CN103188521B - Transcoding distribution method and device, code-transferring method and equipment - Google Patents
Transcoding distribution method and device, code-transferring method and equipment Download PDFInfo
- Publication number
- CN103188521B CN103188521B CN201110452516.6A CN201110452516A CN103188521B CN 103188521 B CN103188521 B CN 103188521B CN 201110452516 A CN201110452516 A CN 201110452516A CN 103188521 B CN103188521 B CN 103188521B
- Authority
- CN
- China
- Prior art keywords
- transcoding
- video segment
- computing equipment
- video
- time
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000009826 distribution Methods 0.000 title claims abstract description 32
- 238000005520 cutting process Methods 0.000 claims description 19
- 239000012634 fragment Substances 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 description 18
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention discloses a kind of transcoding distribution method based on cloud platform, for improving transcoding efficiency.Described method comprises: the transcoding performance value obtaining the transcoding complexity treating each video segment of transcoding and each computing equipment forming described cloud platform; Obtain each described computing equipment according to the described transcoding performance value of the described transcoding complexity of each video segment, each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time; When judged result is no, described first video segment is assigned on described first computing equipment and carries out transcoding.The invention also discloses the device for realizing described method, and disclose a kind of code-transferring method and device.
Description
Technical field
The present invention relates to Video coding and Distributed Calculation field, particularly transcoding distribution method and device, code-transferring method and equipment.
Background technology
Along with the development of video coding technique, increasing coded system and standard are there is, such as H.264 (high compression digital video coding-coding device standard), MPEG-4 (forth generation moving picture experts group standard) and MPEG-2 (second generation moving picture experts group standard) etc.And different environment, need often to need different coding techniquess, this just requires to carry out transcoding between different coding mode.And coding techniques itself is very complicated, unit transcoding often needs the long time, may need to use concurrent technique so will realize fast transcoding.In the prior art, parallel transcoding technology is mainly divided into two kinds, and a kind of is parallel computation based on multinuclear.A kind of is cloud computing based on multimachine device.
Parallel computation based on multinuclear carries out in same the machine having multiple CPU (central processing unit), the resources such as multiple CPU shared drive and hard disk, but independently can carry out computing.Parallel encoding advantage based on multinuclear is, multi-CPU shared resource, communicates between them more convenient, can the reference between fast processing data rely on, thus obtain higher degree of parallelism, namely the video segment of the video slicing Cheng Geng little of required transcoding can be carried out transcoding.But the parallel computation based on multinuclear needs to use multi-core computer, and multi-CPU structure needs corresponding hardware supports, is generally difficult to expansion, and expensive.
And just in time overcome this shortcoming based on the cloud computing (i.e. cloud transcoding) of multimachine device.Cloud transcoding is based on cloud platform, and cloud platform can be made up of by thousands of computer a group quantity, and each computer can independently calculate, by the scheduling of task with distribute and these computers can be allowed to execute the task concurrently thus provide larger computing capability.Due to inside cloud platform, hardware requirement be there is no to computer, can as a part for cloud platform from server to common personal computer.So cloud platform extensibility is high comparatively speaking, and cheap.
Present inventor, in the process realizing the embodiment of the present application technical scheme, at least finds to there is following technical problem in prior art:
In cloud transcoding process, may be distribute at random when video segment is distributed, not consider the characteristic of video segment and Work machine itself, transcoding efficiency so likely can be caused lower.
Summary of the invention
The embodiment of the present invention provides a kind of transcoding distribution method and device, code-transferring method and equipment, for improving transcoding efficiency.
A kind of transcoding distribution method, is applied to the user side in cloud platform, comprises the following steps:
Obtain the transcoding performance value of the transcoding complexity treating each video segment of transcoding and each computing equipment forming described cloud platform;
According to formula
obtain each described computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Wherein f
*for described first average time, m for the total quantity of computing equipment described in described cloud platform, n be the total quantity of the described video segment needing to carry out transcoding, c
ibe the described transcoding complexity of i-th video segment, p
jfor the described transcoding performance value of a jth computing equipment, t
overheadfor video segment mean value start-up time;
Judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time;
When judged result is no, described first video segment is assigned on described first computing equipment and carries out transcoding.
A kind of code-transferring method, is applied to the user side in cloud platform, comprises the following steps:
To treat that the video of transcoding carries out cutting, obtain each video segment treating transcoding;
According to described transcoding distribution method, each described video segment is distributed;
The described video segment distributed carries out after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding by each computing equipment in described cloud platform.
A kind of transcoding distributor, is applied to the user side in cloud platform, comprises:
First acquisition module, for obtaining the transcoding complexity of each video segment treating transcoding and forming the transcoding performance value of each computing equipment of described cloud platform;
Second acquisition module, for according to formula
obtain each described computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Wherein f
*for described first average time, m for the total quantity of computing equipment described in described cloud platform, n be the total quantity of the described video segment needing to carry out transcoding, c
ibe the described transcoding complexity of i-th video segment, p
jfor the described transcoding performance value of a jth computing equipment, t
overheadfor video segment mean value start-up time; Judge module, for judging whether the first video segment transcoding time required on the first computing equipment is greater than described first average time;
Distribution module, during for being no when judged result, being assigned to described first video segment on described first computing equipment and carrying out transcoding.
A kind of transcoding device, is applied to the user side in cloud platform, comprises:
Cutting module, for treating that the video of transcoding carries out cutting, obtains each video segment treating transcoding;
Transcoding distributor, for distributing each described video segment;
Processing module, to be undertaken the described video segment distributed after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding for each computing equipment in described cloud platform.
Code-transferring method in the embodiment of the present invention is the transcoding performance value obtaining the transcoding complexity treating each video segment of transcoding and each computing equipment forming described cloud platform; Obtain each described computing equipment according to the described transcoding performance value of the described transcoding complexity of each video segment, each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time; When judged result is no, described first video segment is assigned on described first computing equipment and carries out transcoding.Obtain each described computing equipment according to the transcoding complexity of each video segment obtained and the transcoding performance value of each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding, when the transcoding time of a video segment on a computing equipment is not more than described first average time, this video segment is assigned on this computing equipment, thus according to the self-characteristic of each video segment and each computing equipment, each video segment is assigned on different computing equipments, save the transcoding time, improve transcoding efficiency.
Accompanying drawing explanation
Fig. 1 is the primary structure figure of embodiment of the present invention transit code distributor;
Fig. 2 is the primary structure figure of embodiment of the present invention transit code equipment;
Fig. 3 is the main flow figure of embodiment of the present invention transit code distribution method;
Fig. 4 is the main flow figure of embodiment of the present invention transit code method.
Embodiment
Transcoding distribution method in the embodiment of the present invention is the transcoding performance value obtaining the transcoding complexity treating each video segment of transcoding and each computing equipment forming described cloud platform; Obtain each described computing equipment according to the described transcoding performance value of the described transcoding complexity of each video segment, each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time; When judged result is no, described first video segment is assigned on described first computing equipment and carries out transcoding.Obtain each described computing equipment according to the transcoding complexity of each video segment obtained and the transcoding performance value of each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding, when the transcoding time of a video segment on a computing equipment is not more than described first average time, this video segment is assigned on this computing equipment, thus according to the self-characteristic of each video segment and each computing equipment, each video segment is assigned on different computing equipments, save the transcoding time, improve transcoding efficiency.
See Fig. 1, the transcoding distributor in the embodiment of the present invention comprises the first acquisition module 101, second acquisition module 102, judge module 103 and distribution module 104.Device described in the embodiment of the present invention can be applied to the user side in cloud platform, namely can be arranged in arbitrary the computing equipment forming cloud platform.The performance forming each computing equipment in the computing equipment of cloud platform can be the same or different.
First acquisition module 101 is for obtaining the transcoding complexity of each video segment treating transcoding and forming the transcoding performance value of each computing equipment of described cloud platform.
First, the first acquisition module 101 needs to obtain some for calculating the parameter of scheduling, and described parameter at least comprises the transcoding complexity of each video segment and forms the transcoding performance value of each computing equipment of described cloud platform.When in the computing equipment forming cloud platform, the performance of each computing equipment is different, the first acquisition module 101 needs the transcoding performance value obtaining each computing equipment forming described cloud platform.First acquisition module 101 can obtain from cutting module 105 video segment segmented, and then can estimate the transcoding complexity of each video segment.Suppose the video segment after having n cutting, be designated as respectively V=(1,2 ..., n), wherein n be not less than 2 integer, their transcoding complexity of acquisition can be designated as respectively C=(c1, c2 ..., cn).First acquisition module 101 can obtain the transcoding historical record of each computing equipment forming cloud platform to server request simultaneously, from the described transcoding historical record of each computing equipment, the first acquisition module 101 can estimate the transcoding performance value of different computing equipment.Wherein, described server can be the management equipment of cloud platform, and it can be served as by arbitrary computing equipment in the computing equipment forming cloud platform, or can be served as by special computing equipment.Suppose there is m platform computing equipment, m be more than or equal to 1 integer, their transcoding performance value can be designated as respectively P=(p1, p2 ..., pn).Each video segment can be estimated as the start-up time of task on different computing equipment simultaneously, and video segment mean value start-up time can be obtained the start-up time on different computing equipment according to each video segment, this video segment mean value start-up time can be designated as t
overhead.Or each video segment is generally more or less the same the start-up time on different computing equipment, even can ignore its difference, therefore also can in all start-up times optional one as t
overhead.The transcoding time needed for video segment is directly proportional to the transcoding complexity of video segment itself, be inversely proportional to the transcoding performance value of computing equipment, therefore can obtain i-th fragment on jth platform Work machine, perform transcoding time needed for transcoding, can be called for the first transcoding time, can t be used
ijrepresent, wherein i, j are the integer being not less than 1:
Second acquisition module 102 carries out the first average time needed for transcoding to the described video segment distributed respectively for obtaining each described computing equipment according to the described transcoding performance value of the described transcoding complexity of each video segment, each computing equipment.
Can according to the t obtained
ijcalculate the average time that all video segments carry out needed for transcoding on its computing equipment be assigned with, namely each described computing equipment carries out the average time needed for transcoding to the described video segment distributed respectively, can be called for the first average time:
Then in this, as reference, the transcoding time needed for every platform computing equipment is allowed to try not to exceed this first average time.F can be used
jrepresent the transcoding time needed for jth platform computing equipment, because every platform computing equipment carries out to video segment the process that transcoding is all serial, that is, a computing equipment once can only carry out transcoding to a video segment, and transcoding can not be carried out to multiple video segment, therefore f simultaneously
jthe transcoding time sum needed for all video segments be assigned on this computing equipment should be equaled.Time initial, the transcoding time of giving tacit consent to all computing equipments is zero, then starts to distribute video segment.
Judge module 103 is for judging whether the first video segment transcoding time required on the first computing equipment is greater than described first average time.
First judge module 103 needs needing each video segment of transcoding to sort by its transcoding complexity, to sort from big to small in the embodiment of the present invention, the size of each computing equipment by its transcoding performance value can be sorted from big to small simultaneously.Can obtain two queues after sequence, be video segment queue to be allocated respectively, and computing equipment queue to be selected.When distributing, the best computing equipment of transcoding performance value can be selected as current pending computing equipment from computing equipment queue to be selected, the computing equipment that computing equipment queue to be selected described in being namely positioned at is the most forward.Then from described video segment queue to be allocated, select the video segment that transcoding complexity is maximum, the video segment being namely positioned at described video segment queue to be allocated the most forward distributes.Judge module 103 can judge described current pending computing equipment perform the transcoding of this video segment after the required transcoding time can not overflow, whether the namely required transcoding deadline is not more than described first average time.
When distribution module 104 is for being no when judged result, described first video segment is assigned on described first computing equipment and carries out transcoding.
When also namely supposing that distribution i-th video segment (or being called the first video segment) is upper to jth platform computing equipment (or being called the first computing equipment), if:
f
j+t
ij≤f
*(3)
Then distribution module 104 determines described first video segment to be assigned on described first computing equipment.
When the first round distributes, the transcoding time needed for each computing equipment can be made as far as possible close to described first average time (but being not more than described first average time).Such as, have 5 video segments in video segment queue to be allocated, have 3 computing equipments in computing equipment queue to be selected, described first average time is 5 seconds.After first video segment is distributed to First computing equipment, judge module 103 determines that the transcoding time needed for First computing equipment is 2 seconds, distribution module 104 determines this first video segment to distribute to this First computing equipment, judge module 103 judges whether this transcoding time needed for First computing equipment equals described first average time, because 2<5, then judge module 103 can continue to determine to be distributed to by second video segment the transcoding time after this First computing equipment needed for this First computing equipment again, if the transcoding time after second video segment is distributed to this First computing equipment needed for this First computing equipment is total up to 4.5 seconds, then distribution module 104 can determine this second video segment also to distribute to this First computing equipment, because of 4.5<5, then judge module 103 can continue to determine to be distributed to by the 3rd video segment the transcoding time after this First computing equipment needed for this First computing equipment, if the transcoding time after the 3rd video segment is distributed to this First computing equipment needed for this First computing equipment is 7 seconds, exceed described first average time, then distribution module 104 is determined the 3rd video segment to be distributed to this First computing equipment, can continue to judge whether the 3rd video segment to be distributed to second computing equipment with same step.
After first round distribution terminates, if judge module 103 is by judging to determine to also have unappropriated video segment in video segment queue to be allocated, then judge module 103 can according to each different video segment, obtain every platform computing equipment and add the transcoding time required after this video segment, namely every platform computing equipment is traveled through for each remaining video segment, obtain different computing equipment and add the transcoding time required after this video segment, therefrom select the computing equipment that the required transcoding time is minimum, this video segment is assigned in this computing equipment by notice distribution module 104.Such as, in video segment queue to be allocated, residue has 3 video segments, 5 computing equipments are had in cloud platform (computing equipment queue namely to be selected), then when distribution first remaining video fragment, judge module 103 can obtain it respectively and be assigned to the transcoding time that in these five computing equipments, rear five computing equipments need respectively, if judge module 103 determines that second computing equipment adds that the transcoding time required after this first remaining video fragment is minimum, then distribution module 104 is determined this first remaining video fragment allocation in this second computing equipment.And then continue to distribute other remaining video fragment according to same steps, until video segment queue to be allocated is empty.
In first round assigning process, if judge module 103 defines the video segment transcoding time be assigned in which computing equipment needed for this computing equipment and is all greater than described first average time, then this video segment can be assigned in the computing equipment adding required transcoding minimal time after this video segment by distribution module 104 when the first round distributes, or can first skip this video segment when the first round distributes, it is not processed, until the first round distribute terminate after distribution module 104 be assigned in the computing equipment adding required transcoding minimal time after this video segment again, to save the transcoding time as far as possible.
As shown in Figure 2, the embodiment of the present invention also provides a kind of transcoding device, and it can also comprise cutting module 105 and processing module 106 except comprising described transcoding distributor.
Cutting module 105, for treating that the video of transcoding carries out cutting, obtains each video segment treating transcoding.Cutting module 105 is responsible for from this locality stores, obtain the original video data treating transcoding, is then at least two video segments that independently can carry out transcoding by its cutting.In order to ensure the independence of data between video segment, need to guarantee to carry out cutting between image sets (Group of pictures, GOP).Rely on for there being reference frame between GOP, need the GOP adding a redundancy after video segment, this assures between two video segments can absolute coding, and also can guarantee the video after obtaining complete transcoding when finally being merged by the video segment after transcoding.
The described video segment distributed to carry out after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding for each computing equipment in described cloud platform by processing module 106.Described processing mode can be merge.After each computing equipment all completes the transcoding of all video segments, processing module 106 obtains the video segment after each transcoding from described server, then can merge in order.Wherein, cutting module 105, by after the video of transcoding carries out cutting, can be numbered the video segment after each cutting, so that the video segment after transcoding can merge according to number order by processing module 106.For the fragment of redundancy that with the addition of a GOP, there will be the repetition of a GOP when former and later two fragments merge, the GOP of redundancy at this moment can be adopted as output.
Adopt described transcoding device to complete transcoding task, the transcoding time can be saved, improve transcoding efficiency.
The embodiment of the present invention also provides a kind of server, and it can be positioned at the network side of cloud platform.The result announcement server that distribution module 104 can will be distributed, gives corresponding computing equipment by network in charge by corresponding video fragment allocation, notifies that corresponding computing equipment carries out transcoding.Announcement server after each computing equipment transcoding completes, the video segment after transcoding can be sent to processing module 106 by server after the equal transcoding of each computing equipment completes, and carries out merging treatment by processing module 106.Wherein, cutting module 105 can be stored in local virtual storage region after being video segment by video slicing, the every platform computing equipment forming cloud platform can have a virtual storage region, and it can form a cloud platform virtual storage region, can by server unified management.After each video segment distributes by module 104 to be allocated, different video fragment allocation is given corresponding computing equipment according to allocation result by server, the video segment that computing equipment sends according to server carries out transcoding, after transcoding, the video segment after transcoding is put into virtual storage region, and announcement server, then by server, the video segment after transcoding is sent to described transcoding distributor.
Transcoding distribution method in the embodiment of the present invention and code-transferring method is introduced below by way of specific embodiment.
See Fig. 3, the concrete grammar flow process that embodiment of the present invention transit code distributes is as follows:
Step 301: the transcoding performance value obtaining each computing equipment needing the transcoding complexity of each video segment carrying out transcoding and form described cloud platform.
Step 302: obtain each described computing equipment according to the described transcoding performance value of the described transcoding complexity of each video segment, each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding.
Step 303: judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time.When judged result is for being, because sorting to each video segment and each computing equipment before, therefore the transcoding time that the computing equipment after can determining performs needed for described first video segment also can be greater than described first average time, then temporarily first can not process described first video segment, this first video segment can be skipped and first process next video segment, this first video segment of reprocessing after the first round, distribution terminated, be assigned in transcoding time required after adding this transcoding time needed for the first video segment minimum computing equipment, or also can directly process this first video segment when the first round distributes, be assigned in transcoding time required after adding this transcoding time needed for the first video segment minimum computing equipment.
Step 304: when judged result is no, is assigned to described first video segment on described first computing equipment and carries out transcoding.
See Fig. 4, the specific implementation flow process of embodiment of the present invention transit code method is as follows:
Step 401: will treat that the video of transcoding carries out cutting, obtains each video segment treating transcoding.
Step 402: each described video segment is distributed according to described transcoding distribution method.
Step 403: the described video segment distributed carries out after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding by each computing equipment in described cloud platform.
Code-transferring method in the embodiment of the present invention is the transcoding performance value obtaining the transcoding complexity treating each video segment of transcoding and each computing equipment forming described cloud platform; Obtain each described computing equipment according to the described transcoding performance value of the described transcoding complexity of each video segment, each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time; When judged result is no, described first video segment is assigned on described first computing equipment and carries out transcoding.Obtain each described computing equipment according to the transcoding complexity of each video segment obtained and the transcoding performance value of each computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding, when the transcoding time of a video segment on a computing equipment is not more than described first average time, this video segment is assigned on this computing equipment, thus according to the self-characteristic of each video segment and each computing equipment, each video segment is assigned on different computing equipments, save the transcoding time, improve transcoding efficiency.By the technical scheme of the embodiment of the present invention, allow the video segment of more complicated can be dispatched on the better computing equipment of Performance Ratio, like this, these computing equipments can obtain relatively less video segment number, thus reduce their task start time.
Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the present invention can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disc store and optical memory etc.) of computer usable program code.
The present invention describes with reference to according to the flow chart of the method for the embodiment of the present invention, equipment (system) and computer program and/or block diagram.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame.These computer program instructions can being provided to the processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computer or other programmable data processing device produce device for realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices is provided for the step realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. a transcoding distribution method, is applied to the user side in cloud platform, it is characterized in that, comprise the following steps:
Obtain the transcoding performance value of the transcoding complexity treating each video segment of transcoding and each computing equipment forming described cloud platform;
According to formula
obtain each described computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Wherein f
*for described first average time, m for the total quantity of computing equipment described in described cloud platform, n be the total quantity of the described video segment needing to carry out transcoding, c
ibe the described transcoding complexity of i-th video segment, p
jfor the described transcoding performance value of a jth computing equipment, t
overheadfor video segment mean value start-up time;
Judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time;
When judged result is no, described first video segment is assigned on described first computing equipment and carries out transcoding.
2. the method for claim 1, it is characterized in that, judging the first video segment transcoding time required on the first computing equipment also comprises step before whether being greater than described first average time: sorted according to the order that transcoding complexity described in it is descending by each described video segment, and each described computing equipment is worth descending order according to transcoding performance described in it is sorting;
Judge whether the first video segment transcoding time required on the first computing equipment is greater than the step of described first average time and comprises: judge whether the transcoding time needed for described first video segment is on described first computing equipment is greater than described first average time according to the sequence of each described video segment and the sequence of each described computing equipment.
3. the method for claim 1, is characterized in that, described first video segment is assigned to described first computing equipment carries out transcoding after also comprise step:
Judge whether the transcoding time needed for described first computing equipment equals described first average time;
When judged result is no, continue judge described first video segment and the second video segment on the first computing equipment needed for the transcoding time whether be greater than described first average time;
When judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is not more than described first average time, described second video segment being assigned on described first computing equipment and carrying out transcoding;
When judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is greater than described first average time, continue to judge whether the transcoding time needed for described second video segment is on the second computing equipment is greater than described first average time.
4. the method for claim 1, is characterized in that, described first video segment is assigned to described first computing equipment carries out transcoding after also comprise step:
Judge whether remaining video fragment;
When judged result is for being, according to each described computing equipment of described remaining video fragment traversal, select a described computing equipment adding the transcoding minimal time after the transcoding time needed for described remaining video fragment needed for it;
Described computing equipment is given by described remaining video fragment allocation.
5. a code-transferring method, is applied to the user side in cloud platform, it is characterized in that, comprise the following steps:
To treat that the video of transcoding carries out cutting, obtain each video segment treating transcoding;
According to the transcoding distribution method as described in any one of claim 1-4, video segment as described in each is distributed;
The described video segment distributed carries out after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding by each computing equipment in described cloud platform.
6. a transcoding distributor, is applied to the user side in cloud platform, it is characterized in that, comprising:
First acquisition module, for obtaining the transcoding complexity of each video segment treating transcoding and forming the transcoding performance value of each computing equipment of described cloud platform;
Second acquisition module, for according to formula
obtain each described computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Wherein f
*for described first average time, m for the total quantity of computing equipment described in described cloud platform, n be the total quantity of the described video segment needing to carry out transcoding, c
ibe the described transcoding complexity of i-th video segment, p
jfor the described transcoding performance value of a jth computing equipment, t
overheadfor video segment mean value start-up time;
Judge module, for judging whether the first video segment transcoding time required on the first computing equipment is greater than described first average time;
Distribution module, during for being no when judged result, being assigned to described first video segment on described first computing equipment and carrying out transcoding.
7. device as claimed in claim 6, is characterized in that, described judge module also for:
Each described video segment is sorted according to the order that transcoding complexity described in it is descending, and each described computing equipment is worth descending order according to transcoding performance described in it sorts;
Judge whether described first video segment transcoding time required on described first computing equipment is greater than described first average time according to the sequence of each described video segment and the sequence of each described computing equipment.
8. device as claimed in claim 6, is characterized in that, described judge module also for: judge whether the transcoding time needed for described first computing equipment equals described first average time; When judged result is no, continue judge described first video segment and the second video segment on the first computing equipment needed for the transcoding time whether be greater than described first average time; And when judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is greater than described first average time, continue to judge whether the transcoding time needed for described second video segment is on the second computing equipment is greater than described first average time;
Described second video segment also for when judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is not more than described first average time, being assigned on described first computing equipment and carrying out transcoding by described distribution module.
9. device as claimed in claim 6, it is characterized in that, described judge module is also for having judged whether remaining video fragment, when judged result is for being, according to each described computing equipment of described remaining video fragment traversal, select a described computing equipment adding the transcoding minimal time after the transcoding time needed for described remaining video fragment needed for it;
Described distribution module is also for giving described computing equipment by described remaining video fragment allocation.
10. a transcoding device, is applied to the user side in cloud platform, it is characterized in that, comprising:
Cutting module, for treating that the video of transcoding carries out cutting, obtains each video segment treating transcoding;
Transcoding distributor as described in any one of claim 6-9, for distributing each described video segment;
Processing module, to be undertaken the described video segment distributed after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding for each computing equipment in described cloud platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110452516.6A CN103188521B (en) | 2011-12-29 | 2011-12-29 | Transcoding distribution method and device, code-transferring method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110452516.6A CN103188521B (en) | 2011-12-29 | 2011-12-29 | Transcoding distribution method and device, code-transferring method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103188521A CN103188521A (en) | 2013-07-03 |
| CN103188521B true CN103188521B (en) | 2015-10-28 |
Family
ID=48679437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110452516.6A Expired - Fee Related CN103188521B (en) | 2011-12-29 | 2011-12-29 | Transcoding distribution method and device, code-transferring method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103188521B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103428494A (en) * | 2013-08-01 | 2013-12-04 | 浙江大学 | Image sequence coding and recovering method based on cloud computing platform |
| CN103686209A (en) * | 2013-12-13 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Transcoding and processing method and system with diverse mechanisms |
| CN104159126B (en) * | 2014-08-07 | 2015-08-05 | 西安交通大学 | Based on the video code conversion method for scheduling task of Map-Reduce |
| CN106686406B (en) * | 2015-11-05 | 2019-05-17 | 中国电信股份有限公司 | For realizing the pretreated method and apparatus of video real-time transcoding |
| CN105898371A (en) * | 2015-12-07 | 2016-08-24 | 乐视云计算有限公司 | Real-time transcoding real-time control method and device |
| CN105872595A (en) * | 2016-03-31 | 2016-08-17 | 乐视控股（北京）有限公司 | Transcoding task distribution method and device |
| CN108512817B (en) * | 2017-02-28 | 2020-09-04 | 北京大学 | Multi-video transcoding scheduling method and device |
| CN108900804B (en) * | 2018-07-09 | 2020-11-03 | 南通世盾信息技术有限公司 | Self-adaptive video stream processing method based on video entropy |
| CN110113660B (en) * | 2019-02-27 | 2021-08-06 | 咪咕视讯科技有限公司 | Method, device, terminal and storage medium for transcoding time length estimation |
| CN110856018B (en) * | 2019-11-14 | 2020-09-08 | 武汉珞佳伟业科技有限公司 | Rapid transcoding method and system in monitoring system based on cloud computing |
| CN112543373B (en) * | 2020-11-30 | 2022-04-22 | 联想(北京)有限公司 | Transcoding control method and device and electronic equipment |
| CN112533065B (en) * | 2020-12-11 | 2022-07-22 | 北京达佳互联信息技术有限公司 | Method and device for publishing video, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420619A (en) * | 2008-11-20 | 2009-04-29 | 四川长虹电器股份有限公司 | Distributed media format code transferring method |
| CN101459848A (en) * | 2008-12-26 | 2009-06-17 | 西安交通大学 | Distributed multi-format digital video transcoding construction design method |
| CN101917386A (en) * | 2009-11-17 | 2010-12-15 | 新奥特（北京）视频技术有限公司 | Cluster multimedia transcoding system and task processing method thereof |
| CN101917387A (en) * | 2009-11-17 | 2010-12-15 | 新奥特（北京）视频技术有限公司 | Multi-media transcoding cluster system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2151970B1 (en) * | 2008-08-09 | 2011-08-03 | Saffron Digital Limited | Processing and supplying video data |
-
2011
- 2011-12-29 CN CN201110452516.6A patent/CN103188521B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420619A (en) * | 2008-11-20 | 2009-04-29 | 四川长虹电器股份有限公司 | Distributed media format code transferring method |
| CN101459848A (en) * | 2008-12-26 | 2009-06-17 | 西安交通大学 | Distributed multi-format digital video transcoding construction design method |
| CN101917386A (en) * | 2009-11-17 | 2010-12-15 | 新奥特（北京）视频技术有限公司 | Cluster multimedia transcoding system and task processing method thereof |
| CN101917387A (en) * | 2009-11-17 | 2010-12-15 | 新奥特（北京）视频技术有限公司 | Multi-media transcoding cluster system |
Non-Patent Citations (1)
| Title |
|---|
| 分布式系统Hadoop平台的视频转码;杨帆，沈奇威;《计算机系统应用》;20111130;第20卷(第11期);80-85 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103188521A (en) | 2013-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103188521B (en) | Transcoding distribution method and device, code-transferring method and equipment | |
| US9916183B2 (en) | Scheduling mapreduce jobs in a cluster of dynamically available servers | |
| US11006137B2 (en) | Scheduler of processes having timed predictions of computing loads | |
| US8959138B2 (en) | Distributed data scalable adaptive map-reduce framework | |
| US8812639B2 (en) | Job managing device, job managing method and job managing program | |
| CN110381322A (en) | Method for decoding video stream, device, terminal device and storage medium | |
| CN106033373A (en) | A method and a system for scheduling virtual machine resources in a cloud computing platform | |
| CN103916438B (en) | Cloud testing environment scheduling method and system based on load forecast | |
| Lin et al. | Parallelizing video transcoding with load balancing on cloud computing | |
| US11983564B2 (en) | Scheduling of a plurality of graphic processing units | |
| CN110874271B (en) | Method and system for rapidly calculating mass building pattern spot characteristics | |
| US10805622B2 (en) | High efficiency video coding method and apparatus, and computer-readable storage medium | |
| CN103503412A (en) | Method and device for scheduling resources | |
| US9471387B2 (en) | Scheduling in job execution | |
| Shao et al. | A load balancing strategy based on data correlation in cloud computing | |
| Ling et al. | Blastnet: Exploiting duo-blocks for cross-processor real-time dnn inference | |
| Yang et al. | A pipeline-based approach for scheduling video processing algorithms on now | |
| CN104348886A (en) | Information processing method and electronic equipment | |
| CN109448092B (en) | Load balancing cluster rendering method based on dynamic task granularity | |
| Paler et al. | Clifford gate optimisation and T gate scheduling: Using queueing models for topological assemblies | |
| Daoud et al. | Processor allocation algorithm based on frame combing with memorization for 2d mesh cmps | |
| CN114237902A (en) | Service deployment method and device, electronic equipment and computer readable medium | |
| CN109412973B (en) | Audio processing method and device and storage medium | |
| Kunis et al. | Optimizing layer‐based scheduling algorithms for parallel tasks with dependencies | |
| CN115774800B (en) | NUMA architecture-based time-varying graph processing method, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20130703 Assignee: China Digital Video (Beijing) Co.,Ltd. Assignor: PEKING UNIVERSITY FOUNDER GROUP Co.,Ltd.|BEIJING FOUNDER ELECTRONICS Co.,Ltd.|Peking University Contract record no.: 2013990000783 Denomination of invention: Method and device for transcoding distribution, method and device for transcoding License type: Exclusive License Record date: 20131122 |
|
| LICC | Enforcement, change and cancellation of record of contracts on the licence for exploitation of a patent or utility model | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230412 Address after: 100871 No. 5, the Summer Palace Road, Beijing, Haidian District Patentee after: Peking University Address before: 100871 No. 5, the Summer Palace Road, Beijing, Haidian District Patentee before: Peking University Patentee before: PEKING UNIVERSITY FOUNDER GROUP Co.,Ltd. Patentee before: BEIJING FOUNDER ELECTRONICS Co.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151028 |