CN117762646B - Digital quantity processing method and system based on cluster type shared cache - Google Patents
Digital quantity processing method and system based on cluster type shared cache Download PDFInfo
- Publication number
- CN117762646B CN117762646B CN202410197598.1A CN202410197598A CN117762646B CN 117762646 B CN117762646 B CN 117762646B CN 202410197598 A CN202410197598 A CN 202410197598A CN 117762646 B CN117762646 B CN 117762646B
- Authority
- CN
- China
- Prior art keywords
- digital quantity
- time
- processing
- redis
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 91
- 230000008859 change Effects 0.000 claims abstract description 68
- 238000000034 method Methods 0.000 claims abstract description 41
- 230000008569 process Effects 0.000 claims abstract description 33
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 2
- 230000003111 delayed effect Effects 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000002194 synthesizing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000013509 system migration Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Memory System Of A Hierarchy Structure (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a digital quantity processing method and a system based on cluster type shared cache, wherein the method comprises the following steps: constructing a digital quantity processing cluster, randomly and averagely receiving acquisition data sent by the front of each subsystem by each instance of the cluster, and storing multi-bit delay data information in a local cache of the instance and a shared cache of a redis cluster; each example in the cluster processes the multi-bit delay digital quantity of the digital quantity cached in the example at regular time to generate a new value, send an alarm, change data and time sequence data; the example processes the multi-bit delay data buffer, the change queue and the alarm queue, and then carries out the multi-bit delay processing process of the next period. The invention can realize flexible configuration and expansion of hardware resources and processing capacity of digital quantity processing, and improves resource utilization rate and system capacity expansibility.
Description
Technical Field
The invention relates to a rail transit monitoring system, in particular to a digital quantity processing method and system based on cluster type shared cache.
Background
Along with the rapid development of an automatic system of a rail transit system, the scale of the automatic system applied to the rail transit industry is increased, the system architecture is more and more complex, and the scale of data inside the system is increased continuously. Particularly, in the application scenes of an on-line network comprehensive monitoring system, a network power dispatching system or the like, the scale of real-time change data exceeds hundreds of thousands, which is a great pressure on the processing capacity and hardware resources of an automatic monitoring system, so that the reasonable and flexible allocation of the hardware resources and the processing capacity is required. Because the digital quantity data has low change frequency, the digital quantity processing process is distributed according to stations and applications, so that the waste of hardware resources and the increase of management cost are caused. With respect to the characteristic of digital quantity, the distributed processing mode is changed into a clustered processing mode on the basis of the digital quantity processing method.
In the traditional digital quantity process deployment mode, the relation between the processing process and the front-end process is 1 to 1, namely, a certain specific classified processing process only receives the classified front-end data sent by the classified front-end process, a plurality of digital quantity point positions are only accepted and processed by the processing process, and the multi-bit delay function does not need to interact with other processes to independently finish the function. However, the resource allocation mode of the deployment mode is inflexible, independent processes are required to be deployed no matter the size of the classified data scale, and the processing capacity of the processes cannot be flexibly expanded when the processing capacity of the processes is insufficient. The digital quantity processing cluster deployment mode can realize flexible allocation and expansion of hardware resources and processing capacity, the relation between the cluster and the preposed processes is 1 to n, namely, the examples in the cluster randomly and averagely receive the preposed data of all the preposed processes, a plurality of point positions of the digital quantity can be received and processed by a plurality of examples, and the examples need to cooperate to complete a multi-bit delay function.
Disclosure of Invention
The invention aims to: the invention aims to provide a digital quantity processing method and a system based on cluster type shared cache, so that flexible configuration and expansion of hardware resources and processing capacity of digital quantity processing are realized, and resource utilization rate and system capacity expansibility are improved.
The technical scheme is as follows: the invention discloses a digital quantity processing method based on cluster type shared cache, which comprises the following steps:
Step 1, constructing a digital quantity processing cluster, wherein all instances in the cluster receive collected data sent by the front of all subsystems at average and randomly, and then multi-bit delay data information is stored in an instance local cache and a shared cache of a redis cluster;
step 2, each example in the cluster processes the multi-bit delay digital quantity of the digital quantity cached in the example at regular time to generate a new value, send an alarm, change data and time sequence data;
and 3, processing the multi-bit delay data buffer, the change queue and the alarm queue by an example, and then performing the multi-bit delay processing process of the next period.
The step 1 of constructing a digital quantity processing cluster refers to: each example in the cluster receives the collected data sent by each subsystem at random on average, in the example, the program automatically judges the point position change of the digital quantity, and the multi-bit delay time is greater than zero, and starts multi-bit delay processing, if the digital quantity delay information is not in the redis shared buffer, the digital quantity is considered to be the first point position change, the change point position information of the digital quantity and the initialization information of other point positions are stored in the redis shared buffer, the key information of the digital quantity is stored in the program internal buffer, and the front time stamp of the digital quantity in the redis is set; if in the redis shared cache, only the change point location information in the redis shared cache is updated and the number quantity is updated to prepend a timestamp in the redis.
The storing of the multi-bit delay data information in the shared cache of the redis cluster in the step 1 refers to: the redis is used as a shared cache of each example, the initialization information, the key words and the local caches of all other points of the first time of digital quantity deflection are stored to be the same, and the field information comprises 'first time deflection time', 'delay time', 'value', 'state', 'second level deflection time', 'millisecond level deflection time' and 'whether deflection is carried out'; the prepositioning time key is a digital quantity key, and the time is the time of any point position change.
The storing of the multi-bit delayed data information in the example local cache described in step 1 refers to: because the prepositive data of the subsystem is randomly and averagely sent to the data processing cluster, each instance in the cluster randomly receives the data packet of the first time point position change of the digital quantity, and the number of multi-bit delay to be processed is basically equal, delay processing pressure can be distributed on each instance, when the digital quantity changes for the first time point position, the key word of the digital quantity point position stored in the instance is the key word of multi-bit delay data information, and the instance storage stores the key word and the current timestamp in the instance.
Each example in the cluster described in step 2 processes the number amount of the internal cache of the example in a timing manner, and the multi-bit delay number amount refers to: each instance in the cluster processes the multi-bit delay digital quantity of the digital quantity cached in the instance at fixed time, obtains multi-bit delay data to be processed of the instance from redis through key cache data in the program after the time interval is defined, judges whether the current time is more than or equal to the delay time of each digital quantity, if the current time meets the condition, indicates that the delay time is reached, processes all point position information of the digital quantity into the latest value of the digital quantity, and sends alarm, change data, time sequence data and other processing steps of the digital quantity.
The generating of the new value, sending the alarm, changing the data and timing data in the step 2 refers to: and synthesizing all the points of the digital quantity into a new value, namely, the point values are d1 and d2 … … dn in sequence, the new value v=d1 x2 1-1+ d2*22-1+ d3*23-1+……+dn*2n-1, comparing the new value with the last value of the digital quantity obtained from the redis, if the value of the digital quantity is changed, updating the redis, inserting the change data information into a change queue, storing the change value into a time sequence database, obtaining the digital quantity meaning of the value of the digital quantity which is defined in advance from the redis, and inserting an alarm into an alarm queue by comparing the definition content of the new value.
The step 3 of processing the multi-bit delay data buffer refers to: reading a front time stamp of the digital quantity in the redis, if the time stamp is larger than the time stamp of the timing task processing, indicating that the digital quantity has new point position change update, so that the related information of the digital quantity is not deleted in an instance internal cache and the redis cache, otherwise, deleting the related information of the digital quantity, processing the change and the alarm queue content, and if the number of the change queue and the alarm queue exceeds a certain self-defined number or the processing period is over, sending out the data in the change queue and the alarm queue and emptying the queue.
The multi-bit delay processing in the step 3 refers to: the monitoring platform is internally provided with a plurality of working states of equipment by digital quantity, and the equipment states are represented by a plurality of bits; after the acquisition unit acquires the real-time state of the equipment in real time, updating a plurality of bits of the digital quantity in a point position mode to modify the state of the equipment, so that an invalid state can be generated in the updating process; in order to avoid the invalid states, when the value needs to be updated, the logic processing is performed after the value is updated.
The digital quantity processing system based on the cluster type shared cache adopts the digital quantity processing method based on the cluster type shared cache, and comprises the following modules:
And a data acquisition module: the system comprises a subsystem, a storage subsystem and a data storage subsystem, wherein the subsystem is used for receiving the preamble data sent by the subsystem and storing multi-bit delay data;
and the delay processing module is used for: the system is used for processing multi-bit delay data in the shared cache and realizing point location processing of the acquisition equipment;
and the cache processing module is used for: the method is used for processing the multi-bit delay buffer, the change queue and the alarm queue.
The data acquisition module is used for constructing a digital quantity processing cluster, and specifically comprises the following steps: each example in the cluster receives the collected data sent by each subsystem at random on average, in the example, the program automatically judges the point position change of the digital quantity, and the multi-bit delay time is greater than zero, and starts multi-bit delay processing, if the digital quantity delay information is not in the redis shared buffer, the digital quantity is considered to be the first point position change, the change point position information of the digital quantity and the initialization information of other point positions are stored in the redis shared buffer, the key information of the digital quantity is stored in the program internal buffer, and the front time stamp of the digital quantity in the redis is set; updating only the change point location information in the redis shared cache if in the redis shared cache, and updating the leading timestamp of the digital quantity in the redis;
The data acquisition module stores multi-bit delay data in two modes, one is to store multi-bit delay data information on a shared cache of a redis cluster, and the method specifically comprises the following steps: the redis is used as a shared cache of each example, the initialization information, the key words and the local caches of all other points of the first time of digital quantity deflection are stored to be the same, and the field information comprises 'first time deflection time', 'delay time', 'value', 'state', 'second level deflection time', 'millisecond level deflection time' and 'whether deflection is carried out'; the prepositioning time key is a digital quantity key, and the time is the time of any point position change; the other is to store multi-bit delay data information in an example local cache, specifically: when the number quantity changes for the first time, the key words of the number quantity point positions stored in the instance are the key words of the multi-bit delay data information, and the instance storage stores the key words and the current time stamp in the instance.
The delay processing module is used for processing multi-bit delay cache, and specifically comprises the following steps: reading a front time stamp of the digital quantity in the redis, if the time stamp is larger than the time stamp of the timing task processing, indicating that the digital quantity has new point position change update, so that the related information of the digital quantity is not deleted in an instance internal cache and the redis cache, otherwise, deleting the related information of the digital quantity, processing the change and the alarm queue content, and if the number of the change queue and the alarm queue exceeds a certain self-defined number or the processing period is over, sending out the data in the change queue and the alarm queue and emptying the queue.
A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method of digital volume processing based on clustered shared cache as described above.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of digital value processing based on clustered shared cache as described above when executing the computer program.
The beneficial effects are that: compared with the prior art, the invention has the following advantages:
1. The invention can realize flexible configuration and expansion of hardware resources and processing capacity of digital quantity processing, and improves resource utilization rate and system capacity expansibility;
2. The system has the advantages of simple deployment mode and flexible system migration, and can be deployed in a traditional mode or in a containerized mode.
Drawings
FIG. 1 is a flow chart of a cluster acceptance number;
fig. 2 is a flow chart of a digital multi-bit delay process.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
A digital quantity processing method based on cluster type shared cache includes the following steps:
And 1, constructing a digital quantity processing cluster.
The monitoring platform uses digital quantity to represent various working states of the equipment, and in order to increase the reliability of the digital quantity, multiple bits are often used to represent the equipment states. After the acquisition unit acquires the real-time state of the equipment in real time, the equipment state is modified by updating a plurality of digits of the digital quantity in a point position mode, so that an invalid state can be generated in the updating process. For example, the switch includes two working states of the split position and the combined position, and in order to increase reliability, the split position and the combined position are respectively denoted by "01" and "10", and "00" and "11" are invalid states, and an intermediate invalid state exists in the process of updating "01" to "10" or updating "10" to "01". In order to avoid the invalid states, when the value needs to be updated, the logic processing is performed after the value is updated.
Constructing a digital quantity processing cluster, wherein each instance in the cluster receives the acquisition data sent by the front of each subsystem at average and randomly, in the instance, a program automatically judges the point position change of the digital quantity value, and the multi-bit delay time is greater than zero, and starts multi-bit delay processing, if the digital quantity delay information is not in a redis shared cache, the digital quantity is considered to be the first point position change, the change point position information of the digital quantity and the initialization information of other point positions are stored in the redis shared cache, key information of the digital quantity is stored in the program internal cache, and a front time stamp of the digital quantity in the redis is set; if in the redis shared cache, only the change point location information in the redis shared cache is updated, and the number quantity is pre-time stamped in the redis, as shown in FIG. 1.
The multi-bit delay data information is stored in an example local cache, so that delay processing pressure is distributed on each example, only when the first time point position of the digital quantity changes, the key words of the point positions of the digital quantity stored in the example are key words of multi-bit delay processing, and because the prepositive data of the subsystem are sent to the data processing cluster in a random average mode, each example in the cluster randomly receives data packets of the first time point position change of the digital quantity, and the number of multi-bit delay needing to be processed is basically equal. For example, the key representing the position of the switch of the device is "et.201.Wz", the number of components is 2, and when any point position changes, the example automatically generates the keys "et.201.Wz#1" and "et.201.Wz#2", and stores the keys in the local cache.
The multi-bit delay data information is stored in a shared cache of a redis cluster, the redis is used as the shared cache of each example, the initialization information of the first change point position and other all point positions of the digital quantity is stored, the key words are the same as the local cache of the example, and the multi-bit delay data information mainly comprises field information such as 'first displacement time', 'delay time', 'value', 'state', 'second displacement time', 'millisecond displacement time', whether displacement or not and the like. The prepositioning time key is a digital quantity key, and the time is the time of any point position change.
And 2, multi-bit delay processing of the processing cluster based on the digital quantity of the shared cache.
Each instance in the cluster processes the multi-bit delay digital quantity of the digital quantity cached in the instance at fixed time, each instance interval 1s in the cluster acquires multi-bit delay data to be processed of the instance from redis through key cache data in the program, judges whether the current time is greater than or equal to the delay time of each digital quantity, if the current time meets the condition, the delay time is reached, then all point location information of the digital quantity is processed into the latest value of the digital quantity, and steps such as digital quantity sending alarm, change data, time sequence data and the like are carried out, as shown in figure 2.
And synthesizing all the points of the digital quantity into a new value, namely, the point values are d1 and d2 … … dn in sequence, the new value v=d1 x 2 1-1+ d2*22-1+ d3*23-1+……+dn*2n-1, comparing the new value with the last value of the digital quantity obtained from the redis, if the value of the digital quantity is changed, updating the redis, inserting the change data information into a change queue, storing the change value into a time sequence database, obtaining the digital quantity meaning of the value of the digital quantity which is defined in advance from the redis, and inserting an alarm into an alarm queue by comparing the definition content of the new value.
And step 3, processing the multi-bit delay cache. Processing the multi-bit delay cache, reading a pre-time stamp of the digital quantity in the redis, and if the time stamp is larger than the time stamp of the timing task processing, indicating that the digital quantity has new point position change update, so that the related information of the digital quantity is not deleted in the instance internal cache and the redis cache, otherwise, deleting the related information of the digital quantity.
And processing the contents of the change and alarm queues, and if the number of the queues exceeds a certain number (which can be customized) or the processing period is over, sending out the data in the change queues and the alarm queues and emptying the queues.
Claims (6)
1. The digital quantity processing method based on the cluster type shared cache is characterized by comprising the following steps of:
Step 1, constructing a digital quantity processing cluster, wherein all instances in the cluster receive collected data sent by the front of all subsystems at average and randomly, and then multi-bit delay data information is stored in an instance local cache and a shared cache of a redis cluster;
step 2, each example in the cluster processes the multi-bit delay digital quantity of the digital quantity cached in the example at regular time to generate a new value, send an alarm, change data and time sequence data;
step 3, the example processes the multi-bit delay data buffer, the change queue and the alarm queue, and then the next period multi-bit delay processing process is carried out,
The step 1 of constructing a digital quantity processing cluster refers to: each example in the cluster receives the collected data sent by each subsystem at random on average, in the example, the program automatically judges the point position change of the digital quantity, and the multi-bit delay time is greater than zero, and starts multi-bit delay processing, if the digital quantity delay information is not in the redis shared buffer, the digital quantity is considered to be the first point position change, the change point position information of the digital quantity and the initialization information of other point positions are stored in the redis shared buffer, the key information of the digital quantity is stored in the program internal buffer, and the front time stamp of the digital quantity in the redis is set; updating only the change point location information in the redis shared cache if in the redis shared cache, and updating the leading timestamp of the digital quantity in the redis;
the storing of the multi-bit delay data information in the shared cache of the redis cluster in the step 1 refers to: the redis is used as a shared cache of each example, the initialization information, the key words and the local caches of all other points of the first time of digital quantity deflection are stored to be the same, and the field information comprises 'first time deflection time', 'delay time', 'value', 'state', 'second level deflection time', 'millisecond level deflection time' and 'whether deflection is carried out'; the prepositioning time key is a digital quantity key, and the time is the time of any point position change;
The storing of the multi-bit delayed data information in the example local cache described in step 1 refers to: because the prepositive data of the subsystem is randomly and averagely sent to the data processing cluster, each instance in the cluster randomly receives the data packet of the first time point position change of the digital quantity, the number of multi-bit delay to be processed is basically equal, so delay processing pressure can be distributed on each instance, when the digital quantity changes for the first time point position, the key word of the digital quantity point position stored by the instance is the key word of multi-bit delay data information, and the instance storage stores the key word and the current timestamp in the instance;
Each example in the cluster described in step 2 processes the number amount of the internal cache of the example in a timing manner, and the multi-bit delay number amount refers to: each instance in the cluster processes the multi-bit delay digital quantity of the digital quantity cached in the instance at fixed time, acquires multi-bit delay data to be processed of the instance from redis through key cache data in the program after the time interval is defined, judges whether the current time is more than or equal to the delay time of each digital quantity, if the current time meets the condition, the delay time is represented, then all point position information of the digital quantity is processed into the latest value of the digital quantity, and the steps of digital quantity sending alarm, change data, time sequence data and other processing are carried out;
The generating of the new value, sending the alarm, changing the data and timing data in the step 2 refers to: combining all the points of the digital quantity into a new value, namely, the point values are d1 and d2 … … dn in sequence, the new value v=d1 x 2 1-1+ d2*22-1+ d3*23-1+……+dn*2n-1, comparing the new value with the last value of the digital quantity obtained from the redis, if the new value has a change, updating the value of the digital quantity of the redis, inserting change data information into a change queue, storing the value of the updated redis digital quantity into a time sequence database, obtaining the digital quantity meaning of the value of the digital quantity defined in advance from the redis, and inserting an alarm into an alarm queue by comparing the definition content of the new value;
The step 3 of processing the multi-bit delay data buffer refers to: reading a front time stamp of the digital quantity in the redis, if the time stamp is larger than the time stamp of the timing task processing, indicating that the digital quantity has new point position change update, so that the related information of the digital quantity is not deleted in an instance internal cache and the redis cache, otherwise, deleting the related information of the digital quantity, processing the change and the alarm queue content, and if the number of the queue exceeds the configured custom number or the processing period is over, sending out the data in the change queue and the alarm queue, and emptying the queue;
The multi-bit delay processing in the step 3 refers to: the monitoring platform is internally provided with a plurality of working states of equipment by digital quantity, and the equipment states are represented by a plurality of bits; after the acquisition unit acquires the real-time state of the equipment in real time, updating a plurality of bits of the digital quantity in a point position mode to modify the state of the equipment, so that an invalid state can be generated in the updating process; in order to avoid the invalid states, when the value needs to be updated, the logic processing is performed after the value is updated.
2. A digital quantity processing system based on a cluster type shared buffer, adopting a digital quantity processing method based on the cluster type shared buffer as claimed in claim 1, characterized by comprising the following modules:
And a data acquisition module: the system comprises a subsystem, a storage subsystem and a data storage subsystem, wherein the subsystem is used for receiving the preamble data sent by the subsystem and storing multi-bit delay data;
and the delay processing module is used for: the system is used for processing multi-bit delay data in the shared cache and realizing point location processing of the acquisition equipment;
and the cache processing module is used for: the method is used for processing the multi-bit delay buffer, the change queue and the alarm queue.
3. The digital quantity processing system based on the clustered shared cache according to claim 2, wherein the data acquisition module is configured to construct a digital quantity processing cluster, specifically: each example in the cluster receives the collected data sent by each subsystem at random on average, in the example, the program automatically judges the point position change of the digital quantity, and the multi-bit delay time is greater than zero, and starts multi-bit delay processing, if the digital quantity delay information is not in the redis shared buffer, the digital quantity is considered to be the first point position change, the change point position information of the digital quantity and the initialization information of other point positions are stored in the redis shared buffer, the key information of the digital quantity is stored in the program internal buffer, and the front time stamp of the digital quantity in the redis is set; updating only the change point location information in the redis shared cache if in the redis shared cache, and updating the leading timestamp of the digital quantity in the redis;
The data acquisition module stores multi-bit delay data in two modes, one is to store multi-bit delay data information on a shared cache of a redis cluster, and the method specifically comprises the following steps: the redis is used as a shared cache of each example, the initialization information, the key words and the local caches of all other points of the first time of digital quantity deflection are stored to be the same, and the field information comprises 'first time deflection time', 'delay time', 'value', 'state', 'second level deflection time', 'millisecond level deflection time' and 'whether deflection is carried out'; the prepositioning time key is a digital quantity key, and the time is the time of any point position change; the other is to store multi-bit delay data information in an example local cache, specifically: when the number quantity changes for the first time, the key words of the number quantity point positions stored in the instance are the key words of the multi-bit delay data information, and the instance storage stores the key words and the current time stamp in the instance.
4. The digital quantity processing system based on cluster type shared buffer according to claim 2, wherein the delay processing module is configured to process multi-bit delay buffer, specifically: reading a front time stamp of the digital quantity in the redis, if the time stamp is larger than the time stamp of the timing task processing, indicating that the digital quantity has new point position change update, so that the related information of the digital quantity is not deleted in an instance internal cache and the redis cache, otherwise, deleting the related information of the digital quantity, processing the change and the alarm queue content, and if the number of the queue exceeds the configured custom number or the processing period is over, sending out the data in the change queue and the alarm queue, and emptying the queue.
5. A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method of digital volume processing based on clustered shared cache as claimed in claim 1.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a cluster-based shared cache digital volume processing method as claimed in claim 1 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410197598.1A CN117762646B (en) | 2024-02-22 | 2024-02-22 | Digital quantity processing method and system based on cluster type shared cache |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410197598.1A CN117762646B (en) | 2024-02-22 | 2024-02-22 | Digital quantity processing method and system based on cluster type shared cache |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117762646A CN117762646A (en) | 2024-03-26 |
CN117762646B true CN117762646B (en) | 2024-05-14 |
Family
ID=90314860
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410197598.1A Active CN117762646B (en) | 2024-02-22 | 2024-02-22 | Digital quantity processing method and system based on cluster type shared cache |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117762646B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102143212A (en) * | 2010-12-31 | 2011-08-03 | 华为技术有限公司 | Cache sharing method and device for content delivery network |
CN103281376A (en) * | 2013-05-31 | 2013-09-04 | 武汉大学 | Method for automatic caching construction of massive timing sequence remote-sensing images in cloud environment |
CN109491975A (en) * | 2018-11-08 | 2019-03-19 | 江苏曲速教育科技有限公司 | Distributed cache system |
US10810051B1 (en) * | 2018-11-13 | 2020-10-20 | Databricks Inc. | Autoscaling using file access or cache usage for cluster machines |
CN115562849A (en) * | 2022-09-01 | 2023-01-03 | 浪潮软件股份有限公司 | Cache data method and system based on high availability |
US11693713B1 (en) * | 2019-09-04 | 2023-07-04 | Pure Storage, Inc. | Self-tuning clusters for resilient microservices |
-
2024
- 2024-02-22 CN CN202410197598.1A patent/CN117762646B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102143212A (en) * | 2010-12-31 | 2011-08-03 | 华为技术有限公司 | Cache sharing method and device for content delivery network |
CN103281376A (en) * | 2013-05-31 | 2013-09-04 | 武汉大学 | Method for automatic caching construction of massive timing sequence remote-sensing images in cloud environment |
CN109491975A (en) * | 2018-11-08 | 2019-03-19 | 江苏曲速教育科技有限公司 | Distributed cache system |
US10810051B1 (en) * | 2018-11-13 | 2020-10-20 | Databricks Inc. | Autoscaling using file access or cache usage for cluster machines |
US11693713B1 (en) * | 2019-09-04 | 2023-07-04 | Pure Storage, Inc. | Self-tuning clusters for resilient microservices |
CN115562849A (en) * | 2022-09-01 | 2023-01-03 | 浪潮软件股份有限公司 | Cache data method and system based on high availability |
Also Published As
Publication number | Publication date |
---|---|
CN117762646A (en) | 2024-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113900810A (en) | Distributed graph processing method, system and storage medium | |
CN109739919A (en) | A kind of front end processor and acquisition system for electric system | |
CN108491332A (en) | A kind of real-time buffering updating method and system based on Redis | |
CN101488919B (en) | Memory address allocation method and apparatus | |
CN111526208A (en) | High-concurrency cloud platform file transmission optimization method based on micro-service | |
CN112069195A (en) | Database-based message transmission method and device, electronic equipment and storage medium | |
CN113360577A (en) | MPP database data processing method, device, equipment and storage medium | |
CN109921970B (en) | Data processing method and system | |
CN117762646B (en) | Digital quantity processing method and system based on cluster type shared cache | |
CN111858657B (en) | Method and equipment for accelerating data parallel query based on high-frequency data processing | |
CN115827788B (en) | Data migration method and device, electronic equipment and readable storage medium | |
CN110888739B (en) | Distributed processing method and device for delayed tasks | |
CN114895985B (en) | Data loading system for graph neural network training based on sampling | |
CN116414564A (en) | Self-adaptive cluster scheduling method and device, computer storage medium and electronic equipment | |
CN111447229A (en) | Large-scale data acquisition method and device based on compressed sensing theory | |
CN114298294B (en) | Neural network memory optimization method and device based on hardware accelerator | |
Modiano et al. | A simple analysis of average queueing delay in tree networks | |
CN112929432B (en) | Broadcasting method, equipment and storage medium based on repeated broadcasting history | |
CN114296959A (en) | Message enqueuing method and device | |
CN114063931A (en) | Data storage method based on big data | |
CN101442458A (en) | System and method for sending sequence type data | |
EP0905619A2 (en) | A list management system and method | |
CN117131000B (en) | NetCDF meteorological data processing method and terminal | |
CN115276777B (en) | TDMA networking parameter management method based on data abstract and time stamp | |
CN113590319B (en) | Method and device for balancing computing resource load of message queue |
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 |