CN104991745A - Data writing method and system of storage system - Google Patents
Data writing method and system of storage system Download PDFInfo
- Publication number
- CN104991745A CN104991745A CN201510432216.XA CN201510432216A CN104991745A CN 104991745 A CN104991745 A CN 104991745A CN 201510432216 A CN201510432216 A CN 201510432216A CN 104991745 A CN104991745 A CN 104991745A
- Authority
- CN
- China
- Prior art keywords
- data
- write
- request
- chinese ink
- writing
- 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
Abstract
The invention discloses a data writing method and system of a storage system. The data writing method comprises: receiving a writing IO request of a calculation node by a data receiving and protocol analysis subsystem; the writing IO request comprising at least one communication message and the communication message comprising a protocol field and an effective load field; in a process of receiving the writing IO request, respectively storing protocol field data and effective load field data of the communication message into different positions of a high-speed storage medium, and independently storing the effective load field data of the communication message; after receiving the writing IO request, transmitting the writing IO request to a data caching subsystem; and after receiving the writing IO request by the data caching subsystem, returning writing operation finishing operation back to the calculation node, and carrying out writing operation on the writing IO request. By virtue of the data writing method and system of the storage system, the data writing performance of the storage system can be improved under the same hardware platform.
Description
Technical field
The present invention relates to technical field of computer data storage, espespecially a kind of memory system data wiring method and system.
Background technology
So far, in the large field of data storage of magnanimity, as one, independently equipment is independent from computing system for storage system for technical development of computer.Fig. 1 is the configuration diagram of the computing system that large data of the present invention store, and as shown in Figure 1, whole computing system is just by computing subsystem, and transmission subsystem and storage subsystem three part form.In this case, along with the raising of the computing power of computing subsystem, the performance requirement just proposed the performance of storage subsystem is just more and more higher.
The main performance index of storage system comprises: input per second and output (IO, Input and Output) number, handling capacity and IO response time.IO number per second is called for short IOps (IO per Second), and be the number of times of storage system performed I/O operation per second, be used to the important indicator weighing storage system IO processing power, the IO processing power of this numerical value larger explanation storage system is stronger.Handling capacity also claims transfer rate or bandwidth, the data volume flow through from the transfer bus of storage system per second when being actual use, this index identifies maximum volume of transmitted data, can be important when sequential access or big data quantity access, this index is generally limited to the performance of hardware bus, as I/O transmission bus bandwidth, the factors such as memory bandwidth.The IO response time is also referred to as IO time delay, being an IO order of reading or write sending from computing system receives to computing system the time that IO responds, this index is for weighing the processing speed of storage system to single IO, and this numerical value less explanation IO processing speed is faster.
At present, the permanent storage media of storage system mainly uses mechanical hard disk, and the performance of system is mainly limited to the memory property of single storage medium.For improving the overall performance of whole system, the method for the multiple storage medium concurrent reading and concurrent writing of the many employings of industry.Simultaneously, other high speed storing media are added between computing subsystem and storage medium, such as solid state hard disc (SSD, Solid State Drives), random access memory (RAM, Random-Access Memory) etc., and data are kept at temporarily on high speed storing medium, when system idles, data are synchronized to permanent storage media from high speed storing medium afterwards.
Summary of the invention
In order to solve the problems of the technologies described above, the invention provides a kind of memory system data wiring method and system, under same hardware platform, memory system data write performance can be improved.
In order to reach the object of the invention, the invention provides a kind of memory system data wiring method, comprise: what data receiver and protocol analysis subsystem received computing node writes I/O request, described I/O request of writing comprises at least one communication message, and described communication message comprises protocol fields and useful load field; Write in the process of I/O request described in reception, the protocol fields data of described communication message and useful load field data are left respectively in the diverse location of high speed storing medium, and the useful load field data of described communication message is independently deposited; Describedly write after I/O request finishes receiving, described I/O request of writing is sent to data buffer storage subsystem; After writing I/O request described in data buffer storage subsystem receives, return write operation to computing node and complete information, and write operation is carried out to described I/O request of writing.
Further, described reception described in write in the process of I/O request, the protocol fields data writing I/O request by described and useful load field data leave high speed storing medium respectively in, be specially: write in the process of I/O request described in reception, by the protocol data district of the protocol fields deposit data in communication message at high speed storing medium, the useful load field data in described communication message is left in the I/O data district of high speed storing medium.
Further, describedly write after I/O request finishes receiving, described I/O request of writing is sent to data buffer storage subsystem, be specially: described in write after I/O request finishes receiving, by described write I/O request and described in write the I/O request queue that the deposit data position of I/O request in high speed storing medium sends data buffer storage subsystem to.
Further, described write operation is carried out to described I/O request of writing, be specially: after writing I/O request described in the I/O request queue of described data buffer storage subsystem receives, wake the cache pool of data buffer storage subsystem up; Described cache pool writes I/O request described in obtaining from I/O request queue, and the described useful load field data writing I/O request corresponding is written in cache pool according to described deposit data position.
Further, described method also comprises: dirty data is write with a brush dipped in Chinese ink subsystem and write with a brush dipped in Chinese ink the data in described data buffer storage subsystem, and the data after writing with a brush dipped in Chinese ink is written in permanent storage media.
Further, described dirty data is write with a brush dipped in Chinese ink subsystem and is write with a brush dipped in Chinese ink the data in described data buffer storage subsystem, be specially: determine to write with a brush dipped in Chinese ink mode according to the type of permanent storage media, described dirty data is write with a brush dipped in Chinese ink subsystem and is adopted the mode of writing with a brush dipped in Chinese ink determined to write with a brush dipped in Chinese ink the data in the cache pool of described data buffer storage subsystem.
Further, described in write with a brush dipped in Chinese ink mode and comprise order bulk and write with a brush dipped in Chinese ink, fixed block size alignment is write with a brush dipped in Chinese ink and is write with a brush dipped in Chinese ink with concurrent dispersion; If permanent storage media is common hard disc, the mode of writing with a brush dipped in Chinese ink determined is that order bulk is write with a brush dipped in Chinese ink; If permanent storage media is the RAID permutation using hard disk composition, the mode of writing with a brush dipped in Chinese ink determined is that the fixed block size alignment that data are carried out according to the band of array is write with a brush dipped in Chinese ink; If permanent storage media is distributed storage pond, the mode of writing with a brush dipped in Chinese ink determined is that concurrent dispersion is write with a brush dipped in Chinese ink.
Present invention also offers a kind of memory system data writing system, comprise: data receiver and protocol analysis subsystem, write I/O request for what receive computing node, described in write I/O request and write at least one communication message of I/O request, described communication message comprises protocol fields and useful load field; Write in the process of I/O request described in reception, the protocol fields data of described communication message and useful load field data are left respectively in the diverse location of high speed storing medium, and the useful load field data of described communication message is independently deposited; Describedly write after I/O request finishes receiving, described I/O request of writing is sent to data buffer storage subsystem; Data buffer storage subsystem, after writing I/O request described in receiving, returns write operation to computing node and completes information, and carry out write operation to described I/O request of writing.
Further, described data receiver and protocol analysis subsystem, specifically for: what receive computing node writes I/O request; Write in the process of I/O request described in reception, by the protocol data district of the protocol fields deposit data of communication message at high speed storing medium, the useful load field data of communication message is left in the I/O data district of high speed storing medium; Describedly write after I/O request finishes receiving, by described write I/O request and described in write I/O request to send data buffer storage subsystem to I/O request queue in the deposit data position of high speed storing medium.
Further, described data buffer storage subsystem, after writing I/O request, returns write operation to computing node and completes information, and wake the cache pool of data buffer storage subsystem up specifically for I/O request queue described in receiving; Described cache pool writes I/O request described in obtaining from I/O request queue, the described useful load field data writing I/O request corresponding is written in cache pool according to described deposit data position.
Further, described device also comprises: dirty data writes with a brush dipped in Chinese ink subsystem, for determining to write with a brush dipped in Chinese ink mode according to the type of permanent storage media, adopt the mode of writing with a brush dipped in Chinese ink determined to write with a brush dipped in Chinese ink the data in the cache pool of described data buffer storage subsystem, and the data after writing with a brush dipped in Chinese ink are written in permanent storage media.
Further, described in write with a brush dipped in Chinese ink mode and comprise order bulk and write with a brush dipped in Chinese ink, fixed block size alignment is write with a brush dipped in Chinese ink and is write with a brush dipped in Chinese ink with concurrent dispersion; If permanent storage media is common hard disc, the mode of writing with a brush dipped in Chinese ink determined is that order bulk is write with a brush dipped in Chinese ink; If permanent storage media is the RAID permutation using hard disk composition, the mode of writing with a brush dipped in Chinese ink determined is that the fixed block size alignment that data are carried out according to the band of array is write with a brush dipped in Chinese ink; If permanent storage media is distributed storage pond, the mode of writing with a brush dipped in Chinese ink determined is that concurrent dispersion is write with a brush dipped in Chinese ink.
Compared with prior art, the present invention, when IO is write in process, by parsing protocol data in advance, avoids the memory copying produced in protocol analysis process, thus internal memory load effectively in reduction system and processor load; It is also processor load in order to effectively reduce system that dirty data is write with a brush dipped in Chinese ink, and the direct effect that internal memory load declines is exactly the raising bringing storage system throughput, processor load decline can result be exactly that processor has more to process and writes I/O request thus the IOPS index of the IO processing power of elevator system and storage system; In addition, write the method that IO completes and shorten by returning in advance the process path writing IO, thus reduce the IO reaction time of write operation.The present invention is based on the computing system that existing large data store, under same hardware platform, effectively can reduce system load, reduce IO time delay, the internal memory load in reduction system and processor, increase system IO processing power.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in instructions, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide the further understanding to technical solution of the present invention, and forms a part for instructions, is used from and explains technical scheme of the present invention, do not form the restriction to technical solution of the present invention with the embodiment one of the application.
Fig. 1 is the configuration diagram of the computing system that large data of the present invention store.
Fig. 2 is the structural representation of storage system in a kind of embodiment of the present invention.
Fig. 3 is the schematic flow sheet of memory system data wiring method in a kind of embodiment of the present invention.
Fig. 4 is the schematic diagram that in memory system data ablation process of the present invention, data message receives process.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, hereinafter will be described in detail to embodiments of the invention by reference to the accompanying drawings.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combination in any mutually.
Can perform in the computer system of such as one group of computer executable instructions in the step shown in the process flow diagram of accompanying drawing.Further, although show logical order in flow charts, in some cases, can be different from the step shown or described by order execution herein.
The present invention is based on the computing system that existing large data store, under same hardware platform, effectively can reduce system load, reduce IO time delay, the internal memory load in reduction system and processor, increase system IO processing power.
Fig. 2 is the structural representation of storage system in a kind of embodiment of the present invention.As shown in Figure 2, memory system data writing system of the present invention comprises: data receiver and protocol analysis subsystem, data buffer storage subsystem and dirty data write with a brush dipped in Chinese ink subsystem, wherein,
Data receiver and protocol analysis subsystem, communicate with computing node for being responsible for, what receive computing node writes I/O request, and writes I/O request result to computing node feedback.
In the present invention, be reduce the RAM load of system, the data received resolved in reception data simultaneously, particularly, by the protocol data in communication message with write I/O data and separately deposit, I/O data will be write and leave separately I/O data region in; After complete write request data receiver completes, the data position of write request and correspondence is passed to data buffer storage subsystem by data receiver and protocol analysis subsystem.
Data buffer storage subsystem, comprises I/O request queue and data buffer storage pond.
Particularly, I/O request queue, what responsible reception passed over from data receiver and protocol analysis subsystem writes I/O request; For shortening IO path, I/O request queue, receiving after data write IO, returns to upper strata at once and writes into, just start the IO work for the treatment of of backstage cache pool afterwards, cache pool takes out and writes I/O request from I/O request queue, then the data of write is merged in data buffer storage and goes.The management algorithm of data buffer storage is known for those skilled in the art, therefore is not repeated herein.
Dirty data writes with a brush dipped in Chinese ink subsystem, data is written in permanent storage media from cache pool.
Particularly, writing with a brush dipped in Chinese ink performance, reducing the system load that dirty data writes with a brush dipped in Chinese ink operation for reaching optimum data, data are write with a brush dipped in Chinese ink module and are write with a brush dipped in Chinese ink scheme according to the type selecting optimum of permanent storage media.In the present invention, scheme of writing with a brush dipped in Chinese ink comprise order bulk write with a brush dipped in Chinese ink, fixed block size is write with a brush dipped in Chinese ink going, and several mode is write with a brush dipped in Chinese ink in concurrent dispersion, if the permanent storage media of rear end is common hard disc, use order bulk write with a brush dipped in Chinese ink; If permanent storage media is the RAID permutation using hard disk composition, data are write with a brush dipped in Chinese ink according to the stripe size alignment of array; If permanent storage media is distributed storage pond, dispersion parallel mode is used to write with a brush dipped in Chinese ink.
Data of the present invention are write I/O request and are initiated by the computing node in computing system, received and process by storage system.Based on above-mentioned storage system, as shown in Figure 3, memory system data wiring method of the present invention, comprising:
Step 301, what data receiver and protocol analysis subsystem received computing node writes I/O request, and this writes at least one communication message of I/O request, and communication message comprises protocol fields and useful load field; Write in the process of I/O request in reception, obtain the useful load field data of this communication message, and useful load field data is left in the diverse location of high speed storing medium, and the useful load field data of communication message is independently deposited; This writes after I/O request finishes receiving, and this is write I/O request and is sent to data buffer storage subsystem.
In this step, what data receiver and protocol analysis subsystem received computing node writes I/O request, and this writes I/O request as shown in Figure 4, comprises one or more communication message, and each communication message comprises protocol fields and useful load field.Write in the process of I/O request in reception, data receiver and protocol analysis subsystem are resolved the I/O request of writing received, the protocol fields data and useful load field data of writing each communication message in I/O request are separately deposited, particularly, the useful load field data of communication message, by the protocol data district of the protocol fields deposit data of communication message at high speed storing medium, is left in the I/O data district of high speed storing medium by data receiver and protocol analysis subsystem.
Write after I/O request finishes receiving complete, this is write I/O request and is sent in the I/O request queue of cache subsystem by data receiver and protocol analysis subsystem, and the deposit data position this being write I/O request corresponding in high speed storing medium sends to data buffer storage subsystem.
Step 302, after data buffer storage subsystem receives and writes I/O request, returns write operation to computing node and completes information, and carries out write operation to writing I/O request.
In this step, the I/O request queue of data buffer storage subsystem returns write operation to computing node and completes information after receiving and writing I/O request, and wakes the cache pool of data buffer storage subsystem up; Cache pool obtains and writes I/O request from I/O request queue, and the useful load field data this being write I/O request corresponding according to deposit data position is written in cache pool, and wherein the management algorithm of data buffer storage is known for those skilled in the art, therefore is not repeated herein.
Step 303, dirty data is write with a brush dipped in Chinese ink subsystem and is write with a brush dipped in Chinese ink the data in data cache subsystem, and the data after writing with a brush dipped in Chinese ink is written in permanent storage media.
In this step, dirty data is write with a brush dipped in Chinese ink subsystem and is write with a brush dipped in Chinese ink the data in the cache pool of data cache subsystem, and the data after writing with a brush dipped in Chinese ink is written in permanent storage media.So, reducing storage system load, making storage system have more sufficient processing power for the treatment of writing I/O request.
Writing with a brush dipped in Chinese ink performance for reaching optimum data, reducing the system load that dirty data writes with a brush dipped in Chinese ink operation, data are write with a brush dipped in Chinese ink module and are write with a brush dipped in Chinese ink scheme according to the type selecting optimum of permanent storage media.In a particular embodiment of the present invention, the scheme of writing with a brush dipped in Chinese ink comprises order bulk and writes with a brush dipped in Chinese ink, and fixed block size is write with a brush dipped in Chinese ink going, and several mode is write with a brush dipped in Chinese ink in concurrent dispersion.If the permanent storage media of such as rear end is common hard disc, use order bulk is write with a brush dipped in Chinese ink; If permanent storage media is the RAID permutation using hard disk composition, data are write with a brush dipped in Chinese ink according to the stripe size alignment of array; If permanent storage media is distributed storage pond, dispersion parallel mode is used to write with a brush dipped in Chinese ink.
Described can be found out by said system, the present invention, when IO is write in process, by parsing protocol data in advance, avoids the memory copying produced in protocol analysis process, thus internal memory load effectively in reduction system and processor load; It is also processor load in order to effectively reduce system that dirty data is write with a brush dipped in Chinese ink, and the direct effect that internal memory load declines is exactly the raising bringing storage system throughput, processor load decline can result be exactly that processor has more to process and writes I/O request thus the IOPS index of the IO processing power of elevator system and storage system; In addition, write the method that IO completes and shorten by returning in advance the process path writing IO, thus reduce the IO reaction time of write operation.
Although the embodiment disclosed by the present invention is as above, the embodiment that described content only adopts for ease of understanding the present invention, and be not used to limit the present invention.Those of skill in the art belonging to any the present invention; under the prerequisite not departing from the spirit and scope disclosed by the present invention; any amendment and change can be carried out in the form implemented and details; but scope of patent protection of the present invention, the scope that still must define with appending claims is as the criterion.
Claims (12)
1. a memory system data wiring method, is characterized in that, comprising:
What data receiver and protocol analysis subsystem received computing node writes I/O request, described in write I/O request and comprise at least one communication message, described communication message comprises protocol fields and useful load field; Write in the process of I/O request described in reception, the protocol fields data of described communication message and useful load field data are left respectively in the diverse location of high speed storing medium, and the useful load field data of described communication message is independently deposited; Describedly write after I/O request finishes receiving, described I/O request of writing is sent to data buffer storage subsystem;
After writing I/O request described in data buffer storage subsystem receives, return write operation to computing node and complete information, and write operation is carried out to described I/O request of writing.
2. memory system data wiring method according to claim 1, it is characterized in that, described reception described in write in the process of I/O request, the protocol fields data of described communication message and useful load field data are left respectively in the diverse location of high speed storing medium, are specially:
Write in the process of I/O request described in reception, by the protocol data district of the protocol fields deposit data in described communication message at high speed storing medium, the useful load field data in described communication message is left in the I/O data district of high speed storing medium.
3. memory system data wiring method according to claim 2, is characterized in that, described in write after I/O request finishes receiving, described I/O request of writing is sent to data buffer storage subsystem, is specially:
Describedly write after I/O request finishes receiving, by described write I/O request and described in write the I/O request queue that the deposit data positional information of I/O request in the I/O data district of high speed storing medium sends data buffer storage subsystem to.
4. memory system data wiring method according to claim 3, is characterized in that, describedly carries out write operation to described I/O request of writing, and is specially:
After writing I/O request described in the I/O request queue of described data buffer storage subsystem receives, wake the cache pool of data buffer storage subsystem up; Described cache pool writes I/O request described in obtaining from I/O request queue, and the described useful load field data writing I/O request is written in cache pool according to described deposit data position.
5. memory system data wiring method according to claim 4, it is characterized in that, described method also comprises: dirty data is write with a brush dipped in Chinese ink subsystem and write with a brush dipped in Chinese ink the data in described data buffer storage subsystem, and the data after writing with a brush dipped in Chinese ink is written in permanent storage media.
6. memory system data wiring method according to claim 5, is characterized in that, described dirty data is write with a brush dipped in Chinese ink subsystem and write with a brush dipped in Chinese ink the data in described data buffer storage subsystem, is specially:
Determine to write with a brush dipped in Chinese ink mode according to the type of permanent storage media, described dirty data is write with a brush dipped in Chinese ink subsystem and is adopted the mode of writing with a brush dipped in Chinese ink determined to write with a brush dipped in Chinese ink the data in the cache pool of described data buffer storage subsystem.
7. memory system data wiring method according to claim 6, is characterized in that, described in write with a brush dipped in Chinese ink mode and comprise order bulk and write with a brush dipped in Chinese ink, fixed block size alignment is write with a brush dipped in Chinese ink and is write with a brush dipped in Chinese ink with concurrent dispersion;
If permanent storage media is common hard disc, the mode of writing with a brush dipped in Chinese ink determined is that order bulk is write with a brush dipped in Chinese ink; If permanent storage media is the RAID permutation using hard disk composition, the mode of writing with a brush dipped in Chinese ink determined is that the fixed block size alignment that data are carried out according to the band of array is write with a brush dipped in Chinese ink; If permanent storage media is distributed storage pond, the mode of writing with a brush dipped in Chinese ink determined is that concurrent dispersion is write with a brush dipped in Chinese ink.
8. a storage system, is characterized in that, comprising:
Data receiver and protocol analysis subsystem, write I/O request for what receive computing node, described in write at least one communication message of I/O request, described communication message comprises protocol fields and useful load field; Write in the process of I/O request described in reception, the protocol fields data of described communication message and useful load field data are left respectively in the diverse location of high speed storing medium, and the useful load field data of described communication message is independently deposited; Describedly write after I/O request finishes receiving, described I/O request of writing is sent to data buffer storage subsystem;
Data buffer storage subsystem, after writing I/O request described in receiving, returns write operation to computing node and completes information, and carry out write operation to described I/O request of writing.
9. storage system according to claim 8, is characterized in that, described data receiver and protocol analysis subsystem, specifically for:
What receive computing node writes I/O request; Write in the process of I/O request described in reception, by the protocol data district of the protocol fields deposit data in described communication message at high speed storing medium, the useful load field data in described communication message is left in the I/O data district of high speed storing medium; Describedly write after I/O request finishes receiving, by described write I/O request and described in write I/O request to send data buffer storage subsystem to I/O request queue in the deposit data position of high speed storing medium.
10. storage system according to claim 9, is characterized in that, described data buffer storage subsystem, after writing I/O request, returns write operation and completes information, and wake the cache pool of data buffer storage subsystem up to computing node specifically for I/O request queue described in receiving; Described cache pool writes I/O request described in obtaining from I/O request queue, the described useful load field data writing I/O request corresponding is written in cache pool according to described deposit data position.
11. storage systems according to claim 10, it is characterized in that, described device also comprises: dirty data writes with a brush dipped in Chinese ink subsystem, for determining to write with a brush dipped in Chinese ink mode according to the type of permanent storage media, adopt the mode of writing with a brush dipped in Chinese ink determined to write with a brush dipped in Chinese ink the data in the cache pool of described data buffer storage subsystem, and the data after writing with a brush dipped in Chinese ink are written in permanent storage media.
12. storage systems according to claim 11, is characterized in that, described in write with a brush dipped in Chinese ink mode and comprise order bulk and write with a brush dipped in Chinese ink, fixed block size alignment is write with a brush dipped in Chinese ink and is write with a brush dipped in Chinese ink with concurrent dispersion;
If permanent storage media is common hard disc, the mode of writing with a brush dipped in Chinese ink determined is that order bulk is write with a brush dipped in Chinese ink; If permanent storage media is the RAID permutation using hard disk composition, the mode of writing with a brush dipped in Chinese ink determined is that the fixed block size alignment that data are carried out according to the band of array is write with a brush dipped in Chinese ink; If permanent storage media is distributed storage pond, the mode of writing with a brush dipped in Chinese ink determined is that concurrent dispersion is write with a brush dipped in Chinese ink.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510432216.XA CN104991745B (en) | 2015-07-21 | 2015-07-21 | A kind of memory system data wiring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510432216.XA CN104991745B (en) | 2015-07-21 | 2015-07-21 | A kind of memory system data wiring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104991745A true CN104991745A (en) | 2015-10-21 |
| CN104991745B CN104991745B (en) | 2018-06-01 |
Family
ID=54303561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510432216.XA Active CN104991745B (en) | 2015-07-21 | 2015-07-21 | A kind of memory system data wiring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104991745B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506146A (en) * | 2017-08-29 | 2017-12-22 | 郑州云海信息技术有限公司 | A kind of data-storage system |
| CN107728936A (en) * | 2017-09-05 | 2018-02-23 | 华为技术有限公司 | Method and apparatus for transmitting data processing request |
| CN109992212A (en) * | 2019-04-10 | 2019-07-09 | 苏州浪潮智能科技有限公司 | A kind of method for writing data and a kind of method for reading data |
| CN114281762A (en) * | 2022-03-02 | 2022-04-05 | 苏州浪潮智能科技有限公司 | Log storage acceleration method, device, equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1870593A (en) * | 2006-04-12 | 2006-11-29 | 杭州华为三康技术有限公司 | Method and device of read-write buffer storage location based on field programable logical array |
| US20070050569A1 (en) * | 2005-09-01 | 2007-03-01 | Nils Haustein | Data management system and method |
| CN102782661A (en) * | 2012-05-18 | 2012-11-14 | 华为技术有限公司 | Data storage system and method |
| CN103064929A (en) * | 2012-12-24 | 2013-04-24 | 创新科存储技术（深圳）有限公司 | Method for server writing data in network file system |
| CN103970688A (en) * | 2013-02-04 | 2014-08-06 | Lsi公司 | Method and system for reducing write latency in a data storage system |
| CN104461936A (en) * | 2014-11-28 | 2015-03-25 | 华为技术有限公司 | Cached data disk brushing method and device |
| CN104536704A (en) * | 2015-01-12 | 2015-04-22 | 浪潮(北京)电子信息产业有限公司 | Dual-controller communication method, transmitting end controller and receiving end controller |
-
2015
- 2015-07-21 CN CN201510432216.XA patent/CN104991745B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070050569A1 (en) * | 2005-09-01 | 2007-03-01 | Nils Haustein | Data management system and method |
| CN1870593A (en) * | 2006-04-12 | 2006-11-29 | 杭州华为三康技术有限公司 | Method and device of read-write buffer storage location based on field programable logical array |
| CN102782661A (en) * | 2012-05-18 | 2012-11-14 | 华为技术有限公司 | Data storage system and method |
| CN103064929A (en) * | 2012-12-24 | 2013-04-24 | 创新科存储技术（深圳）有限公司 | Method for server writing data in network file system |
| CN103970688A (en) * | 2013-02-04 | 2014-08-06 | Lsi公司 | Method and system for reducing write latency in a data storage system |
| CN104461936A (en) * | 2014-11-28 | 2015-03-25 | 华为技术有限公司 | Cached data disk brushing method and device |
| CN104536704A (en) * | 2015-01-12 | 2015-04-22 | 浪潮(北京)电子信息产业有限公司 | Dual-controller communication method, transmitting end controller and receiving end controller |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506146A (en) * | 2017-08-29 | 2017-12-22 | 郑州云海信息技术有限公司 | A kind of data-storage system |
| CN107728936A (en) * | 2017-09-05 | 2018-02-23 | 华为技术有限公司 | Method and apparatus for transmitting data processing request |
| CN107728936B (en) * | 2017-09-05 | 2020-10-09 | 华为技术有限公司 | Method and apparatus for transmitting data processing requests |
| US11169743B2 (en) | 2017-09-05 | 2021-11-09 | Huawei Technologies Co., Ltd. | Energy management method and apparatus for processing a request at a solid state drive cluster |
| CN109992212A (en) * | 2019-04-10 | 2019-07-09 | 苏州浪潮智能科技有限公司 | A kind of method for writing data and a kind of method for reading data |
| CN114281762A (en) * | 2022-03-02 | 2022-04-05 | 苏州浪潮智能科技有限公司 | Log storage acceleration method, device, equipment and medium |
| CN114281762B (en) * | 2022-03-02 | 2022-06-03 | 苏州浪潮智能科技有限公司 | Log storage acceleration method, device, equipment and medium |
| WO2023165196A1 (en) * | 2022-03-02 | 2023-09-07 | 苏州浪潮智能科技有限公司 | Journal storage acceleration method and apparatus, and electronic device and non-volatile readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104991745B (en) | 2018-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10705974B2 (en) | Data processing method and NVME storage device | |
| CN101727299B (en) | RAID5-orientated optimal design method for writing operation in continuous data storage | |
| CN102693198B (en) | DMA (direct memory access) transmission method and system | |
| US9582433B2 (en) | Disk array flushing method and disk array flushing apparatus | |
| CN104407933A (en) | Data backup method and device | |
| CN111897751A (en) | Data transmission method, device, equipment and system | |
| CN103329111A (en) | Data processing method, device and system based on block storage | |
| EP3316150B1 (en) | Method and apparatus for file compaction in key-value storage system | |
| EP2557494A1 (en) | Storage apparatus and data copy method between thin-provisioning virtual volumes | |
| US20130275668A1 (en) | Data processing method and device | |
| CN104991745A (en) | Data writing method and system of storage system | |
| WO2015066489A2 (en) | Efficient implementations for mapreduce systems | |
| CN104765575A (en) | Information storage processing method | |
| CN103002046B (en) | Multi-system data copying remote direct memory access (RDMA) framework | |
| CN109388590A (en) | Promote the dynamic buffering block management method and device of multi-channel DMA access performance | |
| CN103049220A (en) | Storage control method, storage control device and solid-state storage system | |
| CN103336745A (en) | FC HBA (fiber channel host bus adapter) based on SSD (solid state disk) cache and design method thereof | |
| US20160170646A1 (en) | Implementing enhanced performance flash memory devices | |
| CN103092778B (en) | A kind of buffer memory mirror method of storage system | |
| CN103403667A (en) | Data processing method and device | |
| CN108228470A (en) | A kind of method and apparatus for handling the write order to NVM write-in data | |
| CN112632069A (en) | Hash table data storage management method, device, medium and electronic equipment | |
| KR102471966B1 (en) | Data input and output method using storage node based key-value srotre | |
| CN109375868B (en) | Data storage method, scheduling device, system, equipment and storage medium | |
| US20160283379A1 (en) | Cache flushing utilizing linked lists |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |