CN116360709B - Data access system - Google Patents
Data access system Download PDFInfo
- Publication number
- CN116360709B CN116360709B CN202310629133.4A CN202310629133A CN116360709B CN 116360709 B CN116360709 B CN 116360709B CN 202310629133 A CN202310629133 A CN 202310629133A CN 116360709 B CN116360709 B CN 116360709B
- Authority
- CN
- China
- Prior art keywords
- ssd
- data
- hdd
- memory
- hdd disk
- 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
- 230000015654 memory Effects 0.000 claims abstract description 113
- 238000007726 management method Methods 0.000 claims abstract description 12
- 238000013500 data storage Methods 0.000 claims abstract description 10
- 230000009977 dual effect Effects 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 10
- 238000011056 performance test Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000012546 transfer Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0619—Improving the reliability of storage systems in relation to data integrity, e.g. data losses, bit errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0685—Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a data access system, which comprises a first SSD cache array, a second SSD cache array and a data storage unit, wherein the first SSD cache array comprises a plurality of SSD memories which are connected in parallel; a processor connected to the plurality of parallel SSD memories, respectively; the second double-SSD directory backup memory comprises two SSD memories which are mutually backed up and is connected with the first SSD cache array; a first HDD disk array including a plurality of HDD disks for storing data; a plurality of sensors for detecting status data of the SSD memory and the HDD disk; the performance management unit comprises a first interface which is respectively connected to each SSD memory in the first SSD cache array; a third interface respectively connected to each HDD disk in the first HDD disk array; the second interface is connected with the processor; a fourth interface connected to the plurality of sensors for acquiring status data detected by the sensors; and a fifth interface connected to the second dual SSD directory backup memory.
Description
Technical Field
The invention belongs to the technical field of computer data management, and particularly relates to a data access system.
Background
With the increase of network bandwidth, the network is faced with the uploading and downloading of a large amount of data, and requirements on the storage capacity and performance are set. The throughput (bearing capacity) of a conventional system is closely related to the consumption of the CPU, external interfaces, IOs, etc. by read and write requests. The higher the consumption of a single read-write request to the CPU, the slower the external system interface and IO response speed, the lower the system throughput capacity, and conversely, the higher the system throughput capacity. With the improvement of CPU performance, the biggest performance bottleneck of the Oracle database is IO performance. The performance of the database is seriously reduced only by using the HDD disk, so that in order to solve the problem, the industry generally adopts a full flash disk (SSD disk array) array to improve the storage IO performance of the Oracle database, and along with the increasing data volume of the service, the SAS SSD or NVMe SSD with larger capacity is forced to be selected, and then, the problem of high cost and the problem of excessive performance are caused. In addition, in the case of multiple disks, the disks may generate a binding read/write, or the performance of a part of the disks may be degraded, so that the data of the disks cannot be found in time, resulting in low read/write management efficiency, and the advantages of the multiple disks cannot be exerted.
Disclosure of Invention
In order to solve the above-mentioned problems, an object of the present invention is to provide a data access system capable of improving the read/write performance and efficiently managing a plurality of magnetic disks, comprising:
the first SSD cache array comprises a plurality of SSD memories connected in parallel;
a processor respectively connected to the plurality of parallel SSD memories;
the second double-SSD directory backup memory comprises two SSD memories which are mutually backed up, the two SSD memories are respectively connected to the processor, and the second double-SSD directory backup memory is connected with the first SSD cache array;
a first HDD disk array including a plurality of HDD disks for storing data;
a plurality of sensors for detecting status data of the SSD memory and the HDD disk;
the performance management unit comprises a first interface, a second interface, a third interface, a fourth interface and a fifth interface, wherein the first interface is respectively connected to each SSD memory in the first SSD cache array; the third interface is respectively connected to each HDD disk in the first HDD disk array; the second interface is connected with the processor; the fourth interface is connected to the plurality of sensors and acquires state data detected by the sensors;
and a fifth interface connected to the second dual SSD directory backup memory.
Further, the performance management unit includes: the system comprises a performance test unit, a data interface exchange routing unit and a performance statistics allocation unit, wherein the performance test unit is used for testing the read-write performance of an SSD memory and an HDD disk, and the performance statistics allocation unit is used for scheduling a data storage process.
Further, the data interface switching routing unit includes a routing control signal interface, a first data port, and a second data port, where the first data port is connected to the first SSD cache array, and the second data port is connected to the first HDD disk array.
Further, the plurality of sensors includes a first set of temperature sensors and a second set of temperature sensors, the first set of temperature sensors being disposed at a first distance from each SSD memory in the first SSD cache array; the second set of temperature sensors is disposed at the one distance or a different distance from the first distance for each HDD disk in the first array of HDD disks.
Further, the performance test unit is configured to test read-write performance of the SSD memory and the HDD disk, and specifically includes:
the method comprises the steps that a first control instruction is sent to a processor, the processor receives the instruction and sequentially sends a data block writing command to each SSD memory in a first SSD cache array, then each SSD memory is written with a data block of a first preset size, the serial numbers of the SSD memories connected in parallel are 1-n, and the time Tsw 1-Twn when each SSD memory is written with data is recorded;
and sending a second control instruction to a processor, wherein the processor receives the instruction and sequentially sends a data block reading command to each SSD memory in the first SSD cache array, then reads a data block with a first preset size from each SSD memory, and records the time Tsr 1-Tsrn when the data reading from each SSD memory is completed.
Further, a third control instruction is sent to the processor, the processor receives the instruction and sequentially sends a data block writing command to each HDD disk in the first HDD disk array, then a data block with a second preset size is written to each HDD disk, the serial numbers of the plurality of HDD disks are 1~m, and the time Thw 1-Thwm when the writing of data to each HDD disk is completed is recorded;
transmitting a fourth control instruction to a processor, wherein the processor receives the instruction and sequentially transmits a data block reading command to each HDD disk in the first HDD disk array, then reads a data block with a second preset size from each HDD disk, and records the time Thr 1-Thr m when reading data from each HDD disk is completed;
further, the performance statistics allocating unit is configured to schedule a data storage process, and specifically includes:
recording the accumulated data quantity stored in each HDD disk in a preset time period in real time to respectively obtain V1-Vm;
reading temperature data of a plurality of sensors to obtain temperature parameters Tps 1-Tpsn of an SSD memory and temperature parameters Tph 1-Tphm of an HDD disk;
and calculating the read-write time of the HDD disk based on the accumulated data quantity of the preset time period and the temperature parameter to obtain the current performance predicted value of each HDD disk or SSD memory.
Further, the performance statistics allocating unit is configured to schedule a data storage process, and further includes:
judging the size of the current written data block, if the size is larger than a specified threshold value, then:
based on the current performance predicted value of each HDD disk, storing the data block which needs to be written currently into the HDD disk with the highest performance predicted value;
meanwhile, a writing record of current data and an index directory are recorded in a second double SSD directory backup memory, and a disk number and an address of the data to be written are recorded in the index directory.
Further, the index directory is written in redundancy in two SSD memories of the second double SSD directory backup memory.
Further, when the processor needs to read the data, the data size is judged in advance, and when the data size is larger than a preset threshold value, the second double-SSD directory backup memory is preferentially queried, so that the corresponding data is obtained from the corresponding HDD disk.
Compared with the prior art, the invention has the beneficial effects that:
the data access system provided by the invention adopts the combined storage of the SSD and the HDD, and through the scheduling management of the read-write process, the data read-write performance of a plurality of magnetic disks can be effectively improved, the real-time writing capability can be further improved aiming at large-block data, the data can be prevented from being stored in a stacked manner, in addition, the corresponding data can be quickly found by adopting the redundant backup data catalogue, and the data can be prevented from being damaged or lost.
Drawings
FIG. 1 is a block diagram of a data access system of the present invention;
FIG. 2 is a detailed exemplary diagram of a block diagram of a data access system according to the present invention;
fig. 3 is a block diagram of a performance management unit in accordance with the present invention.
Description of the embodiments
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, according to an embodiment of the present invention, a data access system is provided, which can improve the read-write performance and manage multiple disks more efficiently, and specifically includes:
a processor 1 respectively connected to a plurality of SSD memories in a first SSD cache array 2;
the first SSD cache array 2 includes a plurality of parallel SSD memories;
in this embodiment, the SSD memory refers to a solid state disk, and the read-write performance of the SSD memory is better than that of a common HDD mechanical hard disk, so that the read-write speed of the SSD disk buffer array can be improved by using the read-write command executed by the SSD disk buffer array directly read-write processor.
The second double-SSD directory backup memory 4 comprises a first SSD memory 41 and a second SSD memory 42 which are mutually backed up, and is connected to the processor 1, and the second double-SSD directory backup memory 4 and the first SSD cache array 2 are connected through the performance management unit 3;
a first HDD (mechanical hard disk) disk array 5 for storing data.
In the embodiment of the present invention, data is first stored in the SSD storage, and when the data is stored in a predetermined percentage, the data can be transferred to one of a plurality of HDD disks, and in the conventional device shared by the SSD and the HDD, the SSD and the HDD are usually fixedly collocated, however, in the present invention, it is uncertain which of m HDD disks the data is transferred to, that is, the data is not fixedly, therefore, the present invention is provided with the second dual-SSD directory backup storage 4, mainly used for recording files transferred to the HDD from different SSD storage, including transfer logs, and transferred file directories, so that quick file searching can be realized by directly searching the second dual-SSD directory backup storage 4;
further, in the present invention, when transferring and storing the content on the SSD to the HDD, not all transferred files record the directory information to the second dual SSD directory backup memory 4, but it is first determined whether the size of the file to be transferred is larger than a predetermined threshold, for example 300M, and if so, the file block is considered to be larger, and for the file, the directory and the transferred information of the file, and the directory information such as the number stored to the HDD hard disk are recorded in the second dual SSD directory backup memory 4. Therefore, when a larger file needs to be searched, the larger file can be preferentially searched through the second double SSD directory backup memory 4, and the hit rate and the read-write efficiency are improved. Preferably, the second SSD memory 42 in the second dual SSD directory backup memory 4 stores the directory and the transfer information;
further, the first SSD memory 41 in the second dual SSD directory backup memory 4 is further provided with a first shared area, where the shared area is used to store high-frequency shared data, for example, data that is often transferred between the processor cache and the SSD memory array, for example, for dormant data, it is required to access between the SSD and the processor, however, some of the dormant data belongs to system operation data, for which part of the data may be stored in the first SSD memory 41, to prevent the storage space of the SSD memory in the first cache array 2 from being unstable, and may be further stored in a fixed address area of the first SSD memory 41, that is, the shared area may be set to a preset fixed address, so as to further increase the reading speed, and thus, after the dormancy of the computer processor is finished, the system may be restored by directly reading the first shared area in the first SSD memory 41.
Further, common data files, such as files of a registry or a database, may be stored in the second SSD memory 42, thereby increasing the system response speed.
As shown in fig. 1, the performance management unit 3 further includes a first interface 301, a second interface 302, a third interface 303, a fourth interface 304, and a fifth interface 305, where the first interfaces are respectively connected to each SSD memory in the first SSD cache array 2; the third interface is connected to each disk in the first HDD disk array 5; the second interface is connected with the processor 1; the fourth interface is connected to the plurality of sensors and used for acquiring state data of the SSD memory and the HDD disk detected by the sensors; the fifth interface 305 is connected to the second dual SSD directory backup memory 4
And a fifth interface connected to the second dual SSD directory backup memory 4.
Further, as shown in fig. 2-3, the performance management 3 unit includes: the system comprises a performance test unit 31, a data interface exchange routing unit 33 and a performance statistics allocation unit 32, wherein the performance test unit is used for testing the read-write performance of an SSD memory and an HDD disk, and the performance statistics allocation unit is used for scheduling a data storage process. The detailed schematic diagram of the connection relationship between the modules in the performance management unit and the whole system is shown in fig. 2.
Further, the data interface switching routing unit 33 includes a routing control signal interface, and a first data port and a second data port, where the first data port is connected to the first SSD cache array 2, and the second data port is connected to the first HDD disk array 5.
In this embodiment, the data interface switching routing unit receives the control signal through the routing control signal interface, so that it can be determined to transfer the content in the i-th SSD memory in the first SSD cache array to the j-th HDD disk array; i, j is a natural number, i is less than or equal to n, j is less than or equal to m;
further, the plurality of sensors includes a first set of temperature sensors 6, and a second set of temperature sensors 7, the first set of temperature sensors being disposed at a first distance from each SSD memory in the first SSD cache array; the second set of temperature sensors is disposed at the first distance or a second distance different from the first distance of each HDD disk of the first HDD disk array, where different distances from the first SSD cache array and the first HDD disk array are required to be maintained, thereby preventing the temperature from being affected to the same extent.
In this embodiment, by setting a sensor at a first distance between each SSD memory and each HDD disk in the first SSD cache array, for example, the current states of the first SSD cache array and the first HDD disk array can be detected, for example, the sensor is a temperature sensor, and the current temperature of each disk in the first HDD disk array can be monitored in real time, so as to determine whether the current temperature is too frequently read or written, resulting in a decrease in temperature rising performance; or, the current temperature of each SSD memory in the first SDD cache array can be monitored in real time, so that whether the temperature is too high or not is determined, and the performance is reduced, or the sensor can be a vibration sensor, can sense the current vibration state of each disk in the first HDD disk array in real time, and can judge whether the working state is being read or written or not and the vibration condition. For a magnetic disk that vibrates for a long time, the read-write performance thereof is often degraded;
further, the performance test unit is configured to test read-write performance of the SSD memory and the HDD disk, and specifically includes:
the method comprises the steps that a first control instruction is sent to a processor 1, the processor receives the instruction and sequentially sends a data block writing command to each SSD memory in a first SSD cache array, then each SSD memory is written with a data block of a first preset size, the serial number of each SSD memory is 1-n, and the time Tsw 1-Twn when each SSD memory is written with data is recorded; for example, by writing 500M or 5G-sized video files to SSD memory, the speed of writing, including the write time, can be tested;
and sending a second control instruction to a processor, wherein the processor receives the instruction and sequentially sends a data block reading command to each SSD memory in the first SSD cache array, then reads a data block with a first preset size from each SSD memory, and records the time Tsr 1-Tsrn when the data reading from each SSD memory is completed. For example, by reading the above 500M or 5G-sized video files from the SSD memory, the speed of memory reading, including the reading time, can be tested, thereby obtaining the performance of each SSD memory;
further, a third control instruction is sent to the processor, the processor receives the instruction and sequentially sends a data block writing command to each HDD disk in the first HDD disk array, then a data block with a second preset size is written to each HDD disk, the serial number of each HDD disk is 1~m, and the time Thw 1-Thwm when the writing of data to each HDD disk is completed is recorded; for example, by writing a video file of 50M or 1G size to the HDD memory, the writing speed can be tested, including the writing time, or a plurality of scattered small files, such as 1000 text or image files of 30k, can be written;
transmitting a fourth control instruction to a processor, wherein the processor receives the instruction and sequentially transmits a data block reading command to each HDD disk in the first HDD disk array, then reads a data block with a second preset size from each HDD disk, the serial number of each HDD disk is 1~m, and the time Thr 1-Thr m for each HDD disk to read data is recorded; through the read-write test, the read-write speed and the current performance state of the HDD disk can be obtained, so that the HDD disk with better performance can be selected as an optimal disk for accepting the file transferred from the SSD;
further, the performance statistics allocating unit 32 is configured to schedule the data storage process, and the scheduling method specifically includes:
recording the accumulated data quantity stored in each HDD disk in a preset time period in real time to respectively obtain V1-Vm;
reading temperature data of a plurality of sensors to obtain temperature parameters Tps 1-Tpsn of an SSD memory and temperature parameters Tph 1-Tphm of an HDD disk;
and calculating the read-write time of the HDD disk based on the accumulated data quantity of the preset time period and the temperature parameter to obtain the current performance predicted value of each HDD disk or SSD memory.
Specifically, the performance prediction value PHj of each HDD disk can be calculated by the following formula:
j is the disk serial number of the HDD disk;
specifically, the performance prediction value PSi of each SSD memory can be calculated by the following formula:
i is the disk serial number of the SSD memory;
further, the performance statistics allocating unit 32 is configured to schedule a data storage process, and further includes:
judging the size of the current written data block, if the size is larger than a specified threshold value, then:
based on the current performance predicted value of each HDD disk, storing the data block which needs to be written currently into the HDD disk with the highest performance predicted value;
further, the data block which needs to be written by the processor currently can be stored into the SDD memory with the highest performance predicted value based on the current performance predicted value of each SDD memory, and meanwhile, the plurality of SDD memories with the lowest current performance predicted value are suspended to receive new cache data for a plurality of time, such as 1 minute or 15 minutes, and the current performance predicted value is increased by 10% per minute;
meanwhile, a writing record of current data and an index directory are recorded in a second double SSD directory backup memory, and a disk number and an address of the data to be written are recorded in the index directory.
Further, the slave file transfer path is selected by:
< max (PSi) > - < max (PHj) >, so as to select the file on the SSD memory corresponding to the current max (PSi), and transfer to the HDD disk corresponding to max (PHj);
further, if the file is larger than the predetermined size, recording the file directory into a second double SSD directory backup memory;
the address refers to a file directory on the HDD disk, and the disk number refers to the serial number or ID number of the HDD disk.
Further, the index directory is written in redundancy in two SSD memories of the second double SSD directory backup memory.
Further, when the processor needs to read the data, the data size is judged in advance, and when the data size is larger than a preset threshold value, the second double-SSD directory backup memory is preferentially queried, so that the corresponding data is obtained from the corresponding HDD disk.
Finally, it should be noted that: the above is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that the present invention is described in detail with reference to the foregoing embodiments, and modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A data access system, characterized by: comprising the following steps:
the first SSD cache array comprises a plurality of SSD memories connected in parallel;
a processor respectively connected to the plurality of parallel SSD memories;
the second double-SSD directory backup memory comprises two SSD memories which are mutually backed up, the two SSD memories are respectively connected to the processor, and the second double-SSD directory backup memory is connected with the first SSD cache array;
a first HDD disk array including a plurality of HDD disks for storing data;
a plurality of sensors for detecting status data of the SSD memory and the HDD disk;
the performance management unit comprises a first interface, a second interface, a third interface, a fourth interface and a fifth interface, wherein the first interface is respectively connected to each SSD memory in the first SSD cache array; the third interface is respectively connected to each HDD disk in the first HDD disk array; the second interface is connected with the processor;
the fourth interface is connected to the plurality of sensors and acquires state data detected by the sensors;
a fifth interface connected to said second dual SSD directory backup memory;
the performance management unit includes: the system comprises a performance test unit, a data interface exchange routing unit and a performance statistics allocation unit, wherein the performance test unit is used for testing the read-write performance of an SSD memory and an HDD disk, and the performance statistics allocation unit is used for scheduling a data storage process;
the performance test unit is used for testing the read-write performance of the SSD memory and the HDD disk, and specifically comprises the following steps:
the method comprises the steps that a first control instruction is sent to a processor, the processor receives the instruction and sequentially sends a data block writing command to each SSD memory in a first SSD cache array, then each SSD memory is written with a data block with a first preset size, serial numbers of the SSD memories connected in parallel are 1-n, and the time Tsw 1-Twn when each SSD memory is written with data is recorded;
and sending a second control instruction to a processor, wherein the processor receives the instruction and sequentially sends a data block reading command to each SSD memory in the first SSD cache array, then reads a data block with a first preset size from each SSD memory, and records the time Tsr 1-Tsrn when the reading of data from each SSD memory is completed.
2. A data access system according to claim 1, wherein:
the data interface switching routing unit comprises a routing control signal interface, a first data port and a second data port, wherein the first data port is connected to the first SSD cache array, and the second data port is connected to the first HDD disk array.
3. A data access system according to claim 2, wherein:
the plurality of sensors comprise a first group of temperature sensors and a second group of temperature sensors, and the first group of temperature sensors are arranged at a first distance of each SSD memory in the first SSD cache array; the second set of temperature sensors is disposed at the first distance or a second distance different from the first distance for each HDD disk in the first array of HDD disks.
4. A data access system according to claim 2, wherein:
transmitting a third control instruction to a processor, wherein the processor receives the instruction and sequentially transmits a data block writing command to each HDD disk in the first HDD disk array, then writes a data block with a second preset size into each HDD disk, the serial numbers of the plurality of HDD disks are 1-m, and the time Thw 1-Thwm when the writing of data into each HDD disk is completed is recorded;
and sending a fourth control instruction to the processor, wherein the processor receives the instruction and sends a data block reading command to each HDD disk in the first HDD disk array in sequence, then reads a data block with a second preset size from each HDD disk, and records the time Thr 1-Thr m when reading data from each HDD disk is completed.
5. A data access system according to claim 2, wherein: the performance statistics allocating unit is used for scheduling the data storage process, and specifically comprises the following steps:
recording the accumulated data quantity stored in each HDD disk in a preset time period in real time to respectively obtain V1-Vm;
reading temperature data of a plurality of sensors to obtain temperature parameters Tps 1-Tpsn of an SSD memory and temperature parameters Tth 1-Tphm of an HDD disk;
and calculating the read-write time of the HDD disk based on the accumulated data quantity of the preset time period and the temperature parameter to obtain the current performance predicted value of each HDD disk or SSD memory.
6. A data access system according to claim 5, wherein: the performance statistics allocating unit is configured to schedule a data storage process, and further includes:
judging the size of the current written data block, if the size is larger than a specified threshold value, then:
based on the current performance predicted value of each HDD disk, storing the data block which needs to be written currently into the HDD disk with the highest performance predicted value;
meanwhile, a writing record of current data and an index directory are recorded in a second double SSD directory backup memory, and a disk number and an address of the data to be written are recorded in the index directory.
7. A data access system according to claim 6, wherein:
the index directory is written in redundancy in two SSD memories of the second double SSD directory backup memory.
8. A data access system according to claim 7, wherein:
when the processor needs to read the data, the data size is judged in advance, and when the data size is larger than a preset threshold value, the second double SSD directory backup memory is preferentially queried, so that the corresponding data is acquired from the corresponding HDD disk.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310629133.4A CN116360709B (en) | 2023-05-31 | 2023-05-31 | Data access system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310629133.4A CN116360709B (en) | 2023-05-31 | 2023-05-31 | Data access system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116360709A CN116360709A (en) | 2023-06-30 |
CN116360709B true CN116360709B (en) | 2023-08-08 |
Family
ID=86934918
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310629133.4A Active CN116360709B (en) | 2023-05-31 | 2023-05-31 | Data access system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116360709B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101782865A (en) * | 2010-02-05 | 2010-07-21 | 浪潮(北京)电子信息产业有限公司 | Device for realizing disk array and method therefor |
CN105824582A (en) * | 2016-03-28 | 2016-08-03 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN106933516A (en) * | 2017-03-16 | 2017-07-07 | 郑州云海信息技术有限公司 | A kind of storage controlling method and device of the storage system of blending agent |
CN114067892A (en) * | 2021-10-09 | 2022-02-18 | 北京得瑞领新科技有限公司 | Solid state disk temperature-crossing data reading method, storage medium and SSD device |
CN114995760A (en) * | 2022-05-31 | 2022-09-02 | 济南浪潮数据技术有限公司 | Backup recovery method, device and medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9176883B2 (en) * | 2009-04-30 | 2015-11-03 | HGST Netherlands B.V. | Storage of data reference blocks and deltas in different storage devices |
CN102708019B (en) * | 2012-04-28 | 2014-12-03 | 华为技术有限公司 | Method, device and system for hard disk data recovery |
JP7413908B2 (en) * | 2020-04-21 | 2024-01-16 | 富士通株式会社 | Storage controller and backup control program |
-
2023
- 2023-05-31 CN CN202310629133.4A patent/CN116360709B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101782865A (en) * | 2010-02-05 | 2010-07-21 | 浪潮(北京)电子信息产业有限公司 | Device for realizing disk array and method therefor |
CN105824582A (en) * | 2016-03-28 | 2016-08-03 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN106933516A (en) * | 2017-03-16 | 2017-07-07 | 郑州云海信息技术有限公司 | A kind of storage controlling method and device of the storage system of blending agent |
CN114067892A (en) * | 2021-10-09 | 2022-02-18 | 北京得瑞领新科技有限公司 | Solid state disk temperature-crossing data reading method, storage medium and SSD device |
CN114995760A (en) * | 2022-05-31 | 2022-09-02 | 济南浪潮数据技术有限公司 | Backup recovery method, device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN116360709A (en) | 2023-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11314437B2 (en) | Cluster based hard drive SMR optimization | |
US11126378B1 (en) | Rate limit on the transitions of zones to open | |
US10558395B2 (en) | Memory system including a nonvolatile memory and a volatile memory, and processing method using the memory system | |
US10521131B2 (en) | Storage apparatus and storage control apparatus | |
US9251063B2 (en) | Storage system including a plurality of flash memory devices | |
US9612758B1 (en) | Performing a pre-warm-up procedure via intelligently forecasting as to when a host computer will access certain host data | |
US11599304B2 (en) | Data aggregation in ZNS drive | |
CN103985393B (en) | A kind of multiple optical disk data parallel management method and device | |
US11436153B2 (en) | Moving change log tables to align to zones | |
US8762636B2 (en) | Data storage system having a global cache memory distributed among non-volatile memories within system disk drives | |
US11537305B1 (en) | Dissimilar write prioritization in ZNS devices | |
CN105897859A (en) | Storage system | |
US11061598B2 (en) | Optimized handling of multiple copies in storage management | |
CN116360709B (en) | Data access system | |
US11847337B2 (en) | Data parking for ZNS devices | |
KR20240073166A (en) | Controlled system management based on storage device thermal load | |
US11853562B1 (en) | Read look ahead based on key analysis in key value data storage devices | |
US11687263B2 (en) | Full die recovery in ZNS SSD | |
US9542326B1 (en) | Managing tiering in cache-based systems | |
KR20190089796A (en) | Video managing apparatus and method of surveillance systems | |
US11947830B2 (en) | Key value data placement according to expected reads | |
US20230376227A1 (en) | Hot-Cold Chunks Soft-Prediction During Programming | |
US11966630B2 (en) | Key-to-physical table optimization for key value data storage devices | |
TW202127262A (en) | Self-adaptive wear leveling method and algorithm |
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 |