CN116346653A - VPP-based inter-cloud interconnection observability system and method thereof - Google Patents

VPP-based inter-cloud interconnection observability system and method thereof Download PDF

Info

Publication number
CN116346653A
CN116346653A CN202211682221.2A CN202211682221A CN116346653A CN 116346653 A CN116346653 A CN 116346653A CN 202211682221 A CN202211682221 A CN 202211682221A CN 116346653 A CN116346653 A CN 116346653A
Authority
CN
China
Prior art keywords
network
vpp
module
data
observability
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.)
Pending
Application number
CN202211682221.2A
Other languages
Chinese (zh)
Inventor
钟柱梁
罗印威
曾浩
张阳
何志强
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.)
Tianyi Cloud Technology Co Ltd
Original Assignee
Tianyi Cloud Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tianyi Cloud Technology Co Ltd filed Critical Tianyi Cloud Technology Co Ltd
Priority to CN202211682221.2A priority Critical patent/CN116346653A/en
Publication of CN116346653A publication Critical patent/CN116346653A/en
Pending legal-status Critical Current

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
    • H04L43/04—Processing captured monitoring data, e.g. for logfile generation
    • H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
    • 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
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • 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
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0823—Errors, e.g. transmission errors
    • 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
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H04L43/0894—Packet rate
    • 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
    • H04L43/50—Testing arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network

Landscapes

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

Abstract

The invention relates to the field of network communication, in particular to an optimal design of cloud computing VPP. The invention is realized by the following technical scheme: the inter-cloud interconnection observability system based on the VPP comprises a network system, wherein the network system comprises the VPP and a plurality of network ports, and network statistical data of the VPP are acquired from each network port; the observability system also includes a monitoring operating system including a control module and a communication module in communication with the VPP under control of the control module. The invention aims to provide a cloud interconnection observability system and a cloud interconnection observability method based on VPP, which can be used for checking real-time data in the process of observing network flow data of a cloud computing system, and are good in instantaneity, accurate in flow data and small in error.

Description

VPP-based inter-cloud interconnection observability system and method thereof
Technical Field
The invention relates to the field of network communication, in particular to an optimal design of cloud computing VPP.
Background
With the development of networks, social networks, electronic commerce, digital cities, online video, and the like have been increasingly developed. These emerging technologies require support for large storage and high performance servers, but maintenance of such servers requires significant manpower and expensive resources. To solve this problem, cloud computing has been created and developed. Cloud computing has received increased acceptance and widespread attention from the social and academic communities as a major innovation in the information industry.
The cloud computing field is steadily advancing in the construction of IT and communication infrastructures through technical precipitation for many years, and service demands are coming to explosive growth. The increase of the traffic also brings new challenges to the original inter-cloud internet communication equipment, and the original inter-cloud internet communication equipment faces performance problems and also faces how to perform network performance analysis, network problem positioning, fault detection, network topology expansion and the like.
In order to observe the state of a cloud computing system during operation, VPP schemes are used by many manufacturers. VPP is an open source, high performance network communication software. The technical scheme is that a system relied on by the technical scheme is of a three-layer computing structure, the first two layers are both edge computing layers, the third layer is a cloud computing layer, and the cloud computing layer also comprises VPP (virtual private point) and is used for counting data in the running process of the system. Further, as disclosed in chinese patent document with publication number CN202011573194.6, a gateway system and a gateway communication method based on cloud scenario, which include an SDN controller, an FRR protocol stack and a vector packet processing frame VPP. The VPP is used as a management and monitoring module and operates in each node.
However, although VPP is effective as a high-performance network communication software suitable for a cloud computing system, the performance can meet most of service scenarios, but there still exists a disadvantage in operation and maintenance management. Specifically, on the one hand, in the prior art, in the process of counting data, especially in the process of counting network traffic, the error degree of the data is high, and the accuracy is poor. On the other hand, the VPP statistics are accumulated values at time points, and thus lack real-time performance.
Disclosure of Invention
The invention aims to provide a cloud interconnection observability system and a cloud interconnection observability method based on VPP, which can be used for checking real-time data in the process of observing network flow data of a cloud computing system, and are good in instantaneity, accurate in flow data and small in error.
The technical aim of the invention is realized by the following technical scheme: an inter-cloud interconnection observability system based on VPP comprises a network system, wherein the network system comprises VPP and a plurality of network ports,
the network statistics data of the VPP are obtained from each network port;
the observability system also comprises a monitoring operation system, wherein the monitoring operation system comprises a control module and a communication module which is communicated with the VPP under the control of the control module;
the control module includes:
the data acquisition module is used for acquiring network statistical data from the VPP at a sampling period starting point t1 and a sampling period ending point t2;
the timing module is used for recording the time of t1 and t2;
and the calculation module is used for calculating and obtaining the network real-time data of the sampling time period according to the network statistical data sampled at the time t1 and the network statistical data sampled at the time t2.
Preferably, the communication module is a vppctl plug-in.
Preferably, the control module further includes a timing judgment module, where the timing judgment module is configured to judge whether the elapsed time from the start of t1 is greater than a preset minimum interval value, and if so, allow the data acquisition module to request the VPP to acquire the network statistics data at the end point t2 of the sampling period.
Preferably, the network statistics data includes a packet number of a network port, a packet byte number, a packet number, and a packet byte number.
Preferably, the network statistics data further comprises packet reception error statistics and packet transmission error statistics.
The invention preferably further comprises a central WEB display, and the operating system further comprises an uploading module, wherein the uploading module is used for uploading the network real-time data of the sampling time period calculated by the calculating module to the central WEB display.
Preferably, the network system has a plurality of network systems, each network system is independently provided with one operating system, the communication between the two network systems is completed by means of a data link, and each operating system comprises a link detection module for detecting the network connection state of the data link.
Preferably, the uploading module is configured to send the data of the data link network connection state obtained by the link detection module to the central WEB display.
A using method of a VPP-based inter-cloud interconnection observability system comprises the following steps:
s01, a primary acquisition step;
the data acquisition module acquires the network statistical data D1 of the VPP through the communication module, and the timing module records the time t1 at the moment;
s02, taking the number again;
the data acquisition module acquires the network statistical data D2 of the VPP through the communication module again, and the timing module records the time t2 at the moment;
s03, calculating;
the calculation module obtains network real-time data in the time interval from t1 to t2 based on the difference value between D2 and D1.
Preferably, the method further comprises the step of S04 of displaying in real time;
the operation system comprises an uploading module, and in the step, the network real-time data is uploaded to a central WEB display by the uploading module and displayed on the central WEB display in real time.
In the preferred embodiment of the present invention, in S02, the control module determines whether the current time is greater than t1+ for a preset time interval, and if so, allows to obtain the network statistics D2 of VPP, and if not, continues to wait.
Preferably, the network statistics data includes a packet number of a network port, a packet byte number, a packet number, and a packet byte number.
In summary, the invention has the following beneficial effects:
1. all data are taken from the network port, but not from the protocol stack software layer, so that the statistical basis of the network statistical data has high reliability and small error.
2. Because of the design concept of the quadratic fetch and calculation, the network real-time data is a reflection of the instant data in one sampling period, and is not an accumulated value in the prior art.
3. The communication module adopts a VPPCTL plug-in, and the plug-in is convenient to use, has less requirements on resource deployment and is easy to realize.
4. The link detection module acquires the real-time connection state of the link and the real-time receiving and transmitting packet rate of the link, so that a user can conveniently and fast check the health degree of each data link.
Description of the drawings:
FIG. 1 is a schematic diagram of the system architecture of embodiment 1;
FIG. 2 is a schematic diagram of the architecture of the control module of FIG. 1;
fig. 3 is a schematic flow chart of example 1.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The present embodiment is only for explanation of the present invention and is not to be construed as limiting the present invention, and modifications to the present embodiment, which may not creatively contribute to the present invention as required by those skilled in the art after reading the present specification, are all protected by patent laws within the scope of claims of the present invention.
Embodiment 1, a VPP-based inter-cloud interconnection observability system and a method thereof, the architecture of which is shown in fig. 1, can be regarded as three components, namely a monitoring operating system, a network system and a central WEB display. It should be noted that, the number of the network systems is plural (a plurality of network systems are drawn in the figure, only one network system is drawn in fig. 1, and the architecture of each network system is the same.) the number of the monitoring operation systems is also plural, and each network system corresponds to a single monitoring operation system. And the monitoring operating systems, the network systems and the monitoring operating systems correspond to a central WEB display.
The network system is the same as the network system in the prior art, and has no change, and the network system is a logic concept of combining hardware and software. It often includes a server in hardware and a number of network services and network protocols in software. The network system comprises a plurality of network ports, such as a network port 1, a network port 2 and a network port 3 shown in fig. 1, wherein the specific number of the network ports depends on the scale of the network system. The VPP is also installed in the network system, and the operation mode is the same as that of the VPP in the prior art, and the only difference is that the VPP has different acquisition positions for network statistics.
In the prior art, the VPP often acquires network statistics data by counting the packets received and transmitted on the protocol stack software. However, this has a problem of large error and low accuracy. This is because at the protocol stack software level, the transmitted and received packets generated by the network environment may be lost, and the code may be changed to cause statistical errors. In this case, the VPP obtains the network statistics directly from each network port. This avoids errors caused by the above-described situation, and results in high reliability of the statistical base of the network statistics and small errors.
Specifically, the network system may use a vpp+dpdk architecture, where the network port is taken over by the DPDK, and the DPDK also provides a related API interface (such as rte _eth_stats_get) to obtain the network statistics of the network port. The network statistics may include the following types of data: the network port receives the packet number, receives the packet byte number, sends the packet byte number, receives packet error statistics and sends packet error statistics.
And the monitoring operation system can be a monitoring APP installed on a certain server and comprises a communication module, a control module and an uploading module. The communication module can adopt a VPPCTL plug-in unit and can be conveniently and communicatively connected with the VPP. The uploading module is used for uploading part of data to be displayed to the central WEB display.
The control module is an important module of the invention, and the realization of the technical scheme mainly depends on the control module. As shown in fig. 2, the system comprises a data acquisition module, a timing module, a calculation module and a timing judgment module. The workflow and method are shown in fig. 3:
s01, a primary picking step.
At this time, the data acquisition module calls vppctl to communicate with VPP, and obtains network statistics data D1 from the physical network port for the first time. The timing module records the time at this time as t1.
S02, taking the number again.
Before formally taking the number again, the timing judgment module judges the current time. It is determined whether the current time is greater than t1+ a preset time interval, for example 20 seconds. For example, already greater, a recourse is made. If not, then continue waiting.
Again taking the number as S01, the data acquisition module invokes vppctl to communicate with VPP, and obtains network statistics D2 from the physical network port a second time. The timing module records the time at this time as t2.
S03, calculating.
The calculation module obtains network real-time data in the time interval from t1 to t2 based on the difference between D2 and D1.
S04, displaying in real time;
the calculated network real-time data in the previous step is uploaded to a central WEB display by an uploading module and is displayed on the central WEB display in real time.
In summary, based on the technical scheme, on one hand, all data are taken from the network port, but not from the protocol stack software layer, so that the statistical basis of the network statistical data has high reliability and small error. On the other hand, the design concept of the quadratic fetch and calculation exists, so that the network real-time data is a reflection of the instant data in one sampling period, and is not an accumulated value in the prior art.
In addition, the VPPCTL plug-in is adopted as the communication module, so that the plug-in is convenient to use, has less requirements on resource deployment and is easy to realize.
Embodiment 2 differs from embodiment 1 in that the inter-cloud interconnection observation function is added. Specifically, as described above, there are a plurality of network systems each individually configured with one monitoring operating system. Communication between different network systems is achieved by means of data links. Each operating system includes a link detection module for detecting the network connection status of the data link.
In this embodiment, the communication module also adopts a VPPCTL plug-in, and the link detection module invokes a PING command of the VPPCTL plug-in, and obtains a real-time connection state of the link according to a PING return result; the link detection module calls a show ip fib command of the VPPCTL plugin, and acquires the real-time packet receiving and transmitting rate of the link according to the return result of the command. The uploading module sends the real-time connection state of the link and the real-time receiving and transmitting packet rate of the link to the central WEB display, so that a user can conveniently and rapidly check the health degree of each data link.

Claims (12)

1. The utility model provides an interconnection observability system between cloud based on VPP, includes network system, network system includes VPP and a plurality of net gape, its characterized in that: the network statistics data of the VPP are obtained from each network port; the observability system also comprises a monitoring operation system, wherein the monitoring operation system comprises a control module and a communication module which is communicated with the VPP under the control of the control module; the control module comprises a data acquisition module, a sampling time period starting point t1 and a sampling time period ending point t2, wherein the data acquisition module is used for acquiring network statistical data from the VPP; the timing module is used for recording the time of t1 and t2; and the calculation module is used for calculating and obtaining the network real-time data of the sampling time period according to the network statistical data sampled at the time t1 and the network statistical data sampled at the time t2.
2. The VPP-based inter-cloud interconnection observability system of claim 1, wherein: the communication module is a vppctl plug-in.
3. The VPP-based inter-cloud interconnection observability system of claim 1, wherein: the control module further comprises a timing judging module, wherein the timing judging module is used for judging whether the elapsed time from the beginning of t1 is larger than a preset minimum interval value, and if so, the data acquisition module is allowed to acquire network statistical data of the last point t2 of the sampling time period by the VPP.
4. The VPP-based inter-cloud interconnection observability system of claim 1, wherein: the network statistics data comprises the number of network port packet receiving, packet receiving byte number, packet sending number and packet sending byte number.
5. The VPP-based inter-cloud interconnection observability system of claim 4, wherein: the network statistics also include packet reception error statistics and packet transmission error statistics.
6. The VPP-based inter-cloud interconnection observability system of claim 1, wherein: the system comprises an operation system, a calculation module, a central WEB display and an uploading module, wherein the operation system further comprises the uploading module, and the uploading module is used for uploading the network real-time data of the sampling time period obtained by the calculation module to the central WEB display.
7. The VPP-based inter-cloud interconnection observability system of claim 6, wherein: the network system has a plurality of network systems, each network system is independently provided with one operating system, the communication between the two network systems is completed by means of a data link, and each operating system comprises a link detection module for detecting the network connection state of the data link.
8. The VPP-based inter-cloud interconnection observability system of claim 7, wherein: the uploading module is used for sending the data of the data link network connection state obtained by the link detection module to the central WEB display.
9. A method of using the VPP-based inter-cloud interconnection observability system according to claim 1, comprising the steps of: s01, a primary acquisition step; the data acquisition module acquires the network statistical data D1 of the VPP through the communication module, and the timing module records the time t1 at the moment; s02, taking the number again; the data acquisition module acquires the network statistical data D2 of the VPP through the communication module again, and the timing module records the time t2 at the moment; s03, calculating; the calculation module obtains network real-time data in the time interval from t1 to t2 based on the difference value between D2 and D1.
10. The method for using the inter-cloud interconnection observability system based on the VPP according to claim 9, wherein: s04, a real-time display step is also included; the operation system comprises an uploading module, and in the step, the network real-time data is uploaded to a central WEB display by the uploading module and displayed on the central WEB display in real time.
11. The method for using the inter-cloud interconnection observability system based on the VPP according to claim 9, wherein: in the step S02, the control module determines whether the current time is greater than t1+ for a preset time interval, and if so, allows to obtain the network statistics data D2 of VPP, and if not, continues to wait.
12. The method for using the inter-cloud interconnection observability system based on the VPP according to claim 9, wherein: the network statistics data comprises the number of network port packet receiving, packet receiving byte number, packet sending and byte number.
CN202211682221.2A 2022-12-27 2022-12-27 VPP-based inter-cloud interconnection observability system and method thereof Pending CN116346653A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211682221.2A CN116346653A (en) 2022-12-27 2022-12-27 VPP-based inter-cloud interconnection observability system and method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211682221.2A CN116346653A (en) 2022-12-27 2022-12-27 VPP-based inter-cloud interconnection observability system and method thereof

Publications (1)

Publication Number Publication Date
CN116346653A true CN116346653A (en) 2023-06-27

Family

ID=86881052

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211682221.2A Pending CN116346653A (en) 2022-12-27 2022-12-27 VPP-based inter-cloud interconnection observability system and method thereof

Country Status (1)

Country Link
CN (1) CN116346653A (en)

Similar Documents

Publication Publication Date Title
US7561559B2 (en) Hardware time stamping and processor synchronization
US5600632A (en) Methods and apparatus for performance monitoring using synchronized network analyzers
CN101917304B (en) Controlling admission of data streams onto a network based on end-to-end measurements
EP2903213B1 (en) Throughput test method and apparatus
JP3476665B2 (en) Relay device test system, communication device, and communication method
US20060045019A1 (en) Network testing agent with integrated microkernel operating system
CN103299583A (en) Systems and methods for measuring available capacity and tight link capacity of IP paths from a single endpoint
CN107579869B (en) Network performance detection method and network equipment
JP2009303089A (en) Delay time measuring instrument, delay time measuring program, and delay time measuring method
US20100128770A1 (en) Measuring Delay in a Network Segment and/or through a Network Communications Device
US6970429B2 (en) Method and apparatus for measuring internet router traffic
CN105827476A (en) High-speed PING implementation method and PING testing method
CN101282247A (en) Method for measuring network application performance supporting internet high bandwidth real time video application
WO2016182772A1 (en) Uplink performance management
WO2020135429A1 (en) Traffic analysis method and apparatus, and traffic detection method and apparatus
CN111934936A (en) Network state detection method and device, electronic equipment and storage medium
CN108199913B (en) Method and equipment for realizing time delay test
CN112134750B (en) Network time protocol pressure test method and device
CN110838949A (en) Network flow log recording method and device
US11611612B2 (en) Link quality measurements and link status detection
CN116346653A (en) VPP-based inter-cloud interconnection observability system and method thereof
US8289868B2 (en) Network device and method of measuring upstream bandwidth employed thereby
CN109120479B (en) Network throughput testing method based on network message format
US20050102391A1 (en) Method and apparatus providing an asymmetric ping procedure
CN116016282A (en) Time delay measurement method and device, computer equipment and storage medium

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