CN113839887A - Fault processing method and device for photoelectric hybrid switching network and electronic equipment - Google Patents

Fault processing method and device for photoelectric hybrid switching network and electronic equipment Download PDF

Info

Publication number
CN113839887A
CN113839887A CN202111102983.6A CN202111102983A CN113839887A CN 113839887 A CN113839887 A CN 113839887A CN 202111102983 A CN202111102983 A CN 202111102983A CN 113839887 A CN113839887 A CN 113839887A
Authority
CN
China
Prior art keywords
traffic
switching network
hybrid switching
optical
loss
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111102983.6A
Other languages
Chinese (zh)
Other versions
CN113839887B (en
Inventor
王伟
胡乔钧
刘天和
李亚杰
赵永利
张�杰
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.)
Beijing University of Posts and Telecommunications
Original Assignee
Beijing University of Posts and Telecommunications
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 Beijing University of Posts and Telecommunications filed Critical Beijing University of Posts and Telecommunications
Priority to CN202111102983.6A priority Critical patent/CN113839887B/en
Publication of CN113839887A publication Critical patent/CN113839887A/en
Application granted granted Critical
Publication of CN113839887B publication Critical patent/CN113839887B/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
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/80—Actions related to the user profile or the type of traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/10—Packet switching elements characterised by the switching fabric construction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/55—Prevention, detection or correction of errors
    • H04L49/557—Error correction, e.g. fault recovery or fault tolerance

Abstract

The application discloses a fault processing method and device for a photoelectric hybrid switching network and electronic equipment. By applying the technical scheme of the application, when the equipment fault in the photoelectric hybrid switching network is detected, one part of the flow which cannot be forwarded due to the fault can be processed by the residual bandwidth resource of the EPS, and the other part of the flow can be cached on the top rack switch to be processed when the next configuration cycle of the photoelectric hybrid switching network is waited. Therefore, the purposes of improving the bandwidth utilization rate of the network and guaranteeing the performance of the fault network by using the originally idle bandwidth resources are achieved.

Description

Fault processing method and device for photoelectric hybrid switching network and electronic equipment
Technical Field
The present application relates to data processing technologies, and in particular, to a method and an apparatus for processing a fault in an optical-electrical hybrid switching network, and an electronic device.
Background
With the rapid development of cloud computing technology, data centers have become a key infrastructure of the information-oriented society, and current network devices and technologies for data centers are facing serious challenges. On one hand, the modern network application puts higher requirements on the performances such as network capacity and the like in the data center; on the other hand, large-scale network facilities in data centers are consuming more and more electric power energy. In order to meet the above challenges, optical circuit switching network technology with natural advantages of large capacity, low energy consumption, etc. is expected and draws wide attention in academia.
Among them, in the Optical-electrical hybrid switching network in the related art, an OCS (Optical Circuit Switch) based on a MEMS (Micro-Electro-Mechanical Systems) is generally used to implement service processing. However, such a device has no sensing capability for data, and can only schedule the connection of the optical circuit according to a predetermined traffic scheduling mechanism, and once a device failure or a link failure occurs, the traffic scheduling cannot be adaptively adjusted due to a change in the network topology, and traffic forwarding will be seriously affected, so that the performance of the entire network is greatly reduced.
Disclosure of Invention
An embodiment of the present application provides a method and an apparatus for processing a fault of an optical-electrical hybrid switching network, and an electronic device, where according to an aspect of the embodiment of the present application, the method for processing the fault of the optical-electrical hybrid switching network is provided, and is characterized in that the method is applied to the optical-electrical hybrid switching network, and includes:
if the optical circuit switch is detected to have a fault, acquiring equipment information of an OCS (optical circuit switch) with the fault;
calculating loss flow according to the equipment information, wherein the loss flow is used for representing the flow forwarding requirement which cannot be met in the photoelectric hybrid switching network due to the OCS fault;
buffering a first portion of the loss traffic on a top of rack switch (TOR), and processing the first portion of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network.
Optionally, in another embodiment based on the foregoing method of the present application, before the caching the first part of the loss traffic on the top of rack switch ToR, the method further includes:
idle resource information of a packet switch, ESP, is computed and a second portion of the lost traffic is allocated for processing by the idle resources of the ESP.
Optionally, in another embodiment based on the method of the present application, the calculating idle resource information of the packet switch ESP includes:
acquiring port bandwidths of all EPS and configuration cycles of OCS under the photoelectric hybrid switching network;
calculating to obtain the maximum forwarding data volume of the EPS in the configuration period;
and calculating to obtain the original load flow of the port corresponding to the EPS, and obtaining the idle resource information of the ESP according to the difference value between the maximum forwarding data volume and the original load resource.
Optionally, in another embodiment based on the above method of the present application, the allocating a second part of the lost traffic is processed by an idle resource of the ESP, and includes:
calculating a magnitude relationship between idle resource information of the EPS and a second portion of the lost traffic;
and if the idle resource information of the EPS is determined not to be larger than the second part of the lost flow, completely processing the lost flow by using the idle resource of the EPS.
And if the idle resource information of the EPS is determined to be smaller than the second part of the lost flow, processing the lost flow by using the idle resource information part of the EPS, and clearing the residual lost flow.
Optionally, in another embodiment based on the foregoing method of the present application, the calculating the loss flow according to the device information includes:
acquiring a flow sum demand matrix under the photoelectric hybrid switching network;
decomposing the flow sum demand matrix according to a scheduling algorithm to obtain a demand matrix corresponding to each OCS;
and obtaining a demand matrix corresponding to the fault OCS according to the equipment information of the fault OCS, and using the demand matrix as the loss flow.
Optionally, in another embodiment based on the foregoing method of the present application, the traffic summation requirement matrix under the optical-electrical hybrid switching network is obtained according to the following formula:
Dz×z＝{dij}；
wherein i, j ∈ [1, z ]]Z is the number of switches under the optical-electrical hybrid switching network, and when i equals j, dij＝0。
Optionally, in another embodiment based on the foregoing method of the present application, the processing the first part of the loss traffic at the next configuration period of the optical-electrical hybrid switching network includes:
calculating a first part of the loss traffic into a traffic demand matrix of a next configuration period of the photoelectric hybrid switching network;
and when detecting that the next configuration period of the photoelectric hybrid switching network comes, forwarding the traffic demand matrix containing the first part of the loss traffic.
According to another aspect of the embodiments of the present application, there is provided a fault handling apparatus for an optical-electrical hybrid switching network, which is applied to the optical-electrical hybrid switching network, and includes:
the optical circuit switch OCS comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is configured to acquire equipment information of an OCS if the optical circuit switch is detected to have a fault;
a calculation module configured to calculate a loss traffic according to the device information, where the loss traffic is used to characterize an unsatisfiable traffic forwarding requirement in the optical-electrical hybrid switching network due to the OCS failure;
a forwarding module configured to buffer a first portion of the loss traffic on a top of rack switch (TOR) and process the first portion of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network.
According to another aspect of the embodiments of the present application, there is provided an electronic device including:
a memory for storing executable instructions; and
a display for displaying with the memory to execute the executable instructions to complete the operation of the fault handling method of any of the optoelectronic hybrid switching networks.
According to a further aspect of the embodiments of the present application, there is provided a computer-readable storage medium for storing computer-readable instructions, which when executed, perform the operations of the fault handling method of any one of the optical-electrical hybrid switching networks.
In the application, if the optical circuit switch is detected to have a fault, the equipment information of the OCS of the faulty optical circuit switch can be acquired; calculating loss flow according to the equipment information, wherein the loss flow is used for representing the flow forwarding requirement which cannot be met due to the OCS fault in the photoelectric hybrid switching network; buffering a first part of the loss traffic on the top of rack switch ToR, and processing the first part of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network. By applying the technical scheme of the application, when the equipment fault in the photoelectric hybrid switching network is detected, one part of the flow which cannot be forwarded due to the fault can be processed by the residual bandwidth resource of the EPS, and the other part of the flow can be cached on the top rack switch to be processed when the next configuration cycle of the photoelectric hybrid switching network is waited. Therefore, the purposes of improving the bandwidth utilization rate of the network and guaranteeing the performance of the fault network by using the originally idle bandwidth resources are achieved.
The technical solution of the present application is further described in detail by the accompanying drawings and examples.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description, serve to explain the principles of the application.
The present application may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:
fig. 1 is a schematic diagram illustrating a method for handling a fault in an optical-electrical hybrid switching network according to the present application;
fig. 2-4 are schematic system architectures of an optical-electrical hybrid switching network according to the present application;
fig. 5-fig. 7 are schematic diagrams illustrating a fault handling procedure of an optical-electrical hybrid switching network according to the present application;
fig. 8 is a schematic structural diagram of a fault handling electronic device of an optical-electrical hybrid switching network according to the present application;
fig. 9 is a schematic structural diagram of a fault handling electronic device of an optical-electrical hybrid switching network according to the present application.
Detailed Description
Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present application unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the application, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
In addition, technical solutions between the various embodiments of the present application may be combined with each other, but it must be based on the realization of the technical solutions by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination of technical solutions should be considered to be absent and not within the protection scope of the present application.
It should be noted that all the directional indicators (such as upper, lower, left, right, front and rear … …) in the embodiment of the present application are only used to explain the relative position relationship between the components, the motion situation, etc. in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indicator is changed accordingly.
A method for performing fault handling in an opto-electric hybrid switching network according to an exemplary embodiment of the present application is described below with reference to fig. 1 to 7. It should be noted that the following application scenarios are merely illustrated for the convenience of understanding the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.
The application also provides a fault processing method and device of the photoelectric hybrid switching network, a target terminal and a medium.
Fig. 1 schematically shows a flow chart of a fault handling method of an optical-electrical hybrid switching network according to an embodiment of the present application. As shown in fig. 1, the method is applied to an optical-electrical hybrid switching network, and includes:
s101, if the optical circuit switch is detected to be in fault, acquiring equipment information of the OCS of the faulty optical circuit switch.
With the rapid development of cloud computing technology and internet application, the internal traffic load of a data center is larger and larger, and network equipment consumes more and more electric energy, so that an optical switching technology with high capacity and low energy consumption is introduced into a data center network.
Further, for the optical switching technology, the development of the cloud computing technology makes the internal traffic of the data center increase explosively, so that the adoption of a 10GigE switching architecture in the access layer and the adoption of a 40G/100GigE switching architecture in the core layer has basically become a future development trend of the data center network. In this case, the data center electrical interconnection architecture will face the technical requirements of high bandwidth, large capacity, low overhead, and low energy consumption. Optical switching technology can then respond well to the above challenges.
Wherein the optical switching directly switches the input signal to different output terminals in the optical domain via space division, time division or wavelength division without any optical/electrical conversion. Compared with electronic digital program control exchange, the optical exchange does not need to carry out optical/electric or electric/optical conversion between the optical fiber transmission line and the exchanger, and the advantages of high speed, broadband and no electromagnetic induction of optical signals can be fully exerted in the exchange process. Since the optical exchange does not involve electric signals, the optical exchange is not limited by the processing speed of an electronic device, and can be matched with the high-speed optical fiber transmission rate to realize the high speed of the network. The optical switch routes and routes signals according to the wavelength, and the optical switch is irrelevant to the protocol, the data format and the transmission rate adopted by communication, so that transparent data transmission can be realized. The optical switching can ensure the stability of the network and provide a flexible information routing means.
In particular, for the data center optical-electrical hybrid switching network architecture, the large-scale network facilities in the data center are consuming more and more electric power energy. In order to meet the above challenges, optical circuit switching technology having natural advantages such as high capacity and low power consumption is expected and has attracted extensive attention in academia. However, optical circuit switching is essentially a physical layer switching technique, is not compatible with the traditional packet switching architecture used in data centers, and cannot completely replace packet switching equipment. Therefore, the optical-electrical hybrid switching architecture with optical circuit switching and packet switching coexisting is one of the feasible routes to apply optical switching technology in data centers in a short period of time.
Specifically, in the related art, a two-layer optical-electrical hybrid switching architecture (e.g., Helios) is composed of an access layer and a core layer, and a MEMS-based OCS is used in the core layer to provide an inter-ToR optical circuit. And according to the flow demand matrix among different tors, the OCS management plane reconfigures the OCS exchange structure and establishes an optical circuit. The EPS is forwarded in a packet-switched manner in the header, and the OCS is reconfigured periodically according to the traffic demand of each ToR switch. The reconfiguration process and the data transmission process of the OCS both follow a periodicity, during which both the corresponding optical circuits are not available. Most traffic may be forwarded through the OCS, but when part of the traffic does not have available OCS optical circuits to reach the desired destination, the EPS will be responsible for forwarding these traffic.
In the photoelectric hybrid switching network, traffic forwarding among tors (Top of Rack switch) is completed by the cooperation of three modules, namely a traffic estimation module, a traffic scheduling module and a circuit configuration module. The cooperation relationship is shown in fig. 2.
The traffic estimation module shown in fig. 2 may generate a traffic demand matrix according to the traffic counter or the buffer status in the tors, where a row number of the matrix corresponds to a number of a source ToR, a column number of the matrix corresponds to a number of a destination ToR, and an element in the matrix represents the size of traffic to be forwarded.
Further, as shown in fig. 3, the traffic scheduling module may distribute a traffic forwarding task for each OCS and EPS (Electrical Packet Switch) of the core layer according to the traffic demand matrix, and in this process, a specific algorithm is usually used to decompose the total demand matrix to generate a demand matrix corresponding to each Switch.
Further, the circuit configuration module may configure the circuit connection inside the OCS according to the distributed traffic matrix, so as to provide a data channel for subsequent traffic forwarding. As shown in fig. 4, according to the traffic demand matrix, the forwarding direction of the traffic should be: host 1- > host 4, host 2- > host 3, host 3- > host 2, host 4- > host 1. Thus, the OCS internal circuit connections should be configured to: input port 1- > output port 4, input port 2- > output port 3, input port 3- > output port 2, input port 4- > output port 1 (where all links are unidirectional links).
S102, calculating to obtain loss flow according to the equipment information, wherein the loss flow is used for representing the flow forwarding requirement which cannot be met due to the OCS fault in the photoelectric hybrid switching network.
And S103, caching the first part of the loss traffic on the top of rack switch (TOR), and processing the first part of the loss traffic in the next configuration period of the optical-electric hybrid switching network.
It should be noted that, an Optical-electrical hybrid switching architecture (OCS) based on Micro-Electro-Mechanical Systems (MEMS) is generally used in a network, such a device has no sensing capability for data, and can only schedule the connection of an Optical Circuit according to a predetermined traffic scheduling mechanism, and once a device failure or a link failure occurs, the traffic scheduling cannot be adaptively adjusted due to a change in the network topology, traffic forwarding will be seriously affected, and the performance of the entire network is greatly reduced.
Based on the existing problems, as shown in fig. 5, when detecting that an OCS device fails, the present application may first obtain failure information of the device, and then calculate a loss traffic (i.e., optical domain failure loss) between hosts that cannot be processed due to the failure. Next, bandwidth resources (i.e., idle resources in the electrical domain) of each port that are still idle after the EPS completes its traffic forwarding task are calculated.
After the optical domain fault loss (corresponding to the loss traffic) and the idle resource information of the electrical domain are obtained, a part of the optical domain fault loss (corresponding to the first part of the loss traffic) is cached in the ToR, so that the unified processing of the traffic demand matrix of the next configuration period of the optical-electrical hybrid switching network is realized.
Further, because the buffer resources of the ToR are limited, the other part of the optical domain fault loss (i.e., the second part of the loss traffic) can be forwarded by using the idle resources of the electrical domain as much as possible, and if the idle resources of the electrical domain can completely compensate the second part of the loss traffic, the current traffic forwarding process is ended; if the electrical domain free resources are not sufficient to fully compensate for the second portion of the lost traffic, the remaining lost traffic can be discarded.
In the application, if the optical circuit switch is detected to have a fault, the equipment information of the OCS of the faulty optical circuit switch can be acquired; calculating loss flow according to the equipment information, wherein the loss flow is used for representing the flow forwarding requirement which cannot be met due to the OCS fault in the photoelectric hybrid switching network; buffering a first part of the loss traffic on the top of rack switch ToR, and processing the first part of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network. By applying the technical scheme of the application, when the equipment fault in the photoelectric hybrid switching network is detected, one part of the flow which cannot be forwarded due to the fault can be processed by the residual bandwidth resource of the EPS, and the other part of the flow can be cached on the top rack switch to be processed when the next configuration cycle of the photoelectric hybrid switching network is waited. Therefore, the purposes of improving the bandwidth utilization rate of the network and guaranteeing the performance of the fault network by using the originally idle bandwidth resources are achieved.
Optionally, in a possible implementation manner of the present application, before the caching the first part of the loss traffic on the top of rack switch ToR, the method further includes:
idle resource information of a packet switch, ESP, is computed and a second portion of the lost traffic is allocated for processing by the idle resources of the ESP.
Optionally, in a possible embodiment of the present application, the calculating idle resource information of the packet switch ESP includes:
acquiring port bandwidths of all EPS and configuration cycles of OCS under the photoelectric hybrid switching network;
calculating to obtain the maximum forwarding data volume of the EPS in the configuration period;
and calculating to obtain the original load flow of the port corresponding to the EPS, and obtaining the idle resource information of the ESP according to the difference value between the maximum forwarding data volume and the original load resource.
Optionally, in a possible embodiment of the present application, the allocating the second part of the lost traffic is processed by an idle resource of the ESP, and includes:
calculating a magnitude relationship between idle resource information of the EPS and a second portion of the lost traffic;
and if the idle resource information of the EPS is determined not to be larger than the second part of the lost flow, completely processing the lost flow by using the idle resource of the EPS.
And if the idle resource information of the EPS is determined to be smaller than the second part of the lost flow, processing the lost flow by using the idle resource information part of the EPS, and clearing the residual lost flow.
Optionally, in a possible implementation manner of the present application, the calculating the loss traffic according to the device information includes:
acquiring a flow sum demand matrix under the photoelectric hybrid switching network;
decomposing the flow sum demand matrix according to a scheduling algorithm to obtain a demand matrix corresponding to each OCS;
and obtaining a demand matrix corresponding to the fault OCS according to the equipment information of the fault OCS, and using the demand matrix as the loss flow.
Optionally, in a possible implementation manner of the present application, the traffic summation requirement matrix under the optical-electrical hybrid switching network is obtained according to the following formula:
Dz×z＝{dij}；
wherein i, j ∈ [1, z ]]Z is the number of switches under the optical-electrical hybrid switching network, and when i equals j, dij＝0。
Optionally, in a possible implementation manner of the present application, the processing the first part of the loss traffic at the next configuration period of the optical-electrical hybrid switching network includes:
calculating a first part of the loss traffic into a traffic demand matrix of a next configuration period of the photoelectric hybrid switching network;
and when detecting that the next configuration period of the photoelectric hybrid switching network comes, forwarding the traffic demand matrix containing the first part of the loss traffic.
Specifically, for calculating the loss traffic, the application may first obtain the total traffic demand matrix
Dz×z＝{dij}；
Wherein i, j ∈ [1, z ]]Z is the number of switches under the optical-electrical hybrid switching network, and when i equals j, dij＝0
After the total traffic demand matrix is obtained, the method can decompose the matrix into D according to a scheduling algorithm1、D2、...、DyAnd Dy+1Where y is the number of OCS in the optical-electrical hybrid switching network, where D1、D2、...、DyFor each OCS demand matrix, Dy+1Is the demand matrix of the EPS. Then, according to the ID of the faulty device, we can record the corresponding matrix as F, i.e. the optical domain fault loss, and the optical domain traffic matrix is going to:
Figure BDA0003269120080000111
further, for obtaining the idle resource information of the EPS through calculation, all the EPS may be abstracted into one according to the bandwidth parameter of the EPS, the bandwidth of each port is v, the configuration cycle of the OCS is denoted as T, and vT is the maximum data amount that the EPS can forward in one configuration cycle. And note that the link between ToR _ i and OCS _ j is Li，j，i∈[1，z]，j∈[1，y](ii) a Note that the failed link is Lm，nI.e. the link between ToR _ m and OCS _ n. For matrix Dy+1The mth row elements are summed to obtain the original load M of the corresponding port, and at this time, the idle resource information of the port of the EPS is vT-M.
Further, for the idle resource information forwarding loss flow using EPS, the application may note Qz×z＝Dy+1+F＝{qij}，i，j∈[1，z]If for
Figure BDA0003269120080000112
The electric domain flow matrix is oriented to Q → EPS; if the condition is not satisfied, that is, the optical domain fault loss is greater than the electrical domain idle resources, the optical domain loss without compensation is calculated and recorded as F' (i.e., the unrepeated part of the loss traffic).
It can be understood that, after obtaining F', the present application may buffer the part of the traffic in ToR and count it into the traffic demand matrix of the next configuration period of the optical-electrical hybrid switching network, so that the traffic is forwarded in the next configuration period.
Further, as shown in fig. 6, the present application is exemplified by a network topology in which there are four ToR switches (ToR _1, ToR _2, ToR _3, ToR _4), 3 OCS (OCS _1, OCS _2, OCS _3) and 1 EPS, and traffic scheduling follows the Edmonds algorithm. Wherein, the fault optical circuit switch OCD is OCS _ 3:
step 1, as shown in fig. 7, when the OCS device fails, a matrix D is known according to a traffic scheduling algorithm3 (1)The indicated traffic will not be forwarded and we will note the traffic affected by the failure as F(1)；D1 (1)、D2 (1)And D4 (1)The corresponding switch is normally assigned for processing.
Step 2, obtaining F(1)Then, it is first buffered as much as possible in the ToR, and this part of the traffic is denoted as F1 (1)。
And 3, because of the limitation of the cache size, part of the flow cannot be cached, and is marked as F2 (1)，F2 (1)The delivery will be directly to the EPS process. If there is residual traffic left unprocessed, the retransmission must be discarded.
Step 4, after the flow scheduling and the circuit configuration are finished, the exchanger carries out data transmission, F1 (1)It is put on hold waiting for the next configuration period to come.
More specifically, when an OCS device failure is detected, the present application may first obtain failure information of the device, and then calculate a loss traffic (i.e., optical domain failure loss) between hosts that cannot be processed due to the failure. Next, bandwidth resources (i.e., idle resources in the electrical domain) of each port that are still idle after the EPS completes its traffic forwarding task are calculated.
After the optical domain fault loss (corresponding to the loss traffic) and the idle resource information of the electrical domain are obtained, a part of the optical domain fault loss (corresponding to the first part of the loss traffic) is cached in the ToR, so that the unified processing of the traffic demand matrix of the next configuration period of the optical-electrical hybrid switching network is realized.
Further, because the buffer resources of the ToR are limited, the other part of the optical domain fault loss (i.e., the second part of the loss traffic) can be forwarded by using the idle resources of the electrical domain as much as possible, and if the idle resources of the electrical domain can completely compensate the second part of the loss traffic, the current traffic forwarding process is ended; if the electrical domain free resources are not sufficient to fully compensate for the second portion of the lost traffic, the remaining lost traffic can be discarded.
Optionally, in another embodiment of the present application, as shown in fig. 8, the present application further provides a fault handling apparatus for an optical-electrical hybrid switching network. The method includes an obtaining module 201, a calculating module 202, and a forwarding module 203, and is applied to a photoelectric hybrid switching network, including:
an obtaining module 201, configured to obtain, if it is detected that there is a failure of an optical circuit switch, device information of an OCS of the failed optical circuit switch;
a calculating module 202, configured to calculate, according to the device information, a loss traffic, where the loss traffic is used to characterize an unsatisfiable traffic forwarding requirement in the optical-electrical hybrid switching network due to the OCS failure;
a forwarding module 203 configured to buffer a first part of the loss traffic on a top of rack switch ToR, and process the first part of the loss traffic at a next configuration cycle of the optical electrical hybrid switching network.
By applying the technical scheme of the application, when the equipment fault in the photoelectric hybrid switching network is detected, one part of the flow which cannot be forwarded due to the fault can be processed by the residual bandwidth resource of the EPS, and the other part of the flow can be cached on the top rack switch to be processed when the next configuration cycle of the photoelectric hybrid switching network is waited. Therefore, the purposes of improving the bandwidth utilization rate of the network and guaranteeing the performance of the fault network by using the originally idle bandwidth resources are achieved.
In another embodiment of the present application, the obtaining module 201 further includes:
an acquisition module 201 configured to calculate idle resource information of a packet switch, ESP, and to allocate a second part of the lost traffic to be processed by the idle resources of the ESP.
In another embodiment of the present application, the obtaining module 201 further includes:
an obtaining module 201, configured to obtain port bandwidths of all EPS and configuration cycles of an OCS in the optical electrical hybrid switching network;
an obtaining module 201, configured to calculate a maximum forwarding data amount of the EPS in the configuration period;
the obtaining module 201 is configured to calculate an original load flow of a port corresponding to the EPS, and obtain idle resource information of the ESP according to a difference between the maximum forwarding data amount and an original load resource.
In another embodiment of the present application, the obtaining module 201 further includes:
an obtaining module 201 configured to calculate a size relationship between idle resource information of the EPS and a second portion of the lost traffic;
an obtaining module 201, configured to, if it is determined that the idle resource information of the EPS is not greater than the second part of the lost traffic, completely process the lost traffic by using the idle resource of the EPS.
An obtaining module 201, configured to, if it is determined that the idle resource information of the EPS is smaller than the second part of the lost traffic, process the lost traffic by using the idle resource information part of the EPS, and clear the remaining lost traffic.
In another embodiment of the present application, the obtaining module 201 further includes:
an obtaining module 201 configured to obtain a traffic sum requirement matrix under the optical-electrical hybrid switching network;
an obtaining module 201, configured to decompose the traffic sum demand matrix according to a scheduling algorithm to obtain a demand matrix corresponding to each OCS;
the obtaining module 201 is configured to obtain a demand matrix corresponding to the faulty OCS according to the device information of the faulty OCS, and use the demand matrix as the loss traffic.
In another embodiment of the present application, the obtaining module 201 further includes:
an obtaining module 201 configured to count a first part of the loss traffic into a traffic demand matrix of a next configuration period of the optical-electrical hybrid switching network;
an obtaining module 201, configured to forward a traffic demand matrix including a first part of the loss traffic when detecting that a next configuration period of the optical-electrical hybrid switching network arrives.
FIG. 9 is a block diagram illustrating a logical structure of an electronic device in accordance with an exemplary embodiment. For example, the electronic device 300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium, such as a memory, including instructions executable by an electronic device processor to perform a method of fault handling for an optical-electrical hybrid switching network, the method comprising: if the optical circuit switch is detected to have a fault, acquiring equipment information of an OCS (optical circuit switch) with the fault; calculating loss flow according to the equipment information, wherein the loss flow is used for representing the flow forwarding requirement which cannot be met in the photoelectric hybrid switching network due to the OCS fault; buffering a first portion of the loss traffic on a top of rack switch (TOR), and processing the first portion of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network. Optionally, the instructions may also be executable by a processor of the electronic device to perform other steps involved in the exemplary embodiments described above. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, there is also provided an application/computer program product including one or more instructions executable by a processor of an electronic device to perform the method for fault handling in an optical-electrical hybrid switching network described above, the method including: if the optical circuit switch is detected to have a fault, acquiring equipment information of an OCS (optical circuit switch) with the fault; calculating loss flow according to the equipment information, wherein the loss flow is used for representing the flow forwarding requirement which cannot be met in the photoelectric hybrid switching network due to the OCS fault; buffering a first portion of the loss traffic on a top of rack switch (TOR), and processing the first portion of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network. Optionally, the instructions may also be executable by a processor of the electronic device to perform other steps involved in the exemplary embodiments described above.
Fig. 9 is an exemplary diagram of the computer device 30. Those skilled in the art will appreciate that the schematic diagram 9 is merely an example of the computer device 30 and does not constitute a limitation of the computer device 30 and may include more or less components than those shown, or combine certain components, or different components, e.g., the computer device 30 may also include input output devices, network access devices, buses, etc.
The Processor 302 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor 302 may be any conventional processor or the like, the processor 302 being the control center for the computer device 30 and connecting the various parts of the overall computer device 30 using various interfaces and lines.
Memory 301 may be used to store computer readable instructions 303 and processor 302 may implement various functions of computer device 30 by executing or executing computer readable instructions or modules stored within memory 301 and by invoking data stored within memory 301. The memory 301 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to the use of the computer device 30, and the like. In addition, the Memory 301 may include a hard disk, a Memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Memory Card (Flash Card), at least one disk storage device, a Flash Memory device, a Read-Only Memory (ROM), a Random Access Memory (RAM), or other non-volatile/volatile storage devices.
The modules integrated by the computer device 30 may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by hardware related to computer readable instructions, which may be stored in a computer readable storage medium, and when the computer readable instructions are executed by a processor, the steps of the method embodiments may be implemented.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (10)

1. A fault processing method for an optical-electric hybrid switching network is characterized by being applied to the optical-electric hybrid switching network and comprising the following steps:
if the optical circuit switch is detected to have a fault, acquiring equipment information of an OCS (optical circuit switch) with the fault;
calculating loss flow according to the equipment information, wherein the loss flow is used for representing the flow forwarding requirement which cannot be met in the photoelectric hybrid switching network due to the OCS fault;
buffering a first portion of the loss traffic on a top of rack switch (TOR), and processing the first portion of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network.
2. The method of claim 1, wherein prior to said buffering the first portion of the lost traffic on the top of rack switch ToR, further comprising:
idle resource information of a packet switch, ESP, is computed and a second portion of the lost traffic is allocated for processing by the idle resources of the ESP.
3. The method of claim 2, wherein the calculating idle resource information for a packet switch, ESP, comprises:
acquiring port bandwidths of all EPS and configuration cycles of OCS under the photoelectric hybrid switching network;
calculating to obtain the maximum forwarding data volume of the EPS in the configuration period;
and calculating to obtain the original load flow of the port corresponding to the EPS, and obtaining the idle resource information of the ESP according to the difference value between the maximum forwarding data volume and the original load resource.
4. The method of claim 2, wherein said allocating the second portion of the lost traffic is handled by an idle resource of the ESP, comprising:
calculating a magnitude relationship between idle resource information of the EPS and a second portion of the lost traffic;
and if the idle resource information of the EPS is determined not to be larger than the second part of the lost flow, completely processing the lost flow by using the idle resource of the EPS.
And if the idle resource information of the EPS is determined to be smaller than the second part of the lost flow, processing the lost flow by using the idle resource information part of the EPS, and clearing the residual lost flow.
5. The method of claim 1, wherein calculating a loss flow based on the device information comprises:
acquiring a flow sum demand matrix under the photoelectric hybrid switching network;
decomposing the flow sum demand matrix according to a scheduling algorithm to obtain a demand matrix corresponding to each OCS;
and obtaining a demand matrix corresponding to the fault OCS according to the equipment information of the fault OCS, and using the demand matrix as the loss flow.
6. The method of claim 5, wherein the traffic summation requirement matrix under the opto-electric hybrid switching network is obtained according to the following formula:
Dz×z＝{dij}；
wherein i, j ∈ [1, z ]]Z is the number of switches under the optical-electrical hybrid switching network, and when i equals j, dij＝0。
7. The method of claim 1, wherein the processing the first portion of the lost traffic at a next configuration cycle of the optoelectronic hybrid switching network comprises:
calculating a first part of the loss traffic into a traffic demand matrix of a next configuration period of the photoelectric hybrid switching network;
and when detecting that the next configuration period of the photoelectric hybrid switching network comes, forwarding the traffic demand matrix containing the first part of the loss traffic.
8. A fault processing device of an optical-electric hybrid switching network is applied to the optical-electric hybrid switching network and comprises:
the optical circuit switch OCS comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is configured to acquire equipment information of an OCS if the optical circuit switch is detected to have a fault;
a calculation module configured to calculate a loss traffic according to the device information, where the loss traffic is used to characterize an unsatisfiable traffic forwarding requirement in the optical-electrical hybrid switching network due to the OCS failure;
a forwarding module configured to buffer a first portion of the loss traffic on a top of rack switch (TOR) and process the first portion of the loss traffic at a next configuration cycle of the optical-electrical hybrid switching network.
9. An electronic device, comprising:
a memory for storing executable instructions; and the number of the first and second groups,
a processor for displaying with the memory to execute the executable instructions to complete the operations of the fault handling method of the optoelectronic hybrid switching network of any one of claims 1-7.
10. A computer-readable storage medium storing computer-readable instructions, wherein the instructions, when executed, perform the operations of the method for handling faults in an optical-electrical hybrid switching network according to any one of claims 1 to 7.
CN202111102983.6A 2021-09-18 2021-09-18 Fault processing method and device for photoelectric hybrid switching network and electronic equipment Active CN113839887B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111102983.6A CN113839887B (en) 2021-09-18 2021-09-18 Fault processing method and device for photoelectric hybrid switching network and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111102983.6A CN113839887B (en) 2021-09-18 2021-09-18 Fault processing method and device for photoelectric hybrid switching network and electronic equipment

Publications (2)

Publication Number Publication Date
CN113839887A true CN113839887A (en) 2021-12-24
CN113839887B CN113839887B (en) 2023-04-18

Family

ID=78960087

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111102983.6A Active CN113839887B (en) 2021-09-18 2021-09-18 Fault processing method and device for photoelectric hybrid switching network and electronic equipment

Country Status (1)

Country Link
CN (1) CN113839887B (en)

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020030864A1 (en) * 2000-01-28 2002-03-14 Sid Chaudhuri Control of optical connections in an optical network
CN101674500A (en) * 2009-07-22 2010-03-17 电子科技大学 Transmission method of mixed light exchanging network
CN102907057A (en) * 2010-05-20 2013-01-30 惠普发展公司，有限责任合伙企业 Switching in a network device
CN103543375A (en) * 2013-08-26 2014-01-29 上海交通大学 Method for detecting alternating-current fault arcs on basis of wavelet transformation and time-domain hybrid features
US20140086044A1 (en) * 2012-09-27 2014-03-27 International Business Machines Corporation Fencing off switch domains
US20150098678A1 (en) * 2013-10-04 2015-04-09 Calient Technologies, Inc. Compound optical circuit switch
US20150327000A1 (en) * 2014-05-07 2015-11-12 Sk Planet Co., Ltd. Apparatus, method and system for local wireless data communication of hybrid form
US9391843B1 (en) * 2012-12-31 2016-07-12 Juniper Networks, Inc. Pre-computing effects of modifying components in a data center switch
CN106789738A (en) * 2017-01-03 2017-05-31 北京航空航天大学 A kind of spaceborne CICQ fabric switch single multicast mixed service packet scheduling algorithm under GEO channel circumstances
CN107371269A (en) * 2016-05-13 2017-11-21 展讯通信（上海）有限公司 Method, user equipment and the base station of transmitting and scheduling
CN107682263A (en) * 2017-09-22 2018-02-09 西安空间无线电技术研究所 A kind of dispatching method based on the business duration in hybrid switching network
CN109302350A (en) * 2017-07-25 2019-02-01 中国人民解放军国防科学技术大学 One kind being based on photoelectricity multicast hybrid network frame structure and its dispatching method
CN110113271A (en) * 2019-04-04 2019-08-09 中国科学院计算技术研究所 A kind of MPI application acceleration system and method based on photoelectricity hybrid switching network
CN110166372A (en) * 2019-05-27 2019-08-23 中国科学技术大学 The method of on-line scheduling coflow in the data center based on photoelectricity path switching mechanism
CN111372148A (en) * 2020-04-13 2020-07-03 长春光客科技有限公司 Indoor overhead optical router network wireless optical communication device and method

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020030864A1 (en) * 2000-01-28 2002-03-14 Sid Chaudhuri Control of optical connections in an optical network
CN101674500A (en) * 2009-07-22 2010-03-17 电子科技大学 Transmission method of mixed light exchanging network
CN102907057A (en) * 2010-05-20 2013-01-30 惠普发展公司，有限责任合伙企业 Switching in a network device
US20140086044A1 (en) * 2012-09-27 2014-03-27 International Business Machines Corporation Fencing off switch domains
US9391843B1 (en) * 2012-12-31 2016-07-12 Juniper Networks, Inc. Pre-computing effects of modifying components in a data center switch
CN103543375A (en) * 2013-08-26 2014-01-29 上海交通大学 Method for detecting alternating-current fault arcs on basis of wavelet transformation and time-domain hybrid features
US20150098678A1 (en) * 2013-10-04 2015-04-09 Calient Technologies, Inc. Compound optical circuit switch
US20150327000A1 (en) * 2014-05-07 2015-11-12 Sk Planet Co., Ltd. Apparatus, method and system for local wireless data communication of hybrid form
CN107371269A (en) * 2016-05-13 2017-11-21 展讯通信（上海）有限公司 Method, user equipment and the base station of transmitting and scheduling
CN106789738A (en) * 2017-01-03 2017-05-31 北京航空航天大学 A kind of spaceborne CICQ fabric switch single multicast mixed service packet scheduling algorithm under GEO channel circumstances
CN109302350A (en) * 2017-07-25 2019-02-01 中国人民解放军国防科学技术大学 One kind being based on photoelectricity multicast hybrid network frame structure and its dispatching method
CN107682263A (en) * 2017-09-22 2018-02-09 西安空间无线电技术研究所 A kind of dispatching method based on the business duration in hybrid switching network
CN110113271A (en) * 2019-04-04 2019-08-09 中国科学院计算技术研究所 A kind of MPI application acceleration system and method based on photoelectricity hybrid switching network
CN110166372A (en) * 2019-05-27 2019-08-23 中国科学技术大学 The method of on-line scheduling coflow in the data center based on photoelectricity path switching mechanism
CN111372148A (en) * 2020-04-13 2020-07-03 长春光客科技有限公司 Indoor overhead optical router network wireless optical communication device and method

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
余晓杉;王琨;顾华玺;王曦;: "云计算数据中心光互连网络:研究现状与趋势" *
刘英挺 , 朱睿杰 , 杜晓明, 赵永利: "全光网中采用可信度模型的故障定位技术" *
刘英挺，朱睿杰，杜晓明，赵永利: "全光网中采用可信度模型的故障定位技术", 《西安电子科技大学学报》 *
彭甜甜等: "推进绿色节能 新一代光网络体系架构瞄准五大方向", 《通信世界》 *
陈麒等: "自动交换光网络在军用网络中的应用", 《中国新通信》 *
魏威,曾庆济,黄俊,刘继民,肖鹏程: "下一代光因特网体系结构的选择与比较" *

Also Published As

Publication number Publication date
CN113839887B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
US11736402B2 (en) Fast data center congestion response based on QoS of VL
US8806025B2 (en) Systems and methods for input/output virtualization
US10129182B2 (en) Methods and apparatus for providing services in distributed switch
US20160335209A1 (en) High-speed data transmission using pcie protocol
CN110313163A (en) Load balance in distributed computing system
EP2456138A1 (en) Methods and apparatus for centralized virtual switch fabric control
US10097481B2 (en) Methods and apparatus for providing services in distributed switch
US10616141B2 (en) Large scale fabric attached architecture
CN102571554A (en) Methods and apparatus for forwarding-state transport in a distributed control plane
US9596137B1 (en) Methods and apparatus for configuration binding in a distributed switch
EP2466822A1 (en) Methods and apparatus for managing next hop identifiers in a distributed switch fabric system
CN110661690A (en) Techniques for hairpin transport network traffic
CN107786669A (en) A kind of method of load balance process, server, device and storage medium
CN113839886B (en) Fault processing method and device for photoelectric hybrid switching network, electronic equipment and medium
US20150301571A1 (en) Methods and apparatus for dynamic mapping of power outlets
US10033666B2 (en) Techniques for virtual Ethernet switching of a multi-node fabric
CN107168903A (en) A kind of non-volatile memory medium
US10088643B1 (en) Multidimensional torus shuffle box
CN113839887B (en) Fault processing method and device for photoelectric hybrid switching network and electronic equipment
CN105814852A (en) Transmission and reception devices for reducing the delay in end-to-end delivery of network packets
CN116915708A (en) Method for routing data packets, processor and readable storage medium
CN110943939B (en) Network card unit, distributed network switch system and networking method
CN108494700A (en) Across link data transmission method, device, computer equipment and storage medium
US9094740B2 (en) Architecture to scale an IP/MPLS network via multiple network planes
CN110417573A (en) A kind of method and system of data transmission

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