CN110661716B - Network packet loss notification method, monitoring device, switch and storage medium - Google Patents

Network packet loss notification method, monitoring device, switch and storage medium Download PDF

Info

Publication number
CN110661716B
CN110661716B CN201910870529.1A CN201910870529A CN110661716B CN 110661716 B CN110661716 B CN 110661716B CN 201910870529 A CN201910870529 A CN 201910870529A CN 110661716 B CN110661716 B CN 110661716B
Authority
CN
China
Prior art keywords
stage
field
setting
counter
message
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
CN201910870529.1A
Other languages
Chinese (zh)
Other versions
CN110661716A (en
Inventor
晏福旗
汪建惠
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.)
Ruijie Networks Co Ltd
Original Assignee
Ruijie Networks 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 Ruijie Networks Co Ltd filed Critical Ruijie Networks Co Ltd
Priority to CN201910870529.1A priority Critical patent/CN110661716B/en
Publication of CN110661716A publication Critical patent/CN110661716A/en
Application granted granted Critical
Publication of CN110661716B publication Critical patent/CN110661716B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
    • H04L47/2483—Traffic characterised by specific attributes, e.g. priority or QoS involving identification of individual flows
    • 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
    • H04L47/32—Flow control; Congestion control by discarding or delaying data units, e.g. packets or frames
    • 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
    • H04L47/33—Flow control; Congestion control using forward notification

Abstract

The present application relates to the field of computer network technologies, and in particular, to a method for notifying network packet loss, a monitoring device, a switch, and a storage medium. The method comprises the following steps: identifying a target message from a received message stream; acquiring stage state information corresponding to each processing stage of a target message in real time; when determining that a stage state information representation target message is discarded, setting the index of a counter as a preset value corresponding to a processing stage based on the processing stage to which the stage state information representation target message belongs; and triggering the counter to count based on the set index, so that the register value of the counter correspondingly increases, and outputting corresponding increase information, wherein the increase information is used for diagnosing the specific position of the packet loss. The method and the device realize the function of automatically notifying the outside when the message is discarded, are suitable for the switch with cross-chip forwarding, can diagnose whether the packet is lost in the switch, can also position the port through which the target message passes, and can specifically realize the partial processing stage in the switch when the diagnosis position is accurate.

Description

Network packet loss notification method, monitoring device, switch and storage medium
Technical Field
The present application relates to computer network technologies, and in particular, to a method for notifying network packet loss, a monitoring device, a switch, and a storage medium.
Background
The network packet loss means: the phenomenon that a small part of data in a data stream transmitted by a network cannot reach a specified destination through the network exists. The network packet loss rate is the ratio of the number of lost messages in the total number of sent messages in the test, and the calculation method is [ (input message-output message)/input message ] × 100%. In a network environment, the reasons for network packet loss may be various, for example, signal attenuation and channel blocking caused by multipath fading, and network driver failure, switch failure, device configuration problem, other device attack, etc. may cause network packet loss.
Network packet loss may cause jitter of streaming media, online games and video conferences, and may affect other network application terminal service anomalies to some extent. To solve the problem of network packet loss, the specific location and reason of packet loss should be diagnosed first.
In a conventional network packet loss diagnosis technology, when determining whether a network packet loss occurs in a switch, the switch generally adopts the following two technical means: access Control List (ACL) count and mirror packet capture.
When the ACL counting mode is adopted to judge whether the network packet loss occurs, the switch needs to accurately confirm the message inlet and the message outlet, and when the message inlet and the message outlet cannot be confirmed, the switch cannot complete ACL counting. If the switch itself has no packet loss but uses the wrong message outlet to forward the message, it is difficult to monitor this situation by using the ACL counting method.
And when the mirror image packet capturing mode is adopted to judge whether the network packet loss occurs, the operation needs to be carried out close to the switch, and obviously, the conditions are not met in most cases.
In view of the above problems, the prior art discloses an automatic diagnosis method for packet loss fault of ethernet router switch, which is mainly designed for a single-chip switch, and the method specifically comprises the following steps: firstly, sampling a message at regular time, extracting register information of a router or a switch, simulating a message forwarding flow of a router or a switch hardware chip by software, and counting a simulation result of message forwarding into statistical information. When a fault occurs, the fault maintainer outputs the software simulation statistical information and searches the packet loss reason in the packet loss counting table according to the message type of the service fault.
However, the above method requires using multiple registers for message verification, and when extracting the register information of the router or the switch, more register information needs to be collected.
With the development of switch technology, single-chip switches will gradually be replaced by switches that forward across chips. For example, most models currently support cross-chip forwarding, for a boson chip switch. In the cross-chip forwarding switch, a large number of registers are involved at different chip pipeline stages, and if the method is adopted to diagnose the network packet loss of the cross-chip switch, the register information needing to be collected can be multiplied, so that the simulation analysis process is extremely complicated, and the diagnosis of the network packet loss can not be realized at all. That is, the above approach is not applicable to cross-chip forwarding switches.
In view of the above, there is a need to redesign a process to overcome the above-mentioned drawbacks.
Disclosure of Invention
The embodiment of the application provides a network packet loss notification method, a monitoring device, a switch and a storage medium, which are used for solving the problems in the prior art.
The embodiment of the invention provides the following specific technical scheme:
in a first aspect of the embodiments of the present invention, a method for notifying a network packet loss is provided, including:
identifying a target message from the received message stream based on a preset identification characteristic;
in the processing process of the target message, stage state information corresponding to each processing stage of the target message is acquired in real time;
when any stage state information representing that the target message is discarded is determined, setting the index of the counter to be a preset value corresponding to a processing stage based on the processing stage to which the any stage state information belongs;
and triggering the counter to count based on the set index, so that the register value of the counter correspondingly increases, and outputting corresponding increasing information, wherein the increasing information is used for determining a processing stage of packet loss.
Optionally, identifying a target packet from the received packet stream based on a preset identification feature specifically includes:
and respectively executing the following operations aiming at each message in the message flow:
analyzing at least one identification characteristic of a message; the identification characteristics comprise any one or any combination of a source Media Access Control (MAC) address, a destination MAC address, an Ethernet Type (ETYPE), a source Internet Protocol (IP) address and a destination IP address;
and when the at least one identification feature is determined to be matched with the preset identification feature, judging the message as a target message.
Optionally, before identifying the target packet from the received packet stream based on the preset identification feature, the method further includes:
and acquiring preset rules, wherein the preset rules respectively set correspondingly executed processing operations when the target message is discarded in each processing stage, and the processing operations at least comprise a mode of setting an index of a counter.
Optionally, when it is determined that any one of the stage state information represents that the target packet is discarded, the method sets the index of the counter to a corresponding preset value based on the processing stage to which the any one of the stage state information belongs, and specifically includes:
and when the target message is determined to be discarded in any one processing stage, setting the index of the counter as a corresponding combination of a plurality of fields based on the preset rule according to the processing stage to which the state information of any one stage belongs, wherein one combination corresponds to one resource pool of the counter, and setting the value of each field as a corresponding preset value.
Optionally, the setting the value of each field to a corresponding preset value specifically includes:
if the processing stage to which the state information of any one stage belongs is a port stage, setting the index of the counter as the combination of a first field, a second field and a third field, setting the value of the first field as a first preset value, setting the second field as a second preset value and setting the value of the third field as a third preset value; the first field represents whether a processing object is a target message or not, and the second field represents whether the target message is discarded or not; the third preset value represents an input port number or an output port number of the target message;
if the processing stage to which the state information of any stage belongs is any one of a VFP stage, an ING _ PORT stage, an ING _ VLAN stage, an STP stage, an IP DST stage or an ING _ L3_ NEXT _ HOP stage and an EFP stage, setting the index of the counter as the combination of a first field, a second field and a fourth field, setting the value of the first field as a first preset value, setting the value of the second field as a second preset value and setting the value of the fourth field as a fourth preset value; the fourth preset value is used for representing the processing stage of the discarded and/or discarded target message.
In a second aspect of the embodiments of the present invention, a device for monitoring network packet loss is provided, including:
the identification unit is used for identifying a target message from the received message flow based on preset identification characteristics;
the acquisition unit is used for acquiring stage state information corresponding to each processing stage of the target message in real time in the processing process of the target message;
the setting unit is used for setting the index of the counter to be a preset value corresponding to a processing stage based on the processing stage to which the state information of any stage belongs when the state information of any stage represents that the target message is discarded;
and the output unit is used for triggering the counter to count based on the set index, so that the register value of the counter correspondingly increases, and outputting corresponding increase information, wherein the increase information is used for determining a processing stage of packet loss.
Optionally, based on a preset identification feature, the target packet is identified from the received packet, and the identification unit is specifically configured to:
and respectively executing the following operations aiming at each message in the message flow:
analyzing the identification characteristics of a message; the identification characteristics comprise any one or any combination of a source Media Access Control (MAC) address, a destination MAC address, an Ethernet Type (ETYPE), a source Internet Protocol (IP) address and a destination IP address;
and when the at least one identification feature is determined to be matched with the preset identification feature, judging the message as a target message.
Optionally, the method further comprises:
the device comprises a preprocessing unit and a counter, wherein the preprocessing unit is used for acquiring preset rules, the preset rules respectively set processing operations correspondingly executed when a target message is discarded in each processing stage, and the processing operations at least comprise a mode of setting an index of the counter.
Optionally, when it is determined that any one of the stage state information represents that the target packet is discarded, based on the processing stage to which the any one of the stage state information belongs, the setting unit is specifically configured to:
and when the target message is determined to be discarded in any one processing stage, setting the index of the counter as a corresponding combination of a plurality of fields based on the preset rule according to the processing stage to which the state information of any one stage belongs, wherein one combination corresponds to one resource pool of the counter, and setting the value of each field as a corresponding preset value.
Optionally, the value of each field is set to a corresponding preset value, and the setting unit is specifically configured to:
if the processing stage to which the state information of any one stage belongs is a port stage, setting the index of the counter as the combination of a first field, a second field and a third field, setting the value of the first field as a first preset value, setting the second field as a second preset value and setting the value of the third field as a third preset value; the first field represents whether a processing object is a target message or not, and the second field represents whether the target message is discarded or not; the third preset value represents an input port number or an output port number of the target message;
if the processing stage to which the state information of any one stage belongs is any one of a VFP stage, an ING _ PORT stage, an ING _ VLAN stage, an STP stage, an IP DST stage or an ING _ L3_ NEXT _ HOP stage and an EFP stage, setting the index of the counter as the combination of a first field, a second field and a fourth field, setting the value of the first field as a first preset value, setting the value of the second field as a second preset value and setting the value of the fourth field as a fourth preset value; the fourth preset value is used for representing the processing stage of the discarded and/or discarded target message.
In a third aspect of the embodiments of the present invention, there is provided a switch, including: a memory and a processor; wherein, the first and the second end of the pipe are connected with each other,
a memory for storing executable instructions;
a processor for reading and executing executable instructions stored in the memory to implement the method of any one of the above.
A fourth aspect of embodiments of the present invention also provides a storage medium, in which instructions are enabled to perform a method as described in any one of the above when executed by a processor.
The invention has the following beneficial effects:
in the embodiment of the application, firstly, a target message is identified from a received message flow based on a preset identification characteristic, and in the process of processing the target message, stage state information corresponding to each processing stage of the target message is acquired in real time; when any one stage state information representation target message is determined to be discarded, setting the index of the counter as a preset value corresponding to a processing stage based on the processing stage to which any one stage state information belongs; based on the set index, triggering the counter to count, enabling the register value of the counter to correspondingly increase, and outputting corresponding increase information, wherein the increase information is used for determining the processing stage of packet loss, and the increase information can show the corresponding relation between the increase of the register value and the index, that is, the output increase information not only contains the information of the increase of the register value, but also contains the index which causes the increase of the register and corresponds to the register value. Therefore, when a message is discarded in the switch, because the index of the counter is correspondingly set according to the processing stage of the message discarding, when the index triggers the counter to count so that the register value is increased, which index the register value is increased can be determined according to the increase information, and then which processing stage the message is discarded is determined, the function of automatically notifying the message discarding to the outside is realized, and the method can be directly used for diagnosing the packet loss position of the switch.
Drawings
Fig. 1 is a schematic diagram of an internal structure of a monitoring apparatus in a network packet loss notification method in an switch according to an embodiment of the present application;
fig. 2 is a flowchart of a network packet loss notification method in an embodiment of the present application;
FIG. 3 is a schematic diagram of the various processing stages of a switch pipeline in an embodiment of the present application;
FIG. 4 is a domain diagram corresponding to an optional index at an input stage of a flexible counter according to an embodiment of the present application;
FIG. 5 is a domain diagram corresponding to an optional index of an output stage of a flexible counter in an embodiment of the present application;
FIG. 6 is a schematic structural diagram of a monitoring device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a switch in the embodiment of the present application.
Detailed Description
In order to solve the technical problem that a packet loss diagnosis scheme in the prior art cannot be applied to a cross-chip forwarding switch, in the embodiment of the application, stage state information of each processing stage through which a target packet passes is obtained, when the stage state information indicates that the target packet is discarded, different indexes are set according to different processing stages, so that the processing stages correspond to the indexes one by one, register values corresponding to an index trigger counter are increased, increase information is output, and specific indexes causing the register values to increase can be displayed in the increase information.
Preferred embodiments of the present application will be described in further detail below with reference to the accompanying drawings:
referring to fig. 1, in the embodiment of the present application, a monitoring device for implementing a network packet loss notification method is disposed in a switch, and the monitoring device may monitor an input packet flow.
Optionally, the monitoring device is mainly configured to monitor the target packet, obtain stage state information of each processing stage through which the target packet passes, and set different indexes according to different processing stages when it is determined that the stage state information represents that the target packet is discarded, so as to further trigger a register value corresponding to the counter to increase.
The monitoring device may be composed of various types of software, hardware or a combination thereof capable of implementing the above functions, and may be disposed inside the switch as independent hardware, or may be implemented by improving software on the basis of existing internal hardware of the switch, for example, as an implementation manner, the monitoring device may be implemented based on a domain processor (FP) module of a boston chip. In particular, the monitoring device may be implemented by changing or adding the rule of the FP module, and does not necessarily have a corresponding hardware entity.
In the embodiment of the application, the monitoring device should acquire the preset rule in advance. The preset rule sets the corresponding executed processing operation when the target message is discarded in each processing stage, and the processing operation at least comprises a mode of setting the index of the counter.
Referring to fig. 2, in the embodiment of the present application, a detailed flow of notifying a network packet loss is as follows:
step 201: the monitoring device identifies a target message from the received message stream based on a preset identification characteristic.
In the embodiment of the present application, only the target packet is subjected to packet loss diagnosis, so the target packet needs to be identified first. Specifically, the following operations are respectively executed for each packet in the packet stream:
analyzing at least one identification characteristic of a message;
and when the at least one identification feature is determined to be matched with the preset identification feature, judging the message as a target message.
The identification feature includes, but is not limited to, any one or any combination of a source Media Access Control (MAC) Address, a destination MAC Address, an Ethernet Type (ETYPE), a source Internet Protocol (IP) Address, and a destination IP Address.
For example, when a source MAC address and a destination MAC address are used as identification features, the source MAC address and the destination MAC address of a message are analyzed; when the source MAC address and the destination MAC address of a message are determined to fall into the preset MAC address range needing to be monitored, the message is determined to be matched, and the message is determined to be the target message.
In the embodiment of the application, the identified target message is marked, so that the target message can be quickly identified in the subsequent processing stage. For example, when the diagnostic object is a bock switch, the CNG field is used as an identification bit in a VFP (Virtual Local Area Network-Fields Processor) stage to dye the target packet, that is, the value of the CNG field is set to 1, so that the target packet can be quickly identified from the packet stream in an Ingress Fields engine (IFP) stage, an agile counter, and an Egress Fields Engine (EFP) stage of the chip and other chips in the stack system.
Step 202: and the monitoring device acquires the stage state information corresponding to each processing stage of the target message in real time in the processing process of the target message.
The processing process of the target message is that the target message is input from the input port of the switch, processed by the internal pipeline of the switch and output from the output port of the switch.
The operation of acquiring the stage status information is only directed to the target message, i.e. the CNG field of the message should be acquired first, and the subsequent steps 202 and 204 are performed only when CNG is equal to 1.
For example, referring to fig. 3, when the switch is a Broadcom chip switch, the processing procedure of the target message includes the following processing stages: a VFP stage, an Ingress Port (ING _ PORT) stage, an Ingress Virtual Local Area Network (INGREAL) stage, an INGREAL VLAN (INGREAL VLAN) stage, a Spanning Tree Protocol (STP) stage, a two-layer Source Address lookup (FDB SRC) stage, a two-layer Destination Address lookup (FDB DST) stage, an IP Source Address lookup (IP SRC) stage, an IP Destination Address lookup (IP DST) stage, an IFP stage, an Ingress direction three-layer Next Hop lookup (InGRESL 3 Next Hop, ING _ L3_ NEXT _ HOP) stage, an Ingress Flexible Management Counter (InGREAL Counter, INGREAL _ PORT) stage, an INGREAL _ PORT Management Unit (STP), an Egress Local Area Network (MMU) stage, an output Virtual Local Area Network (MMU) stage, EGR _ VLAN), Egress Port (EGR _ Port), and Egress Flexible Counter (EGR _ FLEX Counter).
In the embodiment of the present application, the stage state information, that is, some state parameters used for characterizing the message processing state, which are automatically generated inside when the target message passes through each processing stage of the switch, are used to determine whether the target message has been discarded or is about to be discarded. For example, for a bosch chip switch, the phase state information includes, but is not limited to, DROP, pktRes, L3_ dst _ classid, and the state of the lookup status.
Step 203: when the monitoring device determines that any one stage state information represents that the target message is discarded, the index of the counter is set to be a preset value corresponding to a processing stage based on the processing stage to which the any one stage state information belongs.
And judging whether the target message is discarded or not according to the stage state information acquired in the step 202. For example, for a bosch chip switch, the phase state information obtained includes: if DROP is 1, the message is discarded; if pktRes is unknown _ pkt, it means that the target packet is a packet that cannot be identified by the ING _ PORT stage or the ING _ VLAN stage, and therefore, the target packet is discarded; l3_ dst _ classid is TRAP _ LOCAL, which indicates that the target packet hits the LOCAL route and is discarded, etc.
As the phase state information, most of the phase state information is generated at a specific processing phase except that the DROP field can be generated at each processing phase. For example, when the phase state information is L3_ DST _ class, TRAP _ LOCAL, the phase to which the phase state information belongs may be obtained as an IP DST phase. The FP module may correspondingly determine whether a packet loss occurs in a corresponding processing stage by acquiring stage state information generated when the packet passes through each processing stage.
When determining that any one of the stage state information represents that the target packet is discarded, the monitoring device may set the index of the counter to a preset value corresponding to the processing stage according to the processing stage to which the any one of the stage state information belongs, and may specifically adopt the following manner:
based on the preset rule, the monitoring device sets the index of the counter to be the combination of a plurality of corresponding fields according to the processing stage to which the state information of any one stage belongs, one combination corresponds to one resource pool of the counter, and the value of each field is set to be the corresponding preset value.
Optionally, when the diagnostic object is a blosson chip, the method specifically includes the following steps:
the method I comprises the following steps: and if the processing stage to which the state information of any one stage belongs is a port stage, setting the index of the counter as the combination of a first field, a second field and a third field, setting the value of the first field as a first preset value, setting the second field as a second preset value and setting the value of the third field as a third preset value.
The port stage comprises an input port stage and an output port stage, the first field represents whether a processing object is a target message, and the second field represents whether the target message is discarded; and the third preset value represents an input port number or an output port number of the target message.
Optionally, the first preset value and the second preset value have the same meaning in the subsequent embodiments, and will not be described again.
In the embodiment of the present application, when the diagnostic object is a boston chip switch, the Counter used is a Flexible Counter (flexile Counter). The fields corresponding to the input stage selectable indices of the flexible counter are shown in fig. 4, and the fields corresponding to the output stage selectable indices are shown in fig. 5.
For the PORT phase, the field combination of the index is set to be CNG field + PORT field + DROP field. Specifically, for the input Port stage, CNG is selected from a plurality of fields for setting an index shown in fig. 4 as a first field, DROP is selected as a second field, and Ingress Port is selected as a third field, that is, the index corresponding to the input Port stage is set as CNG field + Ingress Port field + DROP field, where the CNG field is used to indicate whether the CNG field is a target message and occupies two bytes (bit), in this embodiment, a high-order byte is used, and the value of the high-order byte is 0 or 1, and when CNG is 1, the CNG field is indicated as the target message, and CNG is 0, which indicates that the CNG field is not the target message; the DROP field takes a value of 0 or 1, when DROP equals 0, the packet is not discarded, DROP equals 1, the packet is discarded, Ingress Port represents the input Port number, and the lower 6 bytes are used.
Furthermore, the index of the flexible counter is 8 bytes, the first byte is set as CNG, and the value of the target message is 1, that is, the first preset value is set as 1; the 2 nd to 7 th bytes are Ingress ports, and the value is 32 (the input Port number is 32), that is, the third preset value is 32; the 8 th byte is DROP and takes a value of 1, that is, the second preset value is set to 1, and the value of the index corresponding to the input port stage is specifically (10100001).
For the output Port stage, CNG is selected from the fields for setting the index shown in fig. 5 as a first field, DROP is selected as a second field, and Egress Port is selected as a third field, that is, the index corresponding to the output Port stage is set as CNG field + Egress Port field + DROP field. Where Egress Port represents an output Port number. Specifically, similar to the input Port stage, the first byte is CNG and takes a value of 1, the 2 nd to 7 th bytes are Egress ports and take a value of 32 (that is, the output Port number is 32), the 8 th byte is DROP and takes a value of 1, and then the value of the index corresponding to the output Port stage is specifically (10100001).
The second method comprises the following steps: if the processing stage to which the state information of any stage belongs is any one of a VFP stage, an ING _ PORT stage, an ING _ VLAN stage, an STP stage, an IP DST stage or an ING _ L3_ NEXT _ HOP stage and an EFP stage; setting the index of the counter as the combination of a first field, a second field and a fourth field, setting the value of the first field as a first preset value, setting the value of the second field as a second preset value, and setting the value of the fourth field as a fourth preset value, wherein the fourth preset value is used for representing the processing stage of discarding the target message.
Optionally, the fourth preset values are set to different values, which may respectively represent the processing stages of the target packet being discarded, the discarding stage and the reason of part of packet loss, including but not limited to:
discarding in the VFP stage, discarding for an unidentifiable processing object in the ING _ PORT stage and the ING _ VLAN stage, discarding due to a register state of a corresponding register in the STP stage being a spare or BLOCK, discarding due to a hit in a local routing or a hit in a direct network routing in the IP DST stage, or discarding for an unknown layer 3 unicast packet as a processing object.
In the embodiment of the present application, for the flexible counter, a CNG field is selected from fig. 3 and fig. 4 as a first field, a DROP field is selected as a second field, and an Outer Dot1p (also referred to as COS, hereinafter, both are abbreviated as COS) field is selected as a fourth field, that is, indexes corresponding to multiple stages such as the VFP stage and the STP stage are set as CNG field + COS field + DROP field. CNG occupies the 1 st byte, DROP occupies the 8 th byte, and COS occupies the consecutive 3 bytes of the remaining 6 bytes. In the second mode, the values of the first preset value and the second preset value are the same as the first mode, and are not described again. And the fourth preset value, namely the value of the COS field is a value between 0 and 7, and different values correspond to different processing stages and partial discarding reasons thereof.
For example, as an implementation, the indexes of several stages such as VFP, ING _ PORT, etc. are set as follows:
in the VFP stage or the EFP stage, when CNG is 1 and the obtained stage state information DROP is 1, setting COS to 1 by using the FP module, and occupying 5 th to 7 th bytes, the corresponding index is (10000011);
at a PORT (including an ING _ PORT and an EGR _ PORT) or VLAN (including an ING _ VLAN and an EGR _ VLAN), for a target packet of CNG 1, obtaining stage state information corresponding to the stage, for example, pktRes may be obtained, when pktRes is nkown _ pkt, representing a packet that cannot be identified by the PORT and VLAN stages, setting COS 2 by using an FP module, and setting a corresponding index to be (10000101);
in the STP stage, when CNG is 1 and the state of the lookup status register corresponding to STP is BLOCK or LEARN, using the FP module to set COS to 3 and the corresponding index to (10000111);
in the stage of IP DST, when CNG is 1, the obtained stage state information L3_ DST _ class is TRAP _ LOCAL, which represents that a message hits a LOCAL route and is discarded, an FP module is used to set COS to 4, and the corresponding index is (10001001); l3_ dst _ classid, which represents that the message hits the direct connection NETWORK route and is discarded, then the FP module is used to set COS 5, and the corresponding index is (10001011); when CNG is 1, pktRes is UNKOWN — L3UC — PKT, which means that no 3-layer unicast egress can be found, and a missing route results in a discard, the FP module is used to set COS to 6, and the corresponding index is (10001101).
For the ING _ L3_ NEXT _ HOP stage, when CNG is 1, DROP is 0, and L3_ dst _ class is FWD, which indicates that no packet loss occurs before the IFP stage, the DROP information of the final port in the ingress direction should be acquired at this time, and if DROP of the final port in the ingress direction is 1, it indicates that the target packet loss occurs in the ingress direction, and it can be determined that packet loss occurs in the ING _ L3_ NEXT _ HOP stage, at this time, the FP module is used to set COS to 7, and the corresponding index is (10001111).
Step 204: and triggering the counter to count based on the set index, so that the register value of the counter correspondingly increases, and outputting corresponding increasing information.
The growth information is used to determine a processing stage at which packet loss occurs, and specifically, the growth information should display a specific field combination and a value of an index causing the register value to grow, and the processing stage at which packet loss occurs can be determined correspondingly according to the specific field combination and the value of the index.
Therefore, based on the method, the processing stage and part of discarding reasons of the packet loss can be correspondingly obtained according to the combination and value of different fields.
Specifically, when the boston chip switch is used as a diagnosis object and the flexible counter is used as a counter, and the CNG field + PORT field (including Ingress PORT and Egress PORT) and the DROP field are used as field combinations for indexing, which PORTs the target message passes through and whether the packet is lost can be positioned according to the output increase information.
For example, when CNG in the index is 1, DROP is 1, and PORT is 32, the register value of the flexible counter increases, and then the PORT with PORT number 32 has a target packet passing through and packet loss in the direction of the input PORT or the output PORT.
When the CNG field + COS field + DROP field is used as the field combination for indexing, the reason of packet loss in the input direction can be accurately positioned.
For example, when CNG is 1, DROP is 1, and COS is 1 in the index, if the register value of the flexible counter increases, it can be diagnosed that the target packet is lost in the VFP stage;
when CNG in the index is 1, DROP is 1 and COS is 2, the register value of the flexible counter is increased, and the target message can be diagnosed as PORT/VLAN stage packet loss;
CNG in the index is 1, DROP is 1, COS is 3, and the register value of the flexible counter is increased, so that the target message can be diagnosed as the packet loss in the STP stage, and the packet loss reason is discarded because the register in the STP stage is in a LEARN or BLOCK state;
when CNG is 1, DROP is 1 and COS is 4, 5 and 6 respectively in the index, the register value of the flexible counter is increased, the target message can be diagnosed as the lost packet in the IP DST stage, and the reasons of the lost packet are respectively the lost caused by the fact that the message hits the local routing, the lost caused by the fact that the message hits the direct-connected network routing and the lost caused by the fact that the message is an unknown 3-layer unicast message.
In addition, in this embodiment of the application, according to FP module count confirmation, no packet loss occurs before the ING _ L3_ NEXT _ HOP stage, that is, CNG is 1, and DROP is 0, which indicates that the target packet is not packet loss before the ING _ L3_ NEXT _ HOP stage, if the target packet loss still exists at the port in the final entry direction, it is diagnosed that packet loss occurs at the ING _ L3_ NEXT _ HOP stage, at this time, COS 7 is set in the index, and it is displayed in the output increment information, and when CNG is 1 and COS is 7, the register value of the flexible counter is incremented, and it is diagnosed that packet loss occurs at the ING _ L3_ NEXT _ HOP stage no matter DROP is 0 or 1.
In this embodiment, as another possible implementation manner, for the ING _ L3_ NEXT _ HOP stage, when CNG is 1 and the acquired stage state information DROP is 0, COS may be set to 7, which indicates that no packet is lost before the ING _ L3_ NEXT _ HOP stage, and then the FP module continues to acquire DROP information of each processing stage after the ING _ L3_ NEXT _ HOP stage, and if DROP is 1, it is determined that the ING _ L3_ NEXT _ HOP stage or the subsequent processing stage loses packet.
In this embodiment of the present application, if the count of the flexible counter triggered by the ING _ PORT stage can be counted, and the count triggered by the ING _ VLAN stage cannot be counted, it may be diagnosed that a CRC check error occurs on the PORT.
To further understand the invention, a complete embodiment is set forth below:
in the embodiment of the present application, a chip in a switch is described as BCM5686 x. Assume that the target Message to be identified is a network Control Message Protocol (ICMP) Message with a source MAC address of 1.1.1.1 and a destination MAC address of 1.1.1.2.
And presetting rules in the rule group under the FP module, and changing the attribute of the index of the flexible counter. The index of the flexible counter is a combination of different fields, and each combination corresponds to a resource pool of the flexible counter. Specifically, this field combination of setting the CNG field + PORT field + DROP field corresponds to a first resource pool input of the flexible counter, and this field combination of setting the CNG field + COS field + DROP field corresponds to a second resource pool input of the flexible counter.
Referring to the pipeline shown in fig. 3, first, ICMP messages with source and destination addresses 1.1.1.1 and 1.1.1.2 are identified from the input message stream, the CNG flag is set to 1, and COS (i.e., outer dot1p) is marked as 0. The CNG information of the message can be carried by a higig header so as to realize counting aiming at a higig port.
In the following stages, whether the message is a target message needs to be identified, namely whether CNG is 1 is identified, the subsequent steps are executed after the CNG is determined to be 1, and otherwise, the message is skipped, and the next message is monitored.
In the VFP phase, when CNG is 1 and the acquired phase status information DROP is 1, the COS is set to 1 using the FP module.
And in the ING _ PORT stage or the EGR _ PORT stage, when the acquired stage state information DROP is 1, acquiring the PORT number of the input PORT or the output PORT at the same time, and setting the PORT field in the index as the PORT number of the input PORT or the output PORT. And inputting the index after setting through a first resource pool of the flexible counter.
At the stage of PORT or VLAN, when CNG is 1, and the obtained stage state information is pktRes — pkt, which represents a packet that cannot be identified by the stage of PORT and VLAN, the COS is set to 2 by using the FP module.
In the STP stage, when CNG is 1 and the state of the lookup status register corresponding to STP is BLOCK or LEARN, the COS is set to 3 and the ACL counter is set using the FP module.
In the stage of IP DST, when CNG is 1 and the obtained stage state information is L3_ DST _ class is TRAP _ LOCAL, the message hits the LOCAL routing to cause discarding, and the COS is set to be 4 by using FP; when CNG is 1 and the obtained stage state information is L3_ dst _ class is TRAP _ CONNECTED _ NETWORK, it represents that the message hits the direct connection NETWORK route and is discarded, and then the FP module is used to set COS to 5; when CNG is 1 and the phase pktRes is UNKOWN — L3UC _ PKT, the delegate cannot find a layer 3 unicast egress, misses the route and causes the packet to be dropped, then the COS is set to 6 using the FP.
In the ING _ L3_ NEXT _ HOP stage, when CNG is 1, and the obtained stage state information DROP is 0, and L3_ dst _ class is FWD, it indicates that no packet loss occurs before the IFP stage, it is necessary to obtain a DROP value at the final port in the ingress direction, and the DROP value is 1, and COS is set to 7 using FP.
In the EFP phase, when CNG is 1 and the acquisition phase status information DROP is 1, the COS is set to 1 using the FP module.
All indexes containing the COS field are entered through the second resource pool of the flexible counter.
Based on the same inventive concept, the embodiment of the present application further provides a device for monitoring network packet loss. Referring to fig. 6, the apparatus at least includes a recognition unit 601, an acquisition unit 602, a setting unit 603, and an output unit 604.
The identifying unit 601 is configured to identify a target packet from a received packet stream based on a preset identifying feature;
an obtaining unit 602, configured to obtain, in real time, stage state information corresponding to each processing stage of the target packet in a processing process of the target packet;
a setting unit 603, configured to set, when it is determined that any one of the stage state information represents that the target packet is discarded, an index of a counter as a preset value corresponding to a processing stage based on the processing stage to which the any one of the stage state information belongs;
an output unit 604, configured to trigger the counter to count based on the set index, so that the register value of the counter correspondingly increases, and output corresponding increase information, where the increase information is used to determine a processing stage at which packet loss occurs.
Optionally, in this embodiment of the application, when the target packet is identified from the received packet based on the preset identification feature, the identifying unit 601 is specifically configured to: and respectively executing the following operations aiming at each message in the message flow: analyzing the identification characteristics of a message; the identification characteristics comprise any one or any combination of a source MAC address, a destination MAC address, an ETYPE, a source IP address and a destination IP address; and when the at least one identification feature is determined to be matched with the preset identification feature, judging the message as a target message.
Optionally, the apparatus further comprises a pre-processing unit 605. The preprocessing unit 605 is configured to obtain a preset rule, where the preset rule sets a processing operation to be executed correspondingly when the target packet is discarded in each processing stage, and the processing operation at least includes a manner of setting an index of a counter.
Optionally, when it is determined that any one of the stage state information represents that the target packet is discarded, and the index of the counter is set to the preset value corresponding to the processing stage based on the processing stage to which the any one of the stage state information belongs, the setting unit 603 is specifically configured to:
and when the target message is determined to be discarded in any one processing stage, setting the index of the counter as a corresponding combination of a plurality of fields based on the preset rule according to the processing stage to which the state information of any one stage belongs, wherein one combination corresponds to one resource pool of the counter, and setting the value of each field as a corresponding preset value.
Optionally, when the value of each field is set to a corresponding preset value, the setting unit 603 is specifically configured to:
if the processing stage to which the state information of any one stage belongs is a port stage, setting the index of the counter as the combination of a first field, a second field and a third field, setting the value of the first field as a first preset value, setting the second field as a second preset value and setting the value of the third field as a third preset value; the first field represents whether a processing object is a target message or not, and the second field represents whether the target message is discarded or not; the third preset value represents an input port number or an output port number of the target message;
if the processing stage to which the state information of any stage belongs is any one of a VFP stage, an ING _ PORT stage, an ING _ VLAN stage, an STP stage, an IP DST stage or an ING _ L3_ NEXT _ HOP stage and an EFP stage; setting the index of the counter as the combination of a first field, a second field and a fourth field, setting the value of the first field as a first preset value, setting the value of the second field as a second preset value and setting the value of the fourth field as a fourth preset value; and the fourth preset value is used for representing the processing stage of discarding the target message.
Based on the same inventive concept, referring to fig. 7, an embodiment of the present application further provides a switch, where the switch at least includes: a memory 701 and a processor 702, wherein,
a memory 701 for storing executable instructions;
a processor 702, configured to read and execute executable instructions stored in a memory, so as to implement the following network packet loss notification method:
identifying a target message from a received message flow based on a preset identification characteristic;
in the processing process of the target message, stage state information corresponding to each processing stage of the target message is acquired in real time;
when the state information of any stage is determined to represent that the target message is discarded, setting the index of a counter as a preset value corresponding to a processing stage based on the processing stage to which the state information of any stage belongs;
and triggering the counter to count based on the set index, so that the register value of the counter correspondingly increases, and outputting corresponding increasing information, wherein the increasing information is used for determining a processing stage of packet loss.
Optionally, when the target packet is identified from the received packets based on the preset identification feature, the processor 702 is configured to read and execute an executable instruction stored in the memory, and specifically implement:
and respectively executing the following operations aiming at each message in the message flow:
analyzing the identification characteristics of a message; the identification characteristics comprise any one or any combination of a source MAC address, a destination MAC address, an ETYPE, a source IP address and a destination IP address;
and when the at least one identification feature is determined to be matched with the preset identification feature, judging the message as a target message.
Optionally, before the target packet is identified from the received packet stream based on the preset identification feature, the processor 702 is configured to read and execute the executable instruction stored in the memory, and further implement:
and acquiring preset rules, wherein the preset rules respectively set correspondingly executed processing operations when the target message is discarded at each processing stage, and the processing operations at least comprise a mode of setting an index of a counter.
Optionally, when it is determined that any one of the stage state information represents that the target packet is discarded, and the index of the counter is set to a corresponding preset value based on the processing stage to which the any one of the stage state information belongs, the processor 702 is configured to read and execute an executable instruction stored in a memory, and specifically implement:
and when the target message is determined to be discarded in any one processing stage, setting the index of the counter to be a corresponding combination of a plurality of fields based on the preset rule according to the processing stage to which the state information of any one stage belongs, wherein one combination corresponds to one resource pool of the counter, and setting the value of each field to be a corresponding preset value.
Optionally, when the value of each field is set to a corresponding preset value, the processor 702 is configured to read and execute an executable instruction stored in a memory, and implement the following steps:
if the processing stage to which the state information of any one stage belongs is a port stage, setting the index of the counter as the combination of a first field, a second field and a third field, setting the value of the first field as a first preset value, setting the second field as a second preset value and setting the value of the third field as a third preset value; the first field represents whether a processing object is a target message or not, and the second field represents whether the target message is discarded or not; the third preset value represents an input port number or an output port number of the target message;
if the processing stage to which the state information of any stage belongs is any one of a VFP stage, an ING _ PORT stage, an ING _ VLAN stage, an STP stage, an IP DST stage or an ING _ L3_ NEXT _ HOP stage and an EFP stage; setting the index of the counter as the combination of a first field, a second field and a fourth field, setting the value of the first field as a first preset value, setting the value of the second field as a second preset value and setting the value of the fourth field as a fourth preset value; and the fourth preset value is used for representing the processing stage of discarding the target message.
Based on the same inventive concept, the present application also provides a storage medium, wherein when the instructions in the storage medium are executed by a processor, the storage medium enables any one of the methods related to the embodiments to be executed.
In summary, in the embodiment of the present application, the target packet is first identified, and the identified target packet is monitored, including obtaining stage state information of each processing stage through which the target packet passes, and setting different indexes according to different processing stages in combination with the stage state information, so that there is a definite correspondence between the processing stages and the indexes, the index triggers a register value corresponding to the counter to increase, and outputs increase information, and a specific index causing the register value to increase may be displayed in the increase information, so as to know a processing stage at which packet loss occurs.
Based on the method of the embodiment of the application, the automatic notification function of the discarded target message at most of the processing stages in the switch pipeline can be realized, active output and active notification are realized, compared with a simulation technical means based on a large amount of register information in the prior art, complex logic does not need to be introduced, only the state information of some stages in the switch is taken as reference, and for a switch with an internal chip system stacked by multiple chips (namely, a switch with cross-chip forwarding), on one hand, when the number of chips is increased, the steps only need to be repeatedly executed, and the logic for solving the problem does not become more complex; on the other hand, the flexible counter selected in the embodiment of the application can be applied to a back panel port between different chips in a chip stacking system, and the output of the register information of the flexible counter is realized.
In addition, the method is not only suitable for the switch with cross-chip forwarding, and can diagnose whether packet loss occurs in the switch, but also can locate the port through which the target message passes. The packet losses of different processing stages of the internal flow line of the switch can be respectively diagnosed, the positioning precision is further accurate to a plurality of specific processing stages (including a port) of the flow line of the switch, the accurate forwarding path description of the target message in the switch equipment is realized, and the diagnosis precision is relatively higher.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the present application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to encompass such modifications and variations.

Claims (12)

1. A method for notifying network packet loss is characterized by comprising the following steps:
identifying a target message from the received message stream based on a preset identification characteristic;
in the processing process of the target message, stage state information corresponding to each processing stage of the target message is acquired in real time;
when the state information of any stage is determined to represent that the target message is discarded, setting the index of a counter as a preset value corresponding to a processing stage based on the processing stage to which the state information of any stage belongs;
and triggering the counter to count based on the set index, so that the register value of the counter correspondingly increases, and outputting corresponding increasing information, wherein the increasing information is used for determining a processing stage of packet loss.
2. The method of claim 1, wherein identifying a target packet from the received packet stream based on a predetermined identification characteristic comprises:
the following operations are respectively executed for each message in the message flow:
analyzing at least one identification characteristic of a message; the identification characteristics comprise any one or any combination of a source Media Access Control (MAC) address, a destination MAC address, an Ethernet Type (ETYPE), a source Internet Protocol (IP) address and a destination IP address;
and when the at least one identification feature is determined to be matched with the preset identification feature, judging the message as a target message.
3. The method of claim 1 or 2, wherein prior to identifying the target message from the received message stream based on the predetermined identification characteristic, further comprising:
and acquiring preset rules, wherein the preset rules respectively set correspondingly executed processing operations when the target message is discarded at each processing stage, and the processing operations at least comprise a mode of setting an index of a counter.
4. The method according to claim 3, wherein when it is determined that any one of the stage state information represents that the target packet is discarded, setting an index of the counter to a preset value corresponding to a processing stage to which the any one of the stage state information belongs based on the processing stage to which the any one of the stage state information belongs, specifically comprising:
and when the target message is determined to be discarded in any one processing stage, setting the index of the counter to be a corresponding combination of a plurality of fields based on the preset rule according to the processing stage to which the state information of any one stage belongs, wherein one combination corresponds to one resource pool of the counter, and setting the value of each field to be a corresponding preset value.
5. The method of claim 4, wherein setting the value of each field to a corresponding preset value specifically comprises:
if the processing stage to which the state information of any one stage belongs is a port stage, setting the index of the counter as the combination of a first field, a second field and a third field, setting the value of the first field as a first preset value, setting the second field as a second preset value and setting the value of the third field as a third preset value; the first field represents whether a processing object is a target message or not, and the second field represents whether the target message is discarded or not; the third preset value represents an input port number or an output port number of the target message;
if the processing stage to which the state information of any one stage belongs is any one of a VFP stage, an ING _ PORT stage, an ING _ VLAN stage, an STP stage, an IP DST stage or an ING _ L3_ NEXT _ HOP stage and an EFP stage, setting the index of the counter as the combination of a first field, a second field and a fourth field, setting the value of the first field as a first preset value, setting the value of the second field as a second preset value and setting the value of the fourth field as a fourth preset value; the fourth preset value is used for representing the discarded target message and/or the discarded processing stage.
6. A device for monitoring network packet loss, comprising:
the identification unit is used for identifying a target message from the received message flow based on preset identification characteristics;
the acquisition unit is used for acquiring the stage state information corresponding to the target message in each processing stage in real time in the processing process of the target message;
the setting unit is used for setting the index of the counter to be a preset value corresponding to a processing stage based on the processing stage to which the state information of any stage belongs when the state information of any stage represents that the target message is discarded;
and the output unit is used for triggering the counter to count based on the set index, so that the register value of the counter correspondingly increases, and outputting corresponding increase information, wherein the increase information is used for determining a processing stage of packet loss.
7. The apparatus according to claim 6, wherein the target packet is identified from the received packets based on a preset identification feature, and the identifying unit is specifically configured to:
and respectively executing the following operations aiming at each message in the message flow:
analyzing the identification characteristics of a message; the identification characteristics comprise any one or any combination of a source Media Access Control (MAC) address, a destination MAC address, an Ethernet Type (ETYPE), a source Internet Protocol (IP) address and a destination IP address;
and when the at least one identification feature is determined to be matched with the preset identification feature, judging the message as a target message.
8. The apparatus of claim 6 or 7, further comprising:
the device comprises a preprocessing unit and a counter, wherein the preprocessing unit is used for acquiring preset rules, the preset rules respectively set processing operations correspondingly executed when a target message is discarded in each processing stage, and the processing operations at least comprise a mode of setting an index of the counter.
9. The apparatus according to claim 8, wherein when it is determined that any one of the stage state information represents that the target packet is discarded, based on a processing stage to which the any one of the stage state information belongs, an index of a counter is set to a preset value corresponding to the processing stage, and the setting unit is specifically configured to:
and when the target message is determined to be discarded in any one processing stage, setting the index of the counter to be a corresponding combination of a plurality of fields based on the preset rule according to the processing stage to which the state information of any one stage belongs, wherein one combination corresponds to one resource pool of the counter, and setting the value of each field to be a corresponding preset value.
10. The apparatus of claim 9, wherein the values of the fields are set to corresponding preset values, and the setting unit is specifically configured to:
if the processing stage to which the state information of any one stage belongs is a port stage, setting the index of the counter as the combination of a first field, a second field and a third field, setting the value of the first field as a first preset value, setting the second field as a second preset value and setting the value of the third field as a third preset value; the first field represents whether a processing object is a target message or not, and the second field represents whether the target message is discarded or not; the third preset value represents an input port number or an output port number of the target message;
if the processing stage to which the state information of any one stage belongs is any one of a VFP stage, an ING _ PORT stage, an ING _ VLAN stage, an STP stage, an IP DST stage or an ING _ L3_ NEXT _ HOP stage and an EFP stage, setting the index of the counter as the combination of a first field, a second field and a fourth field, setting the value of the first field as a first preset value, setting the value of the second field as a second preset value and setting the value of the fourth field as a fourth preset value; the fourth preset value is used for representing the processing stage of the discarded and/or discarded target message.
11. A switch, characterized in that the switch comprises: a memory and a processor; wherein the content of the first and second substances,
a memory for storing executable instructions;
a processor for reading and executing executable instructions stored in the memory to implement the method of any one of claims 1-5.
12. A storage medium, wherein instructions in the storage medium, when executed by a processor, enable performance of the method of any one of claims 1-5.
CN201910870529.1A 2019-09-16 2019-09-16 Network packet loss notification method, monitoring device, switch and storage medium Active CN110661716B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910870529.1A CN110661716B (en) 2019-09-16 2019-09-16 Network packet loss notification method, monitoring device, switch and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910870529.1A CN110661716B (en) 2019-09-16 2019-09-16 Network packet loss notification method, monitoring device, switch and storage medium

Publications (2)

Publication Number Publication Date
CN110661716A CN110661716A (en) 2020-01-07
CN110661716B true CN110661716B (en) 2022-07-19

Family

ID=69037259

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910870529.1A Active CN110661716B (en) 2019-09-16 2019-09-16 Network packet loss notification method, monitoring device, switch and storage medium

Country Status (1)

Country Link
CN (1) CN110661716B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113259143B (en) * 2020-02-07 2023-04-18 阿里巴巴集团控股有限公司 Information processing method, device, system and storage medium
CN112260899B (en) * 2020-10-20 2022-08-26 苏州盛科通信股份有限公司 Network monitoring method and device based on MMU (memory management unit)
CN112702236B (en) * 2020-12-23 2022-11-11 锐捷网络股份有限公司 Method and processor for realizing packet loss detection
CN113660166A (en) * 2021-08-17 2021-11-16 中国工商银行股份有限公司 Transaction routing control method and device, electronic equipment and storage medium
CN114338554A (en) * 2021-12-31 2022-04-12 锐捷网络股份有限公司 Stream-based random packet loss method and device
CN114615170B (en) * 2022-01-20 2023-08-04 北京华耀科技有限公司 Message processing method, device and computer storage medium
CN114389972B (en) * 2022-02-22 2024-03-26 清华大学 Packet loss detection method and device and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102916883A (en) * 2012-10-11 2013-02-06 杭州华三通信技术有限公司 LINK detection method and routing forwarding equipment
CN103001828A (en) * 2012-12-04 2013-03-27 北京星网锐捷网络技术有限公司 Message statistical method and device and network device based on data flow
CN104917628A (en) * 2015-04-09 2015-09-16 南京邮电大学 Automatic diagnosis method of Ethernet router/switch packet loss fault
WO2016123892A1 (en) * 2015-02-06 2016-08-11 中兴通讯股份有限公司 Packet loss determination processing, determination method, and apparatus
CN106788876A (en) * 2015-11-19 2017-05-31 电信科学技术研究院 A kind of method and system of voice Discarded Packets compensation
US10021031B1 (en) * 2015-12-29 2018-07-10 Amazon Technologies, Inc. Pipelined packet policer
CN108965038A (en) * 2018-10-17 2018-12-07 盛科网络（苏州）有限公司 The method and device that specific stream packet abandons reason is quickly positioned by ACL
CN109561029A (en) * 2017-09-26 2019-04-02 中兴通讯股份有限公司 A kind of message up sending control method and device

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2242273A1 (en) * 2009-04-14 2010-10-20 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Transmission scheme for text-based information
CN105007612A (en) * 2014-04-25 2015-10-28 中兴通讯股份有限公司 Method for obtaining data in wireless body area network and central device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102916883A (en) * 2012-10-11 2013-02-06 杭州华三通信技术有限公司 LINK detection method and routing forwarding equipment
CN103001828A (en) * 2012-12-04 2013-03-27 北京星网锐捷网络技术有限公司 Message statistical method and device and network device based on data flow
WO2016123892A1 (en) * 2015-02-06 2016-08-11 中兴通讯股份有限公司 Packet loss determination processing, determination method, and apparatus
CN104917628A (en) * 2015-04-09 2015-09-16 南京邮电大学 Automatic diagnosis method of Ethernet router/switch packet loss fault
CN106788876A (en) * 2015-11-19 2017-05-31 电信科学技术研究院 A kind of method and system of voice Discarded Packets compensation
US10021031B1 (en) * 2015-12-29 2018-07-10 Amazon Technologies, Inc. Pipelined packet policer
CN109561029A (en) * 2017-09-26 2019-04-02 中兴通讯股份有限公司 A kind of message up sending control method and device
CN108965038A (en) * 2018-10-17 2018-12-07 盛科网络（苏州）有限公司 The method and device that specific stream packet abandons reason is quickly positioned by ACL

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
A Protection Method Based on Message Identification and Flow Monitoring for Managing the Congestion Arising From Network Attacks on Smart Substation;W. Tong等;《IEEE Communications Letters》;20180903;第22卷(第11期);第2214-2217页 *
基于IEEE 802.11e的无线传感器/执行器网络丢包判器设计;姚毅等;《计算机科学》;20160815;第43卷(第08期);第66-70页 *
基于数字视频广播平台的服务质量保证研究;周长志等;《北京理工大学学报》;20030320(第03期);第359-362页 *

Also Published As

Publication number Publication date
CN110661716A (en) 2020-01-07

Similar Documents

Publication Publication Date Title
CN110661716B (en) Network packet loss notification method, monitoring device, switch and storage medium
US10735221B2 (en) Flexible processor of a port extender device
US9258225B2 (en) System and method for efficient matching of regular expression patterns across multiple packets
US8638793B1 (en) Enhanced parsing and classification in a packet processor
US9680720B1 (en) Operations, administration, and maintenance (OAM) engine
US9065770B2 (en) Traffic item impairment emulation
US7881221B2 (en) Hardware implementation of network testing and performance monitoring in a network device
KR101409921B1 (en) System and method for integrating line-rate application recognition in a switch asic
US20060165003A1 (en) Method and apparatus for monitoring data routing over a network
JP2011101346A (en) Detection apparatus and detection method of misdirected packet
EP2530874A1 (en) Method and apparatus for detecting network attacks using a flow based technique
JP2006013737A (en) Device for eliminating abnormal traffic
US20130329572A1 (en) Misdirected packet statistics collection and analysis
US7516364B2 (en) Method for testing network devices using breakpointing
CN106789652A (en) Service shunting method and device
US11108812B1 (en) Data plane with connection validation circuits
CN110071843B (en) Fault positioning method and device based on flow path analysis
CN115514683B (en) Packet loss reason determining method, device, exchange chip and storage medium
CN107612848B (en) Debugging method and device and computer readable storage medium
CN105828218A (en) Method for detecting transmission quality of multicast streams, device and system
CN112118156B (en) Filtering method and device for Ethernet protocol test
EP3092737B1 (en) Systems for enhanced monitoring, searching, and visualization of network data
CN109525438A (en) A kind of implementation method of network connectivty investigation
WO2015105684A1 (en) Apparatus, system, and method for enhanced monitoring and interception of network data
EP2854340B1 (en) Misdirected packet statistics collection and analysis

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