CN116032895A - Bypass intelligent media server scheduling method, system, equipment and medium - Google Patents
Bypass intelligent media server scheduling method, system, equipment and medium Download PDFInfo
- Publication number
- CN116032895A CN116032895A CN202211595358.4A CN202211595358A CN116032895A CN 116032895 A CN116032895 A CN 116032895A CN 202211595358 A CN202211595358 A CN 202211595358A CN 116032895 A CN116032895 A CN 116032895A
- Authority
- CN
- China
- Prior art keywords
- server
- scheduling
- protocol
- script
- data
- 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
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention belongs to the technical field of communication, and discloses a bypass intelligent server scheduling method, a bypass intelligent server scheduling system, bypass intelligent server scheduling equipment and a bypass intelligent server scheduling medium, wherein the bypass intelligent server scheduling method comprises the following steps: step one, starting a detection process in a bypass mode, and readjusting and calculating the weight proportion of the multi-server architecture according to the resource occupancy rate, the hot loading script and the early warning model for a period of time; and step two, sending data according to the ssdp protocol to enable the media engine to adjust and match different strategy modes so as to schedule the server. According to the method, the strategy selection speed of the computing server is improved through the alarm model, the utilization rate of the server is improved, and the running of the server is reduced; the weight is dynamically adjusted, the high availability of the server program group is improved, the idle server is utilized to the maximum extent, the service response time is reduced, meanwhile, IO (input/output) is obtained through ssdp (service request) protocol, CPU (input/output) energy consumption calculation and statistical alarm model data are obtained, the resources of each server are reasonably utilized, the static stability is guaranteed, and the performance utilization efficiency is guaranteed.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a bypass-mode intelligent media server scheduling method, system, equipment and medium.
Background
Currently, media servers are signaling services, forwarding services, storage services, inference services (AI) or other service type servers, collectively referred to as media services, having multiple servers or clusters, respectively. In order to reasonably allocate server resources, the original method comprises the following steps: searching all servers according to signaling of the signaling server, randomly designating a certain server to serve as forwarding service or store after finding a plurality of servers, reasoning, or directly designating a certain server to serve as forwarding service according to weight, or designating a server according to occupancy rate such as CPU (central processing unit) and the like. Weights are typically assigned to the server as normalized numbers, such as server 1:0.7 server 2:0.3, then a seventy percent probability would specify server 1, a thirty percent probability specifies server 2, and the transition probability matrix is [0.7,0.3].
Through the above analysis, the problems and defects existing in the prior art are as follows:
the actual cpu, gpu, memory, disk, network bandwidth occupancy, disk IO requests and power consumption performance of the existing multiple servers are constantly changed, and some servers may already occupy relatively large resources for a long time, but the weight is still heavy over time due to too simple calculation (calculation according to the instant occupancy), so that the servers cannot be reasonably allocated under the condition that media service and AI reasoning service exist and a storage service architecture is constructed.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides an intelligent server scheduling method in a bypass mode. The servers include sip signaling dispatch servers, other media servers. When the client links up, the client can indicate that the client is a release identity or a subscription identity, the signaling scheduling server schedules and distributes other servers, for example, the streaming media server comprises a main server and an edge server, the AI reasoning server comprises a main reasoning server and an edge reasoning server, and the storage server comprises a main storage server and an edge storage server. The weight initially configured by the primary server is relatively heavy.
The invention is realized in such a way that the intelligent server scheduling method of the bypass mode comprises the following steps:
step one, each physical server starts a bypass monitoring process watch, the process detects cpu, gpu, memory and disk io of the physical server, the process sends detected data according to ssdp protocol, the sip signaling service process obtains resource occupancy of cpu, gpu, io and the like according to ssdp protocol, the servers are deleted through a hot loading strategy script and an early warning model, and weight proportion of each server under the condition of calculating multiple servers is readjusted;
hot-load script application process: after the signaling server is started, the event detection script is changed according to the operating system file, and when the script file is changed, the script is read again to acquire a weight formula, so that the server scheduling strategy is updated.
Step two, the bypass process watch sends monitoring data according to ssdp protocol, each server process adds script files and executes functions, the code quantity is very small, the script files can send own functions, IP addresses and the like, the sip center signaling scheduling server detects how many servers are nearby and the functions of each server through ssdp protocol, and simultaneously changes scheduling strategies through hot loading scripts, and a media engine adjusts and matches different strategy modes to schedule the servers, so that the bypass mode scheduling of resources is achieved.
Further, the published data are sequentially transmitted to the streaming media server in a data stream mode at a push end, after the sip center signaling scheduling server detects that the data stream reaches the streaming media server, the server of the current local area network and the functions thereof are detected through ssdp protocol in the streaming media server, meanwhile, the scheduling strategy of the sip center signaling scheduling server is changed through python hot loading script or c++ hot loading script or lua hot loading script or js hot loading script which are prepared in directory service contained in the reasoning server, the streaming media server adjusts the corresponding strategy of a matching mode between an origin main service and an edge server according to the scheduling strategy of the sip center signaling scheduling server, then the sip center signaling scheduling server calls the main reasoning server and the edge reasoning server in the reasoning server to conduct data stream reasoning, the storage server stores the processed data stream, and the sip center signaling scheduling server transmits the processed data stream to a player in a play subscription position through directly calling the data stream in the streaming media server or the data file in the storage server.
Further, the policy mode in the second step includes a bandwidth occupancy rate type and an IO bandwidth type;
assume that different servers occupy different network card interfaces;
the bandwidth occupancy rate is a strategy with high network bandwidth occupancy rate in weight proportion;
the weight proportion calculation process of the bandwidth occupancy rate comprises the following steps:
X＝a*0.4+b*0.3+c*0.1+d*0.1+e*0.1
wherein a is the network bandwidth occupancy rate, b is the CPU occupancy rate, c is the GPU occupancy rate, d is the disk IO occupancy rate, and e is the memory storage block occupancy rate;
the weight proportion calculation process of the IO bandwidth type is as follows:
X＝f/total*0.5+a*0.5
where f is the number of disk IO requests, total is the maximum disk IO request, and the value can be obtained from the configuration of the server.
Further, the specific process of the scheduling is as follows:
the server calculates Y value once every n (n < = 20) seconds, and calculates average Y/n=X/(60/n) once every minute, wherein the average Y/n=X/(60/n) is a time unit group every 5 minutes, and the average Y/n is (Y1, Y2, Y3, Y4 and Y5), and only 5 values of 5 minutes can be stored;
and determining the minimum value as the server with the highest weight according to the Y/n value sent by each server.
The server groups do not directly communicate with each other, data is sent according to ssdp protocol, and each basic weight is dynamically adjusted in the script according to different functions.
Further, the early warning model includes the following data:
h: a cpu alert;
i: an electricity warning;
j: a temperature warning;
k: warning of insufficient memory;
a disk shortage warning;
further, alarm model data within 5 minutes are stored in the server, and the server to be selected is directly deleted according to the early warning model.
The distributed data are sequentially transmitted to a streaming media server in a data stream mode at a push stream end, after the sip center signaling scheduling server detects that the data stream reaches the streaming media server, the server of the current local area network and the functions thereof are detected through ssdp protocol in the streaming media server, meanwhile, the scheduling strategy of the sip center signaling scheduling server is changed through the python hot loading script or the c++ hot loading script or the iua hot loading script or the js hot loading script which are prepared in directory service contained in the reasoning server, the streaming media server adjusts the corresponding strategy of a matching mode between an origin main service and an edge server according to the scheduling strategy of the sip center signaling scheduling server, then the main reasoning server and the edge reasoning server in the sip center signaling scheduling server are called to conduct data stream reasoning, the processed data stream is stored by the storage server, the data stream in the streaming media server or the data file in the storage server is directly called, the data stream or the data file in the storage server is transmitted to a player in a display screen, and the data file is combined with a DLAN (digital subscriber).
Another object of the present invention is to provide a bypass-type intelligent server scheduling system for implementing the bypass-type intelligent server scheduling method, wherein the bypass-type intelligent server scheduling system
The degree system comprises:
a) The system comprises a custom search discovery protocol ssaop, a multicast module and a user network protocol, wherein the custom search discovery protocol ssaop comprises sending and receiving;
1 transmitting module
To the multicast address 239.255.255.123, the port 18000 sends an identity including its own IP address, name, type, location position, cpu occupancy, gpu occupancy, io occupancy, etc. For indicating its identity and network address, e.g. streaming media forwarding service, sip signaling module, AI reasoning module, etc.
2 receiving module
Join multicast address 239.255.255.123, port 18000, receive information, find own interested services from each identity, such as find all streaming media forwarding servers.
B) A signaling gateway service for signaling transmission;
the Sip signaling exchange protocol server is supported and used for recording all devices, such as all streaming media forwarding servers, and recording information of cpu, gpu, io occupation ratios and the like of all servers. Responsible for informing the flow diversion.
C) And the event early warning module is used for event editing and event script.
The formula calculation can be changed at any time in the event of writing, and even the interface can be provided for changing. Acquiring the occupancy rate and event early warning from the multicast address 239.255.255.123 and the port 18000, [ ssiop ], and deleting the sip service if the occupancy rate and the event early warning value are larger than the early warning value.
The system provided by the embodiment of the invention firstly searches the equipment in the current local area network by using a search protocol ssop, comprises camera equipment, routing equipment, PC end equipment and mobile end equipment, remotely manages all network equipment supporting the protocol by using the protocol, comprises monitoring the network state, modifying the network equipment configuration, receiving a network event warning, simultaneously combining a streaming media transmission protocol RTSP, RTMP, RTP, RTCP, collecting TS and PS streams, transmitting the streaming media protocol to a signaling and gateway module, interacting with an AB protocol, then transmitting the collected streaming data to a media engine module by the search protocol ssop module, detecting the server and the function of the current local area network by using the ssop protocol after a sip center signaling scheduling server detects that the data stream reaches the media engine, simultaneously, the scheduling strategy of the sip center signaling scheduling server is changed through a python hot loading script or a c++ hot loading script or a lua hot loading script or a js hot loading script which are prepared in directory services contained in the reasoning server, a media engine adjusts the corresponding strategy of a matching mode between an origin main service and an edge server according to the scheduling strategy of the sip center signaling scheduling server, then the sip center signaling scheduling server calls the main reasoning server in the reasoning server and the edge reasoning server to conduct data stream reasoning according to GPU, CPU, MEMORY and occupation conditions in a DISK, a storage server stores the processed data stream, the sip center signaling scheduling server transmits the data to an html5player or a mobile player in a display module through directly calling the data stream in the streaming media server or a data file in the storage server, and combines with a screen throwing protocol to display the data to a subscriber, and meanwhile, if early warning occurs, the event warning module transmits the event editing data and the event script data to the display module in the form of data streams.
It is a further object of the present invention to provide a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the bypass mode intelligent server scheduling method.
Another object of the present invention is to provide a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the bypass mode intelligent server scheduling method.
Another object of the present invention is to provide an information data processing terminal for implementing the bypass-mode intelligent server scheduling system.
In combination with the above technical solution and the technical problems to be solved, please analyze the following aspects to provide the following advantages and positive effects:
according to the invention, the CPU occupation, the memory occupation, the disk block occupation rate, the io occupation and the bypass mode are calculated, and the server is not interfered with each other by the custom protocol of the ssiop to send data.
The alarm model of the invention improves the strategy selection speed of the calculation server, improves the utilization rate of the server and reduces the running of the server; by dynamically adjusting the weight, the high availability of the server program group is improved, the idle server is utilized to the maximum extent, and the service response time is reduced; acquiring IO (input/output) and CPU (central processing unit) energy consumption calculation and statistics warning by adopting an ssiop protocol; meanwhile, the resources of each server are reasonably utilized, the static stability is ensured, and the performance utilization is ensured.
The expected benefits and commercial values after the technical scheme of the invention is converted are as follows: the automatic discovery and automatic deployment server reduces deployment time, obtains logs and various information according to the ssiop protocol, reduces error detection time, maintains without a plurality of command joint investigation, can obtain all information from the sip server, and saves a large amount of operation and maintenance time.
The technical scheme of the invention fills the technical blank in the domestic and foreign industries: after the server is started, the server process is started at any time to join the automatic model, the server process is automatically linked into a server group, and calculation service is provided according to the thermal integration script, so that media service, storage service and reasoning service are fully automatically carried out without the need of designating a pairing server, such as storage service of a media service video stream and AI reasoning service of the video stream.
Whether the technical scheme of the invention solves the technical problems that people want to solve all the time but fail to obtain success all the time is solved: greatly reduces the operation and maintenance difficulty. Intelligent auto-pairing services.
Drawings
FIG. 1 is a flow chart of an intelligent server scheduling method in a bypass mode provided by an embodiment of the invention;
FIG. 2 is a flow chart of a data presentation process provided by an embodiment of the present invention;
fig. 3 is a schematic diagram of a signal data processing procedure of an intelligent server scheduling system according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In order to fully understand how the invention may be embodied by those skilled in the art, this section is an illustrative embodiment in which the claims are presented for purposes of illustration.
The intelligent server scheduling method of the bypass mode provided by the embodiment of the invention comprises the following steps:
s101, starting a detection process in a bypass mode, and readjusting and calculating the weight proportion of the multi-server architecture according to the resource occupancy rate, the hot loading script and the early warning model for a period of time;
s102, sending data according to the ssp protocol to enable the media engine to adjust and match different strategy modes so as to schedule the server. The server can exert maximum efficiency according to the function hit, and other servers can acquire corresponding data according to the ssdp protocol.
In the embodiment of the present invention, the policy mode in S102 includes a bandwidth occupancy type and an IO bandwidth type;
assume that different servers occupy different network card interfaces;
the bandwidth occupancy rate is a strategy with high network bandwidth occupancy rate in weight proportion;
the weight proportion calculation process comprises the following steps:
X＝a*0.4+b*0.3+c*0.1+d*0.1+e*0.1
wherein a is network bandwidth occupancy, b is CPU occupancy, c is GPU occupancy, d is disk storage block occupancy, and e is memory storage block occupancy;
the weight proportion calculation process of the IO bandwidth type is as follows:
X＝f/total*0.5+a*0.5
where f is the number of disk IO requests, and total is the maximum disk IO request.
In the embodiment of the invention, the specific scheduling process is as follows:
the server calculates Y values once every n (n < = 20) seconds, and calculates an average value Y=X/(60/n) once every minute, wherein each half hour is a time unit group, and the time unit group is (Y1, Y2, Y3...Y 30), and only 30 values of half hour can be stored;
and determining the minimum value as the server with the highest weight according to the Y/n value sent by each server.
The server groups do not directly communicate with each other, data is sent according to ssdp protocol, and each basic weight is dynamically adjusted in the script according to different functions. The script embeds the early warning signaling, exceeds the specified threshold value, the server does not announce the offline, only announces that the server does not accept more service instructions, still serves the client point which is already linked to exist, if the energy consumption of cpu and the like is high (the service is possibly occupied by other processes), the server script announces that the server is offline, the sip deletes the server candidate, meanwhile, the sip signaling server returns the streaming media server address according to the calculated X value, the streaming media server uses the script to calculate the storage server address and the reasoning server address according to the calculation formula, and notifies the storage server and the reasoning server.
If the subscription is made, the subscriber acquires a server address acquisition stream from the sip server or stores a video file.
And determining the weight proportion of the server according to the actual obtained resource occupancy. And (3) adopting a hot loading script, changing a strategy mode by the script, dynamically calculating a script formula, rapidly deleting server candidates according to early warning information (ssdp protocol), and subdividing server weight proportion according to functions.
In an embodiment of the present invention, the early warning model includes the following data:
h: a cpu alert;
i: an electricity warning;
j: a temperature warning;
k: warning of insufficient memory;
a disk shortage warning;
and storing alarm model data within 5 minutes in the server, and directly deleting the server to be selected according to the early warning model.
In the embodiment of the invention, the method for displaying the data to the subscriber by the scheduling method comprises the following steps:
the distributed data are sequentially transmitted to a streaming media server in a data stream mode at a push stream end, after the sip center signaling scheduling server detects that the data stream reaches the streaming media server, the server of the current local area network and the functions thereof are detected through ssdp protocol in the streaming media server, meanwhile, the scheduling strategy of the sip center signaling scheduling server is changed through the python hot loading script or the c++ hot loading script or the iua hot loading script or the js hot loading script which are prepared in directory service contained in the reasoning server, the streaming media server adjusts the corresponding strategy of a matching mode between an origin main service and an edge server according to the scheduling strategy of the sip center signaling scheduling server, then the main reasoning server and the edge reasoning server in the sip center signaling scheduling server are called to conduct data stream reasoning, the processed data stream is stored by the storage server, the data stream in the streaming media server or the data file in the storage server is directly called, the data stream or the data file in the storage server is transmitted to a player in a display screen, and the data file is combined with a DLAN (digital subscriber).
Another object of an embodiment of the present invention is to provide a bypass-mode intelligent server scheduling system for implementing the bypass-mode intelligent server scheduling method, where the bypass-mode intelligent server scheduling system includes:
the media engine module comprises a media calculation layer and a ssp protocol and is used for carrying out a matching mode of an origin main service and an edge server;
the signaling and gateway module is used for interacting with the search protocol ssiop module;
the reasoning engine module comprises a capability AP layer and a session protocol and is used for carrying out directory services and main reasoning services, wherein the directory services comprise python scripts, C++ scripts, lua scripts and js scripts;
the search protocol ssiop module is used for searching and finding equipment and each occupancy rate protocol;
the storage module comprises a capacity AP layer and an SSDP protocol and is used for storing data information;
and the event warning module is used for event editing and event script.
The system provided by the embodiment of the invention firstly searches the equipment in the current local area network by using a search protocol SSDP, comprising camera equipment, routing equipment, PC end equipment and mobile end equipment, remotely manages all network equipment supporting the protocol by using a snmp protocol, comprises monitoring network state, modifying network equipment configuration, receiving network event warning, simultaneously combining a streaming media transmission protocol RTSP, RTMP, RTP, RTCP, collecting TS and PS streams, transmitting the streaming media protocol to a signaling and gateway module, interacting with an AB protocol, then transmitting the collected streaming data to a media engine module by the search protocol SSDP module, detecting a server and functions of the current local area network by using the SSDP protocol after a sip center signaling scheduling server detects that the data stream reaches the media engine, simultaneously changing the scheduling strategy of the sip center signaling scheduling server through a python hot loading script or a c++ hot loading script or a lua hot loading script or a js hot loading script which are prepared in directory services contained in the reasoning server, adjusting the corresponding strategy of a matching mode between an origin main service and an edge server by a media engine according to the scheduling strategy of the sip center signaling scheduling server, then calling the main reasoning server and the edge reasoning server in the reasoning server by the sip center signaling scheduling server according to GPU, CPU, MEMORY and occupation conditions in a DISK to conduct data stream reasoning, storing the processed data stream by a storage server, transmitting the data to an html5player or a mobile player in a display module by the sip center signaling scheduling server, displaying the data to a subscriber, simultaneously, if early warning occurs, the event warning module transmits the event editing data and the event script data to the display module in the form of data streams.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.
Claims (12)
1. The bypass intelligent server scheduling method is characterized by comprising the following steps of:
step one, starting a detection process in a bypass mode, and readjusting and calculating the weight proportion of the multi-server architecture according to the resource occupancy rate, the hot loading script and the early warning model for a period of time;
and step two, sending data according to the ssdp protocol to enable the media engine to adjust and match different strategy modes so as to schedule the server.
2. The intelligent server scheduling method according to claim 1, wherein in step one, each physical server starts a bypass monitoring process watch, the process detects cpu, gpu, memory and disk io of the physical server, the process sends the detected data according to ssdp protocol, the sip signaling service process obtains cpu, gpu and io resource occupancy rate according to ssdp protocol, the servers are deleted by hot loading strategy script and markov early warning model, and weight proportion of each server under the condition of calculating multiple servers is readjusted.
3. The bypass intelligent server scheduling method according to claim 2, wherein the method comprises the steps of:
after the signaling server is started, the event detection script is changed according to the operating system file, and when the script file is changed, the script is read again to acquire a weight formula, so that the server scheduling strategy is updated.
4. The intelligent server scheduling method of bypass mode according to claim 3, wherein the script embeds an early warning signaling, exceeds a specified threshold, the server does not announce the offline, but announces not to accept more service instructions, and still serves the linked existing client point, if cpu and other energy consumption and the like are high, the server script announces the server offline, sip deletes the server candidate, and the sip signaling server returns a streaming media server address according to the calculated X value, the streaming media server calculates a storage server address and an inference server address according to a calculation formula by using the script, and notifies the storage server and the inference server;
if the subscription is the subscription, the subscriber acquires a server address acquisition stream or stores a video file from the sip server;
and determining the weight proportion of the server according to the actual obtained resource occupancy. And (3) adopting a hot loading script, changing a strategy mode by the script, dynamically calculating a script formula, rapidly deleting server candidates according to early warning information (ssdp protocol), and subdividing server weight proportion according to functions.
5. The intelligent server scheduling method of the bypass mode according to claim 1, wherein in the second step, the bypass process watch transmits monitoring data according to ssdp protocol, each server process adds script files and executes functions, the code amount is very small, and the script files can transmit own functions and IP addresses; the sip center signaling scheduling server detects how many servers are nearby and the functions of the servers through ssdp protocol, and changes scheduling strategies through hot loading scripts, and the media engine adjusts and matches different strategy modes to schedule the servers, so that resources are scheduled in a bypass mode.
6. The bypass intelligent server scheduling method according to claim 5, wherein the policy mode in the second step includes a bandwidth occupancy type and an IO bandwidth type;
assume that different servers occupy different network card interfaces;
the bandwidth occupancy rate is a strategy with high network bandwidth occupancy rate in weight proportion;
the weight proportion calculation process of the bandwidth occupancy rate comprises the following steps:
X＝a*0.4+b*0.3+c*0.1+d*0.1+e*0.1
wherein a is network bandwidth occupancy, b is CPU occupancy, c is GPU occupancy, d is disk storage block occupancy, and e is memory storage block occupancy;
the weight proportion calculation process of the IO bandwidth type is as follows:
X＝f/total*0.5+a*0.5
where f is the number of disk IO requests, and total is the maximum disk IO request.
7. The intelligent server scheduling method of the bypass mode according to claim 1, wherein the specific process of the scheduling server is:
the server calculates Y value once every n seconds, n < = 20, calculates once every minute the average value Y = X/(60/n), is a time unit group every half hour, is Y1, Y2, Y3...Y 30, only stores 30 values of half hour; according to the Y/n value sent by each server, determining the minimum value as the server with the highest weight, and directly deleting the server to be selected according to the stored alarm model data within 5 minutes;
the early warning model comprises the following data: cpu warnings, power consumption warnings, temperature warnings, memory shortage warnings, and disk shortage warnings.
8. The bypass intelligent server scheduling method according to claim 1, wherein the scheduling method displays data to subscribers by:
the distributed data are sequentially transmitted to a streaming media server in a data stream mode at a push stream end, after the sip center signaling scheduling server detects that the data stream reaches the streaming media server, the server of the current local area network and the functions thereof are detected through ssdp protocol in the streaming media server, meanwhile, the scheduling strategy of the sip center signaling scheduling server is changed through the python hot loading script or the c++ hot loading script or the iua hot loading script or the js hot loading script which are prepared in directory service contained in the reasoning server, the streaming media server adjusts the corresponding strategy of a matching mode between an origin main service and an edge server according to the scheduling strategy of the sip center signaling scheduling server, then the main reasoning server and the edge reasoning server in the sip center signaling scheduling server are called to conduct data stream reasoning, the processed data stream is stored by the storage server, the data stream in the streaming media server or the data file in the storage server is directly called, the data stream or the data file in the storage server is transmitted to a player in a display screen, and the data file is combined with a DLAN (digital subscriber).
9. An intelligent server scheduling system of bypass mode for implementing the scheduling method of any one of claims 1 to 8, wherein the intelligent server scheduling system of bypass mode comprises:
the media engine module comprises a media calculation layer and an SSDP protocol and is used for carrying out a matching mode of an origin main service and an edge server;
the signaling and gateway module is used for interacting with the search protocol SSDP module;
the reasoning engine module comprises a capacity AP layer and an SSDP protocol and is used for carrying out directory services and main reasoning services, wherein the directory services comprise python scripts, C++ scripts, lua scripts and js scripts;
the search protocol SSDP module is used for searching the protocol SSDP;
the storage module comprises a capacity AP layer and an SSDP protocol and is used for storing data information;
the display module comprises a player and a large screen DLNA protocol;
and the event warning module is used for event editing and event script.
10. A scheduling method using the scheduling system of claim 9, comprising:
firstly, searching equipment in a current local area network by using a search protocol SSDP, wherein the equipment comprises camera equipment, routing equipment, PC end equipment and mobile end equipment, and remotely managing all network equipment supporting the protocol through a snmp protocol, including monitoring network state, modifying network equipment configuration, receiving network event warning, simultaneously combining a streaming media transmission protocol RTSP, RTMP, RTP, RTCP, collecting TS and PS streams, transmitting the streaming media protocol to a signaling and gateway module, and interacting with an AB protocol;
then the search protocol SSDP module transmits the collected stream data to the media engine module, after the sip center signaling scheduling server detects that the data stream reaches the media engine, the server of the current local area network and the functions thereof are detected through the SSDP protocol, and meanwhile, the scheduling strategy of the sip center signaling scheduling server is changed through a python hot loading script or a c++ hot loading script or a lua hot loading script or a js hot loading script which are prepared in directory services contained in the reasoning server, and the media engine adjusts the corresponding strategy of a matching mode between an origin main service and an edge server according to the scheduling strategy of the sip center signaling scheduling server;
and then the sip center signaling scheduling server calls a main reasoning server and an edge reasoning server in the reasoning server to conduct data stream reasoning according to GPU, CPU, MEMORY and occupation conditions in the DISK, the storage server stores the processed data stream, the sip center signaling scheduling server directly calls the data stream in the streaming media server or the data file in the storage server, the data stream is transmitted to an html5 layer or a mobile layer in a display module, the data is displayed to a subscriber by combining a large screen DLAN protocol, and meanwhile, if early warning occurs, the event warning module transmits event editing data and event script data to the display module in a data stream mode.
11. A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the bypass mode intelligent server scheduling method of any one of claims 1-8.
12. An information data processing terminal, characterized in that the information data processing terminal is adapted to implement the intelligent server scheduling system of the bypass mode according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211595358.4A CN116032895A (en) | 2022-12-13 | 2022-12-13 | Bypass intelligent media server scheduling method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211595358.4A CN116032895A (en) | 2022-12-13 | 2022-12-13 | Bypass intelligent media server scheduling method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116032895A true CN116032895A (en) | 2023-04-28 |
Family
ID=86069796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211595358.4A Pending CN116032895A (en) | 2022-12-13 | 2022-12-13 | Bypass intelligent media server scheduling method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116032895A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057527A (en) * | 2023-06-30 | 2023-11-14 | 东风设备制造有限公司 | Intelligent operation and maintenance method and system for industrial Internet of things of automobile manufacturing equipment |
| CN117057527B (en) * | 2023-06-30 | 2024-05-14 | 东风设备制造有限公司 | Intelligent operation and maintenance method and system for industrial Internet of things of automobile manufacturing equipment |
-
2022
- 2022-12-13 CN CN202211595358.4A patent/CN116032895A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057527A (en) * | 2023-06-30 | 2023-11-14 | 东风设备制造有限公司 | Intelligent operation and maintenance method and system for industrial Internet of things of automobile manufacturing equipment |
| CN117057527B (en) * | 2023-06-30 | 2024-05-14 | 东风设备制造有限公司 | Intelligent operation and maintenance method and system for industrial Internet of things of automobile manufacturing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6293969B2 (en) | Method and system for triggering efficient application synchronization | |
| US8949436B2 (en) | System and method for controlling peer-to-peer connections | |
| CN101911636B (en) | Method for managing content storied in content distribution network and content distribution network | |
| US20140082135A1 (en) | Apparatus and method for providing content, and system for providing content with the said apparatus | |
| CN101039281B (en) | Method for sharing load of stream media server | |
| CN107734350B (en) | Live broadcasting system and live broadcasting method | |
| CN101645928A (en) | Content resource caching method, device and system | |
| US10341277B2 (en) | Providing video to subscribers of a messaging system | |
| US20130304877A1 (en) | System and method for dynamic configuration of isn store-based overlay network | |
| CN103873523A (en) | Client cluster access method and device | |
| CN114071168B (en) | Mixed-flow live stream scheduling method and device | |
| US9992140B2 (en) | Electronic apparatus, server, and control method of system | |
| CN114679604A (en) | Resource processing method and device | |
| WO2004105314A2 (en) | Service management using multiple service location managers | |
| CN112169312A (en) | Queuing scheduling method, device, equipment and storage medium for cloud game service | |
| US8467313B1 (en) | PHY bandwidth estimation from backpressure patterns | |
| CN116032895A (en) | Bypass intelligent media server scheduling method, system, equipment and medium | |
| CN101695044A (en) | Stream media service node and load balancing method thereof | |
| US20220182444A1 (en) | Peer-managed content distribution network | |
| WO2022152230A1 (en) | Information flow identification method, network chip, and network device | |
| WO2022268032A1 (en) | Video stream scheduling system and related product | |
| CN114143569B (en) | Webpage recording and live broadcasting method and system | |
| CN112925946B (en) | Service data storage method and device and electronic equipment | |
| WO2014121605A1 (en) | Method, device and system for supporting always online infrastructure of multi-terminal application | |
| CN111327872B (en) | One-to-many access networking code stream distribution method and system |
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 |