CN104702625B - Access request dispatching method and device in a kind of CDN network - Google Patents

Access request dispatching method and device in a kind of CDN network Download PDF

Info

Publication number
CN104702625B
CN104702625B CN201510148470.7A CN201510148470A CN104702625B CN 104702625 B CN104702625 B CN 104702625B CN 201510148470 A CN201510148470 A CN 201510148470A CN 104702625 B CN104702625 B CN 104702625B
Authority
CN
China
Prior art keywords
rank
data
idc
temperature
idc nodes
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.)
Active
Application number
CN201510148470.7A
Other languages
Chinese (zh)
Other versions
CN104702625A (en
Inventor
何广
秦建华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201510148470.7A priority Critical patent/CN104702625B/en
Publication of CN104702625A publication Critical patent/CN104702625A/en
Application granted granted Critical
Publication of CN104702625B publication Critical patent/CN104702625B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/50Queue scheduling

Abstract

The embodiment of the invention discloses access request dispatching method and device in a kind of CDN network, all IDC nodes in the CDN network, at least two storage ranks are divided into advance according to storage capacity, the different other IDC nodes of storage level are respectively used to access request of the response for the data of different temperature ranks, access request dispatching method, may comprise steps of in a kind of CDN network:Receive the access request that user is directed to target data;The data message of each temperature rank obtained according to counting in advance, determines the temperature rank of the target data;Further determine that with the set with the other IDC nodes of the corresponding storage level of temperature rank;An IDC node for being used to respond the access request is selected from identified set.The technical solution provided using the embodiment of the present invention, it is possible to reduce the frequent updating of the data in IDC nodes, lifts the usage experience of user.

Description

Access request dispatching method and device in a kind of CDN network
Technical field
The present invention relates to Internet technical field, access request dispatching method and device in more particularly to a kind of CDN network.
Background technology
With the fast development of Internet technology, many large-scale websites tend to carry out web site contents using CDN technologies Distribution.CDN, full name are Content Distribution Network, i.e. content distributing network.CDN network includes multiple IDC (Internet Data Center, Internet data center) node and dispatch server, each IDC nodes include multiple data Cache server, the data distributed by website are stored with data cache server.When user has the need for accessing website data When asking, by the scheduling of dispatch server, it directly can communicate with the less IDC nodes of cost together and communicate, obtain institute The data needed, alleviate network congestion problems, improve the accelerating website access of user, lift user experience.
A kind of existing access request dispatching method is that dispatch server receives the access request of user, according to user's need The name feature for the data to be accessed, calculates the possibility storage location of data, that is, determines access request for responding user IDC nodes, the access request of user is dispatched in identified IDC nodes.
In practical applications, the process of the access request of IDC nodes response user has two kinds determined by dispatch server Situation, a kind of situation are that the data that user needs to access are stored with the node, the data directly can be returned to use Family, another situation are not to be stored with user in the node to need the data that access, it is necessary to which the overall situation of Hui Yuan to website is deposited Server is stored up, after obtaining the data that user's needs access, is locally preserving and is returning to user.That is, IDC nodes respond The data that the access request of user returns to user are required for being locally stored.But because the storage capacity of IDC nodes is limited, In its constantly the storage request process of response user, if the data wherein stored have reached the upper limit of its storage capacity, need The data that it is stored are updated, that is, the data not being accessed for a long time are deleted, store new access request pair The data answered.Pass through existing this dispatching method, it is more likely that by the access request tune of the relatively low data of many access frequencys Spend in the less IDC nodes of storage capacity so that the data stored in this IDC nodes easily reach its storage capacity The upper limit, causes stored data frequent updating, increases back source flux expense, and the process of Hui Yuan adds response user's request Time delay, influence the usage experience of user.
The content of the invention
To solve the above problems, the embodiment of the invention discloses access request dispatching method and device in a kind of CDN network. Technical solution is as follows:
Access request dispatching method in a kind of CDN network, all IDC nodes in the CDN network, according to storage capacity At least two storage ranks are divided into advance, and the different other IDC nodes of storage level are respectively used to response and are directed to different temperature levels The access request of other data, also, rank A and B are stored for any two, if the IDC nodes that storage rank is A are deposited Energy storage power is less than the storage capacity for the IDC nodes that storage rank is B, then stores the access that rank is responded by the IDC nodes of A and ask Corresponding data temperature is asked to be superior to the corresponding data temperature level of access request that storage rank is responded by the IDC nodes of B Not;The described method includes:
Receive the access request that user is directed to target data;
The data message of each temperature rank obtained according to counting in advance, determines the temperature rank of the target data;
According to the temperature rank of the target data, determine have and the other IDC of the corresponding storage level of the temperature rank The set of node;
According to the communication cost of each IDC nodes in user and identified set, one is selected from identified set For responding the IDC nodes of the access request.
In a kind of embodiment of the present invention, the quantity of the data of each temperature rank is according to having and each temperature The storage capacity of the other IDC nodes of the corresponding storage level of rank is determined.
In a kind of embodiment of the present invention, for the n-th temperature rank, which is determined by the following formula The quantity of other data:The quantity of the data of the temperature rank is equal to Cn*Pn*Qn/Mn
Wherein, CnFor the memory capacity of the other IDC nodes of the corresponding storage level of the n-th temperature rank;PnTo preset the first parameter Value, for characterizing the maximum capacity utilization rate of the corresponding other IDC nodes of storage level of the n-th temperature rank;QnFor default second ginseng Numerical value, the probability being accessed for characterize data in the other IDC nodes of the corresponding storage level of the n-th temperature rank;MnIt is all The average value of size of data.
In a kind of embodiment of the present invention, the access request carries the area information where user, described According to the temperature rank of the target data, determine with the collection with the other IDC nodes of the corresponding storage level of temperature rank Close, including:
According to the area information where the temperature rank of the target data and user, the IDC nodes in the region are being serviced In, determine with the set with the other IDC nodes of the corresponding storage level of temperature rank.
In a kind of embodiment of the present invention, determined by following steps each in user and identified set The communication cost of IDC nodes:
According to user and the range information of each IDC nodes in identified set, the network type of network is used to match One or more of information in degree information, and identified set in the load state information of each IDC nodes, determine user with The communication cost of each IDC nodes in identified set.
Access request dispatching device in a kind of CDN network, all IDC nodes in the CDN network, according to storage capacity At least two storage ranks are divided into advance, and the different other IDC nodes of storage level are respectively used to response and are directed to different temperature levels The access request of other data, also, rank A and B are stored for any two, if the IDC nodes that storage rank is A are deposited Energy storage power is less than the storage capacity for the IDC nodes that storage rank is B, then stores the access that rank is responded by the IDC nodes of A and ask Corresponding data temperature is asked to be superior to the corresponding data temperature level of access request that storage rank is responded by the IDC nodes of B Not;Described device includes:
Access request receiving module, the access request of target data is directed to for receiving user;
Temperature rank determination module, for according to the data message for counting obtained each temperature rank in advance, determining institute State the temperature rank of target data;
IDC node set determining modules, for the temperature rank according to the target data, determine have and the temperature level The set of the not corresponding other IDC nodes of storage level;
IDC node selecting modules, for the communication cost according to each IDC nodes in user and identified set, from institute An IDC node for being used to respond the access request is selected in definite set.
In a kind of embodiment of the present invention, the quantity of the data of each temperature rank is according to having and each temperature The storage capacity of the other IDC nodes of the corresponding storage level of rank is determined.
In a kind of embodiment of the present invention, quantity determining module is further included:
The quantity determining module, for for the n-th temperature rank, determining the data of the temperature rank by the following formula Quantity:The quantity of the data of the temperature rank is equal to Cn*Pn*Qn/Mn
Wherein, CnFor the memory capacity of the other IDC nodes of the corresponding storage level of the n-th temperature rank;PnTo preset the first parameter Value, for characterizing the maximum capacity utilization rate of the corresponding other IDC nodes of storage level of the n-th temperature rank;QnFor default second ginseng Numerical value, the probability being accessed for characterize data in the other IDC nodes of the corresponding storage level of the n-th temperature rank;MnIt is all The average value of size of data.
In a kind of embodiment of the present invention, the IDC node sets determining module, is specifically used for:
According to the area information where the temperature rank of the target data and user, the IDC nodes in the region are being serviced In, determine with the set with the other IDC nodes of the corresponding storage level of temperature rank.
In a kind of embodiment of the present invention, communication cost determining module is further included,
The communication cost determining module, for according to the range information of each IDC nodes in user and identified set, The network type matching degree information of used network, and in identified set in the load state information of each IDC nodes One or more of information, determine user and the communication cost of each IDC nodes in identified set.
The technical solution provided using the embodiment of the present invention, is in advance classified the IDC nodes in CDN network, deposits It is smaller to store up the storage capacity of the low IDC nodes of rank, for responding the access request for the high data of temperature rank, because net Data in standing have obvious hot spot concentration effect, and in certain period of time, the temperature rank of data is more stable, allow difference Access request of the response for the data of corresponding temperature rank in the other IDC sets of node of storage level, it is possible to reduce number in IDC nodes According to frequent updating, save back source flux expense, reduce the time delay of response user's request, lift the usage experience of user.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of implementing procedure figure of access request dispatching method in CDN network in the embodiment of the present invention;
Fig. 2 is another implementing procedure figure of access request dispatching method in CDN network in the embodiment of the present invention;
Fig. 3 is a kind of structure diagram of access request dispatching device in CDN network in the embodiment of the present invention.
Embodiment
The application environment of access request dispatching method carries out in a kind of CDN network provided first the embodiment of the present invention Explanation.
In CDN network, all IDC nodes can be divided at least two in advance according to the storage capacity of each IDC nodes A storage rank, such as, if the storage capacity of IDC nodes is higher than a certain predetermined threshold value, it is determined as the first storage level Not, if the storage capacity of IDC nodes is less than a certain predetermined threshold value, it is determined as the second storage rank, certainly, to IDC The other division of storage level of node can be carried out by operation personnel, storage capacity automatic decision that can also be by system according to IDC.
The different other IDC nodes of storage level are respectively used to access request of the response for the data of different temperature ranks, and And rank A and B are stored for any two, if it is B that the storage capacity for the IDC nodes that storage rank is A, which is less than storage rank, IDC nodes storage capacity, then store the corresponding data temperature rank of access request that is responded by the IDC nodes of A of rank The corresponding data temperature rank of access request responded higher than storage rank by the IDC nodes of B.Store number of levels and temperature level Shuo not be identical.
Under this application environment, access request dispatching method can in a kind of CDN network that the embodiment of the present invention is provided To comprise the following steps:
Receive the access request that user is directed to target data;
The data message of each temperature rank obtained according to counting in advance, determines the temperature rank of the target data;
According to the temperature rank of the target data, determine have and the other IDC of the corresponding storage level of the temperature rank The set of node;
According to the communication cost of each IDC nodes in user and identified set, one is selected from identified set For responding the IDC nodes of the access request.
The executive agent of above-mentioned steps is the dispatch server in CDN network.
In practical applications, the frequency that different data are accessed within a period of time is different, corresponding different temperature, tool There is different temperature ranks.Data are accessed by advance statistical history, the data message of each temperature rank, and root can be obtained According to the information, it may be determined that the temperature rank of target data.Because the other IDC nodes of different storage levels are used to respond for difference The access request of the data of temperature rank, so the temperature rank according to target data, it may be determined that have and the temperature rank The set of the corresponding other IDC nodes of storage level.That is, the IDC nodes in set have consistent storage rank, should Storage rank is corresponding with the temperature rank, these IDC nodes can be used in access request of the response for target data.According to User and the communication cost of each IDC nodes in set, select an IDC node for being used to respond the access request from set, So as to complete the scheduling of access request.
The technical solution provided using the embodiment of the present invention, is in advance classified the IDC nodes in CDN network, deposits It is smaller to store up the storage capacity of the low IDC nodes of rank, for responding the access request for the high data of temperature rank, because net Data in standing have obvious hot spot concentration effect, and in certain period of time, the temperature rank of data is more stable, allow difference Access request of the response for the data of corresponding temperature rank in the other IDC sets of node of storage level, it is possible to reduce number in IDC nodes According to frequent updating, save back source flux expense, reduce the time delay of response user's request, lift the usage experience of user.
In order to make those skilled in the art more fully understand the technical solution in the embodiment of the present invention, below in conjunction with this hair Attached drawing in bright embodiment, is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that described Embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this area Those of ordinary skill's all other embodiments obtained without making creative work, belong to protection of the present invention Scope.
It is shown in Figure 1, a kind of implementation of access request dispatching method in the CDN network provided by the embodiment of the present invention Flow chart, this method may comprise steps of:
S110:Receive the access request that user is directed to target data;
When user needs to access the data of certain website, pin can be sent by the uniform resource position mark URL of the website To the access request of target data, dispatch server receives the access request, determines the target data accessed required for user, after The continuous operation for performing step S120.
S120:The data message of each temperature rank obtained according to counting in advance, determines the temperature of the target data Rank;
As it was previously stated, the storage rank of the IDC nodes in CDN network has predetermined that, the storage level of an IDC node It is not high, represent that the storage capacity of the IDC nodes is big, opposite, the storage rank of an IDC node is low, represents the IDC nodes Storage capacity is small.The different other IDC nodes of storage level are respectively used to access request of the response for the data of different temperature ranks, It is consistent with temperature number of levels to store number of levels, the how many storage ranks by IDC node divisions, a with regard to how many accordingly in advance Temperature rank.
The corresponding data temperature rank of access request that the high IDC nodes of storage rank are responded is low, that is to say, that IDC The storage capacity of node is bigger, and the corresponding data temperature rank of the access request that can be responded is lower.It is higher for temperature rank The quantity of data can do certain limitation, avoid the access request by the excessive data low for temperature rank from being dispatched to In the less IDC nodes of storage capacity, in a kind of embodiment of the present invention, the quantity of the data of each temperature rank It can be determined according to the storage capacity with the other IDC nodes of storage level corresponding with each temperature rank, specifically, being directed to N-th temperature rank, can determine the quantity of the data of the temperature rank by the following formula:
The quantity of the data of the temperature rank is equal to Cn*Pn*Qn/Mn
Wherein, CnFor the memory capacity of the other IDC nodes of the corresponding storage level of the n-th temperature rank;PnTo preset the first parameter Value, can be empirical value for characterizing the maximum capacity utilization rate of the corresponding other IDC nodes of storage level of the n-th temperature rank;Qn To preset the second parameter value, it is accessed for characterize data in the other IDC nodes of the corresponding storage level of the n-th temperature rank general Rate, can be empirical value;MnFor the average value of all size of data.
Specifically, default first parameter value can be set based on experience value, 90% is such as arranged to, presets the second parameter Value can be set based on experience value, such as be arranged to 30%, the average value of all size of data can according to actual conditions into Row is set, and such as the video data of video website, mean size can be set to 30MB.Default first parameter of different temperature ranks Value, default second parameter value, the average value of size of data can be arranged to identical value or different value according to actual conditions.
In practical applications, dispatch server can include scheduling unit and statistic unit, to the access request of user Scheduling can be performed by scheduling unit, history accessing request information is stored with the dispatching log of scheduling unit, to each heat Spending the statistics of the data message of rank can be performed by statistic unit, and statistic unit can be with the scheduling day of real-time collecting scheduling unit Will, and the data targeted to the history access request in dispatching log count, and can obtain the number of each temperature rank It is believed that breath, and the information is pushed into scheduling unit.
Statistic unit can have two ways for the statistics of the data message of each temperature rank:
First way is, statistic unit was analyzed the history access request in the cycle every certain cycle, According to the visit capacity of the targeted data of history access request in the cycle, the temperature of data is calculated, so as to according to temperature Order from high to low, determines the temperature rank of each data.Specifically definite method can be according to predetermined each heat The data proportion or quantity for spending rank are determined.
For convenience of understanding, above-mentioned specifically definite method is illustrated respectively.
Example 1, the temperature rank of each data is determined according to the data proportion of predetermined each temperature rank, it is assumed that Determine to share four temperature ranks according to storage number of levels, after obtaining the temperature of each data, according to the order of temperature from high to low, The data for determining preceding 5% temperature are high dsc data, it is determined as the first temperature rank, the data for determining 5%~15% temperature are Secondary dsc data, it is determined as the second temperature rank, the data for determining 15%~30% temperature are general data, it is determined as the 3rd temperature level Not, other data are unexpected winner data, it is determined as the 4th temperature rank.
Example 2, the temperature rank of each data is determined according to the quantity of the data of identified each temperature rank, it is also assumed that Determine to share four temperature ranks according to storage number of levels, after obtaining the temperature of each data, according to the order of temperature from high to low, Determine that temperature in preceding 10,000 data is high dsc data, it is determined as the first temperature rank, determines preceding 10,000~100,000 data to be time hot Data, it is determined as the second temperature rank, the data for determining preceding 100,000~1,000,000 are general data, it is determined as the 3rd temperature rank, other Data are unexpected winner data, it is determined as the 4th temperature rank.
The second way is that statistic unit analyzes the history access request in each cycle in different cycles, root According to the visit capacity of the targeted data of history access request in each cycle, calculate the temperature of data, so as to according to temperature from High to Low order, determines the temperature rank of each data.Specifically definite method can be according to predetermined each temperature The data proportion or quantity of rank are determined.
For convenience of understanding, this mode is illustrated.
Also assuming that and determine to share four temperature ranks according to storage rank, the first temperature rank corresponds to high dsc data, the Two temperature ranks correspond to time dsc data, and the 3rd temperature rank corresponds to general data, and the 4th temperature rank corresponds to unexpected winner data.
The temperature of every five minutes statistics data within first five minute, according to temperature in descending order, by preset ratio or The temperature rank of the data of person's quantity is set to the first temperature rank, and the temperature rank of preceding 5% data such as is set to the first temperature Rank, or the temperature rank of preceding 10,000 data is set to the first temperature rank;
Count the temperature of the interior data when previous small per hour, according to temperature in descending order, by preset ratio or The temperature rank of the data of quantity is set to the second temperature rank, and the temperature rank of preceding 10% data such as is set to the second temperature level Not, or by the temperature rank of preceding 100,000 data it is set to the second temperature rank;
Statistics is when the temperature of data in the previous day daily, according to temperature in descending order, by preset ratio or quantity The temperature ranks of data be set to the 3rd temperature rank, the temperature rank of preceding 20% data is such as set to the 3rd temperature rank, Or the temperature rank of preceding 1,000,000 data is set to the 3rd temperature rank;
The temperature rank of other data is set to the 4th temperature rank.
Wherein, if certain data there are multiple temperature ranks in different measurement periods, it is subject to highest temperature rank.
It is understood that being counted using the shorter cycle to the data message of high temperature rank, can obtain in time To high fever data message.
Certainly, both the above mode is not limited to for the statistics of the data message of each temperature rank, is also not necessarily limited to the above The described ratio of citing and numerical value, can be adjusted and count according to actual needs.
Statistic unit complete statistical work after, you can statistical result is pushed to scheduling unit, with by scheduling unit according to The data message of each temperature rank, determines the temperature rank of target data.It is understood that statistic unit is accessed according to history Request carries out the statistics of the data message of each temperature rank, may not be the total data of website, and some data may be because New reach the standard grade reason or other reasons, are never accessed by the user, if receiving the access request for these data, and There is no the information of these data in the data message for each temperature rank being previously obtained, can be directly using these data as unexpected winner Data are handled, i.e., the temperature rank of these data is set to minimum temperature rank.In addition, for minimum temperature rank Data message can not keep a record, to save the memory space of dispatch server, when receiving the access request for certain data When, if the data are not belonging to the data of higher thermal degree rank, the temperature rank of the data can be set to minimum temperature level Not.
S130:According to the temperature rank of the target data, determine have and the corresponding storage rank of the temperature rank IDC nodes set;
The temperature rank of target data is determined in step S120, can further determine to have opposite with the temperature rank The set for the other IDC nodes of storage level answered.For example the temperature rank of definite target data is the first temperature rank, with The corresponding storage rank of one temperature rank is the first storage rank, judges which IDC node is the first storage level in CDN network Not, the set with the other IDC nodes of the first storage level is determined.
In practical applications, if placement of the CDN network for IDC nodes is placed according to region, can incite somebody to action IDC nodes in each region carry out the other division of storage level respectively, are taken when in the access request for receiving user, access request During with area information where user, tool in the IDC nodes for servicing the region, can be determined according to the region where user There is the set with the other IDC nodes of the corresponding storage level of temperature rank of target data.So processing can reduce IDC nodes To the response delay of user access request.
S140:According to the communication cost of each IDC nodes in user and identified set, selected from identified set One IDC node for being used to respond the access request.
It is understood that the distance of user and IDC nodes, the network type of used network, or IDC nodes The factors such as load condition, may all influence the usage experience of user, so in a kind of embodiment of the present invention, can be with According to the range information of each IDC nodes in user and identified set, the network type matching degree information of network is used, And one or more of information in identified set in the load state information of each IDC nodes, determine user with it is identified The communication cost of each IDC nodes in set.
Certainly, IDC nodes include multiple data cache servers, when visit of some the definite IDC node for responding user , can be further according to certain algorithm, such as hash algorithm, by information such as data names, from the IDC nodes when asking request A data cache server is selected, and the IP address of the data cache server is returned into user, establishes user and data The communication connection of cache server.
The flow of access request dispatching method carries out whole description, ginseng in the CDN network provided the embodiment of the present invention As shown in Figure 2:
Assuming that the temperature rank of high dsc data is the first temperature rank, the temperature rank compared with dsc data is the second temperature level Not, the temperature rank of general data is the 3rd temperature rank, and the temperature rank of unexpected winner data is the 4th temperature rank.
Step S201, receives the access request that user is directed to target data.
Step S202, determines the temperature rank of target data:
If target data is high dsc data, step S203 is gone to, and then go to step S207;
If target data is compared with dsc data, step S204 is gone to, and then go to step S208;
If target data is general data, step S205 is gone to, and then goes to step S209;
If target data is unexpected winner data, step S206 is gone to, and then go to step S210.
S211, determines data cache server from corresponding IDC nodes.
Wherein, HC IDC shown in Fig. 2 represents the corresponding other IDC nodes of first storage level of the first temperature rank, TC IDC represents the corresponding other IDC nodes of second storage level of the second temperature rank, and LC IDC represent the 3rd temperature rank corresponding the The other IDC nodes of three storage levels, GC IDC represent the corresponding other IDC nodes of 4th storage level of the 4th temperature rank.
The technical solution provided using the embodiment of the present invention, is in advance classified the IDC nodes in CDN network, deposits It is smaller to store up the storage capacity of the low IDC nodes of rank, for responding the access request for the high data of temperature rank, because net Data in standing have obvious hot spot concentration effect, and in certain period of time, the temperature rank of data is more stable, allow difference Access request of the response for the data of corresponding temperature rank in the other IDC sets of node of storage level, it is possible to reduce number in IDC nodes According to frequent updating, save back source flux expense, reduce the time delay of response user's request, lift the usage experience of user.
Corresponding to above method embodiment, the embodiment of the present invention additionally provides access request in a kind of CDN network and dispatches Device, the application scenarios of the device are:All IDC nodes in the CDN network, according to storage capacity by advance be divided into Few two storages rank, the different other IDC nodes of storage level are respectively used to access of the response for the data of different temperature ranks Request, also, rank A and B are stored for any two, if the storage capacity for the IDC nodes that storage rank is A is less than storage Rank is the storage capacity of the IDC nodes of B, then stores the corresponding data heat of access request that rank is responded by the IDC nodes of A Degree is superior to the corresponding data temperature rank of access request that storage rank is responded by the IDC nodes of B.
Shown in Figure 3, which can include with lower module:
Access request receiving module 310, the access request of target data is directed to for receiving user;
Temperature rank determination module 320, for according to the data message for counting obtained each temperature rank in advance, determining The temperature rank of the target data;
IDC node sets determining module 330, for the temperature rank according to the target data, determines have and the heat Spend the set of the other IDC nodes of the corresponding storage level of rank;
IDC nodes selecting module 340, for the communication cost according to each IDC nodes in user and identified set, from An IDC node for being used to respond the access request is selected in identified set.
In a kind of embodiment of the present invention, the quantity of the data of each temperature rank is according to having and each temperature The storage capacity of the other IDC nodes of the corresponding storage level of rank is determined.
In a kind of embodiment of the present invention, quantity determining module can also be included:
The quantity determining module, for for the n-th temperature rank, determining the data of the temperature rank by the following formula Quantity:The quantity of the data of the temperature rank is equal to Cn*Pn*Qn/Mn
Wherein, CnFor the memory capacity of the other IDC nodes of the corresponding storage level of the n-th temperature rank;PnTo preset the first parameter Value, for characterizing the maximum capacity utilization rate of the corresponding other IDC nodes of storage level of the n-th temperature rank;QnFor default second ginseng Numerical value, the probability being accessed for characterize data in the other IDC nodes of the corresponding storage level of the n-th temperature rank;MnIt is all The average value of size of data.
In a kind of embodiment of the present invention, the IDC node sets determining module 330, is specifically used for:
According to the area information where the temperature rank of the target data and user, the IDC nodes in the region are being serviced In, determine with the set with the other IDC nodes of the corresponding storage level of temperature rank.
In a kind of embodiment of the present invention, communication cost determining module can also be included:
The communication cost determining module, for according to the range information of each IDC nodes in user and identified set, The network type matching degree information of used network, and in identified set in the load state information of each IDC nodes One or more of information, determine user and the communication cost of each IDC nodes in identified set.
The device provided using the embodiment of the present invention, is in advance classified the IDC nodes in CDN network, storage level The storage capacity of not low IDC nodes is smaller, for responding the access request for the high data of temperature rank, because in website Data there is obvious hot spot concentration effect, in certain period of time, the temperature rank of data is more stable, allows different storages Access request of the response for the data of corresponding temperature rank in the IDC sets of node of rank, it is possible to reduce data in IDC nodes Frequent updating, saves back source flux expense, reduces the time delay of response user's request, lifts the usage experience of user.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to Non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only will including those Element, but also including other elements that are not explicitly listed, or further include as this process, method, article or equipment Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that Also there are other identical element in process, method, article or equipment including the key element.
Each embodiment in this specification is described using relevant mode, identical similar portion between each embodiment Divide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for device For applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method Part explanation.
Can one of ordinary skill in the art will appreciate that realizing that all or part of step in above method embodiment is To instruct relevant hardware to complete by program, the program can be stored in computer read/write memory medium, The storage medium designated herein obtained, such as:ROM/RAM, magnetic disc, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention It is interior.

Claims (10)

1. access request dispatching method in a kind of CDN network, it is characterised in that all IDC nodes in the CDN network, are pressed At least two storage ranks are divided into advance according to storage capacity, and the different other IDC nodes of storage level are respectively used to response and are directed to The access request of the data of different temperature ranks, also, rank A and B are stored for any two, if storage rank is A's The storage capacity of IDC nodes is less than the storage capacity for the IDC nodes that storage rank is B, then stores IDC node institute of the rank for A The corresponding data temperature of access request of response is superior to the access request that storage rank is responded by the IDC nodes of B and corresponds to Data temperature rank;The described method includes:
Receive the access request that user is directed to target data;
The data message of each temperature rank obtained according to counting in advance, determines the temperature rank of the target data;
According to the temperature rank of the target data, determine have and the other IDC nodes of the corresponding storage level of temperature rank Set;
According to the communication cost of each IDC nodes in user and identified set, from identified set selecting one is used for Respond the IDC nodes of the access request.
2. according to the method described in claim 1, it is characterized in that, the quantity of the data of each temperature rank according to have with it is each The storage capacity of the other IDC nodes of the corresponding storage level of temperature rank is determined.
3. according to the method described in claim 2, it is characterized in that, be directed to the n-th temperature rank, which is determined by the following formula Spend the quantity of the data of rank:The quantity of the data of the temperature rank is equal to Cn*Pn*Qn/Mn
Wherein, CnFor the memory capacity of the other IDC nodes of the corresponding storage level of the n-th temperature rank;PnTo preset the first parameter value, For characterizing the maximum capacity utilization rate of the corresponding other IDC nodes of storage level of the n-th temperature rank;QnTo preset the second parameter Value, the probability being accessed for characterize data in the other IDC nodes of the corresponding storage level of the n-th temperature rank;MnFor all numbers According to the average value of size.
4. according to the method described in claim 1, it is characterized in that, the access request carry user where area information, The temperature rank according to the target data, determines have and the other IDC nodes of the corresponding storage level of temperature rank Set, including:
According to the area information where the temperature rank of the target data and user, in the IDC nodes for servicing the region, really The fixed set with the other IDC nodes of the corresponding storage level of temperature rank.
5. method according to any one of claims 1 to 4, it is characterised in that determine user with institute really by following steps The communication cost of each IDC nodes in fixed set:
According to the range information of each IDC nodes in user and identified set, use the network type matching degree of network One or more of information in information, and identified set in the load state information of each IDC nodes, determine user with institute really The communication cost of each IDC nodes in fixed set.
6. access request dispatching device in a kind of CDN network, it is characterised in that all IDC nodes in the CDN network, are pressed At least two storage ranks are divided into advance according to storage capacity, and the different other IDC nodes of storage level are respectively used to response and are directed to The access request of the data of different temperature ranks, also, rank A and B are stored for any two, if storage rank is A's The storage capacity of IDC nodes is less than the storage capacity for the IDC nodes that storage rank is B, then stores IDC node institute of the rank for A The corresponding data temperature of access request of response is superior to the access request that storage rank is responded by the IDC nodes of B and corresponds to Data temperature rank;Described device includes:
Access request receiving module, the access request of target data is directed to for receiving user;
Temperature rank determination module, for according to the data message for counting obtained each temperature rank in advance, determining the mesh Mark the temperature rank of data;
IDC node set determining modules, for the temperature rank according to the target data, determine have and the temperature rank phase The set of the corresponding other IDC nodes of storage level;
IDC node selecting modules, for the communication cost according to each IDC nodes in user and identified set, from determining Set in selection one be used to respond the IDC nodes of the access request.
7. device according to claim 6, it is characterised in that the quantity of the data of each temperature rank according to have with it is each The storage capacity of the other IDC nodes of the corresponding storage level of temperature rank is determined.
8. device according to claim 7, it is characterised in that further include quantity determining module:
The quantity determining module, for for the n-th temperature rank, determining the number of the data of the temperature rank by the following formula Amount:The quantity of the data of the temperature rank is equal to Cn*Pn*Qn/Mn
Wherein, CnFor the memory capacity of the other IDC nodes of the corresponding storage level of the n-th temperature rank;PnTo preset the first parameter value, For characterizing the maximum capacity utilization rate of the corresponding other IDC nodes of storage level of the n-th temperature rank;QnTo preset the second parameter Value, the probability being accessed for characterize data in the other IDC nodes of the corresponding storage level of the n-th temperature rank;MnFor all numbers According to the average value of size.
9. device according to claim 6, it is characterised in that the IDC node sets determining module, is specifically used for:
According to the area information where the temperature rank of the target data and user, in the IDC nodes for servicing the region, really The fixed set with the other IDC nodes of the corresponding storage level of temperature rank.
10. according to claim 6 to 9 any one of them device, it is characterised in that communication cost determining module is further included,
The communication cost determining module, for according to user and the range information of each IDC nodes in identified set, made With the network type matching degree information of network, and one kind in identified set in the load state information of each IDC nodes Or several information, determine user and the communication cost of each IDC nodes in identified set.
CN201510148470.7A 2015-03-31 2015-03-31 Access request dispatching method and device in a kind of CDN network Active CN104702625B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510148470.7A CN104702625B (en) 2015-03-31 2015-03-31 Access request dispatching method and device in a kind of CDN network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510148470.7A CN104702625B (en) 2015-03-31 2015-03-31 Access request dispatching method and device in a kind of CDN network

Publications (2)

Publication Number Publication Date
CN104702625A CN104702625A (en) 2015-06-10
CN104702625B true CN104702625B (en) 2018-04-13

Family

ID=53349393

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510148470.7A Active CN104702625B (en) 2015-03-31 2015-03-31 Access request dispatching method and device in a kind of CDN network

Country Status (1)

Country Link
CN (1) CN104702625B (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105391765B (en) * 2015-10-14 2018-11-09 中国联合网络通信集团有限公司 A kind of method and system of content storage
CN108347465B (en) * 2017-01-23 2021-02-02 阿里巴巴集团控股有限公司 Method and device for selecting network data center
CN107370811B (en) * 2017-07-14 2020-11-27 北京知道创宇信息技术股份有限公司 Resource distribution method of CDN (content delivery network), computing equipment and readable storage medium
CN107770283B (en) * 2017-11-08 2020-10-23 北京奇艺世纪科技有限公司 Method, device and system for controlling file downloading
CN108234632A (en) * 2017-12-29 2018-06-29 北京奇虎科技有限公司 A kind of data distributing method and device of content distributing network CDN
CN108804351B (en) * 2018-05-30 2021-10-29 郑州云海信息技术有限公司 Cache replacement method and device
CN108810144A (en) * 2018-06-14 2018-11-13 北京中飞艾维航空科技有限公司 A kind of data transmission method, server and storage medium
CN109144791B (en) * 2018-09-30 2020-12-22 北京金山云网络技术有限公司 Data unloading method and device and data management server
CN109981778B (en) * 2019-03-27 2022-09-02 百度在线网络技术(北京)有限公司 Method, device, equipment and storage medium for realizing service of content distribution network
CN111277860B (en) * 2020-01-23 2021-04-06 北京邮电大学 Method, device and equipment for caching video in mobile edge network and readable medium
CN113296924B (en) * 2020-04-28 2022-07-22 阿里巴巴集团控股有限公司 Content distribution method, device, system and storage medium
CN114422522B (en) * 2020-10-13 2024-02-13 贵州白山云科技股份有限公司 Cache distribution method, device, medium and equipment
CN115250295A (en) * 2021-04-26 2022-10-28 北京字跳网络技术有限公司 Media content processing method, device, equipment and storage medium
CN114697683A (en) * 2022-03-25 2022-07-01 腾讯音乐娱乐科技(深圳)有限公司 Intelligent scheduling method, equipment and computer program product for streaming media file

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011143946A1 (en) * 2011-01-24 2011-11-24 华为技术有限公司 Method and system for managing multilevel caches of edge server in cdn
CN102411542A (en) * 2011-10-26 2012-04-11 上海文广互动电视有限公司 Dynamic hierarchical storage system and method
CN103312776A (en) * 2013-05-08 2013-09-18 青岛海信传媒网络技术有限公司 Method and device for caching contents of videos by edge node server
CN104270463A (en) * 2014-10-21 2015-01-07 无锡云捷科技有限公司 CDN dynamic server selection method
CN104394441A (en) * 2014-11-27 2015-03-04 北京奇艺世纪科技有限公司 Video content distribution scheduling method, device and system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011143946A1 (en) * 2011-01-24 2011-11-24 华为技术有限公司 Method and system for managing multilevel caches of edge server in cdn
CN102411542A (en) * 2011-10-26 2012-04-11 上海文广互动电视有限公司 Dynamic hierarchical storage system and method
CN103312776A (en) * 2013-05-08 2013-09-18 青岛海信传媒网络技术有限公司 Method and device for caching contents of videos by edge node server
CN104270463A (en) * 2014-10-21 2015-01-07 无锡云捷科技有限公司 CDN dynamic server selection method
CN104394441A (en) * 2014-11-27 2015-03-04 北京奇艺世纪科技有限公司 Video content distribution scheduling method, device and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"视频网格中自适应热度变化的条块化存储";单芝栋;《专题技术与工程应用》;20130228;第60-64页 *

Also Published As

Publication number Publication date
CN104702625A (en) 2015-06-10

Similar Documents

Publication Publication Date Title
CN104702625B (en) Access request dispatching method and device in a kind of CDN network
CN108874640B (en) Cluster performance evaluation method and device
CN109327550B (en) Access request distribution method and device, storage medium and computer equipment
CN101500022B (en) Data access resource allocation method, system and equipment therefor
CN105337786B (en) A kind of server performance detection method, device and equipment
CN101136911B (en) Method to download files using P2P technique and P2P download system
CN106202581B (en) A kind of data search method and device
CN106888381B (en) A kind of data resource storage method and device
CN103379156B (en) Realize the mthods, systems and devices of memory space dynamic equalization
CN103347068A (en) Method for accelerating network caching based on proxy cluster
CN109672757A (en) File access method and file access processing unit
EP3465966B1 (en) A node of a network and a method of operating the same for resource distribution
CN108108384A (en) A kind of date storage method and device
CN112016030B (en) Message pushing method, device, server and computer storage medium
Yan et al. Big data driven wireless communications: A human-in-the-loop pushing technique for 5G systems
CN109982104A (en) The video of mobile awareness prefetches and caching Replacement Decision method in a kind of mobile edge calculations
CN108319598A (en) data cache method, device and system
CN112947860B (en) Hierarchical storage and scheduling method for distributed data copies
CN109165096A (en) The caching of web cluster utilizes system and method
CN108347459A (en) A kind of high in the clouds data quick storage method and device
CN106936877A (en) A kind of content distribution method, apparatus and system
CN104035807B (en) Metadata cache replacement method of cloud storage system
CN103713852B (en) A kind of information processing method, service platform and electronic equipment
CN102970349B (en) A kind of memory load equalization methods of DHT network
CN106528448A (en) Distributed caching mechanism for multi-source heterogeneous electronic commerce big data

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant