CN117135047A - Implementation method and device of software BYPASS and storage medium - Google Patents

Implementation method and device of software BYPASS and storage medium Download PDF

Info

Publication number
CN117135047A
CN117135047A CN202311084968.2A CN202311084968A CN117135047A CN 117135047 A CN117135047 A CN 117135047A CN 202311084968 A CN202311084968 A CN 202311084968A CN 117135047 A CN117135047 A CN 117135047A
Authority
CN
China
Prior art keywords
performance index
value
software bypass
software
network
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
CN202311084968.2A
Other languages
Chinese (zh)
Inventor
吴庆
王树太
左虹
张长顺
张世超
叶倩
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.)
Hangzhou DPTech Technologies Co Ltd
Original Assignee
Hangzhou DPTech Technologies 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 Hangzhou DPTech Technologies Co Ltd filed Critical Hangzhou DPTech Technologies Co Ltd
Priority to CN202311084968.2A priority Critical patent/CN117135047A/en
Publication of CN117135047A publication Critical patent/CN117135047A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0681—Configuration of triggering conditions
    • 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
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0803—Configuration setting
    • H04L41/0813—Configuration setting characterised by the conditions triggering a change of settings
    • 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
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The application provides a method and a device for realizing software BYPASS and a storage medium. Respectively acquiring the performance index of the network equipment and the value of the related performance index; under the condition that a software BYPASS function of the network equipment is not started, if the value of the performance index reaches a trigger threshold value of the software BYPASS function, triggering the software BYPASS function; and under the condition that the software BYPASS function of the network equipment is started, if the values of the performance index and the related performance index reach the exit threshold value of the software BYPASS, exiting the software BYPASS function. In the application, the value of the performance index and the value of the related performance index are related and judged by considering the software BYPASS exit mechanism, so that the condition that the software BYPASS state oscillates back and forth when the network equipment reaches the performance bottleneck is avoided greatly, and the continuity of user service is ensured.

Description

Implementation method and device of software BYPASS and storage medium
Technical Field
The present application relates to the field of network security technologies, and in particular, to a method and apparatus for implementing software BYPASS, and a storage medium.
Background
With the advent of cloud computing and big data age, current network traffic is increasing. When the current network flow is large or the sudden flow in the peak period occurs, if the current network flow reaches the maximum processing performance upper limit of the network equipment, the equipment packet loss occurs, the network is blocked if the current network flow is light, the network is disconnected if the current network flow is heavy, and the hardware BYPASS is not triggered. In view of this, the application software BYPASS technology solves the technical problem that the network device skips the security service when reaching the performance bottleneck, and preferentially guarantees the service connectivity, which needs to be solved at present.
In the prior art, the software BYPASS technology is usually based on trigger conditions such as a CPU usage threshold, a memory usage threshold, etc., when the trigger condition is higher than a certain configuration threshold, the software BYPASS is triggered, and the exit mechanism is usually when the trigger condition is lower than a certain configuration threshold, or after the software BYPASS state reaches a certain time, the software BYPASS exits.
In the prior art, the exiting mechanism of the software BYPASS technology is incomplete, the increase of the CPU utilization rate and the memory utilization rate is usually caused by the processing of the security service by the network equipment, when the threshold value is too high to trigger the software BYPASS, the security service is not processed any more, the CPU utilization rate, the memory utilization rate and the like can be rapidly reduced, the network equipment can exit the software BYPASS, but the software BYPASS is exited, the network traffic can be always in condition, the CPU utilization rate and the memory utilization rate can rapidly climb, and the software BYPASS can be triggered. The software BYPASS state of the network equipment is caused to oscillate back and forth, and the user service is uninterruptedly influenced.
Disclosure of Invention
The present disclosure provides a method, an apparatus, a device, and a storage medium for implementing a software BYPASS, so as to at least solve the technical problems in the related art. The technical scheme of the present disclosure is as follows:
according to a first aspect of an embodiment of the present disclosure, a method for implementing a software BYPASS is provided, where the method includes:
respectively obtaining the performance index of the network equipment and the value of the related performance index, wherein the performance index and the value of the related performance index are used for representing the load degree of the processing capacity of the network equipment from corresponding dimensions respectively;
under the condition that a software BYPASS function of the network equipment is not started, if the value of the performance index reaches a trigger threshold value of the software BYPASS function, triggering the software BYPASS function;
and under the condition that the software BYPASS function of the network equipment is started, if the values of the performance index and the related performance index reach the exit threshold value of the software BYPASS, exiting the software BYPASS function.
Optionally, the performance index includes a CPU utilization rate and/or a memory utilization rate; the related performance index comprises a newly-built connection number, network throughput and/or concurrent connection number.
Optionally, when the performance index includes a CPU utilization, the relevant performance index includes a new connection number and/or a network throughput; when the performance index includes a memory usage rate, the related performance index includes a concurrent connection number.
Optionally, the values of the performance index and the related performance index are instantaneous usage values, or an average of a plurality of instantaneous usage values acquired in one monitoring period.
Optionally, if the collected instantaneous usage value is stable within a preset duration, the values of the performance index and the related performance index of the network device are the instantaneous usage value.
Optionally, if the collected instantaneous usage value is unstable in a preset duration, the values of the performance index and the related performance index of the network device are the average value.
Optionally, the duration of the monitoring period is inversely related to the magnitude of the value of the performance index.
According to a second aspect of the disclosed embodiments, a device for implementing a software BYPASS is provided, where the device includes an acquisition module, a judgment module, an opening module, and a closing module, where,
the acquisition module is used for acquiring the performance index and the value of the related performance index;
the judging module is used for judging whether the value of the performance index and/or the related performance index reaches a trigger or exit threshold set by the software BYPASS;
the starting module is used for starting the software BYPASS under the condition that the judging module judges that the value of the performance index reaches the set trigger threshold;
and the closing module is used for closing the software BYPASS under the condition that the judging module judges that the values of the performance index and the related performance index reach the set exit threshold value.
According to a third aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the method for implementing the software BYPASS according to the first aspect.
According to a fourth aspect of embodiments of the present disclosure, an electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the implementation method of the software BYPASS according to the first aspect.
According to the scheme, based on the related performance indexes, the values of the performance indexes and the values of the related performance indexes are related and judged by considering a software BYPASS exit mechanism of the network equipment. When the value of the performance index reaches the set exit threshold, the value of the related performance index is required to be judged, if the value of the related performance index does not reach the set exit threshold, the service flow still exceeds the capacity processing of the network equipment, the software BYPASS is not closed at the moment, and if the value of the related performance index reaches the set exit threshold, the network equipment has the capacity to process the received service flow, the software BYPASS can be closed at the moment, so that the condition that the software BYPASS function is switched back and forth and the software BYPASS state is oscillated back and forth due to the fact that the software BYPASS function is closed only according to the performance index is avoided, and the continuity of user service is guaranteed.
Drawings
FIG. 1 is a flow chart of a method for implementing a software BYPASS provided by the application;
FIG. 2 is a flow chart of a trigger software BYPASS provided by the present application;
FIG. 3 is a flow chart of exiting a software BYPASS provided by the present application;
FIG. 4 is a block diagram of an embodiment of a device for software BYPASS provided by the present application;
fig. 5 is a schematic structural diagram of an electronic device provided by the present application.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
Aiming at the problems that in the prior art, the exit mechanism of the software BYPASS technology is incomplete, the software BYPASS in the network equipment is repeatedly opened and closed due to the rise and fall of the CPU utilization rate and the memory utilization rate, so that the state of the software BYPASS oscillates back and forth and the client is not affected, the embodiment of the disclosure provides a method for realizing the software BYPASS, which can be implemented by the network equipment, wherein the network equipment can be DPI (Dots Per Inch) equipment, firewall, IPS (Internet Protocol Suite, internet protocol group), UTM (Unified Threat Management ), IDP (integrated digital packet (IDP), a spam gateway, an anti-virus gateway, special distributed denial of service (DDOS) (Distributed Denial of Service, distributed denial of service attack) equipment, special logic isolation equipment in various fields and the like.
As shown in fig. 1, a flowchart of an implementation method of a software BYPASS according to an embodiment of the disclosure is shown, where the method includes:
in S101, a performance index and a related performance index of a network device are obtained, where values of the performance index and/or the related performance index are used to characterize a load level of a processing capability of the network device.
The performance index and the associated performance index values are used to characterize the load level of the processing capabilities of the network device. In general, the larger the value of the performance index or the related performance index, the larger the used degree of the processing capability of the network device, the closer the processing capability of the network device to the use limit, and the larger the load of the network device; the smaller the value of the performance index or related performance index, the smaller the degree of usage of the processing capability of the network device, and the smaller the load of the network device.
The performance index may be a CPU utilization rate or a memory utilization rate, or a combination of both. CPU utilization refers to the percentage of the computer's processing resources being used by the CPU. It represents the ratio between the time the CPU processor is executing instructions and the idle time. When CPU usage is high, indicating that the CPU processor is performing a large number of tasks, it may cause the computer to slow down or to jam. Memory usage refers to the percentage of memory (RAM) in a computer that is being used. Which represents the proportion of memory being occupied by an application. When the memory usage rate is high, it means that the application program in the computer is using a large amount of memory, which may cause the computer to slow down or cause a stuck phenomenon.
The related performance index may be the number of new connections, network throughput or the number of concurrent connections, or any two of the three, or may include the three simultaneously. The new connection number refers to the number of new network connections established over a period of time. These connections may be TCP connections or UDP connections, which are commonly used to monitor network traffic or network load. On a server, the number of new connections is an important performance indicator, as it tells us how many clients are connecting to the server at a certain time. If the number of new connections is too high, it may mean that the server is accepting too many client requests, which may result in too high a load on the server, affecting the response time and stability of the service. Network throughput refers to the amount of data transmitted over a network connection over a period of time. It is commonly used to measure bandwidth and traffic of a network, and can also be used to evaluate network performance and optimize network configuration. Network throughput may be expressed in different units, such as bits per second (bps), kilobits per second (Kbps), megabits per second (Mbps), gigabits per second (Gbps), or the like. Network throughput depends on the bandwidth, delay, packet loss rate, etc. of the network connection. In practical application, the network throughput can be improved by optimizing the network topology, upgrading the network equipment, using efficient transmission protocols, reducing the data transmission amount and other methods, so that the performance and the reliability of the network are improved. The number of concurrent connections refers to the number of connections that are simultaneously established within a certain period of time. In a computer network, this generally refers to the number of connections established simultaneously with a server, and may also refer to the number of concurrent connections to the same target. The number of concurrent connections is a very important indicator, as it can affect the performance and stability of the server. If the number of concurrent connections is too high, the server may be overloaded, the response time and stability of the service may be affected, and even the server may crash.
In one embodiment, the value of the performance index may be an instantaneous usage value of the network device. If the value of the performance index of the network device does not change or the change amplitude is smaller than the preset value within a period of time, the value of the performance index of the network device is stable, i.e. the processing capacity of the network device is in a stable state. At this time, the instantaneous use value may be adopted as the value of the performance index. Similarly, when the value of the related performance index is stable, the value of the related performance index may also be an instantaneous use value of the network device, which is not described herein.
The instantaneous use value refers to a value of a certain index at a certain instant. This may be any indicator such as CPU utilization, memory utilization, network throughput, number of new connections, number of concurrent connections, etc. as described above. The instantaneous usage values are typically dynamically changing because they reflect the state of the current system. For example, instantaneous CPU usage may reach 100% at one instant and may drop to 10% at another instant. Monitoring the instantaneous usage value may help to learn about the real-time status of the system.
In another embodiment, the value of the performance indicator may also be an average of the values of the plurality of instantaneous performance indicators collected by the network device during a monitoring period. If the value of the performance index of the network device changes frequently during a period of time, it indicates that the value of the performance index of the network device is unstable during the period of time, and the processing capability used is in an unstable state, and at this time, an instantaneous use value cannot be selected as the value of the performance index. In this case, it is necessary to monitor the value of the performance index of the network device, and a technique is adopted in which the average value of a plurality of instantaneous use values is used as the value of the performance index in one monitoring period. Similarly, the values of the related performance indicators also adopt the same technical schemes, and are not described herein again.
The average value of a plurality of instantaneous values can be adopted to smooth the change of the index, so that the long-term trend of the index is reflected better. For example, in monitoring the CPU usage as described above, the use of a single instantaneous value may be affected by instantaneous fluctuations, resulting in erroneous decisions. However, if an average value of a plurality of instantaneous values is used, the influence of such fluctuation can be reduced, reflecting the CPU usage more accurately.
In the above embodiment, the duration of the monitoring period may be a fixed duration set in advance. Alternatively, the duration of the monitoring period may be a dynamic duration, for example: the larger the value of the performance index is, the shorter the monitoring period is; the smaller the value of the performance index is, the longer the monitoring period is, so that the real-time state and performance of the system can be more accurately represented. For example, when the value of the performance index is relatively larger, the processing capacity of the network device is closer to the use limit, and at this time, the state of the network device can be known more frequently by shortening the monitoring period, so that the value of the performance index is more accurate. For another example, when the value of the performance index is relatively smaller, the processing capability of the network device is far away from the use limit, and at this time, the state of the network device can be obtained by increasing the monitoring period without needing to know the state of the network device frequently, so that related resources can be saved, and the influence on the normal service processing function of the network device is reduced.
Each value of the instantaneous performance index is used to characterize the degree to which the processing power of the network device is used at the instant of acquisition. If the instantaneous usage value of the network device changes continuously, the usage degree of the processing capability of the network device changes continuously, a plurality of acquired instantaneous usage values in the monitoring period need to be obtained, and the average value in the monitoring period is used as the value of the performance index of the network device. I.e. the quotient of the sum of the values of the plurality of instantaneous performance indicators and the time length of the monitoring period is calculated. In this case, the obtained value of the performance index can represent a stable condition of the degree of use of the processing capability of the network device in the monitoring period. Similarly, the values of the relevant performance indicators are the same.
It can be appreciated, therefore, that the instantaneous usage value is adopted as the value of the performance index, and is suitable for the case that the processing capability of the network device is stable for a period of time; the average value of the acquired multiple instantaneous use values in one monitoring period is used as the value of the performance index of the network equipment, and is suitable for the condition that the processing capacity of the network equipment is unstable in a period of time. Similarly, the values of the relevant performance indicators are the same. The present solution is not limited in either case, which one is adopted depends on the actual need or the user's mind.
In S102, when the value of the performance index or the related performance index reaches a trigger threshold preset by the software BYPASS, the software BYPASS is triggered.
After determining the load level characterizing the processing capability of the network device, the value of the performance index needs to be compared with a trigger threshold preset by the software BYPASS, where the preset trigger threshold can characterize that the used level of the processing capability of the network device is close to the use limit of the processing capability of the network device.
If the value of the performance index does not exceed the preset threshold, the used degree of the processing capacity of the network equipment is not close to the use limit of the processing capacity of the network equipment, and the monitoring is continued.
If the value of the performance index exceeds the preset threshold, the used degree of the processing capability of the network device approaches to the use limit of the processing capability of the network device, and at this time, the load of the network device is very large, so that the problems of network jamming and faults can exist. Therefore, the software BYPASS needs to be triggered, and the security service processing is skipped.
As shown in fig. 2, a flowchart of the trigger software BYPASS provided by the present application is described in more detail below in conjunction with the flowchart.
Step 201 shows: and acquiring the value of the performance index of the target equipment. The performance index may be CPU utilization and/or memory utilization as described above.
In steps 202 and 203, if the performance indicator is CPU usage, the software BYPASS trigger threshold may be set in percentage form. Since CPU usage= (sum of CPU usage time of all non-idle states)/(sum of CPU time of all states) ×100% is generally embodied in the form of percentage, the determination of CPU usage by the corresponding software bypass may also be set as percentage. For example, when the threshold value set by the software BYPASS for the CPU utilization is 80%, and when the monitoring device monitors that the CPU utilization of the network device is not less than 80%, the software BYPASS needs to be triggered, so as to skip the processing of the security service, and preferentially ensure the connectivity of the service, so that the network device is prevented from being forced to stop the processing of the security service due to the excessively high CPU utilization. The threshold value set by the CPU utilization rate is not required in this embodiment, and whether the threshold value is expressed in a percentage form or not is also not required, and may be specifically set according to the CPU limit processing capability of a specific network device.
If the performance index is memory usage, the set software BYPASS trigger threshold may also be in the form of a percentage. Since the memory usage= (trial memory)/(total memory) ×100% is generally expressed as a percentage, the same configuration as the cpu usage may be adopted. Similarly, the threshold value set by the memory usage rate is not required, and whether the threshold value is expressed in a percentage form or not is not required, so that the threshold value can be specifically set according to the memory limit usage condition of specific network equipment.
It should be noted that the performance index in this embodiment is not limited to the two types of performance indexes, and any other performance index capable of characterizing the load degree of the processing capability of the network device may be used as the judgment standard, which is not limited in this embodiment. When judging whether to trigger the software BYPASS, attention must be paid, and if any one of the performance indexes reaches the set trigger threshold, the software BYPASS needs to be triggered, so that service continuity is ensured.
In step 204, if the value of any performance index does not exceed the set trigger threshold, it indicates that the network device has not reached the performance bottleneck yet and can still continue to process the network security service, and at this time, the software BYPASS is not required to be triggered, and only the value of the performance index is required to be continuously monitored.
In S103, when the values of the performance index and the related performance index reach the exit threshold preset by the software BYPASS, the software BYPASS is exited.
If the value of the performance index is lower than the preset software BYPASS exit threshold, the used degree of the processing capability of the network device is not close to the use limit of the processing capability of the network device, and in order to avoid the software BYPASS state of the network device from oscillating back and forth, before exiting the software BYPASS, whether the value of the relevant performance index changes is observed to determine whether the software BYPASS can be really exited.
In an embodiment, if the performance index is the CPU utilization, then the relevant performance index, such as the newly-built connection number and the network throughput, needs to be observed, if the value of the performance index and the value of the relevant performance index are both lower than a certain proportion of the peak value when the software BYPASS is triggered, the software BYPASS is exited, the security service processing is restored, and otherwise, the triggering state of the software BYPASS is continuously maintained.
In another embodiment, if the performance index is the memory usage rate, then the related performance index, such as the number of concurrent connections, needs to be observed, if the value of the performance index and the value of the related performance index are both lower than a certain proportion of the peak value when the software BYPASS is triggered, the software BYPASS is exited, the security service processing is restored, and otherwise, the triggering state of the software BYPASS is continuously maintained.
As shown in fig. 3, a flowchart of exiting the software BYPASS according to the present application is provided, and will be described in more detail below with reference to the flowchart.
Because the exiting mechanism of the existing software BYPASS has a problem, the most important improvement point of the application is to improve the exiting mechanism of the existing software BYPASS, and effectively solve the problem of the back and forth oscillation of the state of the software BYPASS.
Step 301 is the same as step 201 and requires the acquisition of a value of a performance index, but step 301 also requires the acquisition of a value of a related performance index. Specific performance indicators have been described above, and related performance indicators are described herein.
If the associated performance indicator is the number of new connections, the set software BYPASS exit threshold may be a numerical value. Since the new connection number=the current connection number in the time-the previous connection number in the time, it can be known that the new connection number is used as the relevant performance index to be a numerical value, and then the corresponding software BYPASS can set the judgment of the new connection number to a specific numerical value. The embodiment does not require the threshold value set by the newly-built link number, and can specifically set the exit threshold value of the software BYPASS according to the requirement of the specific network equipment on the newly-built link number.
If the associated performance indicator is network throughput, the exit software BYPASS threshold is typically set as data volume/second. Since the network throughput = amount of data transmitted/transmission time, it can be known that the form of the network throughput as the performance index value is a comparative form, and the corresponding software BYPASS can be set to the form of b/s for the network throughput. The threshold value set by the network throughput is not required in this embodiment, and the exit threshold value of the software BYPASS may be specifically set according to the bearing limit of the specific network device on the network throughput.
If the associated performance indicator is the number of concurrent connections, the exit software BYPASS threshold is typically set to a value. Since the number of concurrent connections=the number of connections in the same period of time, the same setting as the number of newly-built connections can be adopted, and set to a specific value. The embodiment does not require the threshold value set by the concurrent connection number, and can specifically set the exit threshold value of the software BYPASS according to the requirement of the specific network device on the concurrent connection number.
It should be noted that the precondition for exiting the software BYPASS is that the software BYPASS has been triggered, and only if the software BYPASS has been triggered, will there be a closing action of the software BYPASS.
In steps 302 and 303, the form of the set exit threshold is the same as that in the above steps, but the judgment is different. When judging whether the software BYPASS is triggered or not, only any one of the acquired values of the performance indexes is required to be compared with the trigger threshold value. However, in determining whether the software BYPASS exits, the performance index and the related performance index must be studied.
The reason is that on the one hand there is a certain correlation between CPU usage and number of connections. Generally, as the number of connections increases, the CPU utilization increases. This is because each connection requires CPU resources to perform operations, such as processing requests, responding to data, and the like. When the number of connections is excessive, the load of the CPU increases, resulting in an increase in CPU usage. Therefore, one of the reasons for the back-and-forth oscillation of the current software BYPASS state is that when the CPU utilization rate reaches the exit threshold of the software BYPASS, the software BYPASS is turned off, but the newly-built connection number may still be too large, so that the CPU utilization rate rises again, exceeds the trigger threshold, and the software BYPASS is triggered, so that the software BYPASS is turned on and off repeatedly, and the service of the user is seriously affected.
Similarly, there is a link between CPU utilization and network throughput. Generally, as network throughput increases, CPU usage increases. Because the network data packet needs to be processed and forwarded by the CPU, the network data packet comprises protocol analysis, unpacking and grouping of the data packet and the like. When the network load is too high, the load of the CPU also increases, resulting in an increase in CPU usage. At present, when the CPU utilization rate is reduced and the condition of exiting the software BYPASS is reached, the software BYPASS is exited, but at the moment, the network traffic is probably always present, the CPU utilization rate is rapidly climbed, the software BYPASS is triggered, the software BYPASS state of the network equipment is caused to oscillate back and forth, and the user service is uninterruptedly influenced.
On the other hand, there is also a certain relationship between the memory usage and the connection number. Generally, as the number of connections increases, so does the memory usage. This is because each connection needs to occupy memory resources to store related data, state information, etc. When the number of connections is excessive, the load of the memory increases, resulting in an increase in the memory usage. Finally, the software BYPASS state oscillates back and forth, and user service is affected.
Likewise, there is a certain link between memory usage and network throughput. Generally, as network throughput increases, memory usage increases. Because the network data packets need to be buffered and processed through the memory, the network data packets comprise unpacking and packing of the data packets, protocol analysis, data buffering and the like. When the network load is too high, the load of the memory also increases, resulting in an increase in the memory usage. Eventually, the above problems are caused.
Therefore, it is mismatching to monitor only CPU usage and memory usage and use only these two performance indicators as the criteria for exiting the software BYPASS. Therefore, in server management and network monitoring, a manager needs to optimize and adjust the system by monitoring performance indexes such as CPU usage, memory usage, and many related performance indexes such as the number of new connections.
In the application, when judging whether the software BYPASS exits, the related performance indexes are required to be subjected to related research and judgment, and the software BYPASS function can be truly exited only when the values of the performance indexes and the values of the related performance indexes reach the condition of exiting the software BYPASS, thereby avoiding the problem of oscillation back and forth of the state of the software BYPASS.
Corresponding to the foregoing embodiment of the implementation method of the software BYPASS, the present specification also provides an embodiment of an implementation apparatus of the software BYPASS.
Fig. 4 is a block diagram of an embodiment of a device for implementing a software BYPASS according to the present application. Wherein the apparatus 40 comprises:
an obtaining module 401, configured to obtain values of a performance index and a related performance index, where the performance index and the related performance index are used to represent a load degree of a processing capability of the network device from corresponding dimensions, respectively.
An opening module 402, configured to, if the software BYPASS function of the network device is not opened, trigger the software BYPASS function if the value of the performance index reaches a trigger threshold of the software BYPASS function.
A closing module 403, configured to, in case the software BYPASS function of the network device is turned on, exit the software BYPASS function if the values of the performance index and the related performance index both reach the exit threshold of the software BYPASS.
Alternatively to this, the method may comprise,
the performance index comprises CPU utilization rate and/or memory utilization rate;
the related performance index comprises a newly-built connection number, network throughput and/or concurrent connection number.
Alternatively to this, the method may comprise,
when the performance index comprises CPU utilization, the related performance index comprises newly-built connection number and/or network throughput;
when the performance index includes a memory usage rate, the related performance index includes a concurrent connection number.
Optionally, the values of the performance index and the related performance index are instantaneous usage values, or an average of a plurality of instantaneous usage values acquired in one monitoring period.
Optionally, if the collected instantaneous usage value is stable within a preset duration, the values of the performance index and the related performance index of the network device are the instantaneous usage value.
Optionally, if the collected instantaneous usage value is unstable in a preset duration, the values of the performance index and the related performance index of the network device are the average value.
Optionally, the duration of the monitoring period is inversely related to the magnitude of the value of the performance index.
The present disclosure also provides an electronic device, as shown in fig. 5, which includes a processor, an internal bus, a network interface, a memory, and a nonvolatile memory, and may include other required hardware. The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs, and forms the implementation device of the software BYPASS shown in fig. 4 on a logic level. Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present description, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of implementing any of the software BYPASS described above.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the application.

Claims (10)

1. The implementation method of the software BYPASS is characterized by comprising the following steps:
respectively obtaining the performance index of the network equipment and the value of the related performance index, wherein the performance index and the value of the related performance index are used for representing the load degree of the processing capacity of the network equipment from corresponding dimensions respectively;
under the condition that a software BYPASS function of the network equipment is not started, if the value of the performance index reaches a trigger threshold value of the software BYPASS function, triggering the software BYPASS function;
and under the condition that the software BYPASS function of the network equipment is started, if the values of the performance index and the related performance index reach the exit threshold value of the software BYPASS, exiting the software BYPASS function.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the performance index comprises CPU utilization rate and/or memory utilization rate;
the related performance index comprises a newly-built connection number, network throughput and/or concurrent connection number.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
when the performance index comprises CPU utilization, the related performance index comprises newly-built connection number and/or network throughput;
when the performance index includes a memory usage rate, the related performance index includes a concurrent connection number.
4. The method of claim 1, wherein the values of the performance indicator and the associated performance indicator are instantaneous usage values or an average of a plurality of instantaneous usage values collected during one monitoring period.
5. The method of claim 4, wherein the performance indicator and the associated performance indicator of the network device are valued as the instantaneous usage value if the acquired instantaneous usage value is stable for a predetermined period of time.
6. The method of claim 4, wherein the performance index of the network device and the associated performance index are averaged if the collected instantaneous usage value is not stable for a predetermined period of time.
7. The method of claim 6, wherein the duration of the monitoring period is inversely related to the magnitude of the value of the performance indicator.
8. The device for realizing the software BYPASS is characterized by comprising an acquisition module, an opening module and a closing module, wherein,
the acquisition module is used for respectively acquiring the values of the performance index and the related performance index, wherein the values of the performance index and the related performance index are used for respectively representing the load degree of the processing capacity of the network equipment from corresponding dimensions;
the starting module is configured to, when the software BYPASS function of the network device is not started, trigger the software BYPASS function if the value of the performance index reaches a trigger threshold of the software BYPASS function;
the closing module is configured to, when the software BYPASS function of the network device is turned on, exit the software BYPASS function if the performance index and the value of the related performance index both reach the exit threshold of the software BYPASS.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any of claims 1 to 8.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 8 when executing the program.
CN202311084968.2A 2023-08-25 2023-08-25 Implementation method and device of software BYPASS and storage medium Pending CN117135047A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311084968.2A CN117135047A (en) 2023-08-25 2023-08-25 Implementation method and device of software BYPASS and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311084968.2A CN117135047A (en) 2023-08-25 2023-08-25 Implementation method and device of software BYPASS and storage medium

Publications (1)

Publication Number Publication Date
CN117135047A true CN117135047A (en) 2023-11-28

Family

ID=88854045

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311084968.2A Pending CN117135047A (en) 2023-08-25 2023-08-25 Implementation method and device of software BYPASS and storage medium

Country Status (1)

Country Link
CN (1) CN117135047A (en)

Similar Documents

Publication Publication Date Title
US10498661B2 (en) Packet loss tolerant transmission control protocol congestion control
US7287082B1 (en) System using idle connection metric indicating a value based on connection characteristic for performing connection drop sequence
US7724660B2 (en) Communication traffic congestion management systems and methods
Spring et al. Receiver based management of low bandwidth access links
EP1946497B1 (en) Adaptive bandwidth control
US8493859B2 (en) Method and apparatus for adaptive bandwidth control with a bandwidth guarantee
EP2456142A1 (en) Methods and apparatus for detecting and limiting focused server overload in a network
EP1187401A2 (en) Method and systems for alleviating network congestion
EP2725740A1 (en) Adaptive method and device for heartbeat period
US10313244B2 (en) Congestion control within a communication network
US6990073B1 (en) Data packet congestion management technique
CN111935791A (en) Network switching judgment method, judgment system and equipment of shipborne satellite communication terminal
CN112039887A (en) CC attack defense method and device, computer equipment and storage medium
CN117135047A (en) Implementation method and device of software BYPASS and storage medium
Jamjoom et al. Resynchronization and controllability of bursty service requests
CN114079619A (en) Port flow sampling method and device
Key et al. Probing strategies for distributed admission control in large and small scale systems
Meng et al. Demystifying and Mitigating TCP Capping
Järvinen et al. Gazing beyond horizon: The predict active queue management for controlling load transients
Yanev et al. Herding the FLOQ: Flow Optimised Queueing
Pan et al. CW-HSTCP: Fair TCP in high-speed networks
Mahmud et al. Elephants Sharing the Highway: Studying TCP Fairness in Large Transfers over High Throughput Links
Gomez et al. Evaluating TCP BBRv3 performance in wired broadband networks
권광욱 LCC
Richards Keynotes

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