CN116886643A - Method for improving TOE performance - Google Patents
Method for improving TOE performance Download PDFInfo
- Publication number
- CN116886643A CN116886643A CN202311145973.XA CN202311145973A CN116886643A CN 116886643 A CN116886643 A CN 116886643A CN 202311145973 A CN202311145973 A CN 202311145973A CN 116886643 A CN116886643 A CN 116886643A
- Authority
- CN
- China
- Prior art keywords
- control message
- message
- toe
- data message
- unit
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000000872 buffer Substances 0.000 claims abstract description 70
- 230000009471 action Effects 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 18
- 230000005540 biological transmission Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 abstract description 15
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000012464 large buffer Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
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
- H04L47/43—Assembling or disassembling of packets, e.g. segmentation and reassembly [SAR]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/90—Buffering arrangements
- H04L49/9057—Arrangements for supporting packet reassembly or resequencing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Computer And Data Communications (AREA)
Abstract
The application relates to a method for improving TOE performance, which comprises the following steps: the TOE driver provides a sending judging unit, an assembling unit, a control message buffer area and a data message buffer area, wherein the sending judging unit is used for identifying whether the message type to be sent by a user is a control message or a data message according to the protocol action of the core space of the host; the assembling unit is used for respectively assembling the control message and the data message according to the judging result of the judging unit; the assembling unit stores the assembled control message into a control message buffer area and informs the TOE module to process the control message, and stores the assembled data message into a data message buffer area and informs the TOE module to process the data message. The application can ensure the stability and high efficiency of data transmission while ensuring the TCP protocol processing rate under the high concurrency scene by separating the data stream from the control stream and independently controlling the sizes of the data channel and the control channel buffer zone.
Description
Technical Field
The application relates to the field of cloud computing, in particular to a method for improving TOE performance.
Background
In recent years, with the development of the DPU industry, many products have been applied to the fields of cloud computing, so that the computing power of a server CPU consumed on a network is greatly reduced, and the computing resources that can be sold by a cloud computing host are improved. The TCP offload engine, i.e. TOE (TCP Offload Engine), deploys a driver on the cloud computing host, and sinks the protocol processing of TCP to the DPU, and the driver and the DPU together replace the cloud computing host to establish TCP connection, transmit data and close, so as to further reduce the computational power consumed by the CPU of the cloud computing host in network protocol processing, and improve the performance of the TCP network.
However, in the existing TOE implementation technology, a full offload manner is generally adopted, as shown in fig. 1, a control packet and a data packet of a TCP are taken over and drained to a DPU, and the DPU implements the function of a TCP protocol stack. When the TCP connection is high in concurrency, the number of control messages is greatly increased, and the DPU can process a large number of control messages, so that the problem of reducing the TCP data forwarding performance is solved.
Disclosure of Invention
The method for improving TOE performance is provided to overcome the defect that in the prior art, under a high concurrency scene, the DPU intensively processes a large amount of control signals to cause the reduction of data stream processing capacity to generate jitter or even decline of data rate.
In a preferred embodiment of the present application, a method for improving the performance of a TOE is provided in the present application, and the method is used for a host with a TOE full offload function, where the host includes a TOE module for driving a TOE and executing the TOE function, and the method includes:
step S1, the TOE driver provides a sending judging unit which is used for identifying whether the message type to be sent by a user is a control message or a data message according to the protocol action of the core space of the host;
step S2, an assembling unit is also provided for respectively assembling the control message and the data message according to the judging result of the sending judging unit;
step S3, a control message buffer area and a data message buffer area are also provided, the assembly unit stores the assembled control message into the control message buffer area and notifies the TOE module to process the control message, and
the assembling unit stores the assembled data message into the data message buffer area and notifies the TOE module to process the data message.
Further, the method further comprises:
the TOE driver provides a receiving judging unit, and the receiving judging unit judges whether the received message is a control message or a data message according to the notification provided by the TOE module;
step R2, a reading unit is also provided for reading the control message from the control message buffer according to the judgment result of the reception judgment unit, and
reading the data message from the data message buffer;
and R3, a protocol triggering unit is further provided, the read unit sends the read message to the protocol triggering unit, and the protocol triggering unit triggers the protocol action of the core space of the host according to the received message.
Further, the host includes a core space socket library to connect to a user space socket library, in the step S1:
the transmission judgment unit provides a first control message channel, and
a first data message channel for connecting to the core space socket library respectively, for acquiring the control message through the first control message channel according to protocol action, and
and acquiring the data message through the first data message channel.
Further, in the step S3:
the assembly unit provides a control message storage channel to connect the control message buffer area; and
the assembly unit provides a data message storage channel to connect the data message buffers.
Further, in the step R1:
the receiving judging unit provides a second control message channel and a second data message channel to be respectively connected with the TOE module.
Further, in the step R1:
the notification sent by the TOE module comprises an interrupt signal, the TOE module sends the interrupt signal through the second control message channel and the second data message channel, and the receiving judging unit judges whether the control message or the data message is received according to the channel where the interrupt signal is located.
Further, in the step R1:
the TOE module writes the received messages into the control message buffer zone and the data message buffer zone respectively according to the types through the DMA channel.
Further, in the step R2:
the reading unit provides a control message reading channel to be connected with the control message buffer area, and a data message reading channel to be connected with the data message buffer area, the receiving judging unit reads the control message through the control message reading channel, and the receiving judging unit reads the data message through the data message reading channel.
Further, in the step R2:
and the second receiving judging unit judges whether the control message needs to be sent or not according to the read data message, if the control message needs to be sent, the control message is assembled by the assembling unit, the assembled control message is stored in the control message buffer area by the assembling unit, and the TOE module is informed to process the control message.
Further, the TOE driver also provides an adjusting unit for adjusting the size of the control message buffer and the size of the data message buffer, respectively.
The application has the following beneficial effects:
the application can ensure the stability and the high efficiency of data transmission while ensuring the processing rate of the TCP protocol under a high concurrency scene by separating the data stream from the control stream and independently controlling the sizes of the data channel and the buffer zone of the control channel, and also improves the processing performance of the control stream and the data stream due to the parallel processing of the control stream and the data stream which are separated.
Drawings
The above features, technical features, advantages and implementation thereof will be further described in the following detailed description of preferred embodiments with reference to the accompanying drawings in a clearly understandable manner.
FIG. 1 shows a schematic block diagram of a prior art TOE implementation;
FIG. 2 shows a flow chart of a method of improving TOE performance according to one embodiment of the present application;
FIG. 3 is a flow chart of a method of improving TOE performance according to another embodiment of the present application;
FIG. 4 illustrates a functional block diagram of a TOE implementation of one embodiment of the present application with control flow separated from data flow;
fig. 5 shows a schematic diagram of the structure of the TOE processing control flow separated from the data flow according to an embodiment of the present application.
Detailed Description
Various aspects of the application are described in further detail below.
Unless defined or otherwise indicated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, any method and material similar or equivalent to those described may be used in the methods of the present application.
The terms are described below.
The term "or" as used herein includes the relationship of "and" unless specifically stated and defined otherwise. The sum corresponds to the boolean logic operator AND, the OR corresponds to the boolean logic operator OR, AND the AND is a subset of OR.
It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. Thus, a first element could be termed a second element without departing from the teachings of the present inventive concept.
In the present application, the terms "comprising," "including," or "comprising" mean that the various ingredients may be used together in a mixture or composition of the present application. Thus, the term "consisting essentially of.
The terms "connected," "connected," and "connected" in this application are to be construed broadly, as they are, for example, fixedly connected or via an intermediary, in connection with one another, or in connection with one another, as they are in communication with one another, or in an interaction relationship between two elements, unless otherwise specifically indicated and defined. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art according to the specific circumstances.
For example, if an element (or component) is referred to as being "on", "coupled" or "connected" to another element, it can be directly on, coupled or connected to the other element or one or more intervening elements may be present therebetween. Conversely, if the expressions "directly on," "directly with," coupled "and" directly with, "connected" are used herein, then no intervening elements are indicated. Other words used to describe the relationship between elements should be interpreted similarly, such as "between" and "directly between", "attached" and "directly attached", "adjacent" and "directly adjacent", and the like.
It should be further noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to directions in the drawings. The words "inner" and "outer" are used to refer to directions toward or away from, respectively, the geometric center of a particular component. It will be understood that these terms are used herein to describe one element, layer or region's relationship to another element, layer or region as illustrated in the figures. These terms should also encompass other orientations of the device in addition to the orientation depicted in the figures.
Other aspects of the application will be apparent to those skilled in the art in view of the disclosure herein.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will explain the specific embodiments of the present application with reference to the accompanying drawings. It is evident that the drawings in the following description are only examples of the application, from which other drawings and other embodiments can be obtained by a person skilled in the art without inventive effort.
It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present application by way of illustration, and only the components related to the present application are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated. For example, the thickness of elements in the drawings may be exaggerated for clarity.
The application provides a method for improving TOE performance, which is used for a host with a TOE full unloading function, wherein the host comprises a TOE module for TOE driving and executing the TOE function, as shown in fig. 2 and 5, the method comprises the following steps:
step S1, TOE drive provides a sending judging unit which is used for identifying whether the message type to be sent by the user is a control message or a data message according to the protocol action of the core space of the host;
step S2, an assembling unit is also provided for respectively assembling the control message and the data message according to the judging result of the sending judging unit;
step S3, a control message buffer area and a data message buffer area are also provided, the assembly unit stores the assembled control message into the control message buffer area and notifies the TOE module to process the control message, and
the assembly unit stores the assembled data message in the data message buffer area and notifies the TOE module to process the data message.
It can be understood that, according to the supporting mode of the TOE module for the protocol part (such as TCP/IP protocol), the protocol part unloading mode is divided into two modes of full unloading and partial unloading, and in the full unloading mode, the TOE module completes all functions of the protocol part without participation of the CPU.
It will be appreciated that the TOE function is performed by the TOE driver control TOE module installed on the host, i.e., full offloading of the protocol portions can be achieved.
It is understood that the transmission judging unit may recognize whether the message type is a control message or a data message by detecting a header of a message to be transmitted by the user.
It can be understood that, for the host server, the storage space is divided into a memory and an external memory, and the external memory includes a Double Data Rate (DDR) memory of TOE hardware, which is disadvantageous in that the storage space is small, the cost is high, and the performance is low, so that the storage space is easily insufficient when dealing with the protocol part full offload processing. The memory of the host server usually has a larger storage space, such as random access memory (Random Access Memory, RAM), and can store buffer data far more than the DDR memory of the TOE hardware, so that a large buffer space can be physically provided by using the host memory as a data message buffer. In this embodiment, the control message buffer, as well as the data message buffer, is provided through host memory, such as through integrated memory on the host motherboard.
In the above technical solution, when the user space generates a request for sending data through the TCP protocol, the socket library in the core space of the host is connected through the socket, and the socket library in the core space of the host generates a corresponding protocol action according to the type of the request, and sends the corresponding protocol action to the TOE driver, and the sending judgment unit in the TOE driver identifies whether the message to be sent is a control message or a data message by identifying the protocol action, and the assembling unit assembles the message and stores the message in a corresponding storage such as a control message buffer or a data message buffer, and notifies the TOE module to perform further processing. Typically, the TOE module is integrated into a network card, and the related transactions of the TCP protocol are all offloaded to the network card for processing, without the CPU participating in the processing.
In a preferred embodiment, the assembling unit may be provided with an independent control message assembling unit and an independent data message assembling unit, so that the control message and the data message may be assembled and stored independently and in parallel, thereby improving the operation efficiency.
As a preferred embodiment, as shown in fig. 3 and 5, the method further includes:
the method comprises the following steps that R1, a TOE driver provides a receiving judging unit, and the receiving judging unit judges whether a received message is a control message or a data message according to a notification provided by a TOE module;
step R2, a reading unit is also provided for reading the control message from the control message buffer according to the judgment result of the reception judgment unit, and
reading a data message from a data message buffer;
and R3, providing a protocol triggering unit, transmitting the read message to the protocol triggering unit by the reading unit, and triggering the protocol action of the core space of the host by the protocol triggering unit according to the received message.
According to the technical scheme, when the message is received, the receiving judging unit judges whether the received message is the control message or the data message according to the notification of the TOE module, the reading unit reads the corresponding message from the control message buffer area according to the identification result of the receiving judging unit if the received message is the control message, and reads the corresponding message from the data message buffer area if the received message is the data message, and the protocol triggering unit triggers the corresponding protocol action of the socket library in the core space of the host according to the read message to inform the user space to process.
It is to be understood that the steps R1 to R3 and the steps S1 to S3 do not have a sequential relationship, and they may be performed synchronously or asynchronously, or may be performed in a set order.
In a preferred embodiment, the reading unit may be provided with an independent control message reading unit and an independent data message reading unit, so that the control message and the data message can be read independently and in parallel, thereby improving the operation efficiency.
As a preferred embodiment, the host includes a core space socket library to connect with the user space socket library, in step S1:
the transmission judgment unit provides a first control message channel, and
a first data message channel for connecting to the core space socket library respectively to obtain control messages according to protocol actions via the first control message channel, and
and acquiring the data message through the first data message channel.
It will be appreciated that a Socket (Socket) may be considered as an endpoint in a respective communication connection when two network application layers communicate, as is an application programming interface (Application Programming Interface, API) for interprocess communication in a network environment, as well as a communication endpoint that may be named and addressed, each Socket in use having its type and a process connected to it.
According to the technical scheme, the starting unit is connected with the socket library in the core space through the independent first control message channel and the independent first data message channel, and can independently and parallelly process protocol actions of the socket library in the core space, so that the running efficiency can be improved.
As a preferred embodiment, in step S3:
the assembling unit provides a control message storage channel to connect with the control message buffer area; and
the assembly unit provides a data message storage channel to connect to the data message buffer.
According to the technical scheme, the assembly unit is connected with the control message buffer area through the independent control message storage channel and connected with the data message buffer area through the independent data message storage channel, so that the assembly unit can independently and parallelly process the control message storage and the data message storage, and the operation efficiency is improved.
In a preferred embodiment, in the step R1:
the receiving judging unit provides a second control message channel and a second data message channel to be respectively connected with the TOE module.
According to the technical scheme, the receiving judging unit is respectively connected to the TOE module through the independent second control message channel and the second data message channel, so that the notification corresponding to the TOE module can be received from different channels, and the current received message is quickly identified as the control message or the data message, thereby improving the operation efficiency.
In a preferred embodiment, in the step R1:
the notification sent by the TOE module comprises an interrupt signal, the TOE module sends the interrupt signal through a second control message channel and a second data message channel, and the receiving judging unit judges whether the control message or the data message is received according to the channel where the interrupt signal is located.
According to the technical scheme, the TOE module can adopt the interrupt signal mode, and inform the type of the message currently received by the receiving and judging unit by respectively sending different interrupt signals to the second control message channel and the second data message channel, so that the identification speed of the receiving and judging unit is increased, and the operation efficiency is improved.
In a preferred embodiment, in the step R1:
the TOE module writes the received messages into the control message buffer and the data message buffer respectively according to the types through the DMA channel.
In the above technical solution, the TOE module can write the received message into the corresponding control message buffer and the data message buffer directly through DMA (Direct Memory Access ) channel according to the type of the message
In a preferred embodiment, in the step R2:
the reading unit provides a control message reading channel to be connected with the control message buffer area, and a data message reading channel to be connected with the data message buffer area, the receiving judging unit reads the control message through the control message reading channel, and the receiving judging unit reads the data message through the data message reading channel.
In a preferred embodiment, in the step R2:
and a second receiving judging unit is also provided, and judges whether the control message needs to be sent or not according to the read data message, if the control message needs to be sent, the control message is assembled through the assembling unit, the assembled control message is stored into the control message buffer area by the assembling unit, and the TOE module is informed to process the control message.
As a preferred embodiment, the protocol triggering unit further transmits the control message and the data message read by the reading unit to the core space of the host computer by being connected to the core space of the host computer through the first control message channel and the first data message channel.
In a preferred embodiment, the TOE driver further provides an adjusting unit for adjusting the size of the control message buffer and the size of the data message buffer, respectively.
According to the technical scheme, the system can adjust the sizes of the control message buffer zone and the data message buffer zone according to the current message receiving and sending condition by providing the adjusting unit, so that the utilization efficiency of system resources is improved.
Examples
Referring to fig. 4, a method for improving TOE performance according to an exemplary embodiment of the present application includes: in the user state triggering direction, TCP is led to a TOE driver through a TCP protocol take-over module, in the TOE driver, the message type is firstly identified through TCP protocol action, if the message type is a control flow, a control message is assembled and written into a message data message buffer area, and a DPU is notified to process the message; if the message is a data message, the data message is assembled and written into a message data message buffer, informing the DPU of the message handling. In the device interrupt triggering direction, firstly judging whether the device is a control message or a data message according to the interrupt number, if the device is the control message, reading the control message from a message data message buffer zone, and triggering TCP protocol action according to the message content; if the data message is the data message, reading the data message from a message data message buffer area, judging whether to send a control message according to the data message, and if the control message is not needed to be sent, returning the data to a user state through TCP action; and if the control message is required to be sent, sending the control message through the control message sending flow.
The application can ensure the stability and the high efficiency of data transmission while ensuring the processing rate of the TCP protocol under a high concurrency scene by separating the data stream from the control stream and independently controlling the sizes of the data channel and the buffer zone of the control channel, and also improves the processing performance of the control stream and the data stream due to the parallel processing of the control stream and the data stream which are separated.
Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, apparatus may be implemented and/or methods practiced using any number and aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
Those skilled in the art will appreciate that the application provides a system and its individual devices, modules, units, etc. that can be implemented entirely by logic programming of method steps, in addition to being implemented as pure computer readable program code, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, the system and various devices, modules and units thereof provided by the application can be regarded as a hardware component, and the devices, modules and units for realizing various functions included in the system can also be regarded as structures in the hardware component; means, modules, and units for implementing the various functions may also be considered as either software modules for implementing the methods or structures within hardware components.
It should be noted that the above embodiments can be freely combined as needed. The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application, which are intended to be comprehended within the scope of the present application.
All documents mentioned in this disclosure are incorporated by reference in this disclosure as if each were individually incorporated by reference. Further, it is understood that various changes and modifications of the present application may be made by those skilled in the art after reading the above description of the application, and such equivalents are intended to fall within the scope of the application as defined in the appended claims.
Claims (10)
1. A method for improving TOE performance for a host having a TOE full offload function, the host including a TOE module for TOE driving and performing TOE functions, the method comprising:
step S1, the TOE driver provides a sending judging unit which is used for identifying whether the message type to be sent by a user is a control message or a data message according to the protocol action of the core space of the host;
step S2, an assembling unit is also provided for respectively assembling the control message and the data message according to the judging result of the sending judging unit;
step S3, a control message buffer area and a data message buffer area are also provided, the assembly unit stores the assembled control message into the control message buffer area and notifies the TOE module to process the control message, and
the assembling unit stores the assembled data message into the data message buffer area and notifies the TOE module to process the data message.
2. The method for improving TOE performance of claim 1, further comprising:
the TOE driver provides a receiving judging unit, and the receiving judging unit judges whether the received message is a control message or a data message according to the notification provided by the TOE module;
step R2, a reading unit is also provided for reading the control message from the control message buffer according to the judgment result of the reception judgment unit, and
reading the data message from the data message buffer;
and R3, a protocol triggering unit is further provided, the read unit sends the read message to the protocol triggering unit, and the protocol triggering unit triggers the protocol action of the core space of the host according to the received message.
3. The method of improving TOE performance according to claim 1, wherein the host includes a kernel space socket library for connecting to a user space socket library, wherein in step S1, the transmission judgment unit provides a first control message channel, and
a first data message channel respectively connected to the core space socket library for acquiring the control message via the first control message channel according to protocol action, and
and acquiring the data message through the first data message channel.
4. The method for improving TOE performance according to claim 1, wherein in the step S3, the assembling unit provides a control message storage channel to connect the control message buffer; and
the assembly unit provides a data message storage channel to connect the data message buffers.
5. The method of claim 2, wherein the receiving and judging unit in the step R1 provides a second control message channel and a second data message channel to connect the TOE modules respectively.
6. The method for improving TOE performance according to claim 5, wherein the notification sent by the TOE module in step R1 includes an interrupt signal, the TOE module sends the interrupt signal through the second control message channel and the second data message channel, and the reception judging unit judges whether a control message or a data message is received according to the channel in which the interrupt signal is located.
7. The method of improving TOE performance of claim 2 wherein in step R1 said TOE module writes received messages to said control message buffer and said data message buffer, respectively, by type via DMA channels.
8. The method according to claim 2, wherein said reading unit in said step R2 provides a control message reading channel to connect said control message buffer and a data message reading channel to connect said data message buffer, said reception judging unit reads said control message through said control message reading channel, and said reception judging unit reads said data message through said data message reading channel.
9. The method for improving TOE performance according to claim 8, wherein a second receiving and judging unit is further provided in the step R2, and the second receiving and judging unit judges whether a control message needs to be sent according to the read data message, if the control message needs to be sent, the control message is assembled by the assembling unit, the assembled control message is stored in the control message buffer area by the assembling unit, and the TOE module is informed to process the control message.
10. The method of claim 1, wherein the TOE driver further provides an adjustment unit for adjusting the size of the control message buffer and the size of the data message buffer, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311145973.XA CN116886643B (en) | 2023-09-07 | 2023-09-07 | Method for improving TOE performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311145973.XA CN116886643B (en) | 2023-09-07 | 2023-09-07 | Method for improving TOE performance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116886643A true CN116886643A (en) | 2023-10-13 |
| CN116886643B CN116886643B (en) | 2023-11-17 |
Family
ID=88257190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311145973.XA Active CN116886643B (en) | 2023-09-07 | 2023-09-07 | Method for improving TOE performance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116886643B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060007935A1 (en) * | 2004-05-11 | 2006-01-12 | Bennett James D | Method and system for handling out-of-order segments in a wireless system via direct data placement |
| CN103546424A (en) * | 2012-07-10 | 2014-01-29 | 华为技术有限公司 | TCP (transmission control protocol) data transmission method and TCP unloading engine and system |
| CN104598406A (en) * | 2015-02-03 | 2015-05-06 | 杭州士兰控股有限公司 | Expansion function unit and computing equipment expansion system and expansion method |
| CN112953967A (en) * | 2021-03-30 | 2021-06-11 | 扬州万方电子技术有限责任公司 | Network protocol unloading device and data transmission system |
-
2023
- 2023-09-07 CN CN202311145973.XA patent/CN116886643B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060007935A1 (en) * | 2004-05-11 | 2006-01-12 | Bennett James D | Method and system for handling out-of-order segments in a wireless system via direct data placement |
| CN103546424A (en) * | 2012-07-10 | 2014-01-29 | 华为技术有限公司 | TCP (transmission control protocol) data transmission method and TCP unloading engine and system |
| CN104598406A (en) * | 2015-02-03 | 2015-05-06 | 杭州士兰控股有限公司 | Expansion function unit and computing equipment expansion system and expansion method |
| CN112953967A (en) * | 2021-03-30 | 2021-06-11 | 扬州万方电子技术有限责任公司 | Network protocol unloading device and data transmission system |
Non-Patent Citations (1)
| Title |
|---|
| 吴惑 等: "基于FPGA的万兆以太网TCP/IP协议处理架构", 电子设计工程, vol. 28, no. 9, pages 81 - 87 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116886643B (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20040117368A1 (en) | Transmitting acknowledgements using direct memory access | |
| CN112422453A (en) | Message processing method, device, medium and equipment | |
| CN112511840B (en) | Decoding system and method based on FFMPEG and hardware acceleration equipment | |
| US11758023B2 (en) | Multicore electronic device and packet processing method thereof | |
| US20230152978A1 (en) | Data Access Method and Related Device | |
| US8539089B2 (en) | System and method for vertical perimeter protection | |
| CN102196033A (en) | Remote content classification and transmission using multiple transport channels | |
| US7178051B2 (en) | Method for synchronous support of fault-tolerant and adaptive communication | |
| CN116132287A (en) | DPU-based high-performance network acceleration method and system | |
| US7191356B2 (en) | Method for asynchronous support of fault-tolerant and adaptive communication | |
| CN116886643B (en) | Method for improving TOE performance | |
| CN114296659A (en) | Data one-way transmission method, intranet end unit and one-way isolation optical gate system | |
| CN102117261B (en) | Communication method between inner processors of chip | |
| CN110798366B (en) | Task logic processing method, device and equipment | |
| US20030236929A1 (en) | Buffer management methods and apparatus for network device drivers | |
| CN113572695A (en) | Link aggregation method and device, computing equipment and computer storage medium | |
| CN116032498A (en) | Memory area registration method, device and equipment | |
| CN115840650B (en) | Method for realizing three-terminal system communication based on kvisor isolated real-time domain | |
| CN116932454B (en) | Data transmission method, device, electronic equipment and computer readable storage medium | |
| WO2023185666A1 (en) | Switch fabric unit, data forwarding method, switching frame, and network system | |
| CN114328317B (en) | Method, device and medium for improving communication performance of storage system | |
| CN116775418B (en) | Routing node in network on chip, frequency adjustment method and electronic equipment | |
| CN114466088B (en) | Data transmission method and device of sweeping robot, storage medium and terminal | |
| CN115473861B (en) | High-performance processing system and method based on communication and calculation separation and storage medium | |
| CN114500052B (en) | Event-driven-based efficient data encryption forwarding method and device |
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 |