WO2010058790A1 - Dispositif de distribution de contenu, procédé de commande de distribution de contenu, programme de commande de distribution de contenu et dispositif de commande de mémoire cache - Google Patents

Dispositif de distribution de contenu, procédé de commande de distribution de contenu, programme de commande de distribution de contenu et dispositif de commande de mémoire cache Download PDF

Info

Publication number
WO2010058790A1
WO2010058790A1 PCT/JP2009/069558 JP2009069558W WO2010058790A1 WO 2010058790 A1 WO2010058790 A1 WO 2010058790A1 JP 2009069558 W JP2009069558 W JP 2009069558W WO 2010058790 A1 WO2010058790 A1 WO 2010058790A1
Authority
WO
WIPO (PCT)
Prior art keywords
content
cache
block
holding unit
waiting time
Prior art date
Application number
PCT/JP2009/069558
Other languages
English (en)
Japanese (ja)
Inventor
宏之 秦野
Original Assignee
日本電気株式会社
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 日本電気株式会社 filed Critical 日本電気株式会社
Priority to JP2010539239A priority Critical patent/JPWO2010058790A1/ja
Priority to US12/998,696 priority patent/US20110238927A1/en
Publication of WO2010058790A1 publication Critical patent/WO2010058790A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00—Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02—Addressing or allocation; Relocation
    • G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/12—Replacement control
    • G06F12/121—Replacement control using replacement algorithms
    • G06F12/126—Replacement control using replacement algorithms with special data handling, e.g. priority of data or instructions, handling errors or pinning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00—Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02—Addressing or allocation; Relocation
    • G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/12—Replacement control
    • G06F12/121—Replacement control using replacement algorithms
    • G06F12/122—Replacement control using replacement algorithms of the least frequently used [LFU] type, e.g. with individual count value

Definitions

  • the present invention relates to a system for distributing content such as video, and in particular, a content distribution apparatus, a content distribution control method, and the like, which temporarily improve the distribution performance by temporarily storing content in a cache memory and reading and distributing the content from the cache memory
  • the present invention relates to a content distribution control program.
  • the content is stored in the cache memory, and the content is distributed from the cache memory, thereby reducing the number of accesses to the disk device that stores the content and distributing the content.
  • Cache technology that improves performance is used.
  • the cache area needs to be efficiently used because the capacity of the cache memory that caches the content is smaller than the capacity of the disk device.
  • Patent Literature 1 An example of a method for efficiently using a cache area is disclosed in Patent Literature 1 and Patent Literature 2.
  • the use efficiency of the cache area is improved by replacing the content data using the expiration date of the content and the content size.
  • the content is divided into a plurality of blocks and stored in the cache memory, and the cache area is efficiently used by deleting from the cache memory in order from the block last accessed last. We are trying to improve.
  • Patent Document 1 and Patent Document 2 have the following problems.
  • Patent Document 1 The method of deleting content from the cache memory using the content expiration date described in Patent Document 1 has the following problems.
  • the cache memory when there is an access to the content A stored in the cache memory, the content A continues to be stored in the cache memory. Therefore, when only a part of the content A is accessed, the cache memory is used in a large area even though most of the cache data of the content A is unnecessary, and the use efficiency of the cache area is deteriorated. There was a problem. This deterioration in utilization efficiency has a greater effect as the content size increases.
  • the reason is that, when deleting content from the cache area, the last accessed time is the target of deletion.
  • An object of the present invention is to provide a content distribution apparatus, a content distribution control method, and a content distribution control program capable of improving the utilization efficiency of a cache area in content distribution using a cache memory.
  • a content distribution apparatus includes a content holding unit for storing content to be distributed, a cache holding unit for temporarily storing content to be distributed, and a content distribution unit for distributing content stored in the cache holding unit or the content holding unit.
  • cache control means for controlling storage and deletion of the content with respect to the cache holding means.
  • the cache control means divides the content into a plurality of blocks and sets a deletion waiting time until the contents are deleted from the cache holding means for each block. Based on the set cache control information, storage and deletion in the cache holding means are controlled for each block.
  • a content distribution control method is a content distribution control method in a content distribution apparatus for distributing content, wherein the content is distributed from content holding means for storing content or cache holding means for temporarily holding content, Are stored in a plurality of blocks, and storage and deletion in the cache holding unit are controlled for each block based on cache control information in which a deletion waiting time until deletion from the cache holding unit is set for each block.
  • a content distribution control program is a content distribution control program that operates on a computer that constitutes a content distribution apparatus that distributes content.
  • the content distribution control program temporarily stores content holding means or content that holds content in the content distribution apparatus. Cache for each block based on the cache control information in which the content is distributed from the cache holding means to be held, the content is divided into a plurality of blocks, and the deletion waiting time is set for deletion from the cache holding means for each block.
  • a process for controlling storage and deletion in the holding means is executed.
  • the content distribution system includes a content distribution device 10, a client group 20 that receives content, and a network 30.
  • the content distribution apparatus 10 includes a content distribution unit 100, a cache control unit 101, a content holding unit 102, a cache holding unit 103, a cache control information holding unit 104, and a cache control table generation unit 105.
  • the client group 20 is a terminal that receives content and has a function for connecting to a network.
  • the client group 20 will be described as having three client terminals 201a, 201b, and 201c for convenience, but the number of clients is not limited.
  • the network 30 is a network such as the Internet that connects the content distribution apparatus 10 and the client terminals 201a to 201c of the client group 20.
  • the content distribution unit 100 receives a content distribution request from each of the client terminals 201a to 201c of the client group 20. In addition, when the content specified by the content distribution request is stored in the cache holding unit 103, the content distribution unit 100 reads the content from the cache holding unit 103, and each client terminal of the client group 20 via the network 30. Delivered to 201a-201c.
  • the content distribution unit 100 instructs the cache control unit 101 to store the corresponding content in the cache holding unit 103, and the content holding unit.
  • the content is read from 102 and distributed to the client terminals 201 a to 201 c of the client group 20 via the network 30.
  • the cache control unit 101 stores the content stored in the content holding unit 102 in the cache holding unit 103 in accordance with the setting of the cache control table stored in the cache control information holding unit 104 according to an instruction from the content distribution unit 100. In addition, the cache control unit 101 determines the content of each content stored in the cache holding unit 103 according to the access state to the block of content set in the cache control table stored in the cache control information holding unit 104 and the cache deletion timer time. Delete cache in blocks.
  • the content holding unit 102 is a unit that stores distributable content, and is realized by, for example, a hard disk device including a nonvolatile memory such as a magnetic disk or a semiconductor memory.
  • the content stored in the content holding unit 102 is, for example, video content such as a movie or a drama, but is not necessarily limited to video content, and may be other types of content.
  • the cache holding unit 103 has a function as a cache memory for temporarily storing content, and holds distributable content on a region by dividing it into a plurality of blocks.
  • the cache holding unit 103 is realized by a RAM (Random Access Memory) or the like.
  • the cache control table generating unit 105 generates a cache control table 200 as information for controlling the cache held in the cache holding unit 103 for each content.
  • the cache control information holding unit 104 holds the cache control table 200 generated for each content by the cache control table generation unit 105.
  • FIG. 2 is an example of a cache control table.
  • the cache control table 200 includes a content ID 201, a block ID 202, a cache presence / absence 203, an access frequency 204, an access presence / absence 205, and a cache deletion timer time 206.
  • the content ID 201 is an ID assigned to each content.
  • the block ID 202 is an ID assigned to each block when one content is divided into a plurality of blocks, and cache control information is set for each block ID 202.
  • the cache presence / absence 203 is information indicating whether or not the block of the content corresponding to the block ID 202 has been stored in the cache holding unit 103.
  • the access frequency 204 is information indicating the access frequency for the block indicated by the block ID 202, and the number of accesses or the frequency corresponding to the number of accesses is set according to the access to the block.
  • Access presence / absence 205 is information indicating whether or not the cache of the corresponding block ID 202 is being accessed.
  • the cache deletion timer time 206 is information indicating a waiting time until data is deleted when access to the corresponding block is not performed for a predetermined time or more.
  • the cache control table 200 is generated by the cache control table generation unit 105 when content is registered in the content distribution apparatus 10, that is, in the process of storing content in the content holding unit 102, and cache control information is held as cache control information. Register in the means 104 and update as needed.
  • the cache control table generation unit 105 uses a preset rule (for example, a rule set to divide the content every certain size or time) when the process of storing the content in the content holding unit 102 is performed. Based on this, the cache control table 200 described above is generated and registered in the cache control information holding unit 104.
  • a preset rule for example, a rule set to divide the content every certain size or time
  • the administrator when storing content in the content holding unit 102, the administrator can create a cache control table 200 for the stored content and register it in the cache control information holding unit 104.
  • the cache control table generation unit 105 can be omitted.
  • FIG. 20 is a block diagram illustrating a hardware configuration of the content distribution apparatus 10.
  • the content distribution apparatus 10 can be realized by a hardware configuration similar to a general computer apparatus, and includes a CPU (Central Processing Unit) 401, a RAM (Random Access Memory), and the like.
  • a storage unit 402 (which constitutes the cache holding unit 103) used for a work area and a temporary data saving area, a communication unit 403 that transmits / receives data via the network 30, and an input / output that transmits / receives data by connecting to an external device Interface unit 404, ROM (Read Only Memory), auxiliary storage unit 405 (content holding means 102, cache control information holding) which is a hard disk device composed of a nonvolatile memory such as a magnetic disk and a semiconductor memory Configure stage 104), and a system bus 406, an output device 407 and input device 408 such as a keyboard such as a display device to be connected to each other above components.
  • a system bus 406 an output device 407 and input device 408 such as a keyboard such as a display device to be connected to each other above components
  • the content distribution apparatus 10 is a circuit component that is a hardware component such as an LSI (Large Scale Integration) incorporating a content distribution control program that executes content distribution processing, cache control processing, and cache control table generation processing.
  • LSI Large Scale Integration
  • the operation is realized by hardware, and the content distribution control program that provides the functions of the content distribution unit 100, the cache control unit 101, and the cache control table generation unit 105 is supported. It can also be realized in software by storing in the storage unit 405, loading the program into the storage unit 402 and executing it by the CPU 401.
  • the cache control table generating unit 105 When content is stored in the content holding unit 102 (step S101), the cache control table generating unit 105 generates a cache control table 200 for the stored content (step S102) and registers it in the cache control information holding unit 104 (step S103). ).
  • the cache control table generation means 105 registers a content ID 201 for identifying the stored content, divides the content into a plurality of blocks based on a predetermined blocking rule, and blocks each block. An ID 202 is assigned and a cache deletion timer time 206 is registered for each block.
  • This blocking rule indicates, for example, how the content is divided into a plurality of blocks (how to separate the contents) when the content is divided into a plurality of blocks and stored in the cache holding means 103.
  • the data size and playback time of a block are specified as a blocking rule.
  • the data size and the playback time uniquely correspond to each other, and if the content is divided at a certain playback time, the size of each block is the same.
  • the data size and playback time do not uniquely correspond, so if the content is divided at certain playback times, the size of each block will vary depending on the respective rate, When the content is divided for each fixed size, the playback time of each block differs depending on the respective rate.
  • FIG. 8 is an example of the cache control table 200 generated immediately after content registration.
  • the content is divided into six blocks with an appropriate size, and a block ID 202, cache presence / absence 203, access frequency 204, access presence / absence 205, and cache deletion timer time 206 are set for each block.
  • the cache presence / absence 203 is all “none”
  • the access frequency 204 is “0”
  • the access presence / absence 205 is “none”
  • the cache deletion timer time 206 is the initial setting value “10 minutes”. Is set.
  • the client terminals 201 a to 201 c designate the playback location of the content requested to be distributed and make a content distribution request to the content distribution apparatus 10.
  • the content distribution apparatus 10 searches the cache control table 200 for a block corresponding to the requested content and the reproduction location, and stores the block corresponding to the reproduction location of the requested content in the cache holding unit 103 or It is read from the content holding means 102 and distributed to the client terminals 201a to 201c, and the cache control table 200 is updated as necessary.
  • the playback location is, for example, a position specified by the playback time from the beginning of the content.
  • the cache control table in the cache control information holding unit 104 uses the content ID designated for distribution and the playback location as a key. 200 is searched (step S201). Then, the content distribution unit 100 determines whether or not the block corresponding to the designated reproduction location of the requested content is stored in the cache holding unit 103 (step S202).
  • the content distribution unit 100 When the block of the corresponding content is stored in the cache holding unit 103, the content distribution unit 100 reads the data of the block portion of the corresponding content from the cache holding unit 103 and distributes it to the client terminals 201a to 201c (step S203). ). Thereafter, the content distribution unit 100 updates the access frequency 204 and the cache deletion timer time 206 of the block belonging to the corresponding content in the cache control table 200 in the cache control information holding unit 104 (step S205).
  • FIG. 9 is an example of the cache control table 200.
  • the access frequency is recorded in the access frequency 204, and the cache deletion timer time 206 is set according to the frequency.
  • the cache deletion timer time is set longer as the access frequency is higher.
  • the update value of the cache deletion timer time 206 is set to “5 minutes”, and the cache deletion timer time 206 is increased by “5 minutes” every time the cache holding means 103 is accessed once.
  • the cache deletion timer time 206 may be updated by incrementing a certain time for each cache access, and the update value of the cache deletion timer time 206 may be updated for each block or according to the access frequency. It is also possible to change it.
  • a threshold value for example, 10 times
  • the update value is 5 minutes
  • the threshold value is exceeded
  • the update value is 10 minutes
  • a stage for example, the first threshold is 10 times and the second threshold is 20 times
  • the update value exceeds 5 minutes and exceeds the first threshold.
  • the update value can be set to 10 minutes
  • the second threshold value when the second threshold value is exceeded, the update value can be set to 15 minutes.
  • the content distribution unit 100 instructs the cache holding unit 103 to store the data of the block portion of the corresponding content. (Step S204). In addition, the content distribution unit 100 reads the data of the block portion of the corresponding content from the content holding unit 103 and distributes the data to the client terminals 201a to 201c (step S206).
  • the cache control unit 101 When the cache control unit 101 receives a cache storage instruction from the content distribution unit 100, the cache control unit 101 searches the cache control table 200 held in the cache control information holding unit 104 using the designated content ID and playback location as a key (step S301). Then, it is confirmed whether or not a block corresponding to the playback location of the corresponding content is registered in the cache control table 200 (step S302).
  • the cache control unit 101 stores the data of the block portion of the corresponding content in the cache holding unit 103 according to the setting of the cache control table 200. Then, the cache control table 200 is updated (step S303). That is, the cache presence / absence 203 of the corresponding block in the cache control table 200 is set to “present”.
  • FIG. 10 is an example of the cache control table 200 after the update.
  • the data of blocks 001 to 006 of the content (ID: CID001) are registered in the cache holding means 103, all the cache presence / absence information is “present”, but there is no access immediately after storage, so the access frequency 204, access presence / absence 205, and cache deletion timer time 206 are initial values.
  • the cache deletion timer time set for each block is updated as shown in FIG.
  • FIG. 9 shows the state of the cache control table 200 when the cache access is made to each block of the content represented by the cache control table 200 shown in FIG.
  • the block (ID: 001) is 10 times
  • the block (ID: 002) is 5 times
  • the block (ID: 003) is 7 times
  • the block (ID: 004) is 1 time
  • the block (ID: 005) is This indicates that there is a cache access twice, and there is no access to the block (ID: 006).
  • the cache deletion timer time 206 of each block is added with the updated value “5 minutes” for each access, the block (ID: 001) is “60 minutes”, and the block (ID: 002) is “35 minutes”.
  • the block (ID: 003) is updated to“ 45 minutes ”
  • the block (ID: 004) is updated to“ 15 minutes ”
  • the block (ID: 005) is updated to“ 20 minutes ”.
  • the initial value “10 minutes” remains unchanged.
  • the cache control unit 101 refers to the access presence / absence 205 of the cache control table 200 stored in the cache control information holding unit 104 and confirms whether the block of content cached in the cache holding unit 103 is being accessed. (Step S401). If the corresponding block is being accessed, the process proceeds to step S404.
  • the cache control unit 101 next checks whether or not the timer time set in the cache deletion timer time 206 of the cache control table 200 for the corresponding block has expired (step S402). ). If the cache deletion timer time has not expired, the process proceeds to step S404.
  • Whether the cache deletion timer time 206 of the cache control table 200 has expired is determined by comparing the elapsed time from the time when each block is stored in the cache holding means 103 or the last cache access with the cache deletion timer time 206. Whether the elapsed time has passed the cache deletion timer time 206 is determined.
  • the elapsed time from the time when it was stored in the cache holding unit 103 is compared with the cache deletion timer time 206, and the cache accessed block In this case, the elapsed time from the last cache access is compared with the cache deletion timer time 206.
  • the cache deletion timer time has expired, the cache data corresponding to the block is deleted from the cache holding means 103, and the cache presence / absence 203 for the block of the corresponding content in the cache control table 200 is set to “None” (step S403). ).
  • step S401 If the corresponding block is being accessed in step S401, if the cache deletion waiting timer time 206 has not expired in step S402, or if the processing in step S403 is completed, the processing of all blocks in the cache control table 200 is completed. If it has not been completed, the processing from step S401 to S403 is performed for the next block.
  • the cache control unit 101 performs the above-described series of processing (step S401 to step S403) for all the contents registered in the cache control table 200, and ends the processing.
  • the above-described processing by the cache control unit 101 is periodically executed at a time interval such as every minute, and the cache data in the cache control table 200 and the cache holding unit 103 is updated.
  • the content is divided into six blocks and stored. If there is no access to the block ID 006 and there is no access as it is, the cache data of the block ID 006 is deleted from the cache holding means 103 when “12 minutes” which is the time set in the cache deletion timer expires. Is done.
  • the effect of the first embodiment it is the time until the content on the cache holding means 103 is divided into a plurality of blocks, the access frequency statistics are taken for each block, and the block is deleted according to the access frequency. Since the cache deletion timer time is updated, cache control according to the popularity of content can be performed in real time. In this way, blocks with low access frequency can be efficiently deleted from the cache by leaving those with high access frequency in the cache for a longer period of time and deleting those with low access frequency from the cache holding means 103 at an early stage. It becomes possible.
  • the first embodiment it is possible to delete unnecessary blocks in the content from the cache and leave only the minimum necessary cache data, thereby improving the efficiency of use of the cache.
  • the cache hit rate can be improved as compared with the method based on the related technology, and the cache area can be effectively used.
  • the content is encoded by the hierarchical coding method.
  • the hierarchical coding scheme is an example of H.264 defined in ITU-T. H.264 / SVC.
  • the content encoded by the H.264 / SVC scheme is hierarchized as a base layer, an enhancement layer 1, and an enhancement layer 2.
  • a higher-quality video can be reproduced as the higher layers are used, but a video can be reproduced even with data of only a lower layer.
  • content encoded using up to the highest extension layer 2 can be reproduced with a large screen and high image quality.
  • the converted content can be reproduced with a medium screen and medium image quality.
  • the content encoded using only the base layer is reproduced with a small screen and low image quality, compared to the case where the enhancement layers 1 and 2 are included.
  • the data size of the content increases as it includes up to the enhancement layer 2 that is the upper layer, and decreases only in the base layer that is the lower layer.
  • the difference from the first embodiment is that the content is divided not according to the size or playback time but according to the encoding hierarchy.
  • the encoding is performed when storing in the cache using this feature.
  • Each layer is divided into blocks, and the cache deletion timer time is set shorter for higher layer blocks.
  • FIG. 11 shows an example of the cache control table 200 generated by the cache control table generation means 105 in the second embodiment.
  • the content is composed of three layers of a base layer (lower layer), an extension layer 1 (middle layer), and an extension layer 2 (upper layer), and the base layer has a cache deletion timer time 206. “60 minutes”, the extended 1 layer is set to “30 minutes”, and the extended 2 layer is set to “10 minutes”, and the cache deletion timer time 206 is shorter as the upper layer is set. Also, FIG. 11 shows the contents in a state where there is no access immediately after registration in the cache holding means 103, the cache presence / absence information is all “present”, the access frequency 204, the access presence / absence 205, and the cache deletion timer time 206. Each has an initial value.
  • the cache deletion timer time 206 is set to be updated by increment of “5 minutes” every time the cache holding unit 103 is accessed by the cache, the basic layer block (ID: 001) is updated twice.
  • the timer time 206 is updated to “70 minutes” and “15 minutes”, respectively.
  • the initial value “30 minutes” remains unchanged.
  • the content is divided into blocks for each layer to generate the cache control table 200.
  • Other content storage processing, content distribution processing, cache storage processing, and cache deletion processing are as follows. Since it is the same as that of the first embodiment, description thereof is omitted.
  • the cache deletion timer time 206 is updated every time the cache holding means 103 is accessed for each block of each layer.
  • a different update value can be set for each layer of each block.
  • the update values are set such that the base layer is “10 minutes”, the extension layer 1 is “5 minutes”, and the extension layer 2 is “3 minutes”. In this way, if the update value is changed for each layer, the block of the layer that is considered to have a large data size and low access frequency will be deleted from the cache holding means 103 earlier, and the use efficiency of the cache will be further improved. Can do.
  • the cache hit rate is determined when a block whose cache deletion timer time has elapsed after the access is lost is deleted from the cache holding unit 103.
  • the amount of cache data can be gradually reduced while maintaining The cache memory utilization efficiency can be improved along with the improvement of the cache hit rate.
  • the content is divided into a plurality of blocks according to the encoding layer, blocks of a layer having a high access frequency and a small data size are left in the cache for a longer period of time. Therefore, it is possible to delete a layer block having a low data size and a large data size from the cache at an early stage, thereby further improving the utilization efficiency of the cache memory.
  • content is divided into a plurality of blocks according to the encoding hierarchy (layer) as in the second embodiment described above, and further divided into a plurality of blocks in each layer.
  • the cache memory utilization efficiency is further improved.
  • FIG. 13 shows an example of the cache control table 200 generated by the cache control table generation means 105 according to the third embodiment.
  • the content is composed of three layers, each layer is further divided into three blocks, and a cache deletion timer time is set for each block.
  • the cache control table generating unit 105 divides the content into each layer and further divides them into a plurality of blocks, for example, based on the data size and reproduction time of the block. Is divided into a plurality of blocks based on a predetermined blocking rule.
  • the content is composed of three layers of a basic layer (lower layer), an extended layer 1 (middle layer), and an extended layer 2 (upper layer), and each layer is further divided into three blocks.
  • the cache deletion timer time is set for each block.
  • the three basic layer blocks have the cache deletion timer time 206 set to “60 minutes”, the three extended layer 1 blocks are set to “30 minutes”, and the three extended layer 2 blocks are set to “10 minutes”.
  • the cache deletion timer time 206 is shorter for the layers.
  • FIG. 13 shows the contents in a state where there is no access immediately after registration in the cache holding means 103, the cache presence / absence information is all “present”, the access frequency 204, the access presence / absence 505, and the cache deletion timer time 206. Each has an initial value.
  • the cache deletion timer time 206 is set to be updated by adding “5 minutes” every time the cache holding unit 103 is accessed, the basic layer block (ID: 001) is accessed twice.
  • the access to the enhancement layer 1 block (ID: 005) and the enhancement layer 2 block (ID: 007) is made once, the block (ID: 001) in the cache control table 200 shown in FIG.
  • the cache deletion timer time 206 of the block (ID: 005) and the block (ID: 007) is updated to “70 minutes”, “35 minutes”, and “15 minutes”, respectively.
  • the cache control table 200 is generated in which the content is divided into blocks for each layer, and further, the blocks for each layer are divided into a plurality of blocks for each predetermined data size or predetermined reproduction time.
  • the other content storage processing, content distribution processing, cache storage processing, and cache deletion processing are the same as those in the first embodiment, and a description thereof will be omitted.
  • the cache deletion timer time 206 may be updated by incrementing a certain time every cache access, and the update value of the cache deletion timer time 206 may be updated for each block or access. It is also possible to change according to the magnitude of the frequency.
  • the example of the cache control table 200 shown in FIG. 15 shows an example in which the timer coefficient indicating the update value of the cache deletion timer time 206 is set to a different value for each layer.
  • the initial value of the cache deletion timer time 206 is “10 minutes” for all blocks.
  • the timer coefficient is set so that the cache deletion timer time 206 becomes larger as the lower layer is expected to have more accesses.
  • the timer coefficient “6” is set for the base layer
  • “4” is set for the extension 1 layer
  • “2” is set for the extension 2 layer.
  • 6 minutes, 4 minutes and 2 minutes are added 6 minutes, 4 minutes and 2 minutes respectively.
  • the lower layer where more accesses are expected is controlled to exist in the cache holding unit 103 for a longer time.
  • the number of blocks may be different for each layer according to the expected number of accesses. For example, the number of blocks in a layer (basic layer) that is frequently accessed is made larger than those in other layers (extended layers 1 and 2). By doing so, the utilization efficiency of the cache memory can be improved.
  • the cache hit rate can be further improved as compared to the second embodiment, and the cache memory utilization efficiency can be improved. Can be further improved.
  • This fourth embodiment is different from the above-described embodiment in that the content is divided into a plurality of blocks according to the format of data included in the content.
  • FIG. 16 shows an example of the cache control table 200 generated by the cache control table generation means 105 according to the fourth embodiment.
  • the text format portion, the audio format portion, and the video format portion of the data included in the content are divided into two blocks.
  • the cache holding means is longer for data that is expected to be accessed more. 103 to be present.
  • FIG. 16 shows the cache control table 200 in the initial state in which the content is stored in the cache holding means 103, and the access frequency 204 and the cache deletion timer time 206 of each block are initial values.
  • a timer coefficient indicating an updated value of the cache deletion timer time 206 is set for each block.
  • the timer coefficient of the block corresponding to the text format is “5”
  • the timer coefficient of the block corresponding to the audio and video format is “3” and “2”, respectively.
  • FIG. 17 shows that there are four cache accesses for the text block (ID: 001-1) and three cache accesses for the block (ID: 001-2), and twice for the voice block (ID: 002-1).
  • the state of the cache control table 200 when there is one cache access for (ID: 002-2) and one cache access for the video block (ID: 003-1) is shown.
  • the timer coefficient is “5 minutes”, “3 minutes”, and “2 minutes” for each of text, audio, and video
  • the cache deletion timer time 206 of each block is updated as shown in the figure. Yes.
  • the cache deletion timer time 206 remains the initial value of “10 minutes”.
  • the content is divided into a plurality of blocks according to the format of the data included in the content, and the cache control is performed for each block.
  • a block of data that remains in the period cache and is accessed less frequently can be deleted from the cache at an early stage, and the utilization efficiency of the cache memory can be improved.
  • This fifth embodiment is different from the above-described embodiment in that the content is divided into a plurality of blocks according to the content (program content) included in the content such as a program.
  • FIG. 18 shows an example of the cache control table 200 generated by the cache control table generation means 105 according to the fifth embodiment.
  • program 1, program 2, and program 3, which are program contents included in the content, are each divided into two blocks.
  • FIG. 18 shows the cache control table 200 in the initial state in which the content is stored in the cache holding means 103, and the access frequency 204 and the cache deletion timer time 206 of each block are initial values.
  • a timer coefficient indicating an updated value of the cache deletion timer time 206 is set for each block.
  • the timer coefficient of the block corresponding to program 1 is “5”
  • the timer coefficients of the blocks corresponding to program 2 and program 3 are “3” and “2”, respectively.
  • FIG. 19 shows that there is a cache access three times for the block (ID: 001-1) of program 1 and one time for the block (ID: 001-2), and twice for the block of audio (ID: 002-1).
  • the figure shows the state of the cache control table 200 when there is one cache access for the video block (ID: 003-1).
  • the timer coefficient is “5 minutes”, “3 minutes”, and “2 minutes” for each of text, audio, and video
  • the cache deletion timer time 206 of each block is updated as shown in the figure. Yes.
  • the cache block timer time 206 remains at the initial value of “10 minutes” because there is no cache access for the audio block (ID: 003-2) and the video block (ID: 003-2). is there.
  • the content is divided into a plurality of blocks for each content such as a program included in the content, and cache control is performed for each block.
  • a block of a program that remains in the period cache and has a low access frequency can be deleted from the cache at an early stage, and the use efficiency of the cache memory can be improved.
  • the present invention can be applied to the use of distributing video content such as broadcast programs and movies via a network.
  • the present invention can be applied to a content distribution system that has a large-scale subscriber requiring high distribution performance and distributes popular content.
  • the content is not limited to video, and can be applied to various types of content distribution services such as music and games.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Transfer Between Computers (AREA)
  • Memory System Of A Hierarchy Structure (AREA)

Abstract

L'objectif est de résoudre le problème concernant la distribution de contenu à l'aide d'une mémoire cache ayant une capacité limitée, ce par quoi le contenu entier est stocké dans la mémoire cache même lorsqu'un accès est fait uniquement à une partie du contenu, et ainsi l'efficacité d'utilisation de la mémoire cache est médiocre. Ce dispositif de distribution de contenu comprend : un moyen de rétention de contenu (102) qui stocke un contenu devant être distribué ; un moyen de rétention en mémoire cache (103) qui stocke temporairement le contenu devant être distribué ; un moyen de distribution de contenu (100) qui distribue le contenu stocké dans le moyen de rétention en mémoire cache ou le moyen de rétention de contenu ; et un moyen de commande de mémoire cache (101) qui commande le stockage et la suppression de contenu par rapport au moyen de rétention en mémoire cache. Le moyen de commande de mémoire cache (101) découpe le contenu en de multiples blocs, et commande le stockage et la suppression par rapport au moyen de rétention en mémoire cache sur une base bloc par bloc sur la base d'informations de commande de mémoire cache qui règlent un temps d'attente de suppression qui est le temps jusqu'à ce que chacun desdits blocs soit supprimé du moyen de rétention en mémoire cache.
PCT/JP2009/069558 2008-11-21 2009-11-18 Dispositif de distribution de contenu, procédé de commande de distribution de contenu, programme de commande de distribution de contenu et dispositif de commande de mémoire cache WO2010058790A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2010539239A JPWO2010058790A1 (ja) 2008-11-21 2009-11-18 コンテンツ配信装置、コンテンツ配信制御方法、コンテンツ配信制御プログラム、キャッシュ制御装置
US12/998,696 US20110238927A1 (en) 2008-11-21 2009-11-18 Contents distribution device , contents distribution control method, contents distribution control program and cache control device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2008-298242 2008-11-21
JP2008298242 2008-11-21

Publications (1)

Publication Number Publication Date
WO2010058790A1 true WO2010058790A1 (fr) 2010-05-27

Family

ID=42198229

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2009/069558 WO2010058790A1 (fr) 2008-11-21 2009-11-18 Dispositif de distribution de contenu, procédé de commande de distribution de contenu, programme de commande de distribution de contenu et dispositif de commande de mémoire cache

Country Status (3)

Country Link
US (1) US20110238927A1 (fr)
JP (1) JPWO2010058790A1 (fr)
WO (1) WO2010058790A1 (fr)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012081720A1 (fr) * 2010-12-13 2012-06-21 日本電気株式会社 Dispositif, système, programme et procédé de gestion de données
WO2012089044A1 (fr) * 2010-12-31 2012-07-05 华为技术有限公司 Procédé et appareil de partage de mémoire cache pour un réseau de distribution de contenu
JP2012195854A (ja) * 2011-03-17 2012-10-11 Oki Networks Co Ltd コンテンツ配信サーバ、コンテンツ配信システム及びコンテンツ配信プログラム
JP2014153754A (ja) * 2013-02-05 2014-08-25 Ntt Data Corp 中継装置、中継方法、中継プログラム
JP2014225125A (ja) * 2013-05-16 2014-12-04 日本電信電話株式会社 通信制御システム及び方法、並びにキャッシュサーバ
JP2015106188A (ja) * 2013-11-28 2015-06-08 富士通株式会社 データ配信装置及びデータ配信方法
JP2015172897A (ja) * 2014-03-12 2015-10-01 日本電気株式会社 バッファキャッシュ管理装置、バッファキャッシュ管理方法、及び、バッファキャッシュ管理プログラム
JP2015172862A (ja) * 2014-03-12 2015-10-01 日本電気株式会社 データライフサイクルを制御する情報処理装置、データライフサイクル制御方法、及びそのためのプログラム
CN110807009A (zh) * 2019-11-06 2020-02-18 湖南快乐阳光互动娱乐传媒有限公司 文件处理方法及装置
KR20210131601A (ko) * 2020-04-24 2021-11-03 주식회사 케이티 트래픽 적응형 캐싱 방법 및 그 장치

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5408257B2 (ja) * 2009-07-22 2014-02-05 日本電気株式会社 コンテンツ配信システム、コンテンツ配信方法、コンテンツ配信プログラム
EP2532137B1 (fr) * 2010-02-05 2015-08-12 Telefonaktiebolaget L M Ericsson (PUBL) Procédé et entité de n ud pour amélioration de réseau de distribution de contenu
JP5661313B2 (ja) * 2010-03-30 2015-01-28 キヤノン株式会社 記憶装置
EP2634704A1 (fr) * 2010-10-29 2013-09-04 Nec Corporation Système de contrôle de stockage de données, procédé de contrôle de stockage de données et programme de contrôle de stockage de données
JP2012222504A (ja) * 2011-04-06 2012-11-12 Sony Corp 情報処理装置及び方法、並びにプログラム
US9804971B2 (en) * 2012-01-17 2017-10-31 International Business Machines Corporation Cache management of track removal in a cache for storage
US9086957B2 (en) 2012-08-02 2015-07-21 International Business Machines Corporation Requesting a memory space by a memory controller
US10229043B2 (en) 2013-07-23 2019-03-12 Intel Business Machines Corporation Requesting memory spaces and resources using a memory controller
US9710381B2 (en) 2014-06-18 2017-07-18 International Business Machines Corporation Method and apparatus for cache memory data processing

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000209258A (ja) * 1999-01-13 2000-07-28 Mitsubishi Electric Corp 時系列デ―タ蓄積配信システム
JP2000357113A (ja) * 1999-06-14 2000-12-26 Just Syst Corp 情報処理装置、情報処理方法、およびその方法をコンピュータに実行させるプログラムを記録したコンピュータ読み取り可能な記録媒体
JP2001313919A (ja) * 2000-04-28 2001-11-09 Toshiba Corp コンテンツ管理方法、コンテンツ管理システムおよび記憶媒体
JP2006172296A (ja) * 2004-12-17 2006-06-29 Hitachi Software Eng Co Ltd キャッシュ削除方法及びコンテンツ中継サーバ

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09265429A (ja) * 1996-01-23 1997-10-07 Fujitsu Ltd データ配信装置、記憶装置とその制御方法およびデータ転送システム
EP1095373A2 (fr) * 1998-05-15 2001-05-02 Storage Technology Corporation Procede de mise en antememoire pour blocs de donnees de taille variable
US6654766B1 (en) * 2000-04-04 2003-11-25 International Business Machines Corporation System and method for caching sets of objects
JP2002207620A (ja) * 2001-01-10 2002-07-26 Toshiba Corp ファイルシステム及び該システムにおけるデータキャッシング方法
JP2007011565A (ja) * 2005-06-29 2007-01-18 Sony Corp 記録装置および方法、プログラム並びにプログラム記録媒体
US20120158884A1 (en) * 2009-08-31 2012-06-21 Nec Corporation Content distribution device, content distribution method, and program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000209258A (ja) * 1999-01-13 2000-07-28 Mitsubishi Electric Corp 時系列デ―タ蓄積配信システム
JP2000357113A (ja) * 1999-06-14 2000-12-26 Just Syst Corp 情報処理装置、情報処理方法、およびその方法をコンピュータに実行させるプログラムを記録したコンピュータ読み取り可能な記録媒体
JP2001313919A (ja) * 2000-04-28 2001-11-09 Toshiba Corp コンテンツ管理方法、コンテンツ管理システムおよび記憶媒体
JP2006172296A (ja) * 2004-12-17 2006-06-29 Hitachi Software Eng Co Ltd キャッシュ削除方法及びコンテンツ中継サーバ

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5849969B2 (ja) * 2010-12-13 2016-02-03 日本電気株式会社 データ管理装置、システム、プログラム、および、方法
WO2012081720A1 (fr) * 2010-12-13 2012-06-21 日本電気株式会社 Dispositif, système, programme et procédé de gestion de données
CN103262051A (zh) * 2010-12-13 2013-08-21 日本电气株式会社 数据管理设备、系统、程序和方法
WO2012089044A1 (fr) * 2010-12-31 2012-07-05 华为技术有限公司 Procédé et appareil de partage de mémoire cache pour un réseau de distribution de contenu
JP2012195854A (ja) * 2011-03-17 2012-10-11 Oki Networks Co Ltd コンテンツ配信サーバ、コンテンツ配信システム及びコンテンツ配信プログラム
JP2014153754A (ja) * 2013-02-05 2014-08-25 Ntt Data Corp 中継装置、中継方法、中継プログラム
JP2014225125A (ja) * 2013-05-16 2014-12-04 日本電信電話株式会社 通信制御システム及び方法、並びにキャッシュサーバ
JP2015106188A (ja) * 2013-11-28 2015-06-08 富士通株式会社 データ配信装置及びデータ配信方法
JP2015172897A (ja) * 2014-03-12 2015-10-01 日本電気株式会社 バッファキャッシュ管理装置、バッファキャッシュ管理方法、及び、バッファキャッシュ管理プログラム
JP2015172862A (ja) * 2014-03-12 2015-10-01 日本電気株式会社 データライフサイクルを制御する情報処理装置、データライフサイクル制御方法、及びそのためのプログラム
CN110807009A (zh) * 2019-11-06 2020-02-18 湖南快乐阳光互动娱乐传媒有限公司 文件处理方法及装置
CN110807009B (zh) * 2019-11-06 2022-04-26 湖南快乐阳光互动娱乐传媒有限公司 文件处理方法及装置
KR20210131601A (ko) * 2020-04-24 2021-11-03 주식회사 케이티 트래픽 적응형 캐싱 방법 및 그 장치
KR102450951B1 (ko) 2020-04-24 2022-10-05 주식회사 케이티 트래픽 적응형 캐싱 방법 및 그 장치

Also Published As

Publication number Publication date
US20110238927A1 (en) 2011-09-29
JPWO2010058790A1 (ja) 2012-04-19

Similar Documents

Publication Publication Date Title
WO2010058790A1 (fr) Dispositif de distribution de contenu, procédé de commande de distribution de contenu, programme de commande de distribution de contenu et dispositif de commande de mémoire cache
US8812791B2 (en) System and method of selectively caching information based on the interarrival time of requests for the same information
US20080215663A1 (en) Information distribution system, information distributing method, node, and recording medium
WO2011024949A1 (fr) Dispositif de distribution de contenu, procédé de distribution de contenu et programme
JP2006031480A (ja) 情報処理システム及び情報処理方法、並びにコンピュータプログラム
TW201717026A (zh) 用於逐頁記憶體通道交錯之系統及方法
TW201729113A (zh) 使用滑動臨限值位址用於記憶體通道交錯之系統及方法
JP5094388B2 (ja) 拡張可能な情報流通システム用のキャッシュメモリ
TW201717025A (zh) 用於逐頁記憶體通道交錯之系統及方法
CN103078810A (zh) 一种高效率富媒体展现系统和方法
CN102855909B (zh) 一种批量动态加载视频片头的方法
CN101330594B (zh) 对等网络视频点播媒体的存储方法及其媒体点播系统
CN110895515A (zh) 内存缓存管理方法、多媒体服务器及计算机存储介质
US10356175B2 (en) Request multiplexing
CN111694765A (zh) 一种面向移动应用特征的非易失性内存文件系统多粒度空间管理方法
CN101848366A (zh) Iptv系统中时移分片文件的归档及节目播放方法和设备
KR101128293B1 (ko) 캐시 조각 획득시간 기반의 노드 전환을 이용하는 컨텐츠 분산 저장형 멀티미디어 스트리밍 시스템 및 방법
JP5353567B2 (ja) 情報処理システム、情報処理装置、ノード装置及びプログラム並びに情報処理方法
CN101594477A (zh) 一种超长字幕渲染的处理系统
JP2005252402A (ja) コンテンツ記録システム及びコンテンツ記録方法、並びにコンピュータ・プログラム
CN115809263A (zh) 数据处理方法、装置、设备及存储介质
JP2002149352A (ja) データ記憶制御方法、データ記憶制御装置及びデータ記憶制御プログラムを格納した記録媒体
CN1559037A (zh) 一种使数据单元流入终端的备份交换机
CN111506843B (zh) 一种图片加载方法、系统及电子设备和存储介质
CN114866556B (zh) 一种服务器资源请求方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 09827571

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2010539239

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 12998696

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 09827571

Country of ref document: EP

Kind code of ref document: A1