CN107231316B - Message transmission method and device - Google Patents
Message transmission method and device Download PDFInfo
- Publication number
- CN107231316B CN107231316B CN201710503158.4A CN201710503158A CN107231316B CN 107231316 B CN107231316 B CN 107231316B CN 201710503158 A CN201710503158 A CN 201710503158A CN 107231316 B CN107231316 B CN 107231316B
- Authority
- CN
- China
- Prior art keywords
- message
- server
- priority
- packet
- switch
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- H04L47/31—Flow control; Congestion control by tagging of packets, e.g. using discard eligibility [DE] bits
-
- 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
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a message transmission method and device. The method comprises the following steps: receiving a message sent by a first server, and identifying the message; if the message is identified to be an Ethernet frame carrying remote direct data access RDMA, modifying the Ethernet type identifier of the Ethernet frame into a value of RoCEv 2; and setting the priority of the message as the priority of the highest level. According to the embodiment of the invention, by receiving the message sent by the first server, if the message is an Ethernet frame carrying remote direct data access RDMA, the Ethernet type identifier of the Ethernet frame is modified to the value of RoCEv2, and the priority of the message is set to the highest priority, so that no packet loss of each RoCEv2 message is ensured, and the transmission reliability of the RDMA is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of communication, in particular to a message transmission method and device.
Background
Remote Direct Memory Access (RDMA) is generated to solve the delay of server-side data processing in network transmission.
In the prior art, RDMA is carried in an ethernet frame or a User Datagram Protocol (UDP) packet, and since RDMA is carried in a reliable IB network, the IB network is reliable and does not have a packet loss prevention mechanism. While the traditional ethernet is designed according to the best effort concept, once congestion or equipment failure occurs, packet loss is a common situation. Since UDP is an unreliable fast transmission mode, RDMA is carried in a UDP packet, and reliable transmission of RDMA cannot be guaranteed.
Disclosure of Invention
The embodiment of the invention provides a message transmission method and device, which are used for realizing RDMA transmission reliability.
One aspect of the embodiments of the present invention is to provide a method for transmitting a packet, including:
receiving a message sent by a first server, and identifying the message;
if the message is identified to be an Ethernet frame carrying remote direct data access RDMA, modifying the Ethernet type identifier of the Ethernet frame into a value of RoCEv 2;
and setting the priority of the message as the priority of the highest level.
Another aspect of the embodiments of the present invention is to provide a message transmission apparatus, including:
the receiving module is used for receiving the message sent by the first server;
the identification module is used for identifying the message;
the modification module is used for modifying the Ethernet type identifier of the Ethernet frame into a value of RoCEv2 when the message is identified as the Ethernet frame carrying remote direct data access RDMA by the identification module;
and the setting module is used for setting the priority of the message to the priority of the highest level.
According to the message transmission method and device provided by the embodiment of the invention, by receiving the message sent by the first server, if the message is an Ethernet frame carrying remote direct data access RDMA, the Ethernet type identifier of the Ethernet frame is modified to be the value of RoCEv2, and the priority of the message is set to be the highest priority, so that no packet loss of each RoCEv2 message is ensured, and the RDMA transmission reliability is improved.
Drawings
Fig. 1 is a flowchart of a message transmission method according to an embodiment of the present invention;
fig. 2 is a network structure diagram applicable to the transmission method of the packet according to the embodiment of the present invention;
fig. 3 is a flowchart of a message transmission method according to another embodiment of the present invention;
fig. 4 is a structural diagram of a message transmission apparatus according to an embodiment of the present invention;
fig. 5 is a structural diagram of a message transmission apparatus according to another embodiment of the present invention.
Detailed Description
Fig. 1 is a flowchart of a message transmission method according to an embodiment of the present invention. The embodiment of the invention provides a message transmission method aiming at low transmission reliability of RDMA, which comprises the following steps:
step S101, receiving a message sent by a first server, and identifying the message.
In order to ensure that RDMA carried over UDP, namely, RoCEv2 (i.e., enhanced RoCE), does not lose packets, a method for performing traffic mapping by using UDP and ethernet frames for RoCEv2 to solve the problem of no packet loss is proposed herein.
The basic idea of the method is to map the UDP message carrying RoCEv2 into an Ethernet frame, and then to adopt a packet loss-free mechanism of DCB to ensure that the UDP message has no packet loss.
As shown in fig. 2, S1 represents a first server, S2 represents a second server, and a plurality of switches or routers are arranged between S1 and S2, wherein 21-26 are ethernet switches or routers. The ethernet switch or router 21 receives the message sent from S1 to S2 and sends the message to the next hop switch or router, which in turn sends the message to the next hop switch or router until the message is forwarded to S2.
When the ethernet switch or router 21 receives the message sent by S1 to S2, identifies the message, and identifies whether the message is a message of a default port number of RoCEv2 or an IB network layer message, where the message may specifically be a UDP message, and the message may be identified by a destination port number of the UDP message or identified by a payload type of the UDP message.
Specifically, the message is a UDP message carrying RoCEv 2.
And S102, if the message is identified to be an Ethernet frame carrying remote direct data access RDMA, modifying the Ethernet type identifier of the Ethernet frame to a value of RoCEv 2.
If the message is identified as an Ethernet frame carrying remote direct data access RDMA, the Ethernet type identifier of the Ethernet frame is modified to a value of RoCEv2, for example, the Ethernet type identifier is type 0x0800 of IPv4, which can be modified to a RoCEv2 value of 0x 8916.
IB is an InfiniBand architecture, InfiniBand technology is not used for general network connection, and its main design purpose is to address the connection problem on the server side. Thus, InfiniBand technology will be applied to server-to-server (e.g., replication, distributed work, etc.), server-to-storage (e.g., SAN and direct storage attachment), and server-to-network (e.g., LAN, WANs, and the Internet) communications.
Step S103, setting the priority of the message as the priority of the highest level.
In addition, the ethernet switch or router 21 also enables a DCB mechanism, which is a data center bridging technique proposed by IEEE, that enables the ethernet to carry two different types of data streams. Meanwhile, ETS can provide minimum bandwidth guarantee for a certain traffic, so that a network using DCB technology can be used to carry computing services in addition to merging a normal data stream and a high-priority data stream. The DCB provides a packet loss-free technology of the Ethernet, solves the packet loss problem of RoCEv1, and adopts different priority mechanisms in the Ethernet message according to the type of the upper layer message, thereby ensuring that the high priority message does not lose the packet.
The ethernet switch or router 21 sets the priority of the packet flow of the RoCEv2 passing through the ethernet switch or router 21 to be highest, and according to the mechanism of PFC and ETS, each packet of the RoCEv2 will be ensured to have no packet loss.
In this embodiment, by receiving the packet sent by the first server, if the packet is an ethernet frame carrying remote direct data access RDMA, the ethertype identifier of the ethernet frame is modified to the value of RoCEv2, and the priority of the packet is set to the highest priority, so that it is ensured that each RoCEv2 packet does not lose packets, and the transmission reliability of RDMA is improved.
Fig. 3 is a flowchart of a message transmission method according to another embodiment of the present invention. As shown in fig. 3, the steps of the transmission method of the packet provided in this embodiment are as follows:
step S301, receiving a message sent by a first server, and identifying the message.
Step S302, if the message is identified to be an Ethernet frame carrying remote direct data access RDMA, modifying the Ethernet type identifier of the Ethernet frame to a value of RoCEv 2.
Step S303, the priority of the message is set as the priority of the highest level.
Step S301 to step S303 are respectively consistent with step S103 to step S103, and the detailed process is not described herein again.
And step S304, forwarding the message to a next hop router or a switch.
The ethernet switch or router 21 may further forward the packet to the next-hop ethernet switch or router 23, and the ethernet switch or router 23 may also set the ethertype in the packet to RoCEv2, set the priority of the packet to the highest priority, and perform packet-loss-free protection by using a DCB mechanism.
The ethernet switch or router 23 may further forward the message to a next-hop ethernet switch or router 22, the next-hop ethernet switch or router 22 may further forward the message to a next-hop ethernet switch or router 25, the next-hop ethernet switch or router 25 may further forward the message to a next-hop ethernet switch or router 26, the ethernet switch or router may set the ethertype of the message to RoCEv2 and the priority of the message to highest priority each time passing through one ethernet switch or router, until the message is forwarded to the last router or switch 26 in the link from the first server S1 to the second server S2, the last router or switch 26 restores the value of the RoCEv2 of the message to an ethertype identification, e.g., sets the flag back to ox0800 of IPv4, the message is then forwarded to the second server S2.
In addition, when the network node server sends the RoCEv2 message, a module may also be added at the S1 end of the network node server, where the module is responsible for identifying the message received by the device, and modifying the ethertype identifier in the ethernet frame in the message to a new value of RoCEv 2. Therefore, the first-hop switch or the first-hop router can be prevented from carrying out a large amount of message identification work. The first-hop switch or the first-hop router may perform the highest priority processing directly according to the relevant mechanism of the DCB when receiving the message.
According to the embodiment of the invention, by receiving the message sent by the first server, if the message is an Ethernet frame carrying remote direct data access RDMA, the Ethernet type identifier of the Ethernet frame is modified to the value of RoCEv2, and the priority of the message is set to the highest priority, so that no packet loss of each RoCEv2 message is ensured, and the transmission reliability of the RDMA is improved.
Fig. 4 is a structural diagram of a message transmission apparatus according to an embodiment of the present invention. The transmission apparatus for a message provided in the embodiment of the present invention may execute the processing flow provided in the embodiment of the transmission method for a message, and as shown in fig. 4, the transmission apparatus 40 for a message includes: the server comprises a receiving module 41, an identifying module 42, a modifying module 43 and a setting module 44, wherein the receiving module 41 is used for receiving a message sent by a first server; the recognition module 42 is configured to recognize the packet; the modification module 43 is configured to modify the ethertype identifier of the ethernet frame to a value of RoCEv2 when the recognition module recognizes that the packet is an ethernet frame carrying remote direct data access RDMA; the setting module 44 is configured to set the priority of the packet to the priority of the highest level.
According to the embodiment of the invention, by receiving the message sent by the first server, if the message is an Ethernet frame carrying remote direct data access RDMA, the Ethernet type identifier of the Ethernet frame is modified to the value of RoCEv2, and the priority of the message is set to the highest priority, so that no packet loss of each RoCEv2 message is ensured, and the transmission reliability of the RDMA is improved.
Fig. 5 is a structural diagram of a message transmission apparatus according to another embodiment of the present invention. On the basis of the above embodiment, the message is a UDP message carrying RoCEv 2.
The message transmission device 40 further includes: and the sending module 45, wherein the sending module 45 is configured to forward the packet to a next-hop router or a switch. In addition, the sending module 45 is further configured to forward the packet to a last router or switch in a link from the first server to the second server, recover, by the last router or switch, the value of RoCEv2 of the packet to be the ethertype identifier, and forward the packet to the second server. The identifying module 42 is specifically configured to identify the packet according to a destination port number of the UDP packet.
The transmission apparatus for a packet provided in the embodiment of the present invention may be specifically configured to execute the method embodiment provided in fig. 1, and specific functions are not described herein again.
According to the embodiment of the invention, by receiving the message sent by the first server, if the message is an Ethernet frame carrying remote direct data access RDMA, the Ethernet type identifier of the Ethernet frame is modified to the value of RoCEv2, and the priority of the message is set to the highest priority, so that no packet loss of each RoCEv2 message is ensured, and the transmission reliability of the RDMA is improved.
In summary, in the embodiment of the present invention, by receiving the packet sent by the first server, if the packet is an ethernet frame carrying remote direct data access RDMA, the ethertype identifier of the ethernet frame is modified to the value of RoCEv2, and the priority of the packet is set to the highest priority, so that it is ensured that each packet of RoCEv2 does not lose packets, and the transmission reliability of RDMA is improved.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. A method for transmitting a message is characterized by comprising the following steps:
receiving a message sent by a first server, and identifying the message;
if the message is identified to be an Ethernet frame carrying remote direct data access RDMA, modifying the Ethernet type identifier of the Ethernet frame into a value of RoCEv 2;
setting the priority of the message as the priority of the highest level;
wherein the message is a UDP message carrying RoCEv 2;
after setting the priority of the packet to the highest priority, the method further includes:
forwarding the message to a next-hop router or switch;
the forwarding the packet to a next-hop router or switch includes:
and forwarding the message to the last router or switch in the link from the first server to the second server, recovering the RoCEv2 value of the message to be the Ethertype identifier by the last router or switch, and forwarding the message to the second server.
2. The method of claim 1, wherein the identifying the packet comprises:
and identifying the message according to the destination port number of the UDP message.
3. A message transmission apparatus, comprising:
the receiving module is used for receiving the message sent by the first server;
the identification module is used for identifying the message;
the modification module is used for modifying the Ethernet type identifier of the Ethernet frame into a value of RoCEv2 when the message is identified as the Ethernet frame carrying remote direct data access RDMA by the identification module;
the setting module is used for setting the priority of the message to the priority of the highest level;
wherein the message is a UDP message carrying RoCEv 2;
the transmission device further includes:
the sending module is used for forwarding the message to a next hop router or a switch;
the sending module is further configured to forward the packet to a last router or switch in a link from the first server to the second server, recover, by the last router or switch, a value of RoCEv2 of the packet to an ethertype identifier, and forward the packet to the second server.
4. The message transmission apparatus according to claim 3, wherein the identification module is specifically configured to identify the message according to a destination port number of a UDP message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710503158.4A CN107231316B (en) | 2017-06-27 | 2017-06-27 | Message transmission method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710503158.4A CN107231316B (en) | 2017-06-27 | 2017-06-27 | Message transmission method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107231316A CN107231316A (en) | 2017-10-03 |
| CN107231316B true CN107231316B (en) | 2020-03-13 |
Family
ID=59936474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710503158.4A Active CN107231316B (en) | 2017-06-27 | 2017-06-27 | Message transmission method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107231316B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111654447B (en) * | 2018-01-16 | 2023-04-18 | 华为技术有限公司 | Message transmission method and device |
| CN111371580B (en) * | 2018-12-26 | 2023-03-14 | 浙江宇视科技有限公司 | Chain roaming method and device for instructions on data exchange equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1333565C (en) * | 2005-10-20 | 2007-08-22 | 华为技术有限公司 | Method for realizing message transmitting, access network and network apparatus |
| CN102315970B (en) * | 2011-09-23 | 2013-09-18 | 北京星网锐捷网络技术有限公司 | Data center bridging parameter configuration method, system and network equipment |
| CN102801729B (en) * | 2012-08-13 | 2015-06-17 | 福建星网锐捷网络有限公司 | Virtual machine message forwarding method, network switching equipment and communication system |
| CN103812787A (en) * | 2014-03-03 | 2014-05-21 | 国家电网公司 | Electric power telecommunication network message prior forwarding method |
| CN105490961A (en) * | 2014-09-19 | 2016-04-13 | 杭州迪普科技有限公司 | Message processing method, and device and network device |
| CN104410586B (en) * | 2014-12-11 | 2018-08-07 | 福建星网锐捷网络有限公司 | Message processing method and device under a kind of VSU environment |
-
2017
- 2017-06-27 CN CN201710503158.4A patent/CN107231316B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 《Supplement to InfiniBand Architecture Specification》;InfiniBand Trade Association;《Supplement to InfiniBand Architecture Specification Volume 1 Release 1.2.1》;20140902;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107231316A (en) | 2017-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113709057B (en) | Network congestion notification method, proxy node, network node and computer equipment | |
| US11115339B2 (en) | Network congestion control method, device, and system | |
| US11032205B2 (en) | Flow control method and switching device | |
| US11418629B2 (en) | Methods and systems for accessing remote digital data over a wide area network (WAN) | |
| US8792506B2 (en) | Inter-domain routing in an n-ary-tree and source-routing based communication framework | |
| US8306039B2 (en) | Methods and systems for automatic transport path selection for multi-homed entities in stream control transmission protocol | |
| EP3694160A1 (en) | Date transmission method, apparatus and device | |
| CN107342906B (en) | Elephant flow detection method, equipment and system | |
| US8953631B2 (en) | Interruption, at least in part, of frame transmission | |
| CN105745883B (en) | Forwarding table synchronous method, the network equipment and system | |
| US9425893B1 (en) | Methods and apparatus for implementing optical integrated routing with traffic protection | |
| US8416684B2 (en) | Time and data rate policing | |
| US20150215224A1 (en) | Positive feedback ethernet link flow control for promoting lossless ethernet | |
| US11108699B2 (en) | Method, apparatus, and system for implementing rate adjustment at transmit end | |
| CN110943933A (en) | Method, device and system for realizing data transmission | |
| WO2019105317A1 (en) | Method for sending service packet, network device, and system | |
| WO2015172668A1 (en) | Method and device for determining congestion window in network | |
| US20090296738A1 (en) | Method and apparatus for frame relay | |
| WO2000072532A1 (en) | System and method for network packet reduction | |
| CN107231316B (en) | Message transmission method and device | |
| US20180069790A1 (en) | Packet transfer device and packet transfer method | |
| WO2019205756A1 (en) | Data transmission protection method, apparatus, and system, and computer readable storage medium | |
| WO2022028342A1 (en) | Method for processing congestion flow and device | |
| CN113612698A (en) | Data packet sending method and device | |
| CN117354253A (en) | Network congestion notification method, device and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |