of each client, each first control queue corresponds to a flow control policy, if the client is connected to a plurality of network management devices, a plurality of first control queues are configured on the output network port according to the number of the network management devices, each first control queue sets a network rate, which indicates that only data packets not exceeding the set rate are allowed to pass through, and then filtering is performed according to a source IP (representing each client) and a destination IP (iscsitarget), and the flow of each destination IP is allocated to different first control queues, so that bandwidth control for writing data of the stored client can be realized on a gateway node.
Generally, network traffic is controlled at an output port, although network traffic control can be performed at an upstream data input port of a network management device, Linux also has related functions, but generally, an external network device cannot be controlled, so that the flow control of the upstream data input port of the network management device is relatively difficult. Therefore, the present embodiment performs flow control by using the upstream data output port of the client.
When a client reads data from the distributed storage cluster, the client firstly sends a reading request to the network management equipment, the network management equipment analyzes the reading request, calculates the block of hard disk on which the data to be read is stored, then reads the data from the hard disk of the distributed storage cluster according to the block size, encapsulates the data into an iSCSI protocol, and returns the iSCSI protocol to the client through a downlink data output port.
At least one second control queue is configured at the downlink data output port of each network management device, and each second control queue corresponds to a client connected with the network management device; and when the client reads data from the distributed storage cluster, the second control queue controls the flow of the read data sent to the corresponding client by the network management equipment according to a second control strategy configured in advance.
In this embodiment, each second control queue has a second mapping identifier pointing to a corresponding client, where the second mapping identifier is a client IP address.
The second control strategy is a preset storage bandwidth; and the sum of the storage bandwidths corresponding to all the second control strategies on each network control device is less than the maximum bandwidth of the network control device.
Fig. 3 is a schematic diagram of a bandwidth control process when a client reads data according to an embodiment of the present invention; referring to fig. 3, when the client reads data, the client reads data from the local hard disk of the storage server, enters through the downstream data input port (eth2) of the network management device, and then exits through the downstream data output port (eth1) of the network management device, and finally the data reaches the client.
In this embodiment, a second control queue is established on a downstream data output gateway (eth1) of a network management device, a plurality of second control queues are configured on the downstream data output gateway (eth1) according to the number of clients connected to each network management device, a network rate is set on each second control queue, which indicates that only data packets not exceeding the set rate are allowed to pass through, filtering is performed according to a source IP iscsi (target) and a destination IP (representing each client), and the traffic of each destination IP (client) is distributed to different second control queues, so that bandwidth control on data reading of each client can be realized on the network management device.
In this embodiment, the network management device and the client use the classifiable queue to implement the flow control function.
The embodiment also provides a distributed storage method for implementing flow control, which is used for performing flow control on the distributed storage system, and the method includes the following steps:
s1: at least one first control queue is configured at an uplink data output port of each client, and each first control queue corresponds to a network management device connected with the client;
in this embodiment, each first control queue has a first mapping identifier pointing to a corresponding network management device, where the first mapping identifier is an IP address of the network management device.
S2: when a client writes data into the distributed storage cluster, flow control is carried out on the write data sent to the corresponding network management equipment by the client according to a first control strategy pre-configured in a first control queue;
in this embodiment, the first control policy is a pre-configured storage bandwidth; the sum of storage bandwidths corresponding to a first control strategy pointing to the network control equipment on a client connected with each network control equipment is less than the maximum bandwidth of the equipment;
firstly, a client list on each network control device is collected, and the expected allocated storage bandwidth of each client is planned, and the sum of the storage bandwidths of all the clients on a single network control device needs to be smaller than the maximum bandwidth of a physical device.
In this embodiment, the first control queue is a classifiable queue, and the configuration process and the control process specifically include: binding a first control queue on an uplink data output network port of a client node, and setting a scheduling algorithm of the first control queue; in that
Establishing a class on the first control queue, establishing a root class, then establishing a sub-class on the root class, and setting an expected storage write-in bandwidth on the sub-class; and establishing a filter for each sub-classification, wherein the filter carries out filtering classification through a source IP and a destination IP, when the source IP is an IP of an iSCSI initiator (client) and the destination IP is an IP of an iSCSI target (iSCSI gateway), the filter indicates that the source IP is write data to the storage of the client, and the write bandwidth of the storage is limited to a set expected value by the first control queue.
S3: at least one second control queue is configured at a downlink data output port of each network management device, and each second control queue corresponds to a client connected with the network management device;
in this embodiment, each second control queue has a second mapping identifier pointing to a corresponding client, where the second mapping identifier is a client IP address.
S4: and when the client reads data from the distributed storage cluster, controlling the flow of the read data sent to the corresponding client by the network management equipment according to a second control strategy pre-configured in a second control queue.
In this embodiment, the second control policy is a pre-configured storage bandwidth; and the sum of the storage bandwidths corresponding to all the second control strategies on each network control device is less than the maximum bandwidth of the device.
The second control queue is a classifiable queue, and the configuration process and the control process specifically comprise the following steps: binding a second control queue on a downlink data output network port of the network control equipment, and setting a scheduling algorithm of the second control queue; establishing a class on a second control queue, establishing a root class, then establishing a sub-class on the root class, and setting an expected storage and reading bandwidth on the sub-class; and establishing a filter for each sub-classification, wherein the filter performs filtering classification through a source IP and a destination IP, and when the source IP is an IP of an iSCSI target (iSCSI gateway) and the destination IP is an IP of an iSCSI initiator (client), the filter indicates that the storage is read by the client, and the storage reading bandwidth is limited to a set expected value.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A distributed storage system for realizing flow control is characterized by comprising a distributed storage cluster, at least one network management device and a plurality of clients; the client accesses the distributed storage cluster through the network management equipment;
the uplink data output port of each client is configured with at least one first control queue, and each first control queue corresponds to a network management device connected with the client;
when a client writes data into the distributed storage cluster, the first control queue performs flow control on the write data sent to the corresponding network management equipment by the client according to a first control strategy configured in advance;
at least one second control queue is configured at a downlink data output port of each network management device, and each second control queue corresponds to a client connected with the network management device;
and when the client reads data from the distributed storage cluster, the second control queue controls the flow of the read data sent to the corresponding client by the network management equipment according to a second control strategy configured in advance.
2. The distributed storage system according to claim 1, wherein each first control queue has a first mapping identification pointing to a corresponding network management device, the first mapping identification being a network management device IP address.
3. The distributed storage system according to claim 1 or 2, wherein each second control queue has a second mapping identification pointing to a corresponding client, the second mapping identification being a client IP address.
4. The distributed storage system of claim 1, wherein said first control policy is a preconfigured storage bandwidth;
the sum of the storage bandwidths corresponding to the first control strategy pointing to the network control equipment on the client connected with each network control equipment is less than the maximum bandwidth of the equipment.
5. The distributed storage system according to claim 1 or 4, wherein the second control policy is a preconfigured storage bandwidth; and the sum of the storage bandwidths corresponding to all the second control strategies on each network control device is less than the maximum bandwidth of the device.
6. A distributed storage method for implementing flow control is characterized by comprising the following steps:
s1: configuring at least one first control queue at an uplink data output port of each client, wherein each first control queue corresponds to a network management device connected with the client;
s2: when a client writes data into the distributed storage cluster, flow control is carried out on the write data sent to the corresponding network management equipment by the client according to a first control strategy pre-configured in the first control queue;
s3: configuring at least one second control queue at a downlink data output port of each network management device, wherein each second control queue corresponds to a client connected with the network management device;
s4: and when the client reads data from the distributed storage cluster, controlling the flow of the read data sent to the corresponding client by the network management equipment according to a second control strategy pre-configured in the second control queue.
7. The distributed storage method according to claim 6, wherein each first control queue has a first mapping identifier pointing to a corresponding network management device, the first mapping identifier being a network management device IP address.
8. The distributed storage method according to claim 6 or 7, wherein each second control queue has a second mapping identification pointing to a corresponding client, the second mapping identification being a client IP address.
9. The distributed storage method of claim 6, wherein said first control policy is a preconfigured storage bandwidth;
the sum of the storage bandwidths corresponding to the first control strategy pointing to the network control equipment on the client connected with each network control equipment is less than the maximum bandwidth of the equipment.
10. The distributed storage method according to claim 6 or 9, wherein the second control policy is a pre-configured storage bandwidth; and the sum of the storage bandwidths corresponding to all the second control strategies on each network control device is less than the maximum bandwidth of the device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911046664.0A CN111049669A (en) | 2019-10-30 | 2019-10-30 | Distributed storage system and method for realizing flow control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911046664.0A CN111049669A (en) | 2019-10-30 | 2019-10-30 | Distributed storage system and method for realizing flow control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111049669A true CN111049669A (en) | 2020-04-21 |
Family
ID=70232846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911046664.0A Withdrawn CN111049669A (en) | 2019-10-30 | 2019-10-30 | Distributed storage system and method for realizing flow control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111049669A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114500577A (en) * | 2021-12-27 | 2022-05-13 | 天翼云科技有限公司 | Data access system and data access method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7529836B1 (en) * | 2004-01-08 | 2009-05-05 | Network Appliance, Inc. | Technique for throttling data access requests |
| CN105915387A (en) * | 2016-05-31 | 2016-08-31 | 新浪网技术(中国)有限公司 | External network bandwidth speed limiting method, device and system of cloud host in IaaS cloud platform |
| CN107800645A (en) * | 2016-09-06 | 2018-03-13 | 北京京东尚科信息技术有限公司 | The transmission of cloud host data, reception, transmission method and device |
| CN109154883A (en) * | 2017-03-22 | 2019-01-04 | 波利伍德有限责任公司 | Driving stage internal service quality |
| CN109246023A (en) * | 2018-11-16 | 2019-01-18 | 锐捷网络股份有限公司 | Flow control methods, the network equipment and storage medium |
-
2019
- 2019-10-30 CN CN201911046664.0A patent/CN111049669A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7529836B1 (en) * | 2004-01-08 | 2009-05-05 | Network Appliance, Inc. | Technique for throttling data access requests |
| CN105915387A (en) * | 2016-05-31 | 2016-08-31 | 新浪网技术(中国)有限公司 | External network bandwidth speed limiting method, device and system of cloud host in IaaS cloud platform |
| CN107800645A (en) * | 2016-09-06 | 2018-03-13 | 北京京东尚科信息技术有限公司 | The transmission of cloud host data, reception, transmission method and device |
| CN109154883A (en) * | 2017-03-22 | 2019-01-04 | 波利伍德有限责任公司 | Driving stage internal service quality |
| CN109246023A (en) * | 2018-11-16 | 2019-01-18 | 锐捷网络股份有限公司 | Flow control methods, the network equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114500577A (en) * | 2021-12-27 | 2022-05-13 | 天翼云科技有限公司 | Data access system and data access method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200241613A1 (en) | Persistent reservations for virtual disk using multiple targets | |
| US8447872B2 (en) | Load balancing in a storage system | |
| US8571848B2 (en) | System and method of network emlation for test of on-line server processing heavy traffic | |
| CN108023812B (en) | Content distribution method and device of cloud computing system, computing node and system | |
| CN108369530A (en) | Control method, equipment and the system of reading and writing data order in non-volatile cache transfer bus framework | |
| US10574477B2 (en) | Priority tagging based solutions in fc sans independent of target priority tagging capability | |
| EP2685758A1 (en) | Method, device and system for scheduling data flow | |
| CN108881348A (en) | Method for controlling quality of service, device and storage server | |
| US8732381B2 (en) | SAS expander for communication between drivers | |
| CN103746911A (en) | SDN (software defined networking) structure and communication method thereof | |
| CN105122747A (en) | Control device and control method in software defined network (sdn) | |
| US10599600B2 (en) | Peripheral Component Interconnect Express (PCIe) switching for multi-host computing system deployments | |
| WO2021120633A1 (en) | Load balancing method and related device | |
| CN108989399A (en) | A kind of cluster common data querying method, system, device and readable storage medium storing program for executing | |
| CN109408243A (en) | A kind of data processing method based on RDMA, device and medium | |
| CN103501282B (en) | Network message sending control method, virtual switch and physical machine | |
| US10594631B1 (en) | Methods and apparatus for memory resource management in a network device | |
| CN111049669A (en) | Distributed storage system and method for realizing flow control | |
| WO2009059476A1 (en) | A method for distributing the device number in a stacking system | |
| CN109104369B (en) | Path selection method and device | |
| US9317678B2 (en) | System and method for managing logins in a network interface | |
| US11720413B2 (en) | Systems and methods for virtualizing fabric-attached storage devices | |
| CN106209634B (en) | Learning method and device of address mapping relation | |
| US10574579B2 (en) | End to end quality of service in storage area networks | |
| KR20210016802A (en) | Method for optimizing flow table for network service based on server-client in software defined networking environment and sdn switch thereofor |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200421 |
|
| WW01 | Invention patent application withdrawn after publication |