CN112115073A - Recovery method and device applied to Bcache - Google Patents
Recovery method and device applied to Bcache Download PDFInfo
- Publication number
- CN112115073A CN112115073A CN202010925765.1A CN202010925765A CN112115073A CN 112115073 A CN112115073 A CN 112115073A CN 202010925765 A CN202010925765 A CN 202010925765A CN 112115073 A CN112115073 A CN 112115073A
- Authority
- CN
- China
- Prior art keywords
- idle
- buckets
- bucket
- data
- space
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0253—Garbage collection, i.e. reclamation of unreferenced memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5022—Mechanisms to release resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The application discloses a recycling method and device applied to Bcache, and the method comprises the steps of obtaining a non-idle bucket, wherein the non-idle bucket is a cache space containing dirty data and/or outdated data; performing data integration on the non-idle buckets into the idle buckets, and releasing the space of the non-idle buckets; and marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets. The problem that the existing garbage recycling mechanism applied to the Bcache influences the caching effect is solved.
Description
Technical Field
The application relates to the technical field of computer data processing, in particular to a Bcache recycling method and device.
Background
The Bcache is the cache implementation of a Linux kernel block device. It allows one or more high speed storage devices (disks) to be used as a buffer layer for relatively inexpensive low speed mass storage devices (backing disks). Therefore, the large capacity of the low-speed HDD (mechanical hard disk) can be obtained for users, meanwhile, the access speed similar to that of the SSD can be obtained because the access is buffered through the SSD (solid state disk), and the whole access process is transparent for users and is the same as the use mode of a common access block device.
In the design process of the Bcache, the characteristics of the SSD are fully considered, the cache device is divided into a plurality of buckets according to the sizes of the buckets (buckets), and the sizes of the buckets are configurable and are usually set to be consistent with the erasing sizes of the cache SSD device. These buckets also constitute buffer space. The Bcache may use buckets in different policies depending on the configuration, including LRU (least recently used policy), FIFO (first in first out policy), and Random (Random selection policy). The Bcache indexes the LBA (logical area address) to the position of the data of the caching device through a btree (multi-path search tree), namely the key in the btree is used for making the index of the LBA, and the pointer points to the position of the data in the bucket.
The buffering provided by Bcache not only intervenes when reading data, it also provides buffering by opening the writeback feature for write operations. Data that a write operation falls on the SSD will be referred to as dirty data before being written back to the backing device, and the write-back function will subsequently flush the data back to the backing device in the background. During the continuous use of the cache, the buckets are continuously allocated and occupied, so the Bcache needs a recovery mechanism of the buckets, namely a Garbage recovery mechanism of the Bcache, namely a Garbage Collection mechanism, GC for short. The GC may wake up for several occasions and then mark the buckets without dirty data and metadata as recoverable, and then be recovered and put into a free list.
The inventor implements GC and finds that as long as a small amount of dirty data cannot be recovered or a large amount of expired data cannot be recovered, the utilization rate of a barrel space is low, a cache space cannot be timely released to a user, the buffering effect is influenced, and the influence is more obvious particularly in a scene with high write operation cache requirements.
Disclosure of Invention
The main purpose of the present application is to provide a recovery method and apparatus applied to a Bcache, so as to solve the problem that the existing garbage recovery mechanism applied to the Bcache affects the caching effect.
In order to achieve the above object, according to a first aspect of the present application, there is provided a recycling method applied to Bcache.
The recovery method applied to the Bcache according to the application comprises the following steps:
acquiring a non-idle bucket, wherein the non-idle bucket is a cache space containing dirty data and/or outdated data;
performing data integration on the non-idle buckets into the idle buckets, and releasing the space of the non-idle buckets;
and marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets.
Optionally, the data integration of the non-idle bucket into the idle bucket includes:
discarding the expired data in the non-idle bucket;
and sequentially transferring the residual data in the non-idle buckets into the idle buckets according to a rule that the idle bucket occupies the next idle bucket after the idle bucket is full.
Optionally, the data integration of the non-idle bucket into the idle bucket includes:
intensively extracting dirty data in each non-idle bucket;
and reallocating the dirty data in each non-idle bucket to the idle bucket.
Optionally, the releasing the non-idle space of the bucket further includes:
and discarding the non-dirty data in the non-idle buckets with the access frequency lower than the preset frequency value in the preset time period based on the least recent policy LRU.
Optionally, the step of intensively extracting dirty data in each non-idle bucket further includes:
acquiring the occupied space of dirty data in each non-idle bucket;
respectively judging whether the occupied space of the dirty data in each non-idle bucket is smaller than a preset space or not;
and if the space is smaller than the preset space, extracting the dirty data.
Optionally, the method is applied to a write operation cache and/or a read operation cache.
In order to achieve the above object, according to a second aspect of the present application, there is provided a recycling apparatus applied to a Bcache.
The recovery unit who is applied to Bcache according to this application includes:
the device comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a non-idle bucket, and the non-idle bucket is a cache space containing dirty data and/or expired data;
the integration unit is used for performing data integration on the non-idle buckets into the idle buckets and releasing the space of the non-idle buckets;
and the marking unit is used for marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets.
Optionally, the integration unit includes:
the discarding module is used for discarding the expired data in the non-idle bucket;
and the transfer module is used for sequentially transferring the residual data in the non-idle buckets into the idle buckets according to a rule that the idle bucket occupies the next idle bucket after the idle bucket is full.
Optionally, the integration unit further includes:
the extraction module is used for intensively extracting dirty data in each non-idle bucket;
and the distribution module is used for redistributing the dirty data in each non-idle bucket into the idle bucket.
Optionally, the integration unit is further configured to:
and discarding the non-dirty data in the non-idle buckets with the access frequency lower than the preset frequency value in the preset time period based on the least recent policy LRU.
Optionally, the extracting module is further configured to:
acquiring the occupied space of dirty data in each non-idle bucket;
respectively judging whether the occupied space of the dirty data in each non-idle bucket is smaller than a preset space or not;
and if the space is smaller than the preset space, extracting the dirty data.
Optionally, the apparatus is applied to a write operation cache and/or a read operation cache.
In order to achieve the above object, according to a third aspect of the present application, there is provided a computer-readable storage medium storing computer instructions for causing the computer to execute the reclamation method applied to the Bcache of any one of the above first aspects.
In the embodiment of the application, the method and the device are applied to the Bcache recovery, and a non-idle bucket is obtained, wherein the non-idle bucket is a cache space containing dirty data and/or outdated data; performing data integration on the non-idle buckets into the idle buckets, and releasing the space of the non-idle buckets; and marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets. It can be seen that, after non-idle buckets which cannot be marked as recycled are reintegrated, the utilization rate of the buckets can be improved, that is, the number of idle buckets can be increased. The situation that space cannot be timely released to a user and the buffering effect is influenced in the existing bucket recycling mechanism can be improved to a certain extent.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a flow chart of a recycling method applied to Bcache according to an embodiment of the present application;
fig. 2 is an exemplary diagram of a Moving GC provided in accordance with an embodiment of the present application;
FIG. 3 is an exemplary diagram of a Moving GC + Dirty Moving GC according to an embodiment of the present disclosure;
FIG. 4 is an exemplary diagram of indexing LBAs to caching device data locations via a btree according to an embodiment of the present disclosure;
FIG. 5 is a block diagram illustrating components of a recycling device applied to Bcache according to an embodiment of the present disclosure;
FIG. 6 is a block diagram of another recycling device applied to Bcache according to an embodiment of the present disclosure.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to an embodiment of the present application, there is provided a recycling method applied to a Bcache, as shown in fig. 1, the method including the steps of:
s101, acquiring non-idle bucket buckets, wherein the non-idle bucket buckets are cache spaces containing dirty data and/or expired data.
Normally, according to the existing GC, a bucket without dirty data and metadata is marked as recoverable, and then is recovered and put into a free list. And finishing the initial recovery of the idle buckets, wherein the remaining buckets which are not recovered are the non-idle bucket buckets in the embodiment. The non-free bucket buckets contain dirty data and/or stale data and/or non-dirty data.
S102, performing data integration on the non-idle buckets into the idle buckets, and releasing the space of the non-idle buckets.
The method includes the following specific implementation modes that data integration is performed on non-idle buckets to the idle buckets, and the space of the non-idle buckets is released:
first, Moving GC
Discarding the expired data in the non-idle bucket; and then according to a rule that after an idle bucket is full, the next idle bucket is occupied, transferring the rest data (dirty data and non-dirty data except for overdue data) in the non-idle buckets into the idle buckets in sequence, and then releasing the non-idle bucket space. Namely, in the non-idle bucket, dirty data and non-dirty data are moved to a new bucket (idle bucket), and a stall bkey (expired data) is dropped.
Specific examples are given for illustration: as shown in fig. 2, the buckets _1 to _4 are non-idle buckets, in each bucket, dirty is dirty, non-dirty is dirty, and stall is expired, and after discarding the expired data, the dirty and non-dirty data are moved to new buckets, namely, the buckets _5 to _ 7; and releasing the spaces of the packet _1 to the packet _4, so that three packets are occupied by the data in the original 4 non-idle packets after integration, and one more idle packet is obtained. In fig. 2, "after moving gc" means "after integration in the first manner described above".
Second, Dirty Moving GC
With the first approach, space for stale data can be freed up, but there is a deficiency that a small amount of dirty data in a packet cannot be marked as recoverable, even if a significant portion of the packet is non-dirty data, and it is necessary to wait until all dirty data in the packet is written back. This is a great trouble for the user in the environment of using buffered write operations as the main directory, because the dirty data scrubbing is not performed on a per-packet basis, so it often happens that the dirty data is rarely accumulated on the caching device, but is distributed in many non-idle packets, so that the following write operations cannot be buffered without idle packets. Therefore, the embodiment of the present application provides a second integration manner, that is: intensively extracting dirty data in each non-idle bucket; and reallocating the dirty data in each non-idle bucket to the idle bucket, and then releasing the space of the non-idle bucket. That is, the bucket space occupied by the fragmented non-dirty data is integrated into a complete bucket as much as possible, so that the GC can mark the complete bucket as recyclable and further recycle the recyclable bucket into a free list for subsequent use. The implementation logic is summarized as that dirty data is uniformly collected and put into a new bucket, meanwhile, non-dirty data is discarded, and the previously occupied bucket is released for use.
Specific examples are given for illustration: for example, there are two non-idle buckets in the system, bucket _ 1: dirty data has 500k, bucket _ 2: the Dirty data has 4k, and after the Dirty Moving GC function is started, 500k Dirty data of packet _1 and 4k Dirty data of packet _2 can be written into packet _3, and meanwhile, packet _1 and packet _2 are recycled, so that compared with the existing GC recycling mechanism, a space for recycling packets is increased. And these more bucket spaces will promote the cache _ available _ percentage, and further let the Bcache return to the normal writeback mode.
Third, Moving GC + Dirty Moving GC
Specifically, the first mode and the second mode are jointly applied to the recovery of the non-idle bucket. Namely, on the basis of Moving GC, dirty data are collected uniformly and put into a new bucket, meanwhile, non-dirty data are discarded, and the previously occupied bucket is released for use.
The above specific examples are given for illustration: as shown in fig. 3, each of the buckets _1 to _4 is a non-free bucket, dirty data is dirty data, non-dirty data is dirty data, and stall is expired data, the data in the buckets _1 to _4 are collected into a subsequent bucket _5 through a combination of expired data discarding and zero-fragmentation dirty data, and finally, only the bucket _5 is a non-free bucket, and the buckets _1 to _4 are all marked as recyclable, which is equivalent to increasing the space of three recyclable buckets.
It should be noted that, during the integration, batch or group implementation may be performed, that is, non-idle buckets are divided into different batches or groups, and data in the non-idle buckets in each batch and each group are integrated in the above manner. The rules of the batches or the groups can be divided according to actual needs, such as dividing according to data types or access time of buckets or access objects, and the like.
S103, marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets.
And after the non-idle buckets are reintegrated according to the integration mode, marking the non-idle buckets after the space is released as idle buckets, and recycling the idle buckets into an idle list by the GC to finish recycling the idle buckets again. After the data in the original non-idle buckets are integrated, the occupied space is reduced, namely more idle buckets can be vacated, namely the number of idle buckets is increased.
From the above description, it can be seen that in the recycling method applied to the Bcache in the embodiment of the present application, a non-idle bucket is obtained, where the non-idle bucket is a cache space containing dirty data and/or stale data; performing data integration on the non-idle buckets into the idle buckets, and releasing the space of the non-idle buckets; and marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets. It can be seen that, after non-idle buckets which cannot be marked as recycled are reintegrated, the utilization rate of the buckets can be improved, that is, the number of idle buckets can be increased. The situation that space cannot be timely released to a user and the buffering effect is influenced in the existing bucket recycling mechanism can be improved to a certain extent.
Further, when dirty data in non-idle buckets are extracted in a centralized manner, the dirty data is mainly extracted for the non-idle buckets with fragmented dirty data. Therefore, a non-free bucket containing fragmented dirty data is first found before the centralized extraction. The specific implementation mode is as follows: acquiring the occupied space of dirty data in each non-idle bucket; respectively judging whether the occupied space of the dirty data in each non-idle bucket is smaller than a preset space or not; if the dirty data is smaller than the preset space, defining the dirty data as non-idle buckets with fragmented dirty data, and performing centralized extraction on the dirty data.
Further, it should be noted that in this embodiment, non-dirty data in a non-idle bucket whose access frequency is lower than a preset frequency value within a preset time period may be discarded by using a least-recently-policy-based LRU of the bucket. That is, non-dirty data in non-idle packets with low access frequency are preferentially discarded.
In addition, in this embodiment, the Bcache still indexes the LBA to the data location of the caching device through the btree. Briefly, it is an index of LBA by key in btree, pointer points to the location of data in bucket, as shown in FIG. 4.
Finally, it should be noted that the reclamation method applied to the Bcache in this embodiment may be applied to the write operation cache and/or the read operation cache. Especially, the optimization is more important in the scene of high cache requirement of write operation. For example, when the backing device is cephrbd, the write operation will bring extra delay to the write amplification, so that the performance jitter of the number of available packets in a critical state can be avoided. Otherwise, when the number of available packets is too low, Bcache can make the write operation into bypass and directly drop to low-speed backing equipment.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present application, there is also provided a recycling apparatus applied to a Bcache for implementing the method described in fig. 1, as shown in fig. 5, the apparatus including:
an obtaining unit 21, configured to obtain a non-idle bucket, where the non-idle bucket is a cache space containing dirty data and/or stale data;
the integration unit 22 is configured to perform data integration on the non-idle buckets into the idle buckets, and release the space of the non-idle buckets;
the marking unit 23 is configured to mark a non-idle bucket after the space is released as an idle bucket, so as to increase the number of idle buckets.
From the above description, it can be seen that, in the recovery apparatus applied to the Bcache in the embodiment of the present application, a non-idle bucket is obtained, where the non-idle bucket is a cache space containing dirty data and/or stale data; performing data integration on the non-idle buckets into the idle buckets, and releasing the space of the non-idle buckets; and marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets. It can be seen that, after non-idle buckets which cannot be marked as recycled are reintegrated, the utilization rate of the buckets can be improved, that is, the number of idle buckets can be increased. The situation that space cannot be timely released to a user and the buffering effect is influenced in the existing bucket recycling mechanism can be improved to a certain extent.
Further, as shown in fig. 6, the integration unit 22 includes:
a discarding module 221, configured to discard the expired data in the non-idle bucket;
the transfer module 222 is configured to sequentially transfer remaining data in non-idle buckets to idle buckets according to a rule that an idle bucket occupies a next idle bucket after being full.
Further, as shown in fig. 6, the integration unit 22 further includes:
an extracting module 223, configured to extract dirty data in each non-idle bucket in a centralized manner;
and an allocating module 224, configured to reallocate the dirty data in each non-idle bucket to an idle bucket.
Further, the integration unit 22 is further configured to:
and discarding the non-dirty data in the non-idle buckets with the access frequency lower than the preset frequency value in the preset time period based on the least recent policy LRU.
Further, as shown in fig. 6, the extracting module 223 is further configured to:
acquiring the occupied space of dirty data in each non-idle bucket;
respectively judging whether the occupied space of the dirty data in each non-idle bucket is smaller than a preset space or not;
and if the space is smaller than the preset space, extracting the dirty data.
Further, the device is applied to a write operation cache and/or a read operation cache.
Specifically, the specific process of implementing the functions of each unit and module in the device in the embodiment of the present application may refer to the related description in the method embodiment, and is not described herein again.
According to an embodiment of the present application, there is further provided a computer-readable storage medium, where the computer-readable storage medium stores computer instructions for causing the computer to execute the foregoing method for recycling applied to the Bcache.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A recovery method applied to Bcache is characterized by comprising the following steps:
acquiring a non-idle bucket, wherein the non-idle bucket is a cache space containing dirty data and/or outdated data;
performing data integration on the non-idle buckets into the idle buckets, and releasing the space of the non-idle buckets;
and marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets.
2. The recycling method applied to the Bcache of claim 1, wherein the data integration of the non-idle buckets into the idle buckets comprises:
discarding the expired data in the non-idle bucket;
and sequentially transferring the residual data in the non-idle buckets into the idle buckets according to a rule that the idle bucket occupies the next idle bucket after the idle bucket is full.
3. The recycling method applied to the Bcache according to claim 1 or 2, wherein the data integration of the non-idle buckets into the idle buckets comprises:
intensively extracting dirty data in each non-idle bucket;
and reallocating the dirty data in each non-idle bucket to the idle bucket.
4. The recycling method applied to Bcache according to claim 3, wherein the releasing of the non-free space of the bucket further comprises:
and discarding the non-dirty data in the non-idle buckets with the access frequency lower than the preset frequency value in the preset time period based on the least recent policy LRU.
5. The recycling method applied to Bcache according to claim 3, wherein the step of collectively extracting dirty data in each non-idle bucket further comprises the steps of:
acquiring the occupied space of dirty data in each non-idle bucket;
respectively judging whether the occupied space of the dirty data in each non-idle bucket is smaller than a preset space or not;
and if the space is smaller than the preset space, extracting the dirty data.
6. The Bcache recycling method according to any one of claims 1, 2, 4 and 5, wherein the method is applied to a write operation cache and/or a read operation cache.
7. A recovery device for Bcache applications, the device comprising:
the device comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a non-idle bucket, and the non-idle bucket is a cache space containing dirty data and/or expired data;
the integration unit is used for performing data integration on the non-idle buckets into the idle buckets and releasing the space of the non-idle buckets;
and the marking unit is used for marking the non-idle buckets after the space is released as idle buckets so as to increase the number of the idle buckets.
8. The recycling apparatus for Bcache according to claim 7, wherein the integration unit comprises:
the discarding module is used for discarding the expired data in the non-idle bucket;
and the transfer module is used for sequentially transferring the residual data in the non-idle buckets into the idle buckets according to a rule that the idle bucket occupies the next idle bucket after the idle bucket is full.
9. The recycling device for Bcache according to claim 7 or 8, wherein the integration unit further comprises:
the extraction module is used for intensively extracting dirty data in each non-idle bucket;
and the distribution module is used for redistributing the dirty data in each non-idle bucket into the idle bucket.
10. A computer-readable storage medium storing computer instructions for causing a computer to perform the reclamation method as recited in any one of claims 1-6 applied to the Bcache.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010925765.1A CN112115073A (en) | 2020-09-04 | 2020-09-04 | Recovery method and device applied to Bcache |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010925765.1A CN112115073A (en) | 2020-09-04 | 2020-09-04 | Recovery method and device applied to Bcache |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112115073A true CN112115073A (en) | 2020-12-22 |
Family
ID=73801828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010925765.1A Pending CN112115073A (en) | 2020-09-04 | 2020-09-04 | Recovery method and device applied to Bcache |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115073A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050108496A1 (en) * | 2003-11-13 | 2005-05-19 | International Business Machines Corporation | Hardware support for superpage coalescing |
| CN102725752A (en) * | 2011-10-20 | 2012-10-10 | 华为技术有限公司 | Method and device for processing dirty data |
| CN104461914A (en) * | 2014-11-10 | 2015-03-25 | 浪潮电子信息产业股份有限公司 | Self-adaptive optimization method for automatic thin provisioning |
| CN109558334A (en) * | 2017-09-27 | 2019-04-02 | 北京忆恒创源科技有限公司 | Junk data recovery method and solid storage device |
-
2020
- 2020-09-04 CN CN202010925765.1A patent/CN112115073A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050108496A1 (en) * | 2003-11-13 | 2005-05-19 | International Business Machines Corporation | Hardware support for superpage coalescing |
| CN102725752A (en) * | 2011-10-20 | 2012-10-10 | 华为技术有限公司 | Method and device for processing dirty data |
| CN104461914A (en) * | 2014-11-10 | 2015-03-25 | 浪潮电子信息产业股份有限公司 | Self-adaptive optimization method for automatic thin provisioning |
| CN109558334A (en) * | 2017-09-27 | 2019-04-02 | 北京忆恒创源科技有限公司 | Junk data recovery method and solid storage device |
Non-Patent Citations (2)
| Title |
|---|
| 唐华敏: "基于Linux的混合存储系统Bcache的研究与改进", 《中国优秀硕士学位论文全文数据库 （信息科技辑）》 * |
| 王培杰等: "《Borland C++环境下Windows3.1-95编程技术及实例》", 31 May 1997, 机械工业出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804031B (en) | Optimal record lookup | |
| US9767140B2 (en) | Deduplicating storage with enhanced frequent-block detection | |
| US9069484B2 (en) | Buffer pool extension for database server | |
| US9779027B2 (en) | Apparatus, system and method for managing a level-two cache of a storage appliance | |
| US8161240B2 (en) | Cache management | |
| US7089396B2 (en) | Method and profiling cache for management of virtual memory | |
| US20130080732A1 (en) | Apparatus, system, and method for an address translation layer | |
| CN106502587B (en) | Hard disk data management method and hard disk control device | |
| US20060218347A1 (en) | Memory card | |
| US20180107601A1 (en) | Cache architecture and algorithms for hybrid object storage devices | |
| Bisson et al. | Reducing hybrid disk write latency with flash-backed I/O requests | |
| KR101017067B1 (en) | Locality-Aware Garbage Collection Technique for NAND Flash Memory-Based Storage Systems | |
| CN113672166B (en) | Data processing method, device, electronic equipment and storage medium | |
| US11169968B2 (en) | Region-integrated data deduplication implementing a multi-lifetime duplicate finder | |
| Kim et al. | $ ezswap $: Enhanced compressed swap scheme for mobile devices | |
| CN104102735A (en) | File system optimizing method and file system optimizing device aiming at database files | |
| EP3293625B1 (en) | Method and device for accessing file, and storage system | |
| CN112115073A (en) | Recovery method and device applied to Bcache | |
| US8135911B2 (en) | Managing a region cache | |
| CN107122124A (en) | Data processing method and device | |
| CN114461405B (en) | Storage method and related device for locking page in memory | |
| Lee et al. | Enhanced configurable snapshot: snapshot-based fast booting on nand flash with lifetime control | |
| Koo et al. | A case for application-managed flash | |
| CN107122264B (en) | Disaster-tolerant backup method for mass data | |
| Lee et al. | Alleviating I/O Interference in Virtualized Systems With VM-Aware Persistency Control |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201222 |
|
| RJ01 | Rejection of invention patent application after publication |