CN112073253B - Service performance processing method and system - Google Patents
Service performance processing method and system Download PDFInfo
- Publication number
- CN112073253B CN112073253B CN201910497363.3A CN201910497363A CN112073253B CN 112073253 B CN112073253 B CN 112073253B CN 201910497363 A CN201910497363 A CN 201910497363A CN 112073253 B CN112073253 B CN 112073253B
- Authority
- CN
- China
- Prior art keywords
- service performance
- service
- message
- level
- query
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/06—Generation of reports
- H04L43/067—Generation of reports using time frame reporting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/02—Standardisation; Integration
- H04L41/0246—Exchanging or transporting network management information using the Internet; Embedding network management web servers in network elements; Web-services-based protocols
- H04L41/0266—Exchanging or transporting network management information using the Internet; Embedding network management web servers in network elements; Web-services-based protocols using meta-data, objects or commands for formatting management information, e.g. using eXtensible markup language [XML]
Abstract
The invention discloses a method and a system for processing service performance, and relates to the technical field of communication. The service performance processing method comprises the following steps: in the network equipment, a main control panel generates a query message according to a received query command of the service performance and sends the query message to a corresponding service single panel; the service single disc acquires service performance data according to the query message, and returns a response message carrying the service performance data when the service performance data is not 0; otherwise, returning an empty response message; and the master control disk summarizes and uploads the returned service performance data. The invention can reduce the calculation amount and the calculation time of the master control panel and the network manager.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and a system for processing service performance.
Background
Currently, various distributed communication transmission devices need to check the performance of a service object, called service performance, through a Network management or a device Command Line (CLI), for example, a Label Switching Path (LSP), a Pseudo Wire (PW), a Virtual Container (VC), a three-Layer Virtual Private Network (L3 VPN), and the like, and check the traffic curve statistical data of a certain two-Layer (Layer 2, L2) and three-Layer (Layer3, L3) services through a traffic tool.
In the distributed network equipment, a service passes through a plurality of service single disks, all the service single disks register the line number of the service object, and the service performance of the service object is counted. According to the current distributed network architecture, when a network manager and a flow tool carry out service performance statistics, the service performance of all service disks in network equipment is inquired, and then accumulated calculation is carried out, so that a large amount of service performance data is transmitted and processed among the service disks, a master control and the network manager, and as the service performance is completely reported to the network manager for data statistics and summarization, under the condition of more network equipment and large service volume, the data calculation amount is extremely large, and the condition that the use rate of a Central Processing Unit (CPU) is too high to cause the incapability of calculation often occurs.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a service performance processing method and a service performance processing system, which can reduce the calculation amount and the calculation time of a master control panel and a network manager.
The invention provides a method for processing service performance, which comprises the following steps:
in the network equipment, a main control panel generates a query message according to a received query command of the service performance and sends the query message to a corresponding service single panel;
the service single disc acquires service performance data according to the query message, and returns a response message carrying the service performance data when the service performance data is not 0; otherwise, returning an empty response message;
and the master control disk summarizes and uploads the returned service performance data.
On the basis of the technical scheme, the service performance data is a second-level service performance value or a service performance value with a preset time length, wherein the preset time length is equal to or more than 1 minute;
the master control panel collects the second-level service performance values returned by more than two service single panels according to the second-level time, wherein at each second-level time for collection, all the service single panels have the second-level service performance values;
and the master control panel counts and summarizes the service performance value of the preset time.
On the basis of the technical scheme, the query command comprises a positioning source character string used for representing the service performance and the service object to which the service performance belongs;
a first mapping table pre-configured by a master control panel comprises a corresponding relation between a positioning source character string and a keyword, wherein the keyword comprises an identifier ID and parameter information of a service object;
the main control panel converts the keywords into a data structure according to a second mapping table configured in advance, and determines the association relationship between the query message and the response message according to the comparison result of the data structure.
On the basis of the above technical solution, after the master control disk generates the query message according to the received query command of the service performance, the method further includes:
and the master control disk establishes a cache linked list for storing the service performance data based on the query command and the query message, and deletes the corresponding node in the cache linked list when receiving the empty response message.
On the basis of the above technical solution, before the master control disk generates the query message according to the received query command of the service performance, the method further includes:
the master control disk generates a collection message according to the received collection command of the service performance and sends the collection message to a corresponding service single disk;
the service single disc starts to acquire a service performance value according to the acquired message;
the service performance data is obtained based on a service performance value obtained between the acquisition message and the query message.
On the basis of the technical scheme, the method further comprises the following steps:
and the service single disk restarts to acquire the service performance value according to the query command, acquires new service performance data based on the service performance value acquired between the query message and the new query message when receiving the new query message transmitted by the master control disk, and returns a new response message.
The invention also provides a processing system of the service performance, which is arranged in the network equipment comprising a master control panel and a plurality of service single panels, wherein the system comprises a summarizing module, a first message processing module and a storage module in the master control panel, and an acquisition module and a second message processing module which are arranged in each service single panel;
the first message processing module is used for generating a query message according to the received query command of the service performance and sending the query message to the second message processing module; the second message processing module is also used for receiving a response message returned by the second message processing module and extracting service performance data carried by the response message; uploading the result summarized by the summarizing module;
the summarizing module is used for summarizing the service performance data;
the storage module is used for storing the service performance data and the result summarized by the summarizing module;
the second message processing module is used for analyzing the query message and then sending the analyzed query message to the acquisition module; the first message processing module is further configured to generate the response message according to the service performance data obtained by the obtaining module, and return the response message to the first message processing module, where the response message carries service performance data that is not 0 or is a null message;
the acquisition module is used for acquiring service performance data according to the analysis result of the query message and sending the service performance data to the second message processing module.
On the basis of the technical scheme, the service performance data is a second-level service performance value or a service performance value with a preset time length, wherein the preset time length is equal to or more than 1 minute;
the summarizing module is used for summarizing the second-level service performance values returned by more than two acquiring modules according to the second-level time, wherein at each second-level time for summarizing, all the acquiring modules have the second-level service performance values; and the method is also used for counting and summarizing the service performance value of the preset time.
On the basis of the technical scheme, the first message processing module is further configured to generate a collection message according to the received collection command of the service performance, and send the collection message to the second message processing module;
the second message processing module is also used for analyzing the collected message and then sending the analyzed message to the acquisition module;
the acquisition module is further configured to start to acquire a service performance value based on the analysis result of the acquisition packet, and obtain the service performance data according to the service performance value acquired between the acquisition packet and the query packet.
On the basis of the technical scheme, the summarizing module is further used for restarting to acquire the service performance value according to the analysis result of the query command; obtaining new service performance data based on the service performance value obtained between the query message and the new query message;
the second message processing module is also used for analyzing the new query message sent by the first message processing module and then sending the new query message to the acquisition module; and returning a new response message according to the new service performance data.
Compared with the prior art, the method for processing the service performance of the embodiment of the invention comprises the following steps: in the network equipment, a main control panel generates a query message according to a received query command of the service performance and sends the query message to a corresponding service single panel; the service single disc acquires service performance data according to the query message, and returns a response message carrying the service performance data when the service performance data is not 0; otherwise, returning an empty response message; the master control panel summarizes and uploads the returned service performance data, so that the calculation amount and the calculation time of the master control panel and the network manager are reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for processing service performance according to an embodiment of the present invention;
FIG. 2A is a schematic diagram of a summary of class-second service performance values for normal situations;
FIG. 2B is a schematic diagram of a summary of class-two service performance values under abnormal conditions;
FIG. 3A is a schematic diagram of a single disk cache linked list;
fig. 3B is a schematic diagram of a network management cache linked list;
fig. 4 is a flowchart of step S160;
FIG. 5 is a schematic diagram of a processing system for service performance according to an embodiment of the present invention;
fig. 6 is an application diagram of a service performance processing system according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and the embodiments.
Referring to fig. 1, an embodiment of the present invention provides a method for processing service performance, which is applied to a network device, where the network device includes a master control disk and a plurality of service disks, and the method for processing service performance includes:
s110, the master control disk generates a query message according to the received query command of the service performance and sends the query message to the corresponding service single disk.
Specifically, the master control disk may receive the query Command of the service performance from the network manager, and may also receive the query Command of the service performance through a Command-Line Interface (CLI), which is not limited.
The service object includes one or more service capabilities, for example, a pseudo wire (pseudo wire) includes service capabilities such as a number of received packets (RX _ packets), a number of transmitted packets (TX _ packets), a number of BYTES of transmitted packets (TX _ BYTES), and a number of BYTES of received packets (RX _ BYTES).
The query mode of the network manager or the CLI comprises the following steps:
1) enquiry by single disc
The query command can specify all service performance of one service single disk, and the master control disk sends the query message to the service single disk.
2) Query by business object
The query command may specify to query the service performance of the plurality of service disks, the master control disk sends the query message to the plurality of service disks, and the query command may specify to query one or more service performance in one service object, without limitation.
And S120, the service single disk acquires service performance data according to the query message.
S130, judging whether the service performance data is 0, if not, entering the step S140; otherwise, the process proceeds to step S150.
S140 returns a response packet carrying the service performance data, and then the process goes to step S160.
S150 returns an empty response message, and the process proceeds to step S160.
And S160, the master control panel summarizes and uploads the returned service performance data.
For a distributed network device, all service disks have keywords of a service object (see the description of the following embodiments), and statistics on service performance of the service object may be performed, but for a single disk hardware drive, only an egress disk and an ingress disk of the service may collect performance data and send the performance data to a single disk Management Unit Library (BMU _ LIB), and other service disks on the network device cannot collect the service performance data from the hardware drive, for example: a PW service, which is created on all service disks, slot 1 is an egress disk, and slot 2 is an ingress disk, so that only the hardware drivers above slot 1 and slot 2 can acquire the performance value, i.e. the packet transceiving count, and the packet transceiving performance values of PW above other slots, e.g. slot 3, slot 4, slot 5 and slot 6, are all 0 values. Therefore, in the BMU _ LIB of these service profiles, the service performance value of the service object is 0 value.
If all the service single disks respond, the reported invalid service performance data not only occupies the resources of the service single disks, but also causes a large amount of invalid service performance data to be transmitted and processed among the service single disks, the master control and the network manager, and the master control disk needs to analyze and calculate the response messages of all the service single disks, so that the calculation amount and the calculation time of the master control disk are inevitably greatly increased, especially under the condition that a large number of service single disks exist in network equipment.
In addition, for a complex scenario of a Link Aggregation Group (LAG) port, Link Aggregation refers to bundling a plurality of physical ports together to form one logical port, so as to realize load sharing of ingress/egress traffic among each member port. LAG has a plurality of egress disks and ingress disks, and if the switch performs complicated iterative calculations to obtain the egress disks and the ingress disks, and then the master disk queries only the ingress disks and the egress disks, a large amount of computation and computation time are required.
In the embodiment of the invention, on one hand, the master control disk queries all the service single disks of the service when querying the service performance, and because the master control disk does not need to perform iterative computation of the service ingress disk and the service egress disk, the computation amount and the computation time of the master control disk are reduced, and the computation amount and the computation time of the network management are correspondingly reduced.
On the other hand, when the master control disk queries the PW service performance, it sends query messages to all of the slots 1 to 6, and since the service single disk does not reply to the service performance value of 0, the master control disk only needs to parse the response messages carrying the service performance data returned by the service single disks of the slots 1 and 2, and does not need to parse the empty response messages, and then performs calculation, thereby further reducing the calculation amount and the calculation time of the master control disk. Meanwhile, the network manager can inquire the service performance according to the service object without data statistics and accumulation, the performance data of the performance file is greatly reduced, the data volume is greatly reduced in processing efficiency compared with the prior method, the calculation is simple, and the warehouse entry inquiry efficiency is high, so that the calculation amount and the calculation time of the network manager are reduced.
The performance of the network device may be divided into basic performance and service performance, and on the basis of the embodiment of the present invention, the basic performance may also be queried by a method in the prior art, which is not described in detail.
In an alternative embodiment, the service performance data is a service performance value of a second level or a predetermined time length, wherein the predetermined time length is equal to or longer than 1 minute.
Specifically, the second-level service performance value, that is, a service profile counts one service performance value every 1 second, and the second-level service performance value only generates two service performance values, namely, a packet receiving rate (RX _ PPS) and a packet sending rate (TX _ PPS). Generally speaking, the network manager collects data once every 10 to 15 seconds, the network device responds to the network manager with data of each sampling point of the packet receiving rate (RX _ PPS) and the packet sending rate (TX _ PPS) in the two collection intervals, and the network manager performs drawing according to the data of the sampling point.
Specifically, the predetermined time period is determined according to actual needs, for example, the service performance value of the predetermined time period may be a service performance value of 15 minutes, that is, the service performance value is counted every 15 minutes by the service unit.
In order to further reduce the calculation amount and the calculation time of the master control panel and the network management, the master control panel summarizes the second-level service performance values returned by more than two service panels according to the second-level time, wherein at each second-level time for summarizing, all the service panels have the second-level service performance values.
As an example, fig. 2A and 2B show a schematic diagram of a summary of second-level service performance values for the same service object, where "V" represents a second-level service performance value and "D" represents a time point, expressed in hour: minute: second. Here, in order to make the explanation easy and clear, the second-class service performance values are unified into a shape, the second-class time points ignore the year, month and day portions, and the same second-class time points are aligned in the vertical direction.
Fig. 2A is a schematic diagram showing a summary of the second-level service performance values under normal conditions, where the master control is respectively 11: 10: 12 and 11: 10: disc 1, disc 2 and disc 3 are sent 18 a query message. Under normal conditions, the master receives the service performance values of class two for the egress disk (disk 1) and the ingress disk (disk 3), including from 11: 10: 13 to 11: 10: the time point interval is 1 second, and the second-level service performance values of 6 time points are total. The disk 2 is a pass-through single disk, and since data cannot be acquired, the principle that a value 0 is not reported is followed, and the second-level service performance value of the disk 2 received by the master control disk is null.
And the master control disk sequentially accumulates and summarizes the second-level service performance values according to the second-level time to obtain a summarized result and replies to the network management.
Fig. 2B is a schematic diagram of summarizing the second-level service performance values under the abnormal condition, because the time of each service menu is asynchronous and the communication between the menus is abnormal, the second-level time points replied by the service menus are not completely the same, and the master control panel performs processing according to the following steps when summarizing, where the summarizing steps are as follows:
(1) and determining the service single disk which returns the response message carrying the service performance data.
In fig. 2B, the response messages of the three service disks carry data disks, and the three service disks must have data at the same second-level time point for aggregation. For example, disks 1-11: 10: 13, 11: 10: 18, disks 2-11: 10: 12, 11: 10: 13, disks 3-11: 10: 18, 11: 10: 19.
(2) and accumulating and calculating the same service object and the same service performance and having the second-level service performance value at the second-level moment.
(3) In the response message of the reply network manager, only the summary result of four second-level time points is returned, which includes 11: 10: 14-11: 10: 17.
when the network manager draws a second-level service performance value curve, the skip point data (11: 10: 12, 11: 10: 13) are subjected to smooth connection processing, so that a user cannot perceive the skip point value.
The master control panel summarizes the second-level service performance values returned by more than two service single panels according to specific services, and the summarizing may be cumulative calculation (as shown in fig. 2A and 2B), or may be a maximum value, and the like, without limitation.
In order to further reduce the calculation amount and the calculation time of the master control panel and the network manager, the master control panel performs statistics and summarization on the service performance value of a preset time duration.
Specifically, under the condition of the same service object and the same service performance, the statistical summary may include:
(1) the maximum value is the maximum value of the maximum values of all the service performance values;
(2) the minimum value is the minimum value in the minimum values of all the service performance values;
(3) the current value is the accumulated value in the current values of all the service performance values;
(4) the service performance value time is the minimum time for reporting the service performance value.
For Link Aggregation Group (LAG) port scenarios, the statistical summary includes:
in the LAG scenario, M (M > ═ 1) number of egress disks and N (N > ═ 1) number of ingress disks are provided, and for the master control disk, more than K (K > ═ 2) number of service single disks reply non-0 value performance data. The main control panel can still process and summarize the LAG port service performance according to the flow.
In an alternative embodiment, the query command includes a location source string that represents the business capability and the business object to which it belongs.
The first mapping table pre-configured by the master control panel comprises the corresponding relation between the positioning source character string and the keyword, and the keyword comprises the identifier ID and the parameter information of the service object.
The main control panel converts the keywords into a data structure according to a second mapping table configured in advance, and determines the association relationship between the query message and the response message according to the comparison result of the data structure.
In order to further reduce the calculation amount and the calculation time of the master control disk and the network manager, the master control disk translates the positioning source character string into a keyword comprising an Identifier (ID) of a service object and parameter information according to a first mapping table configured in advance; and converting the key word into a data structure according to a second mapping table configured in advance.
Further, the query message and the response message carrying the service performance data both include keywords and performance codes for indicating the service performance.
For example, the query command carries a location source string of a service object, for example, a pseudo wire name pw1, the master control disk converts the location source string into a KEY (KEY) according to a first mapping table configured in advance, and only once converts the location source string when issuing a query message, for example, the KEY is a 10-byte character TYPE (char) array having a value of 0x 000 x 000 x 010 x 000 x 100 x 100 x 100 x10, the KEY is structured as VC _ ID [4] + VC _ TYPE [2] + PEER _ IP [4], the structural members are long-integer TYPE VC _ ID, short-integer TYPE VC _ TYPE and long-integer TYPE PEER _ IP, where VC _ ID [4] represents VC _ ID of a virtual container, 4 bytes, TYPE of a virtual container [2] byte, opposite end [4] PEER [ IP ] represents Internet Protocol (Internet Protocol) address IP, 4 bytes.
When the master control panel collects, the key words and the performance codes of the service performance are used as collecting key words to collect all the service performance data.
For example, if both disk 1 and disk 2 have the key, and then look at the service performance value under the service object, and both disk 1 and disk 2 have the number of received packets (RX _ PACKS), the number of transmitted packets (TX _ PACKS), the number of transmitted packets BYTES (TX _ BYTES), and the number of received packets BYTES (RX _ BYTES), then the service performance value of RX _ PACKS on disk 1 and the service performance value of RX _ PACKS on disk 2 are accumulated, so that the aggregate of other service performance data is similarly performed for the aggregate RX _ PACKS service performance value of the PW service object.
Specifically, the response message returned by the service single disk includes a message protocol header, a data length, a keyword KEY, a performance code, and a service performance value. If all the message contents need to be analyzed according to the complete analysis rule, and the keyword KEY replied by each service single disk is compared with the performance codes one by one, the keyword KEY is composed of character CHAR arrays with different lengths of 4-50, under the condition of full allocation, such as '255 frames with full allocation', the method is equivalent to complete analysis of 255 messages, and the calculated amount and the calculating time are still very large.
In the embodiment of the invention, when the master control panel processes the response message, the keyword is converted into the structural body according to the second mapping table which is configured in advance, so that the keyword comparison is directly carried out one by one according to the structural body members.
The embodiment of the invention sinks the translation operation of the positioning source character string to the master control disk of the network equipment, the master control disk finishes the translation operation of the positioning source character string, and the network manager does not need to process the translation of the positioning source character strings of all the network equipment in the whole network in a centralized way, thereby reducing the pressure of the network manager.
In an optional implementation manner, after the master control disk generates the query packet according to the received query command of the service performance, the method for processing the service performance further includes:
the main control disk establishes a cache linked list for storing service performance data based on the query command and the query message, and deletes corresponding nodes in the cache linked list when receiving an empty response message. And when receiving a response message carrying the service performance data, storing the service performance data into the corresponding node in the cache linked list.
Further, the cache linked list includes a single-disk cache linked list and a network management cache linked list, where the single-disk cache linked list is used to record all query messages issued to each service single disk, and the network management cache linked list is used to record each query command and corresponding service single disk.
Fig. 3A is a diagram of a single-disk cache chain showing query commands 1, 2. Fig. 3B is a schematic diagram of a webmaster cache chain table, for example, the webmaster cache chain table includes query commands 1, 2, and a query packet generated according to the query command 1 is sent to corresponding service disks 1, 2, the.
Referring to fig. 4, step S160 includes:
s1601, the master control disk receives a message sent by the service single disk.
S1602, judging whether the message is a response message of the query message, if so, entering the step S1603; if not, ending.
S1603 parses the response packet and looks up the query packet in the single-disk cache linked list.
S1604, judging whether the query message is found, if so, entering the step S1605; if not, the process proceeds to step S1612.
S1605, the found inquiry message is cleared in the single disk cache linked list.
S1606 searches the service single disk in the network management cache linked list.
S1607, judging whether the service single disk is found, if yes, entering the step S1608; if not, the process proceeds to step S1612.
S1608 buffers the service performance data in the network management buffer linked list.
S1609 is polled by a timer.
S1610 judges whether all the service single disks receiving the query message in the network management cache linked list are responded, if yes, the step S1611 is executed; if not, the process returns to step S1609.
And S1611, aggregating and uploading, and ending.
S1612 discards the service performance data.
In the embodiment of the invention, the main control panel monitors the response message through the single-panel cache linked list and the network management cache linked list, and ensures that an accurate service performance data summarizing result is obtained.
In an optional implementation manner, in step S110, the master control disk generates a query message according to a received query command of the service performance, where the query command specifies a specified service performance and a sampling duration thereof, for example, the query command specifies a second-level service performance value of the number of received packets (RX _ packets) of the pseudo wire within 10 seconds.
Step S120, the service single disk acquires service performance data according to the query message, wherein the service performance data is a second-level service performance value of the number of received pseudo wires (RX _ PACKS) acquired within 10 seconds from the time of receiving the query message.
In an optional implementation manner, in step S110, the master control disk generates a query message according to the received query command of the service performance.
Step S120, the service single disk acquires service performance data according to the query packet, where the service performance data is a service performance value acquired in a predetermined period, that is, a second-level service performance value or a service performance value of a predetermined duration, where the predetermined period is included in configuration information received in advance by the service single disk.
In an optional implementation manner, the method for processing the service performance includes:
s210, the master control disk generates a collection message according to the received collection command of the service performance and sends the collection message to the corresponding service single disk.
And S220, the service single disk starts to acquire the service performance value according to the acquired message.
And S230, the master control disk generates a query message according to the received query command of the service performance and sends the query message to the corresponding service single disk.
S240, the service single disk obtains service performance data based on the service performance value obtained between the collected message and the query message.
S250, judging whether the service performance data is 0, if not, entering the step S260; otherwise, the process proceeds to step S270.
S260 returns a response packet carrying the service performance data, and then the process goes to step S280.
S270 returns an empty response message, and the process proceeds to step S280.
And S280, the master control disk summarizes and uploads the returned service performance data.
In an optional implementation manner, the service single disk restarts to acquire the service performance value according to the query command, and when a new query message sent by the master control disk is received, new service performance data is obtained based on the service performance value acquired between the query message and the new query message, and a new response message is returned.
The service performance processing method comprises the following steps:
s310, the master control disk generates a query message according to the received query command of the service performance and sends the query message to the corresponding service single disk.
S320, the service single disk acquires the service performance data according to the query message, and restarts acquiring the service performance value according to the query command, and then steps S330 and S370 are performed, respectively.
S330, judging whether the service performance data is 0, if not, entering the step S340; otherwise, the process proceeds to step S350.
S340 returns a response packet carrying the service performance data, and then step S360 is performed.
S350 returns an empty response message, and then the process proceeds to step S360.
And S360, the master control panel summarizes and uploads the returned service performance data.
S370, the master control disk generates a new query message according to the received new query command and sends the new query message to the corresponding service single disk.
S380, the service single disk obtains new service performance data based on the service performance value obtained between the query message and the new query message, and returns a new response message;
and S390, the master control disk remits and uploads the new service performance data.
On the basis of the embodiment of the invention, the master control panel can also receive the query command at intervals, and can collect and upload the service performance data obtained based on the service performance value obtained between two adjacent query messages, the interval duration of the two adjacent query messages can be the same or different, and when the interval duration of the two adjacent query messages is the same, the service performance data can be collected and uploaded periodically.
Referring to fig. 5, an embodiment of the present invention provides a service performance processing system, which is disposed in a network device including a master control disk and a plurality of service disks, and is configured to implement the method in the foregoing embodiment.
The service performance processing system comprises a summarizing module, a first message processing module and a storage module in a master control panel, and an acquisition module and a second message processing module which are arranged in each service single panel.
The first message processing module is used for generating a query message according to the received query command of the service performance and sending the query message to the second message processing module; the second message processing module is also used for receiving a response message returned by the second message processing module and extracting service performance data carried by the response message; and uploading the result summarized by the summarizing module.
And the summarizing module is used for summarizing the service performance data.
The storage module is used for storing the service performance data and the result summarized by the summarizing module.
The second message processing module is used for analyzing the query message and then sending the query message to the acquisition module; and the first message processing module is also used for generating a response message according to the service performance data obtained by the obtaining module and returning the response message to the first message processing module, wherein the response message carries service performance data which is not 0 or is an empty message.
The acquisition module is used for acquiring the service performance data according to the analysis result of the query message and sending the service performance data to the second message processing module.
In an alternative embodiment, the service performance data is a service performance value of a second level or a predetermined time length, wherein the predetermined time length is equal to or longer than 1 minute.
The summarizing module is used for summarizing the second-level service performance values returned by the more than two acquiring modules according to the second-level time, wherein at each second-level time for summarizing, all the acquiring modules have the second-level service performance values; and the method is also used for counting and summarizing the service performance value of the preset time.
In an optional implementation manner, the first message processing module is further configured to generate a collection message according to the received collection command of the service performance, and send the collection message to the second message processing module.
The second message processing module is also used for analyzing the collected message and then sending the analyzed message to the acquisition module;
the acquisition module is also used for starting to acquire the service performance value based on the analysis result of the acquired message and acquiring the service performance data according to the service performance value acquired between the acquired message and the query message.
In an optional implementation manner, the summarizing module is further configured to restart to acquire the service performance value according to the analysis result of the query command; and obtaining new service performance data based on the service performance value obtained between the query message and the new query message.
The second message processing module is also used for analyzing the new query message sent by the first message processing module and then sending the new query message to the acquisition module; and returning a new response message according to the new service performance data.
In an alternative embodiment, the query command includes a location source string that represents the business capability and the business object to which it belongs.
The first mapping table pre-configured by the master control panel comprises the corresponding relation between the positioning source character string and the keyword, and the keyword comprises the identifier ID and the parameter information of the service object.
The first message processing module is used for converting the keywords into a data structure according to a second mapping table which is configured in advance, and determining the association relationship between the query message and the response message according to the comparison result of the data structure.
In an optional implementation manner, the first packet processing module is configured to establish a cache linked list for storing service performance data based on the query command and the query packet, and delete a corresponding node in the cache linked list when receiving an empty response packet.
Fig. 6 is a structural block diagram of a network device, which includes a master control disk and a service single disk, where the master control disk and the service single disk communicate and issue configuration through a Message Transfer Link (MTL) between the disks.
The master control dish includes:
command line interface CLI module: for command line input and output.
SCK STUB module: and the socket network communication management between the master control panel and the network manager is provided.
Node Management Unit (NMU): the network element management function is provided and comprises a communication adaptation module, a positioning source conversion module, a communication adaptation layer, a performance summarizing module and an alarm summarizing module.
The summarizing module, the first message processing module and the storage module are all arranged in the performance processing module.
The positioning source conversion module is used for:
1) the cache device basic configuration (interface and single disk information) and related service configuration (LSP, PW and L3VPN), etc.
2) Positive conversion processing of a positioning source: and converting the performance alarm reported by the service single disk and the KEY word (KEY) in the response message into a character string which can be identified by the network manager and is used for positioning source according to a first mapping table which is configured in advance, wherein the character string comprises positioning information, additional information and accessory list translation.
3) And (3) reverse conversion processing of a positioning source: and converting the positioning source character string into a KEY (KEY) according to a first mapping table configured in advance.
Network management communication adaptation module: for receiving and transmitting User Datagram Protocol (UDP) messages with a network manager; the UDP listening port of the management device.
An alarm processing module: the method is used for processing the master control disk protocol alarm, storing network element alarm data, reversing network element alarm, shielding network element alarm and the like.
Communication adaptation layer: the device has the functions of Protocol Data Unit (PDU) Data adaptation for processing UDP Protocol messages of the network management, packet packing, compression and decompression of the UDP Protocol messages and the like.
Main control transmission Network Element module (TNE): for transmitting configuration messages and MTL communication channel management between the master control disk and the service disk.
The service single disk comprises:
and the transmission network element proxy module (BMU _ TNE) is used for transmitting the configuration message and managing the MTL communication channel between the master control panel and the service single panel.
Single disk Management Unit Library (Board Management Unit Library, BMU _ LIB): the acquisition module and the second message processing module of the embodiment of the invention are arranged in the BMU _ LIB, and the acquisition module receives the service performance value acquired by the service module and provides service performance value statistics of the service single disk.
A service module: the system is used for creating and destroying business objects on a business single disk; and providing a hardware driving interface to obtain the original service performance value.
Hardware driving: original service performance values are provided.
The present invention is not limited to the above-described embodiments, and it will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and such modifications and improvements are also considered to be within the scope of the present invention. Those not described in detail in this specification are within the skill of the art.
Claims (8)
1. A method for processing service performance, comprising:
in the network equipment, a main control panel generates a query message according to a received query command of the service performance and sends the query message to a corresponding service single panel;
the service single disc acquires service performance data according to the query message, and returns a response message carrying the service performance data when the service performance data is not 0; otherwise, returning an empty response message;
the master control panel collects and uploads the returned service performance data;
the service performance data is a second-level service performance value, the master control panel summarizes the second-level service performance values returned by more than two service single panels according to the second-level time, wherein at each second-level time for summarizing, all the service single panels have the second-level service performance values;
when the second-level service performance values of the same service object are summarized, the same second-level time points are aligned in the vertical direction;
under normal conditions, the steps of summarizing the second-level service performance value by the master control panel are as follows:
the master control disk sequentially accumulates and summarizes the service performance values of the service single disks returning the response messages carrying the service performance data according to the second-level time to obtain a summarizing result of each second-level time, and replies to the network management;
under abnormal conditions, the steps of summarizing the second-level service performance value by the master control panel are as follows:
determining a service single disc for returning a response message carrying service performance data, wherein the determined service single disc needs to have a second-level service performance value at the same second-level time point for summarizing;
the same service object and the same service performance are added and calculated when the second-level time has the second-level service performance value;
in the response message of the network management, only the summary result of every second-level moment with the service performance value at the same second-level moment is returned;
the abnormal conditions are the conditions that the time of each service single disk is asynchronous, the communication between disks is abnormal, and the second-level time points replied by the service single disks are not completely the same;
and when the network manager draws the second-level service performance value curve, the network manager performs smooth connection processing on the jumping point data.
2. The method for processing service performance according to claim 1, characterized in that:
the query command comprises a positioning source character string used for representing the service performance and the service object to which the service performance belongs;
a first mapping table pre-configured by a master control panel comprises a corresponding relation between a positioning source character string and a keyword, wherein the keyword comprises an identifier ID and parameter information of a service object;
the main control panel converts the keywords into a data structure according to a second mapping table configured in advance, and determines the association relationship between the query message and the response message according to the comparison result of the data structure.
3. The method for processing service performance according to claim 1, wherein after the master controller generates the query message according to the received query command of service performance, the method further comprises:
and the master control disk establishes a cache linked list for storing the service performance data based on the query command and the query message, and deletes the corresponding node in the cache linked list when receiving the empty response message.
4. The method for processing service performance according to claim 1, wherein before the master controller generates the query message according to the received query command of service performance, the method further comprises:
the master control disk generates a collection message according to the received collection command of the service performance and sends the collection message to a corresponding service single disk;
the service single disc starts to acquire a service performance value according to the acquired message;
the service performance data is obtained based on a service performance value obtained between the acquisition message and the query message.
5. The method for processing service performance according to claim 1, wherein the method further comprises:
and the service single disk restarts to acquire the service performance value according to the query command, acquires new service performance data based on the service performance value acquired between the query message and the new query message when receiving the new query message transmitted by the master control disk, and returns a new response message.
6. A processing system of service performance is arranged in a network device comprising a master control disk and a plurality of service single disks, and is characterized in that:
the system comprises a gathering module, a first message processing module and a storage module in a master control panel, and an acquisition module and a second message processing module which are arranged in each service single panel;
the first message processing module is used for generating a query message according to the received query command of the service performance and sending the query message to the second message processing module; the second message processing module is also used for receiving a response message returned by the second message processing module and extracting service performance data carried by the response message; uploading the result summarized by the summarizing module;
the summarizing module is used for summarizing the service performance data;
the storage module is used for storing the service performance data and the result summarized by the summarizing module;
the second message processing module is used for analyzing the query message and then sending the analyzed query message to the acquisition module; the first message processing module is further configured to generate the response message according to the service performance data obtained by the obtaining module, and return the response message to the first message processing module, where the response message carries service performance data that is not 0 or is a null message;
the acquisition module is used for acquiring service performance data according to the analysis result of the query message and sending the service performance data to the second message processing module;
the service performance data is a second-level service performance value, the summarizing module is used for summarizing the second-level service performance values returned by more than two acquiring modules according to second-level time, wherein at each second-level time for summarizing, all the acquiring modules have the second-level service performance values;
when the second-level service performance values of the same service object are summarized, the same second-level time points are aligned in the vertical direction;
under normal conditions, the step of summarizing the second-level service performance value by the summarizing module is as follows:
the summarizing module sequentially accumulates and summarizes the service performance values of the acquiring modules which return the response messages carrying the service performance data according to the second-level time to obtain a summarizing result of each second-level time and replies to the network management;
under abnormal conditions, the step of summarizing the second-level service performance value by the summarizing module is as follows:
determining an acquisition module for returning a response message carrying service performance data, wherein the determined acquisition module only needs to have a second-level service performance value at the same second-level time point for summarizing;
the same service object and the same service performance are added and calculated when the second-level time has the second-level service performance value;
in the response message of the network management, only the summary result of every second-level moment with the service performance value at the same second-level moment is returned;
the abnormal conditions are the conditions that the time of each service single disk is asynchronous, the communication between disks is abnormal, and the second-level time points replied by the service single disks are not completely the same;
and when the network manager draws the second-level service performance value curve, the network manager performs smooth connection processing on the jumping point data.
7. The traffic performance processing system of claim 6, characterized by:
the first message processing module is further configured to generate a collection message according to the received collection command of the service performance, and send the collection message to the second message processing module;
the second message processing module is also used for analyzing the collected message and then sending the analyzed message to the acquisition module;
the acquisition module is further configured to start to acquire a service performance value based on the analysis result of the acquisition packet, and obtain the service performance data according to the service performance value acquired between the acquisition packet and the query packet.
8. The traffic performance processing system of claim 6, characterized by:
the summarizing module is also used for restarting to acquire the service performance value according to the analysis result of the query command; obtaining new service performance data based on the service performance value obtained between the query message and the new query message;
the second message processing module is also used for analyzing the new query message sent by the first message processing module and then sending the new query message to the acquisition module; and returning a new response message according to the new service performance data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910497363.3A CN112073253B (en) | 2019-06-10 | 2019-06-10 | Service performance processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910497363.3A CN112073253B (en) | 2019-06-10 | 2019-06-10 | Service performance processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112073253A CN112073253A (en) | 2020-12-11 |
| CN112073253B true CN112073253B (en) | 2022-03-18 |
Family
ID=73658142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910497363.3A Active CN112073253B (en) | 2019-06-10 | 2019-06-10 | Service performance processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112073253B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109768900A (en) * | 2019-01-04 | 2019-05-17 | 烽火通信科技股份有限公司 | Network element second grade processing method for performance and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7032119B2 (en) * | 2000-09-27 | 2006-04-18 | Amphus, Inc. | Dynamic power and workload management for multi-server system |
| CN100470507C (en) * | 2003-11-12 | 2009-03-18 | 华为技术有限公司 | Method for rewriting in magnetic disc array structure |
| CN102404154B (en) * | 2011-11-30 | 2014-04-16 | 烽火通信科技股份有限公司 | Method for webmaster for batch repairing of service faults |
| CN105812208B (en) * | 2016-05-06 | 2019-10-11 | 烽火通信科技股份有限公司 | The performance accounting method and system of a kind of multipoint service in frame datacom device |
-
2019
- 2019-06-10 CN CN201910497363.3A patent/CN112073253B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109768900A (en) * | 2019-01-04 | 2019-05-17 | 烽火通信科技股份有限公司 | Network element second grade processing method for performance and system |
Non-Patent Citations (1)
| Title |
|---|
| 网元性能统计方案中主控的设计与实现;张轶琦;《光通信研究》;20180514;第1-2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112073253A (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3593528B2 (en) | Distributed network management system and method | |
| US7787454B1 (en) | Creating and/or managing meta-data for data storage devices using a packet switch appliance | |
| US9065767B2 (en) | System and method for reducing netflow traffic in a network environment | |
| US11888744B2 (en) | Spin-leaf network congestion control method, node, system, and storage medium | |
| EP3082293B1 (en) | Switching device and packet loss method therefor | |
| CN111769998B (en) | Method and device for detecting network delay state | |
| US8179799B2 (en) | Method for partitioning network flows based on their time information | |
| CN105227341A (en) | For the system and method by content center network management devices | |
| US20220407791A1 (en) | Network performance detection method and apparatus, and network device | |
| US20220191140A1 (en) | Data transmission control method, apparatus, and storage medium | |
| CN112511376A (en) | Method and terminal for measuring TSN network forwarding time characteristic | |
| US11050649B2 (en) | Delay measurement method of network node device, apparatus, and network node device | |
| CN111049698A (en) | Telemetering data acquisition method and device | |
| CN115118663A (en) | Method for acquiring network congestion information by combining in-band network telemetry | |
| CN112073253B (en) | Service performance processing method and system | |
| CN111726410B (en) | Programmable real-time computing and network load sensing method for decentralized computing network | |
| EP2747341B1 (en) | Connecting computer management systems via cellular digital telecommunication networks | |
| CN116346634A (en) | State sensing information processing method and device of network management and control system and electronic equipment | |
| WO2022152230A1 (en) | Information flow identification method, network chip, and network device | |
| US11909623B2 (en) | Device presence method and system for mesh network management | |
| CN111131932A (en) | Master-slave communication method in OLT system | |
| CN112383924B (en) | Base station equipment management method, device and system | |
| CN114189565B (en) | Head area restoration system, method and related equipment | |
| CN114124470A (en) | Network flow metadata acquisition technical algorithm | |
| KR100534619B1 (en) | Apparatus and method of network management |
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 |