CN116405377B - Network state detection method, protocol conversion component, equipment and storage medium - Google Patents

Network state detection method, protocol conversion component, equipment and storage medium Download PDF

Info

Publication number
CN116405377B
CN116405377B CN202310665797.6A CN202310665797A CN116405377B CN 116405377 B CN116405377 B CN 116405377B CN 202310665797 A CN202310665797 A CN 202310665797A CN 116405377 B CN116405377 B CN 116405377B
Authority
CN
China
Prior art keywords
information
node
state
queue
target
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
Application number
CN202310665797.6A
Other languages
Chinese (zh)
Other versions
CN116405377A (en
Inventor
刘蕊丽
强鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Taichu Wuxi Electronic Technology Co ltd
Original Assignee
Taichu Wuxi Electronic Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Taichu Wuxi Electronic Technology Co ltd filed Critical Taichu Wuxi Electronic Technology Co ltd
Priority to CN202310665797.6A priority Critical patent/CN116405377B/en
Publication of CN116405377A publication Critical patent/CN116405377A/en
Application granted granted Critical
Publication of CN116405377B publication Critical patent/CN116405377B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0677—Localisation of faults

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention relates to the technical field of communication and discloses a network state detection method, a protocol conversion assembly, equipment and a storage medium.

Description

Network state detection method, protocol conversion component, equipment and storage medium
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a network state detection method, a protocol conversion component, a device, and a storage medium.
Background
As technology advances, a Network On Chip (NOC) may support simultaneous access from multiple first nodes to multiple second nodes, e.g., request information is generated by a first node and transmitted to a corresponding second node for processing via a routing Network. Likewise, the responses generated by the respective second nodes are fed back to the corresponding first nodes via the routing network in the same manner. However, in the process of information transmission, if the network node is abnormal, information transmission cannot be performed. In the related art, each network node (such as the first node or the second node) only manages its own state, so that the network node in the related art cannot learn the network state of the entire network, and thus cannot quickly locate an abnormal node in the network.
Disclosure of Invention
In view of the above, the present invention provides a network state detection method, a protocol conversion component, a device and a storage medium, which can quickly locate an abnormal node in a network.
In a first aspect, the present invention provides a network state detection method, the method being applicable to a network state detection system, the network state detection system comprising: at least one first node, at least one second node and a third node, wherein a first network interface unit (first NIU) corresponding to the first node and a second network interface unit (second NIU) corresponding to the second node are respectively arranged, and the first NIU and the second NIU comprise protocol conversion components; the method is performed by a protocol conversion component, the method comprising:
determining the first information quantity of acquired request information and the second information quantity of acquired response information, wherein the request information is information sent by a first node to a second node, and the response information is information sent by the second node to the first node;
determining a target information quantity according to the first information quantity and the second information quantity;
Determining first queue state information of a first cache queue and second queue state information of a second cache queue, wherein the first cache queue is used for caching the request information and the response information, and the second cache queue is used for caching routing information converted from the response information and routing information converted from the request information;
determining node state information of a target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information, wherein the target node is the first node and/or the second node; the node state information comprises an idle state and a busy state;
the determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
when the number of the target information is equal to a preset threshold, the first queue state information indicates that the first cache queue is in an empty state, the second queue state information indicates that the second cache queue is in an empty state, and node state information of a target node corresponding to the protocol conversion component is determined to be in the idle state;
The determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
when the number of the target information is not equal to a preset threshold value, and/or the first queue state information indicates that the first cache queue is in a non-empty state, and/or the second queue state information indicates that the second cache queue is in a non-empty state, determining that node state information of a target node corresponding to the protocol conversion component is the busy state;
and sending the node state information to the third node, so that the third node detects the network state according to the node state information, and thus abnormal nodes in the network are rapidly positioned.
In an alternative embodiment, when the initial amount of information is stored in the protocol conversion component, the method further comprises:
and determining the target information quantity according to the first information quantity, the second information quantity and the initial information quantity.
In an alternative embodiment, the determining the first information amount of the acquired request information and the second information amount of the acquired response information includes:
When the request information is converted into the route information, determining the first information quantity of the acquired request information;
when the response information is converted into the routing information, determining a second information amount of the acquired response information.
In an optional embodiment, the sending the node status information to the third node, so that the third node detects a network status according to the node status information, includes:
when the node state information corresponding to the first node is in a busy state, and when the node state information corresponding to the second node is in an idle state, the third node determines that the network state of the first node is abnormal;
or when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in a busy state, the third node determines that the network state of the second node is in an abnormal state;
or when the node state information corresponding to the first node is a busy state and the node state information corresponding to the second node is a busy state, the third node determines that the network state of the second node is an abnormal state;
Or when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in an idle state, the third node determines that the network state of the first node and the network state of the second node are both in a normal state.
In a second aspect, the present invention provides a protocol conversion assembly comprising:
the first quantity determining module is used for determining the first information quantity of the acquired request information and the second information quantity of the acquired response information, wherein the request information is information sent by a first node to a second node, and the response information is information sent by the second node to the first node;
a second number determining module, configured to determine a target information number according to the first information number and the second information number;
the queue state information determining module is used for determining first queue state information of a first cache queue and second queue state information of a second cache queue, the first cache queue is used for caching the request information and the response information, and the second cache queue is used for caching routing information converted from the response information and routing information converted from the request information;
The node state information determining module is used for determining node state information of a target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information, wherein the target node is the first node and/or the second node; the node state information comprises an idle state and a busy state;
the determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
when the number of the target information is equal to a preset threshold, the first queue state information indicates that the first cache queue is in an empty state, the second queue state information indicates that the second cache queue is in an empty state, and node state information of a target node corresponding to the protocol conversion component is determined to be in the idle state;
the determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
When the number of the target information is not equal to a preset threshold value, and/or the first queue state information indicates that the first cache queue is in a non-empty state, and/or the second queue state information indicates that the second cache queue is in a non-empty state, determining that node state information of a target node corresponding to the protocol conversion component is the busy state;
and the first network state detection module is used for sending the node state information to a third node, so that the third node detects the network state according to the node state information, and abnormal nodes in the network are rapidly positioned.
In a third aspect, the present invention provides a computer device comprising: the network state detection system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions, so that the network state detection method of the first aspect or any implementation mode corresponding to the first aspect is executed.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the network state detection method of the first aspect or any of its corresponding embodiments.
According to the method provided by the embodiment of the invention, the target information quantity is obtained by determining the first information quantity of the request information and the second information quantity of the response information, then the node state information of the target node can be determined by the target information quantity, the first queue state information and the second queue state information, and finally the node state information is sent to the third node, so that the third node can detect the network state according to the node state information, namely, the third node can acquire the node state information of each target node, and the network state can be rapidly determined by the node state information of each target node, so that abnormal nodes in the network can be rapidly positioned.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a network status detection system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another network status detection system according to an embodiment of the present invention;
FIG. 3 is a flow chart of a network status detection method according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating a specific method of step S101 in FIG. 3;
FIG. 5 is a flow chart of another network status detection method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a network status detection system provided in accordance with another embodiment of the present invention;
FIG. 7 is a block diagram of a protocol conversion component provided in accordance with one embodiment of the present invention;
fig. 8 is a block diagram of a network device according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
For the purpose of facilitating an understanding of the embodiments of the present invention, reference will now be made to the following description of specific embodiments, taken in conjunction with the accompanying drawings, which are not intended to limit the embodiments of the invention.
With the development of technology, a simple bus structure on a chip has not been able to meet the requirements of high-performance and high-throughput transactions, so a Network On Chip (NOC) has been developed. In the network-on-chip, simultaneous access from a plurality of first nodes (i.e., the maters) to a plurality of second nodes (i.e., the slave) may be supported, for example, as shown in fig. 1, the request information is generated by the first nodes, and is transmitted on the routing network by converting the first network interface unit (Network Interface Unit, NIU) corresponding to the first nodes into the routing information based on a corresponding protocol (such as an advanced extensible interface (Advanced eXtensible Interface, AXI) protocol or other protocol), then the routing information is converted back into the corresponding request information by the second network interface unit corresponding to the second nodes based on the corresponding protocol, and finally the request information is transmitted to the corresponding second nodes for processing. Likewise, the responses generated by the respective second nodes are fed back to the corresponding first nodes via the routing network in the same manner. However, in the process of information transmission, if the network node is abnormal, information transmission cannot be performed. In the related art, each network node (such as the first node or the second node) only manages its own state, so that the network node in the related art cannot learn about the situation of the whole network, and thus cannot quickly locate an abnormal node in the network. Furthermore, the network node in the related art cannot determine whether the transmission of information in the network is completed.
Based on this, the embodiment of the invention provides a network state detection method, which obtains the target information quantity by determining the first information quantity of the request information and the second information quantity of the response information, then determines the node state information of the target node by the target information quantity, the first queue state information and the second queue state information, and finally sends the node state information to the third node, so that the third node can detect the network state according to the node state information, that is, the third node can acquire the node state information of each target node, and quickly determine the network state by the node state information of each target node, thereby quickly positioning the abnormal node in the network. In addition, the third node can also determine whether the information transmission in the network is completed according to the node state information of each target node.
Fig. 2 is a schematic diagram of a network status detection system according to an embodiment of the present invention, as shown in fig. 2. In the example of fig. 2, the network state detection system includes a first node, a second node, a third node, a first network interface unit NIU corresponding to the first node, and a second NIU corresponding to the second node, where the first NIU and the second NIU are communicatively connected through a routing network, the first node is communicatively connected with the first NIU, the second node is communicatively connected with the second NIU, the third node is communicatively connected with the first node, and protocol conversion components are included in the first NIU and the second NIU.
The first node is used for managing and controlling a second node which is in communication connection with the first node in the communication cluster; the second node is a distributed node used for executing tasks in the communication cluster; the third node is used for managing and controlling all the first nodes and all the second nodes in the communication cluster.
Specifically, the first node and the second node communicate through an information transmission channel, the information transmission channel comprises a first NIU and a second NIU, the first NIU and the second NIU are provided with a first cache queue and a second cache queue besides a protocol conversion assembly, and when the information transmission channel is a read channel, the first cache queue comprises a read request queue and a read response queue; when the information transmission channel is a writing channel, the first cache queue comprises a writing request queue, a writing data queue and a writing response queue; when the information transmission channel comprises a read channel and a write channel, the first buffer queue comprises a read request queue, a read response queue, a write request queue, a write data queue and a write response queue. The second cache queue includes a request routing queue and a response routing queue.
The read request queue is used for reading request information, the read response queue is used for reading response information, the write request queue is used for writing request information, the write data queue is used for writing data information, the write response queue is used for writing response information, the request routing queue is used for caching routing information converted from the response information, and the response routing queue is used for caching routing information converted from the request information.
The protocol conversion component is provided with an information detection component, and the information detection component is provided with a counter which is used for counting transmitted information. Specifically, when the information transmission channel comprises a read channel and a write channel, and the read channel and the write channel are combined together, only one information detection component is arranged in the protocol conversion component in the information transmission channel; or when the information transmission channel comprises a reading channel and a writing channel, and the reading channel and the writing channel are independent of each other, two information detection components are arranged in the protocol conversion component in the information transmission channel, and one information detection component corresponds to the reading channel; the other information detection component corresponds to a write channel.
In an embodiment, the request routing queue may be further divided into a request routing packet input queue and a request routing packet output queue, and the response routing queue may be further divided into a response routing packet input queue and a response routing packet output queue, which are not particularly limited herein.
In an embodiment, the number of first nodes may be plural, the number of second nodes may be plural, each first node may be communicatively connected to a different second node, or may be communicatively connected to only one second node, and the third node may be communicatively connected to all first nodes.
In an embodiment, when the number of the first nodes is plural, the third node may be one of the first nodes or may be a node independent of all the first nodes; when the number of the first nodes is one, the third node may be the first node or may be a node independent from the first node.
The system architecture and the application scenario described in the embodiments of the present invention are for more clearly describing the technical solution of the embodiments of the present invention, and do not constitute a limitation on the technical solution provided by the embodiments of the present invention, and those skilled in the art can know that, with the evolution of the system architecture and the appearance of the new application scenario, the technical solution provided by the embodiments of the present invention is applicable to similar technical problems.
It will be appreciated by those skilled in the art that the system architecture shown in fig. 2 is not limiting of the embodiments of the invention and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
According to an embodiment of the present invention, there is provided a network state detection method embodiment, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
In this embodiment, a network state detection method is provided, which may be used in the protocol conversion component in the first NIU or the protocol conversion component in the second NIU, and fig. 3 is a flowchart of a network state detection method according to an embodiment of the present invention, as shown in fig. 3, where the flowchart includes the following steps:
step S101, determining a first information amount of the acquired request information and a second information amount of the acquired response information.
The request information is information sent by the first node to the second node, and the response information is information sent by the second node to the first node.
In addition, the request information may be write request information, and/or read request information; also, the response information may be write response information, and/or read response information. For example, when the information transmission channel applied by the network state detection method is a write channel, the request information is write request information, and the response information is write response information; for another example, when the information transmission channel applied by the network state detection method is a read channel, the request information is read request information, and the response information is read response information; for another example, when the information transmission channel applied by the network state detection method includes a read channel and a write channel, the request information may be read request information or write request information, and the response information may be read response information or write response information, which is not particularly limited herein.
Step S102, determining the target information quantity according to the first information quantity and the second information quantity.
In this step, after determining the first information amount of the acquired request information, the counter may add the first information amount, and after determining the second information amount of the acquired response information, the counter may subtract the second information amount, so that the data finally recorded by the counter is the target information amount; alternatively, the first information amount may be subtracted from the counter after the first information amount of the acquired request information is determined, and the second information amount may be added to the counter after the second information amount of the acquired response information is determined, so that the data finally recorded by the counter is the target information amount, which is not particularly limited herein.
Step S103, determining first queue status information of the first cache queue and second queue status information of the second cache queue.
The first buffer queue is used for buffering the request information and the response information, and the second buffer queue is used for buffering the route information converted from the response information and the route information converted from the request information.
Specifically, when the network state detection method is applied to the protocol conversion component in the first NIU, after the first node generates the request information, the request information is cached in the first cache queue, then the protocol conversion component converts the request information into the route information, then the route information is cached in the second cache queue, the counter in the information detection component counts, and finally the route information is sent to the route network by the second cache queue and is sent to the second node by the route network. Further, the second buffer queue may buffer the route information converted from the response information sent by the second node, and the route information converted from the response information is then subjected to protocol conversion by the protocol conversion component to obtain the response information, and finally the response information is buffered in the first buffer queue, and the counter counts the response information and then is sent to the first node by the first buffer queue.
Similarly, when the network state detection method is applied to the protocol conversion component in the second NIU, the second buffer queue receives the route information converted from the request information, the second buffer queue sends the route information to the protocol conversion component, the protocol conversion component converts the route information into the request information, at this time, the counter in the information detection component counts, and the request information is buffered to the first buffer queue. Further, when the second node initiates response information according to the request information, the response information is cached to the first cache queue, then the first cache queue sends the response information to the protocol conversion component, the protocol conversion component converts the response information into route information, at the moment, the counter counts the response information, the route information is cached to the second cache queue, and finally the second cache queue sends the route information out and sends the route information to the first node through the route network.
Step S104, determining node state information of the target node corresponding to the protocol conversion assembly according to the target information quantity, the first queue state information and the second queue state information.
The target node is a first node or a second node. Specifically, when the network state detection method is applied to the protocol conversion component in the first NIU, the target node is a first node connected with the first NIU; when the network state detection method is applied to the protocol conversion component in the second NIU, the target node is the second node connected with the second NIU.
In addition, the node state information may include an idle state for characterizing a state when the node is inactive and a busy state for characterizing a state when the node is active.
Step S105, sending node status information to the third node, so that the third node detects the network status according to the node status information.
In the embodiment of the invention, the target information quantity is obtained by determining the first information quantity of the request information and the second information quantity of the response information, then the node state information of the target node can be determined by the target information quantity, the first queue state information and the second queue state information, and finally the node state information is sent to the third node, so that the third node can detect the network state according to the node state information, that is, the third node can acquire the node state information of each target node, and the network state can be rapidly determined by the node state information of each target node, thereby rapidly positioning the abnormal node in the network.
In some alternative embodiments, when the initial amount of information is stored in the protocol conversion component, the method further comprises:
And determining the target information quantity according to the first information quantity, the second information quantity and the initial information quantity.
The initial information amount may be any integer, for example, 0, 1, -1 or other values, and may be set according to practical situations, which is not limited herein.
In an embodiment, the initial information amount may be subtracted by the first information amount and the second information amount may be added to obtain the target information amount; alternatively, the target information amount may be obtained by adding the first information amount to the initial information amount and subtracting the second information amount, and may be set according to the actual situation, without specific limitation.
In some alternative embodiments, the step S104 includes:
when the number of the target information is equal to a preset threshold value, the first queue state information indicates that the first cache queue is in an empty state, the second queue state information indicates that the second cache queue is in an empty state, and node state information of a target node corresponding to the protocol conversion assembly is determined to be in an idle state.
The preset threshold may be set according to an actual situation, for example, when the initial information amount is stored in the protocol conversion component, the preset threshold may be the initial information amount. In addition, the empty state is used to characterize that there is no cache information in the cache queue.
In some alternative embodiments, the step S104 includes:
when the number of the target information is not equal to a preset threshold value, and/or the first queue state information indicates that the first cache queue is in a non-empty state, and/or the second queue state information indicates that the second cache queue is in a non-empty state, determining that node state information of a target node corresponding to the protocol conversion component is in a busy state.
The non-empty state is used for representing that information is cached in the cache queue.
In some alternative embodiments, referring to fig. 4, the step S101 includes:
step S201, when the request information is converted into the route information, the first information amount of the acquired request information is determined.
In this step, when the protocol conversion component converts the request information into the route information, it indicates that the first information amount of the acquired request information can be counted, that is, the amount of the route information converted from the request information is equal to the first information amount.
Step S202, when the response information is converted into the route information, determining the second information amount of the acquired response information.
In this step, when the protocol conversion module converts the response information into the route information, it indicates that the second information amount of the acquired response information can be counted, that is, the amount of the route information converted from the response information is equal to the second information amount.
In the embodiment of the application, the first information quantity of the acquired request information and the second information quantity of the acquired response information are determined, so that the target information quantity is determined according to the first information quantity and the second information quantity in the subsequent steps.
In this embodiment, a network state detection method is provided, which may be used in the third node in the network state detection system, and fig. 5 is a flowchart of the network state detection method according to an embodiment of the present invention, as shown in fig. 5, where the flowchart includes the following steps:
step S301, node state information corresponding to the first node and fed back by the protocol conversion component in the first NIU, and node state information corresponding to the second node and fed back by the protocol conversion component in the second NIU are respectively acquired.
It can be understood that the node status information carries identification information of the corresponding node.
Step S302, detecting the network state according to the node state information corresponding to the first node and the node state information corresponding to the second node.
In the embodiment of the invention, the third node can detect the network state according to the node state information corresponding to the first node and the node state information corresponding to the second node, which are fed back by the protocol conversion assembly in the first NIU, and the node state information corresponding to the second node and fed back by the protocol conversion assembly in the second NIU, so that the abnormal node in the network can be positioned quickly.
In some optional embodiments, in the case that the node state information includes an idle state and a busy state, detecting the network state according to the node state information corresponding to the first node and the node state information corresponding to the second node may have various embodiments, for example, when the node state information corresponding to the first node is the busy state and the node state information corresponding to the second node is the idle state, determining that the network state of the first node is abnormal; or when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in a busy state, determining that the network state of the second node is in an abnormal state; or when the node state information corresponding to the first node is in a busy state and the node state information corresponding to the second node is in a busy state, determining that the network state of the second node is in an abnormal state; or when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in an idle state, determining that the network state of the first node and the network state of the second node are both in a normal state.
It can be understood that when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in an idle state, it can be indicated that the information transmission in the network is completed; when the node status information corresponding to the first node is busy status and/or the node status information corresponding to the second node is busy status, it may be indicated that the information transmission in the network is not completed.
It will also be appreciated that in an upper level application, most transactions (i.e. information interactions) are completed, but when there is a long incomplete transaction, a preliminary determination of the network status can be made by this embodiment.
In order to more clearly describe the processing flow of the network state detection method, a specific example will be described below.
Fig. 6 is a schematic diagram of a network status detection system according to an embodiment of the present invention, as shown in fig. 6. In the example of fig. 6, the network status detection system includes a first node, a second node, a first network interface unit NIU corresponding to the first node, and a second NIU corresponding to the second node, wherein the first NIU and the second NIU are communicatively connected through a routing network, the first node is communicatively connected to the first NIU, and the second node is communicatively connected to the second NIU. In addition, the information transmission channel for the first node and the second node to transmit information comprises a reading channel and a writing channel, and the reading channel and the writing channel are mutually independent.
The protocol conversion assembly in the first NIU is provided with two information detection assemblies, a first cache queue and a second cache queue, the protocol conversion assembly in the second NIU is also provided with two information detection assemblies, a first cache queue and a second cache queue, the first cache queues corresponding to the first NIU and the second NIU comprise a read request queue, a read response queue, a write request queue, a write data queue and a write response queue, and the second cache queues corresponding to the first NIU and the second NIU comprise a request routing queue and a response routing queue. The read request queue and the read response queue corresponding to the first NIU and the second NIU are disposed in the read channel, the write request queue, the write data queue and the write response queue corresponding to the first NIU and the second NIU are disposed in the write channel, and in addition, the read channel and the write channel are disposed with the second buffer queue corresponding to the first NIU and the second NIU.
Specifically, in the write channel, after the first node generates the write request information, the write request information is cached in a write request queue of the first NIU, then the write request queue of the first NIU sends the write request information to a protocol conversion component of the first NIU, the protocol conversion component of the first NIU converts the write request information based on a preset protocol to obtain route information, at this time, a counter in the first NIU and disposed in an information detection component of the write channel is added with 1 to obtain a first information amount corresponding to the first NIU, and route information obtained by converting the write request information is cached in a request route queue in the first NIU.
Further, the request routing queue sends the routing information to the second NIU through the routing network, the request routing queue in the second NIU caches the routing information, and then the protocol conversion component in the second NIU converts the routing information based on a preset protocol to obtain write request information, at this time, a counter in the second NIU and disposed in the information detection component of the write channel is incremented by 1 to obtain a first information amount corresponding to the second NIU, and the write request information is cached in the write request queue in the second NIU.
Then, after the second node feeds back the write response information according to the write request information, the write response information is cached in a write response queue of the second NIU, then the write response queue of the second NIU sends the write response information to a protocol conversion assembly of the second NIU, the protocol conversion assembly of the second NIU converts the write response information based on a preset protocol to obtain route information, at this time, a counter in the second NIU and disposed in an information detection assembly of a write channel is decremented by 1 to obtain a second information quantity corresponding to the second NIU, the route information converted by the write response information is cached in a response route queue in the second NIU, and finally the value of the counter in the second NIU is the target information quantity.
Then, the response route queue sends the route information to the first NIU through the route network, the response route queue in the first NIU caches the route information, the protocol conversion component in the first NIU converts the route information based on a preset protocol to obtain write response information, at this time, the counter in the first NIU and arranged in the information detection component of the write channel is decremented by 1 to obtain second information quantity corresponding to the first NIU, the write response information is cached in the write request queue in the first NIU, and finally the value of the counter in the first NIU is the target information quantity.
And then, determining the first queue state information of the first buffer queue corresponding to the first NIU and the second queue state information of the second buffer queue corresponding to the first NIU, and determining the node state information of the first node to be in an idle state when the target information quantity is equal to a preset threshold value, the write request queue, the write data queue and the write response queue are in an idle state, and the request routing queue and the response routing queue are in an idle state.
And when the target information quantity is equal to a preset threshold value, and the write request queue, the write data queue and the write response queue are all in an empty state, and the request routing queue and the response routing queue are also in an empty state, determining that node state information of the second node is in an idle state.
At this time, it may be determined that the write channel is idle.
The node state in the read channel is similar to the detection process of the node state in the write channel, and will not be described here again.
If the node state information of the first node and the second node in the read channel are idle, the read channel is also indicated to be idle. At this time, it may be determined that in the write channel and the read channel, the node state information of the first node is in an idle state, and the node state information of the second node is also in an idle state.
Further, if the node status information of the first node in the writing channel and/or the reading channel is in a busy state, and if the node status information of the first node in the writing channel and/or the reading channel is in a busy state, determining that the network status of the second node is in an abnormal state, at this time, the node can be abnormally located according to the node status information of the second node, for example, whether a fault occurs in a first cache queue, a second cache queue or a protocol conversion component of the second node can be queried, and then the fault is repaired.
In the embodiment of the present application, the preset protocol may be an AXI protocol or other protocols, which is not limited herein.
In this embodiment, a protocol conversion component is further provided, and the component is used to implement the foregoing embodiments and preferred implementations, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The present embodiment provides a protocol conversion module, as shown in fig. 7, including:
A first number determining module 401, configured to determine a first number of pieces of information of the acquired request information, and a second number of pieces of information of the acquired response information, where the request information is information sent by the first node to the second node, and the response information is information sent by the second node to the first node;
a second number determining module 402, configured to determine a target information number according to the first information number and the second information number;
a queue status information determining module 403, configured to determine first queue status information of a first cache queue and second queue status information of a second cache queue, where the first cache queue is configured to cache request information and response information, and the second cache queue is configured to cache route information converted from the response information and route information converted from the request information;
the node state information determining module 404 is configured to determine node state information of a target node corresponding to the protocol conversion component according to the target information amount, the first queue state information, and the second queue state information, where the target node is a first node or a second node;
the first network state detection module 405 is configured to send node state information to the third node, so that the third node detects the network state according to the node state information.
In some alternative embodiments, when the initial amount of information is stored in the protocol conversion component, the protocol conversion component further comprises:
and the third quantity determining module is used for determining the target information quantity according to the first information quantity, the second information quantity and the initial information quantity.
In some alternative embodiments, the node state information includes an idle state and a busy state.
In some alternative embodiments, the node state information determination module 404 includes:
the first node state information unit is used for determining that node state information of a target node corresponding to the protocol conversion component is in an idle state when the number of target information is equal to a preset threshold value, the first queue state information indicates that the first buffer queue is in an idle state, and the second queue state information indicates that the second buffer queue is in an idle state.
In some alternative embodiments, the node state information determination module 404 includes:
the second node state information determining unit is used for determining that node state information of the target node corresponding to the protocol conversion component is in a busy state when the number of the target information is not equal to a preset threshold value, and/or the first queue state information indicates that the first buffer queue is in a non-empty state, and/or the second queue state information indicates that the second buffer queue is in a non-empty state.
In some alternative embodiments, the first quantity determination module 401 includes:
a first number determining unit configured to determine a first information number of the acquired request information when the request information is converted into the route information;
and a second number determining unit configured to determine a second information number of the acquired response information when the response information is converted into the route information.
The present embodiment provides a network device, as shown in fig. 8, including:
an information obtaining module 501, configured to obtain node state information corresponding to a first node and fed back by a protocol conversion module in a first NIU, and node state information corresponding to a second node and fed back by a protocol conversion module in a second NIU, respectively;
the second network state detection module 502 is configured to detect a network state according to the node state information corresponding to the first node and the node state information corresponding to the second node.
In some alternative embodiments, where the node state information includes an idle state and a busy state, the second network state detection module 502 includes:
the first network state detection unit is used for determining that the network state of the first node is abnormal when the node state information corresponding to the first node is in a busy state and the node state information corresponding to the second node is in an idle state.
In some alternative embodiments, where the node state information includes an idle state and a busy state, the second network state detection module 502 includes:
and the second network state detection unit is used for determining that the network state of the second node is an abnormal state when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in a busy state.
In some alternative embodiments, where the node state information includes an idle state and a busy state, the second network state detection module 502 includes:
and the third network state detection unit is used for determining that the network state of the second node is an abnormal state when the node state information corresponding to the first node is a busy state and the node state information corresponding to the second node is a busy state.
In some alternative embodiments, where the node state information includes an idle state and a busy state, the second network state detection module 502 includes:
and the fourth network state detection unit is used for determining that the network state of the first node and the network state of the second node are both normal states when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in an idle state.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The protocol conversion component and network device in this embodiment are presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit ) circuits, processors and memories executing one or more software or fixed programs, and/or other devices that can provide the above described functionality.
The embodiment of the invention also provides computer equipment which is provided with the protocol conversion component shown in the figure 7 or the network equipment shown in the figure 8.
Referring to fig. 9, fig. 9 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 9, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 9.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods shown in implementing the above embodiments.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.

Claims (7)

1. A network state detection method, the method being adapted to a network state detection system, the network state detection system comprising: at least one first node, at least one second node and a third node, wherein a first network interface unit (first NIU) corresponding to the first node and a second network interface unit (second NIU) corresponding to the second node are respectively arranged, and the first NIU and the second NIU comprise protocol conversion components; the method is performed by a protocol conversion component, the method comprising:
determining the first information quantity of acquired request information and the second information quantity of acquired response information, wherein the request information is information sent by a first node to a second node, and the response information is information sent by the second node to the first node;
determining a target information quantity according to the first information quantity and the second information quantity;
Determining first queue state information of a first cache queue and second queue state information of a second cache queue, wherein the first cache queue is used for caching the request information and the response information, and the second cache queue is used for caching routing information converted from the response information and routing information converted from the request information;
determining node state information of a target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information, wherein the target node is the first node and/or the second node; the node state information comprises an idle state and a busy state;
the determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
when the number of the target information is equal to a preset threshold, the first queue state information indicates that the first cache queue is in an empty state, the second queue state information indicates that the second cache queue is in an empty state, and node state information of a target node corresponding to the protocol conversion component is determined to be in the idle state;
The determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
when the number of the target information is not equal to a preset threshold value, and/or the first queue state information indicates that the first cache queue is in a non-empty state, and/or the second queue state information indicates that the second cache queue is in a non-empty state, determining that node state information of a target node corresponding to the protocol conversion component is the busy state;
and sending the node state information to the third node, so that the third node detects the network state according to the node state information, and thus abnormal nodes in the network are rapidly positioned.
2. The method of claim 1, wherein when the initial amount of information is stored in the protocol conversion component, the method further comprises:
and determining the target information quantity according to the first information quantity, the second information quantity and the initial information quantity.
3. The method according to claim 1 or 2, wherein said determining a first information amount of acquired request information and a second information amount of acquired response information comprises:
When the request information is converted into the route information, determining the first information quantity of the acquired request information;
when the response information is converted into the routing information, determining a second information amount of the acquired response information.
4. The method of claim 1, wherein the sending the node status information to the third node, such that the third node detects a network status from the node status information, comprises:
when the node state information corresponding to the first node is in a busy state, and when the node state information corresponding to the second node is in an idle state, the third node determines that the network state of the first node is abnormal;
or when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in a busy state, the third node determines that the network state of the second node is in an abnormal state;
or when the node state information corresponding to the first node is a busy state and the node state information corresponding to the second node is a busy state, the third node determines that the network state of the second node is an abnormal state;
Or when the node state information corresponding to the first node is in an idle state and the node state information corresponding to the second node is in an idle state, the third node determines that the network state of the first node and the network state of the second node are both in a normal state.
5. A protocol conversion assembly, the protocol conversion assembly comprising:
the first quantity determining module is used for determining the first information quantity of the acquired request information and the second information quantity of the acquired response information, wherein the request information is information sent by a first node to a second node, and the response information is information sent by the second node to the first node;
a second number determining module, configured to determine a target information number according to the first information number and the second information number;
the system comprises a queue state information determining module, a first buffer memory, a second buffer memory, a first buffer memory and a second buffer memory, wherein the queue state information determining module is used for determining first queue state information of a first buffer memory queue and second queue state information of a second buffer memory queue, the first buffer memory queue is used for buffering the request information and the response information, and the second buffer memory queue is used for buffering route information converted by the response information and route information converted by the request information;
The node state information determining module is used for determining node state information of a target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information, wherein the target node is the first node and/or the second node; the node state information comprises an idle state and a busy state;
the determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
when the number of the target information is equal to a preset threshold, the first queue state information indicates that the first cache queue is in an empty state, the second queue state information indicates that the second cache queue is in an empty state, and node state information of a target node corresponding to the protocol conversion component is determined to be in the idle state;
the determining node state information of the target node corresponding to the protocol conversion component according to the target information quantity, the first queue state information and the second queue state information includes:
When the number of the target information is not equal to a preset threshold value, and/or the first queue state information indicates that the first cache queue is in a non-empty state, and/or the second queue state information indicates that the second cache queue is in a non-empty state, determining that node state information of a target node corresponding to the protocol conversion component is the busy state;
and the first network state detection module is used for sending the node state information to a third node, so that the third node detects the network state according to the node state information, and abnormal nodes in the network are rapidly positioned.
6. A computer device, comprising:
a memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the network state detection method of any of claims 1 to 4.
7. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the network state detection method of any one of claims 1 to 4.
CN202310665797.6A 2023-06-07 2023-06-07 Network state detection method, protocol conversion component, equipment and storage medium Active CN116405377B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310665797.6A CN116405377B (en) 2023-06-07 2023-06-07 Network state detection method, protocol conversion component, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310665797.6A CN116405377B (en) 2023-06-07 2023-06-07 Network state detection method, protocol conversion component, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN116405377A CN116405377A (en) 2023-07-07
CN116405377B true CN116405377B (en) 2023-08-08

Family

ID=87009092

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310665797.6A Active CN116405377B (en) 2023-06-07 2023-06-07 Network state detection method, protocol conversion component, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116405377B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016045411A1 (en) * 2014-09-26 2016-03-31 华为技术有限公司 Network on chip system, and method for establishing network on chip communication link
CN108848001A (en) * 2018-05-25 2018-11-20 电子科技大学 A kind of network-on-chip test encapsulation based on one-way transmission path
CN108924123A (en) * 2018-06-29 2018-11-30 北京京东尚科信息技术有限公司 Information processing method, device and system in block chain
CN110890972A (en) * 2018-09-07 2020-03-17 中国移动通信集团浙江有限公司 Health degree evaluation method and device of business system
CN112506850A (en) * 2020-11-27 2021-03-16 北京大学 On-chip and inter-chip interconnection network
CN114374651A (en) * 2021-12-31 2022-04-19 海光信息技术股份有限公司 Transport flow control method, network on chip, electronic device, and storage medium
CN115174432A (en) * 2022-06-30 2022-10-11 苏州浪潮智能科技有限公司 RDMA (remote direct memory Access) network state monitoring method, device, equipment and readable storage medium
CN115543938A (en) * 2021-06-30 2022-12-30 腾讯科技（深圳）有限公司 Data processing method and device, electronic equipment and storage medium
CN116055303A (en) * 2023-02-14 2023-05-02 中孚安全技术有限公司 Link monitoring processing method and device, electronic equipment and storage medium

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016045411A1 (en) * 2014-09-26 2016-03-31 华为技术有限公司 Network on chip system, and method for establishing network on chip communication link
CN108848001A (en) * 2018-05-25 2018-11-20 电子科技大学 A kind of network-on-chip test encapsulation based on one-way transmission path
CN108924123A (en) * 2018-06-29 2018-11-30 北京京东尚科信息技术有限公司 Information processing method, device and system in block chain
CN110890972A (en) * 2018-09-07 2020-03-17 中国移动通信集团浙江有限公司 Health degree evaluation method and device of business system
CN112506850A (en) * 2020-11-27 2021-03-16 北京大学 On-chip and inter-chip interconnection network
CN115543938A (en) * 2021-06-30 2022-12-30 腾讯科技（深圳）有限公司 Data processing method and device, electronic equipment and storage medium
CN114374651A (en) * 2021-12-31 2022-04-19 海光信息技术股份有限公司 Transport flow control method, network on chip, electronic device, and storage medium
CN115174432A (en) * 2022-06-30 2022-10-11 苏州浪潮智能科技有限公司 RDMA (remote direct memory Access) network state monitoring method, device, equipment and readable storage medium
CN116055303A (en) * 2023-02-14 2023-05-02 中孚安全技术有限公司 Link monitoring processing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN116405377A (en) 2023-07-07

Similar Documents

Publication Publication Date Title
CN107729559B (en) Method, system, equipment and storage medium for database read-write asynchronous access
EP3839749A1 (en) Data storage method, device and server
CN113765980A (en) Current limiting method, device, system, server and storage medium
CN110119304B (en) Interrupt processing method and device and server
CN111400041A (en) Server configuration file management method and device and computer readable storage medium
CN113067875A (en) Access method, device and equipment based on dynamic flow control of micro-service gateway
US9448827B1 (en) Stub domain for request servicing
CN105681404A (en) Metadata node management method and device of distributed cache system
EP2568379A1 (en) Method for preventing node controller deadlock and node controller
CN111200637A (en) Cache processing method and device
CN110222034A (en) A kind of database maintenance method and device
CN116405377B (en) Network state detection method, protocol conversion component, equipment and storage medium
CN103500108A (en) System memory access method, node processor and multi-processor system
CN111125168B (en) Data processing method and device, electronic equipment and storage medium
CN111913815A (en) Call request processing method and device, electronic equipment and readable storage medium
KR20170117326A (en) Direct memory access control device for at least one processing unit having a random access memory
US8938588B2 (en) Ensuring forward progress of token-required cache operations in a shared cache
CN116389357B (en) Hole address processing method, device, equipment and medium based on network on chip
CN113641604A (en) Data transmission method and system
CN111092817A (en) Data transmission method and device
CN112148508A (en) Information processing method and related device
CN113961489B (en) Method, device, equipment and storage medium for data access
CN109445984A (en) A kind of service restoration method, device, arbitrating server and storage system
CN109510864A (en) A kind of retransmission method of cache request, transmission method and relevant apparatus
CN115657975B (en) Disk data read-write control method, related components and front-end shared card

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