CN103647984A - Load distribution method and system for video processing servers - Google Patents
Load distribution method and system for video processing servers Download PDFInfo
- Publication number
- CN103647984A CN103647984A CN201310566475.2A CN201310566475A CN103647984A CN 103647984 A CN103647984 A CN 103647984A CN 201310566475 A CN201310566475 A CN 201310566475A CN 103647984 A CN103647984 A CN 103647984A
- Authority
- CN
- China
- Prior art keywords
- gop
- video processing
- processing server
- speed
- server
- 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
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The embodiment of the invention provides a load distribution method for video processing servers. The method includes: calculating the speeds of the video processing servers in processing groups of pictures (GOP); performing statistics on the number of unprocessed GOPs of the video processing servers at present; sending the speeds of the video processing servers in processing the GOPs and the number of the unprocessed GOPs at present to a task allocation server; and the task allocation server allocating the GOPs to be processed for the video processing servers according to the speeds of the video processing servers in processing the GOPs and the number of the unprocessed GOPs at present. The embodiment of the invention also provides a corresponding system for load distribution of the video processing servers. Through use of the method and the system, statistics of the speed of each video processing server in processing the GOPs and the number of the unprocessed GOPs can be performed so that a specific algorithm is used to allocate the GOPs for each video processing server and thus the processing capability of each video processing server can be made use to the largest extent and transcoding efficiency is improved.
Description
Technical field
The present invention relates to field of computer technology, relate in particular to the method and system that a kind of Video processing server load distributes.
Background technology
When having multitude of video to carry out format transformation, can adopt the transcoding software of many standalone versions to carry out transcoding; And more efficient way is to design a distributed trans-coding system to carry out transcoding.Video code conversion generally can be divided into four steps to carry out: a, decapsulation, b, video decode coding, c, audio decoder coding, d, encapsulation.In these four steps, video decode this step of encoding will expend time of whole transcoding process 80%-90%.In order to improve transcoding speed, what the whole time of minimizing transcoding was most crucial is the processing time that will reduce video decode coding.
The thought of distributed trans-coding is to utilize multiple servers to walk abreast to entering GOP(Group of Pictures, picture group simultaneously) decoding and coding processing, the server of parallel processing GOP is more, and whole transcoding process is consuming time just fewer.Distributed trans-coding system is typically designed as for this reason: a station server is responsible for decapsulation, and multiple servers is responsible for processing GOP, and a station server is responsible for processing audio bag, and a station server is responsible for encapsulation export target video file.Shown in Fig. 1, be the system schematic of distributed trans-coding.
According to this figure, can find out that GOP distributes to Video processing server by decapsulation module, the disposal ability of every Video processing server is different with the situation of working procedure can cause the speed difference of processing GOP, or even difference is very large, in order farthest to utilize the disposal ability of each Video processing server, improve the efficiency of transcoding, load how to accomplish these Video processing servers of balance just seems very important, and in prior art, can't accomplish well the load balance of Video processing server.
Summary of the invention
In order to solve the unbalanced problem of Video processing server load existing in prior art, the embodiment of the present invention proposes the method and system that a kind of Video processing server load distributes.
One aspect of the present invention, a kind of method that provides Video processing server load to distribute, comprising:
Calculate the speed of Video processing server process picture group GOP;
Add up the quantity of the current untreated described GOP of described Video processing server;
The speed of GOP described in described Video processing server process and the quantity of current untreated described GOP are sent to task distribution server;
The speed of GOP and the quantity of current untreated described GOP described in the comprehensive described Video processing server process of described task distribution server are the pending described GOP of described Video processing server-assignment.
Another aspect of the present invention, the system that provides a kind of Video processing server load to distribute, comprising:
Statistical server and task distribution server;
Described statistical server is for calculating the speed of Video processing server process picture group GOP, add up the quantity of the current untreated described GOP of described Video processing server, the speed of GOP described in described Video processing server process and the quantity of current untreated described GOP are sent to task distribution server;
Described task distribution server, for the speed of GOP and the quantity of current untreated described GOP described in comprehensive described Video processing server process, is the pending described GOP of described Video processing server-assignment.
The method and system that uses the disclosed Video processing server load of the embodiment of the present invention to distribute, speed by each Video processing server process GOP of task distribution server comprehensive statistics, and the quantity of untreated GOP in each Video processing server, according to these statisticss, using specific algorithm is the pending GOP of each Video processing server-assignment, thereby can utilize to greatest extent the disposal ability of each Video processing server, improve transcoding efficiency.
Accompanying drawing explanation
It shown in Fig. 1, is the system schematic of distributed trans-coding;
It shown in Fig. 2, is the method schematic diagram that a kind of Video processing server load that the embodiment of the present invention provides distributes;
It shown in Fig. 3, is the schematic diagram of a kind of Video processing server load that the embodiment of the present invention the provides system of distributing.
Embodiment
In embodiments of the present invention, speed by each Video processing server process GOP of task distribution server comprehensive statistics, and the quantity of untreated GOP in each Video processing server, according to these statisticss, using specific algorithm is the pending GOP of each Video processing server-assignment, thereby can utilize to greatest extent the disposal ability of each Video processing server, improve transcoding efficiency.
The method that the Video processing server load that below describing the embodiment of the present invention in detail provides distributes.
The method schematic diagram that Figure 2 shows that the Video processing server load distribution that one embodiment of the invention provides, according to this figure, describes each step in detail as follows:
The speed of step 201, calculating Video processing server process picture group GOP;
Wherein, the speed of GOP described in the described Video processing server process of described calculating, comprising:
The successful described GOP quantity of statistical disposition within the time period of a setting;
The time period of the foundation successful GOP quantity of described processing and described setting calculates the processing time of each GOP in this period and processes the speed of GOP.
Wherein, outside abovementioned steps, also comprise: measurement period is set;
According to described measurement period, regularly calculate the speed of GOP described in described Video processing server process, and the quantity of current untreated described GOP;
According to described measurement period, regularly the speed of GOP described in described Video processing server process and the quantity of current untreated described GOP are sent to task distribution server.
The speed of GOP and the quantity of current untreated described GOP described in step 204, the comprehensive described Video processing server process of described task distribution server are the pending described GOP of described Video processing server-assignment.
Wherein, the speed of GOP and the quantity of current untreated described GOP described in the comprehensive described Video processing server process of described task distribution server, be the pending described GOP of described Video processing server-assignment, comprising:
Described task distribution server is calculated as the pending GOP quantity of described Video processing server-assignment according to following formula:
Wherein, N represents GOP quantity to be allocated;
S represents described Video processing number of servers;
The speed of GOP described in i Video processing server process of V (i) expression;
M (i) represents untreated and described GOP quantity in i Video processing server;
A (i) is expressed as the described GOP quantity of i Video processing server-assignment.
In abovementioned steps, the quantity of described Video processing server is at least one.
The method of using the disclosed Video processing server load of the embodiment of the present invention to distribute, speed by each Video processing server process GOP of task distribution server comprehensive statistics, and the quantity of untreated GOP in each Video processing server, according to these statisticss, using specific algorithm is the pending GOP of each Video processing server-assignment, thereby can utilize to greatest extent the disposal ability of each Video processing server, improve transcoding efficiency.
Below introduce the system that a kind of Video processing server load distributes, the method for distributing in order to realize the disclosed Video processing server load of previous embodiment.
Figure 3 shows that the schematic diagram of the system of the Video processing server load distribution that one embodiment of the invention provides.According to this figure, the system that discloses a kind of Video processing server load distribution is as follows.
As shown in the figure, described system comprises statistical server 301 and task distribution server 302.
Described statistical server 301 is for calculating the speed of Video processing server process picture group GOP, add up the quantity of the current untreated described GOP of described Video processing server, the speed of GOP described in described Video processing server process and the quantity of current untreated described GOP are sent to task distribution server 302;
Described task distribution server 302 is processed the speed of described GOP and the quantity of current untreated described GOP for comprehensive described Video processing server 301, is the quantity of the pending described GOP of described Video processing server 301 distribution.
Wherein, described statistical server 301 calculates the speed of GOP described in described Video processing server process, comprising:
The successful described GOP quantity of statistical disposition within the time period of a setting;
The time period of the foundation successful GOP quantity of described processing and described setting calculates the processing time of each GOP in this period and processes the speed of GOP.
The speed of GOP and the quantity of current untreated described GOP described in the comprehensive described Video processing server process of described task distribution server 302, be the pending described GOP of described Video processing server-assignment, comprising:
Described task distribution server is calculated as the pending GOP quantity of described Video processing server-assignment according to following formula:
Wherein, N represents GOP quantity to be allocated;
S represents described Video processing number of servers;
The speed of GOP described in i Video processing server process of V (i) expression;
M (i) represents untreated and described GOP quantity in i Video processing server;
A (i) is expressed as the described GOP quantity of i Video processing server-assignment.
Aforementioned statistical server 301 can be positioned at described Video processing server, also can be independent of described Video processing server and dispose separately.
The system of using the disclosed Video processing server load of the embodiment of the present invention to distribute, speed by each Video processing server process GOP of task distribution server comprehensive statistics, and the quantity of untreated GOP in each Video processing server, according to these statisticss, using specific algorithm is the pending GOP of each Video processing server-assignment, thereby can utilize to greatest extent the disposal ability of each Video processing server, improve transcoding efficiency.
One of ordinary skill in the art will appreciate that: all or part of step that realizes said method embodiment can complete by the relevant hardware of program command, aforesaid program can be stored in read/write memory medium, this program, when carrying out, is carried out the step that comprises said method embodiment; And aforesaid storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc, CD, network node, schedulers.
Finally it should be noted that: these are only the preferred embodiments of the present invention, be not limited to the present invention, although the present invention is had been described in detail with reference to previous embodiment, for a person skilled in the art, its technical scheme that still can record aforementioned each embodiment is modified, or part technical characterictic is wherein equal to replacement.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (9)
1. the method that Video processing server load distributes, is characterized in that, comprising:
Calculate the speed of Video processing server process picture group GOP;
Add up the quantity of the current untreated described GOP of described Video processing server;
The speed of GOP described in described Video processing server process and the quantity of current untreated described GOP are sent to task distribution server;
The speed of GOP and the quantity of current untreated described GOP described in the comprehensive described Video processing server process of described task distribution server are the pending described GOP of described Video processing server-assignment.
2. method according to claim 1, is characterized in that, the speed of GOP described in the described Video processing server process of described calculating, comprising:
The successful described GOP quantity of statistical disposition within the time period of a setting;
The time period of the foundation successful GOP quantity of described processing and described setting calculates the processing time of each GOP in this period and processes the speed of GOP.
3. method according to claim 1 and 2, is characterized in that, also comprises:
Measurement period is set;
According to described measurement period, regularly calculate the speed of GOP described in described Video processing server process, and the quantity of current untreated described GOP;
According to described measurement period, regularly the speed of GOP described in described Video processing server process and the quantity of current untreated described GOP are sent to task distribution server.
4. according to the method described in any one in claim 1-2, it is characterized in that, the speed of GOP and the quantity of current untreated described GOP described in the comprehensive described Video processing server process of described task distribution server, for the pending described GOP of described Video processing server-assignment, comprising:
Described task distribution server is calculated as the pending GOP quantity of described Video processing server-assignment according to following formula:
Wherein, N represents GOP quantity to be allocated;
S represents described Video processing number of servers;
The speed of GOP described in i Video processing server process of V (i) expression;
M (i) represents untreated and described GOP quantity in i Video processing server;
A (i) is expressed as the described GOP quantity of i Video processing server-assignment.
5. method according to claim 4, is characterized in that, the quantity of described Video processing server is at least one.
6. the system that Video processing server load distributes, is characterized in that, comprising:
Statistical server and task distribution server;
Described statistical server is for calculating the speed of Video processing server process picture group GOP, add up the quantity of the current untreated described GOP of described Video processing server, the speed of GOP described in described Video processing server process and the quantity of current untreated described GOP are sent to task distribution server;
Described task distribution server, for the speed of GOP and the quantity of current untreated described GOP described in comprehensive described Video processing server process, is the pending described GOP of described Video processing server-assignment.
7. system according to claim 6, is characterized in that, described statistical server calculates the speed of GOP described in described Video processing server process, comprising:
The successful described GOP quantity of statistical disposition within the time period of a setting;
The time period of the foundation successful GOP quantity of described processing and described setting calculates the processing time of each GOP in this period and processes the speed of GOP.
8. according to the system described in claim 6 or 7, it is characterized in that, the speed of GOP and the quantity of current untreated described GOP described in the comprehensive described Video processing server process of described task distribution server, be the pending described GOP of described Video processing server-assignment, comprising:
Described task distribution server is calculated as the pending GOP quantity of described Video processing server-assignment according to following formula:
Wherein, N represents GOP quantity to be allocated;
S represents described Video processing number of servers;
The speed of GOP described in i Video processing server process of V (i) expression;
M (i) represents untreated and described GOP quantity in i Video processing server;
A (i) is expressed as the described GOP quantity of i Video processing server-assignment.
9. according to the system described in any one in claim 6-7, it is characterized in that, described statistical server is positioned at described Video processing server, or is independent of described Video processing server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310566475.2A CN103647984A (en) | 2013-11-14 | 2013-11-14 | Load distribution method and system for video processing servers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310566475.2A CN103647984A (en) | 2013-11-14 | 2013-11-14 | Load distribution method and system for video processing servers |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103647984A true CN103647984A (en) | 2014-03-19 |
Family
ID=50253125
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310566475.2A Pending CN103647984A (en) | 2013-11-14 | 2013-11-14 | Load distribution method and system for video processing servers |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103647984A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105245880A (en) * | 2015-09-21 | 2016-01-13 | 北京暴风科技股份有限公司 | Video file cutting method and distributed transcoding method |
CN109146212A (en) * | 2017-06-16 | 2019-01-04 | 佛山科学技术学院 | Extensive isomorphism method for allocating tasks in crowdsourcing system |
CN110650345A (en) * | 2019-09-25 | 2020-01-03 | 杭州当虹科技股份有限公司 | Master-slave multi-node coding method for 8K ultra-high definition |
CN112165572A (en) * | 2020-09-10 | 2021-01-01 | Oppo(重庆)智能科技有限公司 | Image processing method, device, terminal and storage medium |
CN114710680A (en) * | 2022-03-16 | 2022-07-05 | 中星电子股份有限公司 | Distributed server cluster for video coding and decoding |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001086460A (en) * | 1999-09-14 | 2001-03-30 | Nec Corp | Method and device for accelerating transcoding |
CN1538696A (en) * | 2003-10-24 | 2004-10-20 | 清华大学 | Multipath real time video-frequency gateway for supporting large capacity user and its application method |
EP1838105A1 (en) * | 2006-02-24 | 2007-09-26 | Samsung Electronics Co., Ltd. | Video transcoding method and apparatus |
CN102404567A (en) * | 2011-11-03 | 2012-04-04 | 深圳市融创天下科技股份有限公司 | System and method for transcoding network monitoring video in real time according to need |
CN103309946A (en) * | 2013-05-16 | 2013-09-18 | 华为技术有限公司 | Method, device and system for processing multimedia file |
-
2013
- 2013-11-14 CN CN201310566475.2A patent/CN103647984A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001086460A (en) * | 1999-09-14 | 2001-03-30 | Nec Corp | Method and device for accelerating transcoding |
CN1538696A (en) * | 2003-10-24 | 2004-10-20 | 清华大学 | Multipath real time video-frequency gateway for supporting large capacity user and its application method |
EP1838105A1 (en) * | 2006-02-24 | 2007-09-26 | Samsung Electronics Co., Ltd. | Video transcoding method and apparatus |
CN102404567A (en) * | 2011-11-03 | 2012-04-04 | 深圳市融创天下科技股份有限公司 | System and method for transcoding network monitoring video in real time according to need |
CN103309946A (en) * | 2013-05-16 | 2013-09-18 | 华为技术有限公司 | Method, device and system for processing multimedia file |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105245880A (en) * | 2015-09-21 | 2016-01-13 | 北京暴风科技股份有限公司 | Video file cutting method and distributed transcoding method |
CN105245880B (en) * | 2015-09-21 | 2018-04-13 | 暴风集团股份有限公司 | Video file cutting method and distributed trans-coding method |
CN109146212A (en) * | 2017-06-16 | 2019-01-04 | 佛山科学技术学院 | Extensive isomorphism method for allocating tasks in crowdsourcing system |
CN109146212B (en) * | 2017-06-16 | 2022-03-25 | 佛山科学技术学院 | Large-scale isomorphic task allocation method in crowdsourcing system |
CN110650345A (en) * | 2019-09-25 | 2020-01-03 | 杭州当虹科技股份有限公司 | Master-slave multi-node coding method for 8K ultra-high definition |
CN112165572A (en) * | 2020-09-10 | 2021-01-01 | Oppo(重庆)智能科技有限公司 | Image processing method, device, terminal and storage medium |
CN114710680A (en) * | 2022-03-16 | 2022-07-05 | 中星电子股份有限公司 | Distributed server cluster for video coding and decoding |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111699695B (en) | Method, apparatus and storage medium for decoding encoded data sets | |
CN103647984A (en) | Load distribution method and system for video processing servers | |
CN105451031B (en) | Video transcoding method and system | |
CN103763343A (en) | Method and device for processing service access | |
CN109479146B (en) | Bit packing for incremental color compression | |
US10694199B2 (en) | Method for distributed video transcoding | |
CN104159150A (en) | Cloud terminal, cloud server, media data stream playing system and method | |
CN102802022A (en) | Coding and decoding system and method | |
CN102802024A (en) | Transcoding method and transcoding system realized in server | |
CN102625140A (en) | Method for frame-granularity real-time downloading and play of streaming media server | |
CN103902384A (en) | Method and device for allocating physical machines for virtual machines | |
CN105187845A (en) | Video data decoding device and method | |
US20140358996A1 (en) | Distributed encoding and decoding system, method, and device | |
CN104144202A (en) | Hadoop distributed file system access method, system and device | |
CN107197296B (en) | A kind of HEVC parallel encoding method and system based on COStream | |
CN104394415B (en) | A kind of method of video big data distribution decoding | |
CN103826138A (en) | System and method for realizing cloud transcoding on various code rates and encoding formats of audio and video contents | |
CN101945271B (en) | Image compression system and compression method | |
CN102685266B (en) | Zone file signature method and system | |
CN103618902B (en) | Transcoding method, device and system for video file | |
CN105100663B (en) | Recording system, audio-video processing unit and method for recording based on hardware coder | |
CN104253807A (en) | Media resource control method and device | |
CN103092607A (en) | Encoding and decoding method of telecommunications call ticket | |
CN111399755A (en) | Data storage management method and device | |
CN103647970B (en) | Audio and video synchronization method and system for distributed transcoding |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140319 |