CN104598392A - Method for realizing server cache structure by multi-stage Hash - Google Patents

Method for realizing server cache structure by multi-stage Hash Download PDF

Info

Publication number
CN104598392A
CN104598392A CN201310527807.6A CN201310527807A CN104598392A CN 104598392 A CN104598392 A CN 104598392A CN 201310527807 A CN201310527807 A CN 201310527807A CN 104598392 A CN104598392 A CN 104598392A
Authority
CN
China
Prior art keywords
server
caches
buffer
multistage hash
line number
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.)
Pending
Application number
CN201310527807.6A
Other languages
Chinese (zh)
Inventor
不公告发明人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Sirun Software Co Ltd
Original Assignee
Nanjing Sirun Software Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Sirun Software Co Ltd filed Critical Nanjing Sirun Software Co Ltd
Priority to CN201310527807.6A priority Critical patent/CN104598392A/en
Publication of CN104598392A publication Critical patent/CN104598392A/en
Pending legal-status Critical Current

Links

Abstract

The invention relates to a method for realizing a server cache structure by multi-stage Hash, and can solve the problem of overmany server caches. At present, a computer application technology is penetrated into every walk of life, each industry has the own server, overmany caches exist in the servers, so that the operation efficiency of the server is low after a long time. By aiming at the problem of low working efficiency of the server due to serious caches in the server, the invention realizes a method for realizing the server cache structure by multi-stage Hash, a directory structure of the caches generated in a server operation process can be obtained, and then, the obtained directory structure of the caches of the server can be cleared.

Description

A kind of implementation method utilizing multistage Hash server buffer structure
Technical field
The present invention relates to a kind of implementation method utilizing multistage Hash server buffer structure.The invention belongs to field of computer technology.
Background technology
Current, computer technology has penetrated into often goes in every industry, and server network data transmit-receive does not do buffer memory with storing.If the significant data of company is stored in disk, and data have portion upgrade and have a large amount of access close to office's static but every day, do not do the high-performance that buffer memory can not play machine.Such as, usually, there is the server concentrating fixing model in intra-company, and often kind has its performance boundary, generally comprises but is not limited to CPU computing power, network interface card transmitting-receiving bag ability, memory size and disk size and his read or write speed.Multistage hash is namely relevant with memory size.Suppose that a dell server memory is 8G, if do buffer memory with multistage hash, so just can consider that to the capacity of buffer memory be 6G, namely 3/4 or 2/3 of general memory capacity consider the very big capacity being used as buffer memory.Certain server is certain business service, and simply think that the value of business is key-value form, usually, key has fixed size Ksize certainly, and value maximal value also has ultimate value Vsize_max.
Summary of the invention
The high performance problem that buffer memory can not play machine is not done for this, and as far as possible for company saves human cost, saves time, there is provided work more efficient, invention describes a kind of implementation method utilizing multistage Hash server buffer structure, meet the high-performance operating requirements of corporate server.Concrete steps are as follows:
Step 1: the time range of buffer memory is removed in setting.According to system need carry out the clear of server buffer, time range can be determine according to server time.
Step 2: priority assignation.In order to the security of Deterministic service device data, removing caching function must through authorizing.System manager can carry out right assignment to personnel.The user only having authority could carry out the removing of server buffer in the server.
Step 3: buffer memory is removed.After the logging in system by user had permission, click " removing server buffer " function, system is just automatic by the removing of server buffer, and limited rights user can according to the time selectively to the removing carrying out server buffer in server.。
Step 4: server removes caching record.User is to obtaining after the server buffer of coming removes, and system can the information such as time, operator of automatic record purge buffer memory.
Whether whether the method automatically record active user can remove server buffer in this month (or season, year).In addition, if method also provides the buffer memory needing to remove server just generation within certain time range, in order to avoid important information is eliminated.
Embodiment
Embodiment one
Use Microsoft Visual Studio 2012 as developing instrument, use special database management tools SQL Server on market to set up the database required for system.
1. carry out according to the needs of server the setting can removing server time scope, time range can be determine according to server time, and removing to keep server buffer can not be the up-to-date buffer memory running generation of server.
2. in order to the security of Deterministic service device CACHE DIRECTORY structure.It is need system authorization to use that server buffer removes function.
3., after the logging in system by user had permission, click " removing server buffer " function, system just automatic last time was removed after new generation buffer structure after go, the buffer memory that acquisition is come is according to rise time auto-sequencing.In operation, system can operate vestige by record automatically, records the record that this user removes server buffer.
4. user can carry out clear operation to server buffer according to actual needs.
In addition to the implementation, the present invention can also have other embodiments.All employings are equal to the technical scheme of replacement or equivalent transformation formation, all drop on the protection domain of application claims.

Claims (5)

1. the significant data of company is stored in disk, and data are close to static but have local updating every day and have a large amount of access, do not do the high-performance that buffer memory can not play machine.
2. usually, there is the server concentrating fixing model in intra-company, often kind has its performance boundary, and generally comprise but be not limited to CPU computing power, network interface card transmitting-receiving bag ability, memory size and disk size and his read or write speed, multistage hash is namely relevant with memory size.
3. multistage hash just can realize two characteristics of server buffer above-mentioned, and the first, be cached with power-carrying; The second, each key-value unit have fixed size (Ksize+Vsize_max).
4. multistage hash line number is more, and its space availability ratio is higher, and right seek rate just slows down gradually; Otherwise line number is fewer, then multistage hash seek rate is faster, and right space availability ratio is low, so within line number should be controlled in 50 row, be generally advisable between 20 to 35 row.
5. insertion is provided in method, searches and deletion action.
CN201310527807.6A 2013-10-31 2013-10-31 Method for realizing server cache structure by multi-stage Hash Pending CN104598392A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310527807.6A CN104598392A (en) 2013-10-31 2013-10-31 Method for realizing server cache structure by multi-stage Hash

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310527807.6A CN104598392A (en) 2013-10-31 2013-10-31 Method for realizing server cache structure by multi-stage Hash

Publications (1)

Publication Number Publication Date
CN104598392A true CN104598392A (en) 2015-05-06

Family

ID=53124200

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310527807.6A Pending CN104598392A (en) 2013-10-31 2013-10-31 Method for realizing server cache structure by multi-stage Hash

Country Status (1)

Country Link
CN (1) CN104598392A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1437357A (en) * 2002-02-07 2003-08-20 华为技术有限公司 Virtual channel mark/virtual route mark searching method of multipl hash function
US20050267992A1 (en) * 2001-04-02 2005-12-01 Microsoft Corporation Peer-to-peer name resolution protocol (PNRP) and multilevel cache for use therewith
CN1871587A (en) * 2003-10-20 2006-11-29 罗得岛及普罗维登斯属地高等教育管理委员会 Bottom-up cache structure for storage servers
CN101887398A (en) * 2010-06-25 2010-11-17 浪潮(北京)电子信息产业有限公司 Method and system for dynamically enhancing input/output (I/O) throughput of server
CN102279810A (en) * 2011-08-11 2011-12-14 浪潮(北京)电子信息产业有限公司 Network storage server and method for caching data

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050267992A1 (en) * 2001-04-02 2005-12-01 Microsoft Corporation Peer-to-peer name resolution protocol (PNRP) and multilevel cache for use therewith
CN1437357A (en) * 2002-02-07 2003-08-20 华为技术有限公司 Virtual channel mark/virtual route mark searching method of multipl hash function
CN1871587A (en) * 2003-10-20 2006-11-29 罗得岛及普罗维登斯属地高等教育管理委员会 Bottom-up cache structure for storage servers
CN101887398A (en) * 2010-06-25 2010-11-17 浪潮(北京)电子信息产业有限公司 Method and system for dynamically enhancing input/output (I/O) throughput of server
CN102279810A (en) * 2011-08-11 2011-12-14 浪潮(北京)电子信息产业有限公司 Network storage server and method for caching data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ALEXANDER S: "介绍一种服务器缓存结构---多级Hash", 《英特尔开发人员专区》 *

Similar Documents

Publication Publication Date Title
CN102222085B (en) Data de-duplication method based on combination of similarity and locality
Tang et al. {RIPQ}: Advanced photo caching on flash for facebook
CN103336849B (en) A kind of database retrieval system improves the method and device of retrieval rate
US11537584B2 (en) Pre-caching of relational database management system based on data retrieval patterns
Stoica et al. Enabling efficient OS paging for main-memory OLTP databases
CN104145468B (en) File access authority control method and device thereof
US20150067001A1 (en) Cache management in a computerized system
US10042885B2 (en) Index table based routing for query resource optimization
CN108733507A (en) The method and apparatus of file backup and recovery
CN107003814A (en) Effective metadata in storage system
CN104239234B (en) The management of a kind of local cache efficiently and reading/writing method
CN105335219A (en) Distribution-based task scheduling method and system
CN104054071A (en) Method for accessing storage device and storage device
US11080207B2 (en) Caching framework for big-data engines in the cloud
EP2765522B1 (en) Method and device for data pre-heating
CN105339903A (en) Restoring a file system object
US20140082316A1 (en) Selecting pages implementing leaf nodes and internal nodes of a data set index for reuse
CN102694828A (en) Method and apparatus for data access in distributed caching system
CN104978324A (en) Data processing method and device
CN110399096A (en) Metadata of distributed type file system caches the method, apparatus and equipment deleted again
US10996857B1 (en) Extent map performance
CN109086462A (en) The management method of metadata in a kind of distributed file system
US10459947B2 (en) Frequency dependent partial index
CN106020720A (en) Method for optimizing IO performance of Smart Rack nodes
CN103823634A (en) Data processing method and system supporting non-random write mode

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20150506

WD01 Invention patent application deemed withdrawn after publication