CN109471875A - Based on data cached temperature management method, server and storage medium - Google Patents
Based on data cached temperature management method, server and storage medium Download PDFInfo
- Publication number
- CN109471875A CN109471875A CN201811114772.2A CN201811114772A CN109471875A CN 109471875 A CN109471875 A CN 109471875A CN 201811114772 A CN201811114772 A CN 201811114772A CN 109471875 A CN109471875 A CN 109471875A
- Authority
- CN
- China
- Prior art keywords
- data
- notebook
- temperature
- queue
- management method
- 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.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The present embodiments relate to hot spot data identification technology fields, disclose a kind of based on data cached temperature management method, server and storage medium.When this method includes the data in hit caching, judge whether this access interval of the notebook data of hit is more than or equal to preset interval；Wherein, the time interval being divided between this access between this access time of notebook data and previous access time；If this access interval is more than or equal to preset interval, this temperature of successively decreasing of notebook data is calculated according to the preset temperature formula that successively decreases；The hot value of notebook data is successively decreased to obtain this hot value of notebook data according to this temperature of successively decreasing of notebook data；Target data queue belonging to notebook data is determined according to this hot value of notebook data；When the data queue that notebook data is currently located is not the target data queue belonging to it, notebook data is transferred to the target data queue belonging to it.So as to more accurately identify dsc data, buffer efficiency is improved.
Description
Technical field
It is the present embodiments relate to hot spot data identification technology field, in particular to a kind of based on data cached temperature pipe
Reason method, server and storage medium.
Background technique
In storage system operation, constantly there are data to be buffered, buffer area storage medium can be gradually occupied full, therefore how
Lower grade legacy data is replaced away from buffer area, to cache new data, to guarantee that entire caching system data are read
The hit rate taken is an Important Problems of caching system.
In the prior art, LRU (Least Recently Used, least recently used) algorithm is generally basede on to be cached
Displacement.In this kind of caching replacement method, a doubly linked list can be safeguarded, current data cached letter is safeguarded in doubly linked list
Breath, when new data enters caching, can be inserted into chained list head, whenever cache hit (i.e. data cached accessed), then will
The data are moved to chained list head, abandon the data of chained list tail portion when chained list is full.Specifically, there is maintenance in chained list
Map, when new data is inserted into chained list head, the reference of new data can be put into map.It is logical first whenever needing using caching
It crosses key to search in map, the data of hit is moved to chained list head after hit caching, by chained list tail when chained list is full
The data in portion abandon, and delete corresponding data in map.Each node of doubly linked list has prev and next, in movement
When data, it is only necessary to which the next attribute assignment the prev node of the node is the next node of the node, while the node
Next node prev attribute assignment be the node prev node, and the node is put into chained list head.Therefore,
When data cached hit, hiting data can be replaced from current location to chained list head, it, can be from when needing to eliminate legacy data
Chained list tail portion carries out superseded.Being the most recently used data can be protected, and is not used by always and time longest in the buffer
Data can be eliminated, so achieve the purpose that eliminate least recently used data cached.
At least there are the following problems in the prior art for inventor's discovery: secondary by accessing in some caching replacement methods
The temperature of several pairs of data counts, and dsc data is put into dsc data queue, and cold data is put into cold data queue, this kind displacement
The problem of method can may be removed to a certain extent to avoid dsc data caused by some instantaneous a large amount of discrete access requests.
But existing method of replacing still has several drawbacks, can not more accurately eliminate the few data of amount of access.
Summary of the invention
Being designed to provide for embodiment of the present invention is a kind of based on data cached temperature management method, the operation heat
The server of management method and the storage medium of the storage temperature management method are spent, by this access interval to data temperature
Successively decrease, so as to the dsc data that more accurately identification access is frequent, the continuous access time is long, and then it is few to eliminate amount of access
Cold data, be conducive to improve buffer efficiency.
In order to solve the above technical problems, embodiments of the present invention provide it is a kind of based on data cached temperature manager
Method, comprising: when hitting the data in caching, judge this access interval of the notebook data of hit whether more than or equal to pre-
If interval；Wherein, it is described this access between be divided between this access time of the notebook data and previous access time when
Between be spaced；If this described access interval is more than or equal to the preset interval, successively decrease formula meter according to preset temperature
Calculation obtains this temperature of successively decreasing of the notebook data；According to this temperature of successively decreasing of the notebook data to the temperature of the notebook data
Value is successively decreased to obtain this hot value of the notebook data；The notebook data is determined according to this hot value of the notebook data
Affiliated target data queue；When the data queue that the notebook data is currently located is not the target data queue belonging to it,
The notebook data is transferred to the target data queue belonging to it.
Embodiments of the present invention additionally provide a kind of server, comprising: at least one processor；And with it is described extremely
The memory of few processor communication connection；Wherein, the memory, which is stored with, to be executed by least one described processor
Instruction, described instruction is executed by least one described processor, so that at least one described processor is able to carry out such as preceding institute
State based on data cached temperature management method.
Embodiments of the present invention additionally provide a kind of storage medium, are stored with computer program, the computer program
It realizes when being executed by processor as previously described based on data cached temperature management method.
Embodiment of the present invention in terms of existing technologies, when calculating the hot value of the data in caching, judges to order
In this access interval of notebook data whether be more than or equal to preset interval, be more than or equal at this access interval pre-
If this temperature of successively decreasing of notebook data is calculated according to the preset temperature formula that successively decreases when interval, then according to the sheet of notebook data
Secondary temperature of successively decreasing successively decreases the hot value of notebook data to obtain this hot value of notebook data, and according to this heat of notebook data
Angle value determines target data queue belonging to notebook data, is not the number of targets belonging to it in the data queue that notebook data is currently located
When according to queue, notebook data is transferred to the target data queue belonging to it.By the heat for being spaced biggish data to this access
Angle value is gradually successively decreased, can be according to data compared to the temperature management method of existing least recently used algorithm etc.
Access duration updates data temperature, and then helps more accurately to identify access frequency height and continuous access time
Long hot spot data is conducive to improve caching service efficiency.
As one embodiment, the temperature is successively decreased formula are as follows: is successively decreased this temperature of successively decreasing=unit gap M*
Reference value；Wherein, M is the integral multiple at this access interval and unit gap.In this way, this access is spaced the heat of longer data
Angle value is successively decreased faster, is conducive to quickly eliminate temperature in reduced data.
As one embodiment, the reference value of successively decreasing of the unit gap is based on single reference temperature value added and is set
It is fixed.
As one embodiment, the ratio of the successively decrease reference value and the single reference temperature value added of the unit gap
∈ [5%, 20%].
As one embodiment, described this hot value according to the notebook data determines target belonging to the notebook data
Data queue specifically includes: judging whether this hot value of the notebook data is more than or equal to preset hot pixel threshold；?
When this hot value of the notebook data is more than or equal to preset hot pixel threshold, target data team belonging to the notebook data
It is classified as dsc data queue, when this hot value of the notebook data is less than the hot pixel threshold, the number of targets of the notebook data
It is cold data queue according to queue.
It is described based on data cached temperature management method further include: according in the caching as one embodiment
The whole temperature state dynamic of data adjusts the size of the dsc data queue and cold data queue.
It is described based on data cached temperature management method as one embodiment further include: in miss caching
When data, the data of miss are inserted into the cold data queue, and record this access time of the data of the miss,
And the data hot value of the miss is initialized.
As one embodiment, the data queue of the caching is provided with data expired time；It is current in the system of caching
When the interval of the previous access time of data in time and the caching is greater than the data expired time, by expired data
It is deleted from the caching.So as to effectively remove long-term not visited data in caching.
Detailed description of the invention
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element in attached drawing with same reference numbers label are expressed as similar element, remove
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is the flow chart based on data cached temperature management method of first embodiment according to the present invention；
Fig. 2 is the structural block diagram of the server of third embodiment according to the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Each embodiment be explained in detail.However, it will be understood by those skilled in the art that in each embodiment party of the present invention
In formula, in order to make the reader understand this application better, many technical details are proposed.But even if without these technical details
And various changes and modifications based on the following respective embodiments, the application technical solution claimed also may be implemented.
The first embodiment of the present invention is related to a kind of based on data cached temperature management method, can be applied to server
Deng cache management system.Referring to Fig. 1, the present embodiment based on data cached temperature management method include step 101 to
Step 108.
In the present embodiment, hot value can be divided to multiple Heat ranges, and multiple data teams are arranged according to Heat range
Column, for example, data temperature is divided into two Heat ranges according to hot value, corresponding data queue is respectively dsc data queue
It is so without being limited thereto with cold data queue, in practical applications, three or more Heat ranges can also be marked off, thus
The data queue of three or more corresponding different Heat ranges.Data in caching are stored in corresponding data queue,
Data queue can use LRU chained list, and the map of a thread-safe can be safeguarded in chained list, and data queue can also be arranged simultaneously
Send out section, queue maximum length etc..
Step 101: judge whether the data in hit caching, if the data in hit caching, then follow the steps 102, if
Data in miss caching, then follow the steps 102.
Step 102: when the data of miss being inserted into cold data queue, and recording this access of data of miss
Between, and the data hot value of the miss is initialized.
Step 103: judge whether this access interval of the notebook data of hit is more than or equal to preset interval, if this
Access interval is more than or equal to preset interval, thens follow the steps 104, otherwise, if this access interval is less than preset interval,
Execute step 106.Wherein, it is divided between the time between this access time of notebook data and previous access time between this access
Every.
In step 101~step 103, when receiving read request, judge whether this read request is buffered hit, such as not
It is buffered hit, then can search data in exterior storage medium, and the data found are put into caching.In hit caching
Data when, the data corresponding with this read request being hit in caching are known as notebook data, and notebook data this is calculated
Access interval, and determine whether to successively decrease to this hot value of notebook data according to this access time interval.Specifically, when
When requesting the corresponding data of some key, can first judge the key with the presence or absence of dsc data queue, judge the key whether cold again
Data queue, if the key, in some data queue, which is buffered hit, if the key not in any data queue,
Then the read request is not buffered hit, at this point, then by the corresponding data of the read request (i.e. the data of miss) from external storage
Medium is put into caching, that is, is inserted into cold data queue, and records this access time of the data of the miss, in addition, simultaneously
Data hot value initialization to miss, such as 1 is added to the data hot value of miss.
Wherein, when the data in caching are hit every time, it can recorde timestamp when hit, this access interval is
Time interval between the timestamp of this access and the timestamp of previous access, the previous access interval of notebook data can be similar
It calculates, details are not described herein again.The access interval of notebook data is bigger, indicates that visiting frequency of the notebook data in the access interval is got over
It is small, when several access intervals of notebook data are in increase tendency, indicate that the visiting frequency of notebook data gradually decreases, and data
Practical temperature is related to its visiting frequency, i.e. visiting frequency reduction shows that the temperature of data is reducing.According to temporal locality, one
Just when accessed, then the item data may be accessed again in the recent period, but there are also data, at one section for item data
Interior amount of access is larger, and hot value may be very high, and the amount of access within the next long period may greatly reduce,
Hot spot data standard is even not achieved, the prior art does not consider that the visiting frequency of data changes the influence to its temperature, thus needle
It is very high to the hot value of data, but when visiting frequency decline or rapid decline, the prior art is difficult to precisely identify its practical heat
The problem of spending, the embodiment of the present invention is by gradually passing the hot value of notebook data according to each time of notebook data access interval
Subtract, so that the hot value of notebook data can more reflect its practical temperature.
Since the practical temperature of the access interval reflection data of data, such as some access are spaced lesser data, in fact
Border temperature is higher, and the temperature for determining the need for data by setting preset interval in the present embodiment is successively decreased, can be with
Dsc data is more accurately declined fast data separation with temperature to come.Specifically, it is higher to can reflect temperature for unit gap
The access interval of data, preset interval can be 1 times of unit gap or more, for example, the 2 of unit gap times or 3 times, from
And the data protection that access interval can be less than to preset interval is got up, i.e., does not successively decrease to its temperature.The present embodiment for
The value of preset interval is not specifically limited, and suitable preset interval can be arranged according to actual needs.
Step 104: this temperature of successively decreasing of the notebook data is calculated according to the preset temperature formula that successively decreases.
Step 105: the hot value of the notebook data being successively decreased to obtain according to this temperature of successively decreasing of the notebook data
This hot value of the notebook data.
Specifically, in practical applications, for the data in caching after each hit, the hot value of the data can be by more
Newly, the update mode of the hot value of data is, for example, that every hit is primary, and the hot value of the data is added 1, and (1 can be described as single reference
Temperature value added), it is so without being limited thereto, such as every hit is once, hot value can also add 2.Step 104, in 105, in aforementioned heat
On the basis of angle value update mode, successively decrease to its hot value also according to this access interval of notebook data to obtain this heat
Angle value, thus this hot value of notebook data can be used following formula and be calculated:
This temperature of successively decreasing of this hot value=previous hot value+single reference temperature value added-；
Wherein, this temperature of successively decreasing can be calculated using the following temperature formula that successively decrease:
This temperature of successively decreasing=unit gap M* reference value of successively decreasing；
Wherein, M is the integral multiple at this access interval and unit gap, and the reference value of successively decreasing of unit gap can be based on single
Secondary access temperature value added set.Unit gap, which can be used for reflecting, carries out the minimum interval that temperature is successively decreased.It is single
Bit interval for example refers to the corresponding access interval of the average access frequency of hot spot data, such as can pass through temperature in statistics caching
The average access interval for being worth higher data obtains unit gap, and unit gap is for example set as 5S (second), i.e. heat in caching
It is each that the visiting frequency of point data basically reaches 5S/, so without being limited thereto.
In the present embodiment, each parameter in the calculation formula of this temperature of successively decreasing can there are many variations, such as according to meter
Precision is calculated to need, M can also take decimal, and when M round numbers, it is possible to reduce calculation amount.The reference value of successively decreasing of unit gap can also
Think the presupposition multiple of the previous hot value of notebook data.Successively decrease reference value and the single reference temperature of unit gap in the present embodiment
The ratio ∈ [5%, 20%] of value added, i.e. the reference value of successively decreasing of unit gap can take more than or equal to 5% and be less than or
Any number of single reference temperature value added of the person equal to 20%, which is, for example, 10%, and so without being limited thereto, the ratio is also
It can be 8%, 15%, 20%.In some instances, which might be less that 5% or is greater than 20%, such as equal to 3%,
Or it is equal to 25%.
10%, single reference are equal to the ratio of the successively decrease reference value and single reference temperature value added of unit gap below
Temperature value added is that the calculating of hot value is described as follows for 1, unit gap is equal to 5S:
Assuming that this access interval of notebook data is equal to 60S, then M=12, this temperature=M*0.1=1.2 that successively decreases,
This hot value=previous hot value+1-1.2, i.e. this hot value=previous hot value -0.2.As it can be seen that data
Hot value is linearly successively decreased with the increase at access interval, i.e. access interval is bigger, and hot value is successively decreased faster.Thus, if
The previous hot value of some data is very high, but if this access interval is very big, this temperature of successively decreasing is very big, thus its
This hot value may become smaller rapidly.It should be appreciated that temperature decrement algorithm can be set according to actual needs, such as can also adopt
With decreases in non-linear calculation etc..
Step 106: directly obtaining this hot value for the notebook data not successively decreased.
Step 107: target data queue belonging to notebook data is determined according to this hot value of notebook data.
Target data queue is the corresponding data queue of Heat range belonging to the hot value with data.In step 107,
Since this hot value of notebook data has been successively decreased according to this access interval of notebook data, thus this temperature of notebook data
Value may change greatly, and thus change Heat range belonging to notebook data, so that the target data queue of notebook data is sent out
It is raw to change.For example, the corresponding target data queue of the hot value of notebook data is dsc data queue before hot value is successively decreased, and temperature
Heat range belonging to this hot value of notebook data declines after value is successively decreased, thus its target data queue is also required to occur therewith
Change.In step 107, the corresponding mesh of notebook data can be determined by analyzing Heat range belonging to this hot value of notebook data
Mark data queue.Wherein, after step 105, target data queue belonging to notebook data may change, it is also possible to not send out
Changing.
Step 108: when the data queue that notebook data is currently located is not the target data queue belonging to it, by notebook data
It is transferred to the target data queue belonging to it.
Specifically, judge whether this hot value of notebook data is more than or equal to preset hot pixel threshold, in notebook data
This hot value when being more than or equal to preset hot pixel threshold, target data queue belonging to notebook data is dsc data team
Column, when this hot value of notebook data is less than hot pixel threshold, the target data queue of notebook data is cold data queue.It is wherein hot
Point threshold value is for distinguishing Heat range belonging to data.
In step 108,
If notebook data is in cold data queue, and this hot value after successively decreasing is greater than hot pixel threshold, then notebook data is mobile
To dsc data queue；
If notebook data, in cold data queue, this hot value after successively decreasing is lower than hot pixel threshold, then data still stay in cold
Data queue；
If notebook data, in dsc data queue, this hot value after successively decreasing is higher than hot pixel threshold, then data still stay in heat
Data queue；
If notebook data, in dsc data queue, this hot value after successively decreasing is lower than hot pixel threshold, then notebook data is moved to
Cold data queue.
By dividing dsc data queue and cold data queue, when there are instantaneous a large amount of discrete access requests, due to it
Hot pixel threshold is not achieved in hot value, so such data can be placed into cold data queue, when cold data queue full, wherein
Cold data can be kicked out of caching, to realize cold and hot data isolation, avoid kicking out of hot spot data into caching.
The embodiment of the present invention compared with prior art, by being successively decreased according to the access interval of data to its hot value,
It can more accurately identify the hot spot data that access is frequent and the continuous access time is long, be conducive to accurately eliminate access quantitative change
Few cold data, to improve the service efficiency of caching.
Second embodiment of the present invention is related to a kind of based on data cached temperature management method.Second embodiment exists
Improvement is made on the basis of first embodiment, is mainly theed improvement is that: in second embodiment of the invention, can also be set
Data expired time is set, to reject the data not used for a long time in caching.
Specifically, caching data queue data expired time can also be set, caching current time in system with
When the interval of the previous access time of data in caching is greater than data expired time, expired data are removed from the cache.
Specifically, the data expired time of dsc data queue and cold data queue can be same or different.Data expired time can be with
Obtained by the visiting frequency of statistical data, for example, in caching the smaller access interval of data be 24 hours/each, then data mistake
Time phase for example can be 48 hours.So without being limited thereto, data expired time can be arranged according to the actual application, as long as energy
It is enough to reject the data not used for a long time in caching.
It is noted that in practical applications, can also be adjusted according to the whole temperature state dynamic of the data in caching
Each parameter in whole hot spot data management method, such as: dsc data queue size, cold data queue size, hot pixel threshold, unit
Interval, preset interval, the data expired time of the data expired time of dsc data queue and cold data queue.Wherein, it caches
In the whole temperature states of data can be judged by the size of dsc data queue and the cold data queue of needs, i.e.,
In the case that current dsc data queue is full, and cold data queue is discontented, both sizes of adjustable data queue can also
With by adjusting hot pixel threshold, preset interval, unit gap etc., so that dsc data and cold data are properly stored.
The present embodiment compared with previous embodiment, by setting data expired time and dynamic adjusting data queue it is big
It is small, hot spot data can be more efficiently stored, and effectively eliminate amount of access cold data less and less, improve the use of caching
Efficiency.
The step of various methods divide above, be intended merely to describe it is clear, when realization can be merged into a step or
Certain steps are split, multiple steps are decomposed into, as long as including identical logical relation, all in the protection scope of this patent
It is interior；To adding inessential modification in algorithm or in process or introducing inessential design, but its algorithm is not changed
Core design with process is all in the protection scope of the patent.
Third embodiment of the invention is related to a kind of server, as shown in Fig. 2, the server includes at least one processor
201；And the memory 202 with the communication connection of at least one described processor 201；Wherein, the memory 202 is stored with
The instruction that can be executed by least one described processor 201, described instruction are executed by least one described processor 201, so that
At least one described processor 201 is able to carry out as previously described based on data cached temperature management method.
Wherein, memory is connected with processor using bus mode, and bus may include the bus of any number of interconnection
And bridge, bus is by one or more processors together with the various circuit connections of memory.Bus can also will be such as peripheral
Together with various other circuit connections of management circuit or the like, these are all well known in the art for equipment, voltage-stablizer
, therefore, it will not be further described herein.Bus interface provides interface between bus and transceiver.Transceiver
Can be an element, be also possible to multiple element, such as multiple receivers and transmitter, provide for over a transmission medium with
The unit of various other device communications.The data handled through processor are transmitted on the radio medium by antenna, further,
Antenna also receives data and transfers data to processor.
Processor is responsible for managing bus and common processing, can also provide various functions, including periodically, peripheral interface,
Voltage adjusting, power management and other control functions.And memory can be used for storage processor and execute operation when institute
The data used.
The embodiment of the present invention compared with prior art, passs the hot value of data by being spaced according to the access of data
Subtract, can more accurately identify the hot spot data that access is frequent and the continuous access time is long, be conducive to accurately eliminate amount of access
The cold data to tail off, to improve the service efficiency of caching.
Four embodiment of the invention is related to a kind of storage medium, is stored with computer program.Computer program is processed
Device realizes above method embodiment when executing.
The embodiment of the present invention compared with prior art, passs the hot value of data by being spaced according to the access of data
Subtract, can more accurately identify the hot spot data that access is frequent and the continuous access time is long, be conducive to accurately eliminate amount of access
The cold data to tail off, to improve the service efficiency of caching.
That is, it will be understood by those skilled in the art that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, which is stored in a storage medium, including some instructions are to make
It obtains an equipment (can be single-chip microcontroller, chip etc.) or processor (processor) executes side described in each embodiment of the application
The all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
It will be understood by those skilled in the art that the respective embodiments described above are to realize specific embodiments of the present invention,
And in practical applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
Claims (10)
1. a kind of based on data cached temperature management method characterized by comprising
When hitting the data in caching, between judging that whether this access of the notebook data of hit is spaced more than or equal to presetting
Every；Wherein, it is divided between the time between this access time of the notebook data and previous access time between this described access
Every；
If this described access interval is more than or equal to the preset interval, calculated according to the preset temperature formula that successively decreases
To this temperature of successively decreasing of the notebook data；
The hot value of the notebook data is successively decreased to obtain the notebook data according to this temperature of successively decreasing of the notebook data
This hot value；
Target data queue belonging to the notebook data is determined according to this hot value of the notebook data；
When the data queue that the notebook data is currently located is not the target data queue belonging to it, the notebook data is shifted
To the target data queue belonging to it.
2. according to claim 1 based on data cached temperature management method, which is characterized in that the temperature is successively decreased public affairs
Formula are as follows:
This temperature of successively decreasing=unit gap M* reference value of successively decreasing；Wherein, M is the integer at this access interval and unit gap
Times.
3. according to claim 2 based on data cached temperature management method, which is characterized in that the unit gap
Reference value of successively decreasing is based on single reference temperature value added and is set.
4. according to claim 3 based on data cached temperature management method, which is characterized in that the unit gap
The ratio ∈ [5%, 20%] of reference value of successively decreasing and the single reference temperature value added.
5. according to claim 1 based on data cached temperature management method, which is characterized in that described according to described
This hot value of data determines target data queue belonging to the notebook data, specifically includes:
Judge whether this hot value of the notebook data is more than or equal to preset hot pixel threshold；
When this hot value of the notebook data is more than or equal to preset hot pixel threshold, target belonging to the notebook data
Data queue is dsc data queue, when this hot value of the notebook data is less than the hot pixel threshold, the notebook data
Target data queue is cold data queue.
6. according to claim 5 based on data cached temperature management method, which is characterized in that described based on caching number
According to temperature management method further include:
The dsc data queue and cold data queue are adjusted according to the whole temperature states of the data in caching dynamic
Size.
7. according to claim 5 based on data cached temperature management method, which is characterized in that described based on caching number
According to temperature management method further include:
When data in miss caching, the data of miss are inserted into the cold data queue, record the miss
This access time of data, and the data hot value of the miss is initialized.
8. according to any one of claim 1 to 7 based on data cached temperature management method, which is characterized in that institute
The data queue for stating caching is provided with data expired time；
The interval of the previous access time of data in the current time in system of caching and the caching is greater than the data mistake
When time phase, expired data are deleted from the caching.
9. a kind of server characterized by comprising
At least one processor；And
The memory being connect at least one described processor communication；Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
Manage device execute so that at least one described processor be able to carry out as described in any in claim 1 to 8 based on data cached
Temperature management method.
10. a kind of storage medium, is stored with computer program, which is characterized in that when the computer program is executed by processor
It realizes described in any item of the claim 1 to 8 based on data cached temperature management method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811114772.2A CN109471875B (en) | 2018-09-25 | 2018-09-25 | Hot degree management method based on cache data, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811114772.2A CN109471875B (en) | 2018-09-25 | 2018-09-25 | Hot degree management method based on cache data, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109471875A true CN109471875A (en) | 2019-03-15 |
| CN109471875B CN109471875B (en) | 2021-08-20 |
Family
ID=65663173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811114772.2A Active CN109471875B (en) | 2018-09-25 | 2018-09-25 | Hot degree management method based on cache data, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109471875B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918575A (en) * | 2019-03-29 | 2019-06-21 | 阿里巴巴集团控股有限公司 | A kind of superseded method and apparatus of the data applied to search system |
| CN110008142A (en) * | 2019-04-16 | 2019-07-12 | 苏州浪潮智能科技有限公司 | Storing data management method, device, equipment and computer readable storage medium |
| CN111045598A (en) * | 2019-10-10 | 2020-04-21 | 深圳市金泰克半导体有限公司 | Data storage method and device |
| CN111651520A (en) * | 2020-05-25 | 2020-09-11 | 北京字节跳动网络技术有限公司 | Cache architecture access method, device, medium and electronic equipment |
| CN111737170A (en) * | 2020-05-28 | 2020-10-02 | 苏州浪潮智能科技有限公司 | Cache data management method, system, terminal and storage medium |
| CN111913924A (en) * | 2020-07-21 | 2020-11-10 | 华中科技大学 | Log structure file system data management method based on heat degree |
| CN112015674A (en) * | 2020-08-27 | 2020-12-01 | 平安科技（深圳）有限公司 | Cache resource access method and device based on multiple hierarchies and computer equipment |
| CN112269947A (en) * | 2020-09-23 | 2021-01-26 | 咪咕文化科技有限公司 | Spatial text data caching method and device, electronic equipment and storage medium |
| CN112579652A (en) * | 2020-12-28 | 2021-03-30 | 咪咕文化科技有限公司 | Method and device for deleting cache data, electronic equipment and storage medium |
| CN112835892A (en) * | 2021-01-15 | 2021-05-25 | 卓望数码技术（深圳）有限公司 | Hot spot data detection method and device, electronic equipment and storage medium |
| CN112988040A (en) * | 2019-12-18 | 2021-06-18 | 深圳大普微电子科技有限公司 | Data storage method, device and equipment and readable storage medium |
| WO2021120731A1 (en) * | 2019-12-18 | 2021-06-24 | 深圳大普微电子科技有限公司 | Data storage method and assembly, and data processing method and assembly |
| CN113590031A (en) * | 2021-06-30 | 2021-11-02 | 郑州云海信息技术有限公司 | Cache management method, device, equipment and computer readable storage medium |
| CN113608685A (en) * | 2021-06-30 | 2021-11-05 | 济南浪潮数据技术有限公司 | Hot spot identification method and system of distributed storage block device |
| CN113760178A (en) * | 2021-01-29 | 2021-12-07 | 北京京东拓先科技有限公司 | Cache data processing method and device, electronic equipment and computer readable medium |
| CN113760782A (en) * | 2021-08-23 | 2021-12-07 | 南京森根科技股份有限公司 | Dynamically adjustable annular cache system and control method thereof |
| CN113885801A (en) * | 2021-09-30 | 2022-01-04 | 中国工商银行股份有限公司 | Memory data processing method and device |
| CN115914374A (en) * | 2022-12-02 | 2023-04-04 | 中国工商银行股份有限公司 | Data transmission method, data transmission device, computer equipment, storage medium and program product |
| CN117472967A (en) * | 2023-12-28 | 2024-01-30 | 江西铜锐信息技术有限公司 | Data life cycle management method and system based on data use heat |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080162779A1 (en) * | 2006-12-29 | 2008-07-03 | John Mark Morris | Transparent data temperature sensitive cluster duplication |
| CN106021445A (en) * | 2016-05-16 | 2016-10-12 | 努比亚技术有限公司 | Cached data loading method and apparatus |
| CN106951550A (en) * | 2017-03-27 | 2017-07-14 | 广东欧珀移动通信有限公司 | Data processing method, device and mobile terminal |
| CN107305475A (en) * | 2016-04-22 | 2017-10-31 | 中国科学院微电子研究所 | A kind of flashcache mixes the buffer scheduling method and system of storage system |
-
2018
- 2018-09-25 CN CN201811114772.2A patent/CN109471875B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080162779A1 (en) * | 2006-12-29 | 2008-07-03 | John Mark Morris | Transparent data temperature sensitive cluster duplication |
| CN107305475A (en) * | 2016-04-22 | 2017-10-31 | 中国科学院微电子研究所 | A kind of flashcache mixes the buffer scheduling method and system of storage system |
| CN106021445A (en) * | 2016-05-16 | 2016-10-12 | 努比亚技术有限公司 | Cached data loading method and apparatus |
| CN106951550A (en) * | 2017-03-27 | 2017-07-14 | 广东欧珀移动通信有限公司 | Data processing method, device and mobile terminal |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918575A (en) * | 2019-03-29 | 2019-06-21 | 阿里巴巴集团控股有限公司 | A kind of superseded method and apparatus of the data applied to search system |
| CN110008142A (en) * | 2019-04-16 | 2019-07-12 | 苏州浪潮智能科技有限公司 | Storing data management method, device, equipment and computer readable storage medium |
| CN111045598A (en) * | 2019-10-10 | 2020-04-21 | 深圳市金泰克半导体有限公司 | Data storage method and device |
| CN111045598B (en) * | 2019-10-10 | 2023-08-15 | 深圳市金泰克半导体有限公司 | Data storage method and device |
| CN112988040B (en) * | 2019-12-18 | 2023-02-24 | 深圳大普微电子科技有限公司 | Data storage method, device and equipment and readable storage medium |
| WO2021120731A1 (en) * | 2019-12-18 | 2021-06-24 | 深圳大普微电子科技有限公司 | Data storage method and assembly, and data processing method and assembly |
| CN112988040A (en) * | 2019-12-18 | 2021-06-18 | 深圳大普微电子科技有限公司 | Data storage method, device and equipment and readable storage medium |
| CN111651520A (en) * | 2020-05-25 | 2020-09-11 | 北京字节跳动网络技术有限公司 | Cache architecture access method, device, medium and electronic equipment |
| CN111651520B (en) * | 2020-05-25 | 2023-04-18 | 北京字节跳动网络技术有限公司 | Cache architecture access method, device, medium and electronic equipment |
| CN111737170A (en) * | 2020-05-28 | 2020-10-02 | 苏州浪潮智能科技有限公司 | Cache data management method, system, terminal and storage medium |
| CN111737170B (en) * | 2020-05-28 | 2022-07-08 | 苏州浪潮智能科技有限公司 | Cache data management method, system, terminal and storage medium |
| CN111913924B (en) * | 2020-07-21 | 2024-03-19 | 华中科技大学 | Log structure file system data management method based on heat |
| CN111913924A (en) * | 2020-07-21 | 2020-11-10 | 华中科技大学 | Log structure file system data management method based on heat degree |
| CN112015674A (en) * | 2020-08-27 | 2020-12-01 | 平安科技（深圳）有限公司 | Cache resource access method and device based on multiple hierarchies and computer equipment |
| CN112015674B (en) * | 2020-08-27 | 2023-05-30 | 平安科技（深圳）有限公司 | Multi-level-based cache resource access method and device and computer equipment |
| CN112269947A (en) * | 2020-09-23 | 2021-01-26 | 咪咕文化科技有限公司 | Spatial text data caching method and device, electronic equipment and storage medium |
| CN112579652A (en) * | 2020-12-28 | 2021-03-30 | 咪咕文化科技有限公司 | Method and device for deleting cache data, electronic equipment and storage medium |
| CN112579652B (en) * | 2020-12-28 | 2024-04-09 | 咪咕文化科技有限公司 | Method and device for deleting cache data, electronic equipment and storage medium |
| CN112835892A (en) * | 2021-01-15 | 2021-05-25 | 卓望数码技术（深圳）有限公司 | Hot spot data detection method and device, electronic equipment and storage medium |
| CN113760178A (en) * | 2021-01-29 | 2021-12-07 | 北京京东拓先科技有限公司 | Cache data processing method and device, electronic equipment and computer readable medium |
| CN113608685A (en) * | 2021-06-30 | 2021-11-05 | 济南浪潮数据技术有限公司 | Hot spot identification method and system of distributed storage block device |
| CN113590031A (en) * | 2021-06-30 | 2021-11-02 | 郑州云海信息技术有限公司 | Cache management method, device, equipment and computer readable storage medium |
| CN113590031B (en) * | 2021-06-30 | 2023-09-12 | 郑州云海信息技术有限公司 | Cache management method, device, equipment and computer readable storage medium |
| CN113760782A (en) * | 2021-08-23 | 2021-12-07 | 南京森根科技股份有限公司 | Dynamically adjustable annular cache system and control method thereof |
| CN113885801A (en) * | 2021-09-30 | 2022-01-04 | 中国工商银行股份有限公司 | Memory data processing method and device |
| CN115914374A (en) * | 2022-12-02 | 2023-04-04 | 中国工商银行股份有限公司 | Data transmission method, data transmission device, computer equipment, storage medium and program product |
| CN117472967A (en) * | 2023-12-28 | 2024-01-30 | 江西铜锐信息技术有限公司 | Data life cycle management method and system based on data use heat |
| CN117472967B (en) * | 2023-12-28 | 2024-05-03 | 江西铜锐信息技术有限公司 | Data life cycle management method and system based on data use heat |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109471875B (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109471875A (en) | Based on data cached temperature management method, server and storage medium | |
| US10133679B2 (en) | Read cache management method and apparatus based on solid state drive | |
| US10198363B2 (en) | Reducing data I/O using in-memory data structures | |
| EP3089039B1 (en) | Cache management method and device | |
| CN109154920B (en) | Method for monitoring marked memory and processing equipment | |
| CN108763110B (en) | Data caching method and device | |
| KR102043886B1 (en) | Profiling Cache Substitution | |
| US10430338B2 (en) | Selectively reading data from cache and primary storage based on whether cache is overloaded | |
| US7249152B2 (en) | Dynamic disk space management by multiple database server instances in a cluster configuration | |
| EP3066572B1 (en) | Cache memory budgeted by chunks based on memory access type | |
| EP3230874B1 (en) | Fully associative cache memory budgeted by memory access type | |
| US7039766B1 (en) | Prescheduling sequential data prefetches in a preexisting LRU cache | |
| CN103795781B (en) | A kind of distributed caching method based on file prediction | |
| CN110297787B (en) | Method, device and equipment for accessing memory by I/O equipment | |
| WO2022062524A1 (en) | Memory management method and apparatus, device and storage medium | |
| CN110413545B (en) | Storage management method, electronic device, and computer program product | |
| US20150100739A1 (en) | Enhancing Lifetime of Non-Volatile Cache by Injecting Random Replacement Policy | |
| CN112445794B (en) | Caching method of big data system | |
| US9767043B2 (en) | Enhancing lifetime of non-volatile cache by reducing intra-block write variation | |
| CN114930306A (en) | Bandwidth balancing method and device | |
| US20240111668A1 (en) | Elastic column store with minimal impact on workload using smart eviction and fast repopulation | |
| CN117149781B (en) | Group-associative self-adaptive expansion cache architecture and access processing method thereof | |
| CN112015679B (en) | Cache optimization method and system based on access frequency | |
| EP4261712A1 (en) | Data elimination method and apparatus, cache node, and cache system | |
| CN109857680B (en) | LRU flash memory cache management method based on dynamic page weight |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |