[go: up one dir, main page]

CN112000487B - Scrub pressure adjusting method, device and medium - Google Patents

Scrub pressure adjusting method, device and medium Download PDF

Info

Publication number
CN112000487B
CN112000487B CN202010821283.1A CN202010821283A CN112000487B CN 112000487 B CN112000487 B CN 112000487B CN 202010821283 A CN202010821283 A CN 202010821283A CN 112000487 B CN112000487 B CN 112000487B
Authority
CN
China
Prior art keywords
scrub
task
cluster
process pressure
objects
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
Application number
CN202010821283.1A
Other languages
Chinese (zh)
Other versions
CN112000487A (en
Inventor
李彦博
孟祥瑞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
IEIT Systems Co Ltd
Original Assignee
Inspur Electronic Information Industry Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Inspur Electronic Information Industry Co Ltd filed Critical Inspur Electronic Information Industry Co Ltd
Priority to CN202010821283.1A priority Critical patent/CN112000487B/en
Publication of CN112000487A publication Critical patent/CN112000487A/en
Application granted granted Critical
Publication of CN112000487B publication Critical patent/CN112000487B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/52Program synchronisation; Mutual exclusion, e.g. by means of semaphores
    • G06F9/524Deadlock detection or avoidance
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083Techniques for rebalancing the load in a distributed system

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Feedback Control In General (AREA)
  • Measuring Fluid Pressure (AREA)

Abstract

本发明实施例公开了一种scrub压力调整方法、装置和介质,获取集群的进程压力;依据集群的进程压力以及scrub任务的执行条件,触发scrub状态机,此时系统会自动对scrub任务进行加锁操作,为了降低本次加锁操作占用的时长,可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数;依据对象个数执行本次扫描任务。每完成一次扫描任务则根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数,直至scrub任务包含的所有扫描任务全部完成则结束操作。根据进程压力自动调整当前所需扫描的对象个数,有效的降低了scrub任务对前端业务影响。

Figure 202010821283

The embodiment of the present invention discloses a method, device and medium for adjusting the scrub pressure, which acquires the process pressure of the cluster; triggers the scrub state machine according to the process pressure of the cluster and the execution conditions of the scrub task, and the system automatically adds the scrub task at this time. Lock operation, in order to reduce the time taken by this lock operation, you can adjust the number of objects in the scrub task to perform this scan task according to the process pressure of the cluster; perform this scan task according to the number of objects. Each time a scan task is completed, the number of objects in the scrub task to perform the scan task is adjusted according to the process pressure of the cluster, and the operation ends when all the scan tasks included in the scrub task are completed. According to the process pressure, the number of objects to be scanned is automatically adjusted, which effectively reduces the impact of the scrub task on the front-end business.

Figure 202010821283

Description

一种scrub压力调整方法、装置和介质A kind of scrub pressure adjustment method, device and medium

技术领域technical field

本发明涉及分布式存储技术领域,特别是涉及一种scrub压力调整方法、装置和计算机可读存储介质。The present invention relates to the technical field of distributed storage, and in particular, to a scrub pressure adjustment method, device and computer-readable storage medium.

背景技术Background technique

对于分布式存储集群,需要保障副本之间数据的一致性。集群运行过程中,由于各种原因可能会导致副本之间数据的不一致,数据一致性校验(scrub)为我们提供了感知副本间数据不一致的机制,scrub将扫描到的副本之间的数据进行比较,发现数据不一致时会呈现出来。For distributed storage clusters, data consistency between replicas needs to be guaranteed. During the operation of the cluster, data inconsistency between replicas may occur due to various reasons. Data consistency check (scrub) provides us with a mechanism to perceive data inconsistency between replicas. Scrub will scan the data between replicas. Compare, and it will show up when data inconsistency is found.

scrub操作在执行时需要进行加pg锁的处理,而集群的前端业务的执行也需要加pg锁,scrub操作和前端业务由于加pg锁的关系,属于互斥操作,当存在大量scrub触发的时候,会严重影响集群的前端业务。The scrub operation needs to be processed by adding pg locks, and the execution of the front-end business of the cluster also needs to add pg locks. Due to the relationship between the pg locks, the scrub operation and the front-end business are mutually exclusive operations. When there are a large number of scrub triggers , which will seriously affect the front-end services of the cluster.

可见,如何降低scrub任务对前端业务影响,是本领域技术人员需要解决的问题。It can be seen that how to reduce the impact of the scrub task on the front-end business is a problem that needs to be solved by those skilled in the art.

发明内容SUMMARY OF THE INVENTION

本发明实施例的目的是提供一种一种scrub压力调整方法、装置和计算机可读存储介质,可以降低scrub任务对前端业务影响。The purpose of the embodiments of the present invention is to provide a scrub pressure adjustment method, device and computer-readable storage medium, which can reduce the impact of scrub tasks on front-end services.

为解决上述技术问题,本发明实施例提供一种scrub压力调整方法,包括:To solve the above technical problems, an embodiment of the present invention provides a scrub pressure adjustment method, including:

获取集群的进程压力;Get the process pressure of the cluster;

依据所述集群的进程压力以及scrub任务的执行条件,触发scrub状态机;Trigger the scrub state machine according to the process pressure of the cluster and the execution conditions of the scrub task;

根据所述集群的进程压力,调整所述scrub任务中执行本次扫描任务的对象个数;According to the process pressure of the cluster, adjust the number of objects in the scrub task to perform this scan task;

依据所述对象个数执行本次扫描任务,每完成一次扫描任务则根据所述集群的进程压力,调整所述scrub任务中执行本次扫描任务的对象个数,直至所述scrub任务包含的所有扫描任务全部完成,则结束操作。Execute this scan task according to the number of objects, and adjust the number of objects to perform this scan task in the scrub task according to the process pressure of the cluster each time a scan task is completed, until all the objects included in the scrub task are When all the scanning tasks are completed, the operation ends.

可选地,所述依据所述集群的进程压力以及scrub任务的执行条件,触发scrub状态机包括:Optionally, the triggering of the scrub state machine according to the process pressure of the cluster and the execution conditions of the scrub task includes:

当PG处于任务执行状态并且当前时间满足scrub任务的执行时间时,判断所述集群的进程压力是否属于预设高压力范围;When the PG is in the task execution state and the current time satisfies the execution time of the scrub task, determine whether the process pressure of the cluster belongs to the preset high pressure range;

当所述集群的进程压力不属于预设高压力范围,则触发scrub状态机;When the process pressure of the cluster does not belong to the preset high pressure range, the scrub state machine is triggered;

当所述集群的进程压力属于预设高压力范围,则等待所述scrub任务达到截止时间时则触发scrub状态机。When the process pressure of the cluster falls within the preset high pressure range, the scrub state machine is triggered when the scrub task reaches the deadline.

可选地,在所述依据所述对象个数执行本次扫描任务之后还包括:Optionally, after performing this scan task according to the number of objects, it also includes:

判断所述集群的进程压力是否属于预设高压力范围;Determine whether the process pressure of the cluster belongs to a preset high pressure range;

当所述集群的进程压力属于预设高压力范围时,则等待预设时间后再执行所述根据所述集群的进程压力,调整所述scrub任务中执行本次扫描任务的对象个数的步骤。When the process pressure of the cluster falls within the preset high pressure range, wait for a preset time before executing the step of adjusting the number of objects in the scrub task to perform the scan task according to the process pressure of the cluster .

可选地,所述根据所述集群的进程压力,调整所述scrub任务中执行本次扫描任务的对象个数包括:Optionally, according to the process pressure of the cluster, adjusting the number of objects in the scrub task to perform this scan task includes:

从预先建立的对应关系列表中查找与所述集群的进程压力相匹配的对象个数,并将所述对象个数作为所述scrub任务中执行本次扫描任务的对象个数;其中,所述对应关系列表中记载了不同进程压力范围与对象个数的对应关系。Find the number of objects matching the process pressure of the cluster from the pre-established correspondence list, and use the number of objects as the number of objects in the scrub task to perform this scan task; wherein, the The correspondence list records the correspondence between different process pressure ranges and the number of objects.

可选地,在所述依据所述对象个数执行本次扫描任务之后还包括:Optionally, after performing this scan task according to the number of objects, it also includes:

判断执行本次扫描任务获取的对象数据与备用设备反馈的对象数据是否一致;Determine whether the object data obtained by executing this scan task is consistent with the object data fed back by the standby device;

当执行本次扫描任务获取的对象数据与备用设备反馈的对象数据不一致时,则将所述scrub任务标记为错误状态。When the object data obtained by executing the current scan task is inconsistent with the object data fed back by the standby device, the scrub task is marked as an error state.

本发明实施例还提供了一种scrub压力调整装置,包括获取单元、触发单元、调整单元和执行单元;The embodiment of the present invention also provides a scrub pressure adjustment device, including an acquisition unit, a trigger unit, an adjustment unit and an execution unit;

所述获取单元,用于获取集群的进程压力;The obtaining unit is used to obtain the process pressure of the cluster;

所述触发单元,用于依据所述集群的进程压力以及scrub任务的执行条件,触发scrub状态机;The triggering unit is used to trigger the scrub state machine according to the process pressure of the cluster and the execution conditions of the scrub task;

所述调整单元,用于根据所述集群的进程压力,调整所述scrub任务中执行本次扫描任务的对象个数;The adjustment unit is configured to adjust the number of objects in the scrub task to perform this scan task according to the process pressure of the cluster;

所述执行单元,用于依据所述对象个数执行本次扫描任务,每完成一次扫描任务则根据所述集群的进程压力,调整所述scrub任务中执行本次扫描任务的对象个数,直至所述scrub任务包含的所有扫描任务全部完成,则结束操作。The execution unit is configured to perform the scan task according to the number of objects, and adjust the number of objects in the scrub task to perform the scan task according to the process pressure of the cluster each time a scan task is completed, until the scan task is completed. When all the scanning tasks included in the scrub task are completed, the operation ends.

可选地,所述触发单元包括判断子单元、执行子单元和等待子单元;Optionally, the triggering unit includes a judging subunit, an executing subunit and a waiting subunit;

所述判断子单元,用于当PG处于任务执行状态并且当前时间满足scrub任务的执行时间时,判断所述集群的进程压力是否属于预设高压力范围;The judging subunit is used to judge whether the process pressure of the cluster belongs to the preset high pressure range when the PG is in the task execution state and the current time meets the execution time of the scrub task;

所述执行子单元,用于当所述集群的进程压力不属于预设高压力范围,则触发scrub状态机;The execution subunit is used to trigger the scrub state machine when the process pressure of the cluster does not belong to the preset high pressure range;

所述等待子单元,用于当所述集群的进程压力属于预设高压力范围,则等待所述scrub任务达到截止时间时则触发scrub状态机。The waiting subunit is configured to trigger the scrub state machine when the process pressure of the cluster belongs to a preset high pressure range and wait for the scrub task to reach the deadline.

可选地还包括压力判断单元和等待单元;Optionally also includes a pressure judging unit and a waiting unit;

所述压力判断单元,用于判断所述集群的进程压力是否属于预设高压力范围;the pressure judgment unit, configured to judge whether the process pressure of the cluster belongs to a preset high pressure range;

所述等待单元,用于当所述集群的进程压力属于预设高压力范围时,则等待预设时间后再执行所述根据所述集群的进程压力,调整所述scrub任务中执行本次扫描任务的对象个数的步骤。The waiting unit is configured to, when the process pressure of the cluster belongs to a preset high pressure range, wait for a preset time before executing the scan according to the process pressure of the cluster and adjusting the scrub task to execute this scan The number of steps for the number of objects in the task.

可选地,所述调整单元具体用于从预先建立的对应关系列表中查找与所述集群的进程压力相匹配的对象个数,并将所述对象个数作为所述scrub任务中执行本次扫描任务的对象个数;其中,所述对应关系列表中记载了不同进程压力范围与对象个数的对应关系。Optionally, the adjustment unit is specifically configured to find the number of objects matching the process pressure of the cluster from a pre-established correspondence list, and use the number of objects as the number of objects in the scrub task to execute this time. The number of objects of the scanning task; wherein, the correspondence list records the correspondence between different process pressure ranges and the number of objects.

可选地,还包括数据判断单元和标记单元;Optionally, also include a data judging unit and a marking unit;

所述数据判断单元,用于判断执行本次扫描任务获取的对象数据与备用设备反馈的对象数据是否一致;The data judging unit is used for judging whether the object data obtained by executing this scanning task is consistent with the object data fed back by the standby device;

所述标记单元,用于当执行本次扫描任务获取的对象数据与备用设备反馈的对象数据不一致时,则将所述scrub任务标记为错误状态。The marking unit is configured to mark the scrub task as an error state when the object data obtained by executing the current scan task is inconsistent with the object data fed back by the standby device.

本发明实施例还提供了一种scrub压力调整装置,包括:The embodiment of the present invention also provides a scrub pressure adjustment device, including:

存储器,用于存储计算机程序;memory for storing computer programs;

处理器,用于执行所述计算机程序以实现如上述任意一项所述scrub压力调整方法的步骤。The processor is configured to execute the computer program to implement the steps of the scrub pressure adjustment method according to any one of the above.

本发明实施例还提供了一种计算机可读存储介质,所述计算机可读存储介质上存储有计算机程序,所述计算机程序被处理器执行时实现如上述任一项所述scrub压力调整方法的步骤。An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for adjusting the scrub pressure according to any one of the above-mentioned methods is implemented. step.

由上述技术方案可以看出,获取集群的进程压力;依据集群的进程压力以及scrub任务的执行条件,触发scrub状态机。scrub状态机被触发后系统会自动对scrub任务进行加锁操作。为了降低本次加锁操作所占用的时长,可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数;依据对象个数执行本次扫描任务。一个scrub任务中所需扫描的对象个数往往较多,一般需要执行多次扫描任务,因此每完成一次扫描任务则可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数,直至scrub任务包含的所有扫描任务全部完成,则结束操作。在该技术方案中,可以根据集群的进程压力,自动调整当前scrub任务所需扫描的对象个数,在保证scrub任务能够顺利执行的情况下,有效的降低了scrub任务占用pg锁的时间,从而有效的降低了scrub任务对前端业务影响。It can be seen from the above technical solutions that the process pressure of the cluster is obtained; the scrub state machine is triggered according to the process pressure of the cluster and the execution conditions of the scrub task. After the scrub state machine is triggered, the system automatically locks the scrub task. In order to reduce the time occupied by this locking operation, you can adjust the number of objects in the scrub task to perform this scan task according to the process pressure of the cluster; perform this scan task according to the number of objects. The number of objects to be scanned in a scrub task is often large. Generally, multiple scan tasks need to be performed. Therefore, each time a scan task is completed, the number of objects to be scanned in the scrub task can be adjusted according to the process pressure of the cluster. , until all the scan tasks included in the scrub task are completed, the operation ends. In this technical solution, the number of objects to be scanned by the current scrub task can be automatically adjusted according to the process pressure of the cluster. Under the condition that the scrub task can be executed smoothly, the time that the scrub task occupies the pg lock can be effectively reduced, so that the Effectively reduce the impact of scrub tasks on front-end business.

附图说明Description of drawings

为了更清楚地说明本发明实施例,下面将对实施例中所需要使用的附图做简单的介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to explain the embodiments of the present invention more clearly, the following will briefly introduce the accompanying drawings that need to be used in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention, which are not relevant to ordinary skills in the art. As far as personnel are concerned, other drawings can also be obtained from these drawings on the premise of no creative work.

图1为本发明实施例提供的一种scrub压力调整方法的流程图;FIG. 1 is a flowchart of a method for adjusting scrub pressure according to an embodiment of the present invention;

图2为本发明实施例提供的一种scrub压力调整装置的结构示意图;2 is a schematic structural diagram of a scrub pressure adjustment device provided by an embodiment of the present invention;

图3为本发明实施例提供的一种scrub压力调整装置的硬件结构示意图。FIG. 3 is a schematic diagram of a hardware structure of a scrub pressure adjusting device according to an embodiment of the present invention.

具体实施方式Detailed ways

下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下,所获得的所有其他实施例,都属于本发明保护范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

为了使本技术领域的人员更好地理解本发明方案,下面结合附图和具体实施方式对本发明作进一步的详细说明。In order to make those skilled in the art better understand the solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

接下来,详细介绍本发明实施例所提供的一种scrub压力调整方法。图1为本发明实施例提供的一种scrub压力调整方法的流程图,该方法包括:Next, a scrub pressure adjustment method provided by an embodiment of the present invention is described in detail. FIG. 1 is a flowchart of a method for adjusting scrub pressure according to an embodiment of the present invention, and the method includes:

S101:获取集群的进程压力。S101: Obtain the process pressure of the cluster.

对象存储设备(Object-based Storage Device,OSD)启动之后,会为每个归置组(Placement Group,PG)注册scrub任务。After an Object-based Storage Device (OSD) is started, a scrub task is registered for each Placement Group (PG).

集群的进程压力可以包括CPU的使用率以及磁盘的使用率等。在本发明实施例中,OSD可以定时扫描PG,以采集周期时间内集群的进程压力。周期时间的长短可以根据实际需求设置,例如,可以将周期时间设置为1分钟。The process pressure of the cluster can include CPU usage and disk usage. In this embodiment of the present invention, the OSD may periodically scan the PG to collect the process pressure of the cluster within the period. The length of the cycle time can be set according to actual needs, for example, the cycle time can be set to 1 minute.

需要说明的是,为了保证进程压力能够准确的反映出集群当前的压力情况,在本发明实施例中,所涉及的集群的进程压力均是指最新周期时间内集群的进程压力,以周期时间为1分钟为例,可以以当前时间作为基准时间,获取过去1分钟内集群的进程压力。It should be noted that, in order to ensure that the process pressure can accurately reflect the current pressure situation of the cluster, in this embodiment of the present invention, the process pressure of the cluster involved refers to the process pressure of the cluster within the latest cycle time, and the cycle time is Take 1 minute as an example, you can use the current time as the reference time to obtain the process pressure of the cluster in the past 1 minute.

S102:依据集群的进程压力以及scrub任务的执行条件,触发scrub状态机。S102: Trigger the scrub state machine according to the process pressure of the cluster and the execution conditions of the scrub task.

当PG处于active+clean状态即PG处于任务执行状态,并且当前时间满足scrub任务的执行时间时,OSD可以触发scrub状态机,从而开启执行scrub任务的操作流程。scrub状态机被触发后系统会自动对scrub任务进行加锁操作。When the PG is in the active+clean state, that is, the PG is in the task execution state, and the current time meets the execution time of the scrub task, the OSD can trigger the scrub state machine to start the operation process for executing the scrub task. After the scrub state machine is triggered, the system automatically locks the scrub task.

在本发明实施例中,为了降低scrub任务对前端业务影响,当PG处于任务执行状态并且当前时间满足scrub任务的执行时间时,可以判断集群的进程压力是否属于预设高压力范围。In the embodiment of the present invention, in order to reduce the impact of the scrub task on the front-end business, when the PG is in the task execution state and the current time meets the execution time of the scrub task, it can be determined whether the process pressure of the cluster belongs to the preset high pressure range.

其中,预设高压力范围可以设置为CPU的使用率大于50%或者磁盘的使用率大于50%。Wherein, the preset high pressure range can be set as the usage rate of the CPU is greater than 50% or the usage rate of the disk is greater than 50%.

当集群的进程压力不属于预设高压力范围时,说明集群中的OSD可以快速的处理scrub任务,此时可以直接触发scrub状态机。When the process pressure of the cluster is not within the preset high pressure range, it means that the OSD in the cluster can quickly process the scrub task, and the scrub state machine can be triggered directly.

当集群的进程压力属于预设高压力范围时,说明集群的资源占用率较高,如果此时触发scrub状态机,由于OSD无法快速的处理scrub任务,会导致scrub任务的加锁操作占用较长的时间,从而影响集群中前端业务的执行,因此在集群的进程压力属于预设高压力范围时,可以等待scrub任务达到截止时间时再触发scrub状态机。When the process pressure of the cluster falls within the preset high pressure range, it means that the resource occupancy rate of the cluster is relatively high. If the scrub state machine is triggered at this time, since the OSD cannot process the scrub task quickly, the lock operation of the scrub task will take up a long time. Therefore, when the process pressure of the cluster falls within the preset high pressure range, you can wait for the scrub task to reach the deadline before triggering the scrub state machine.

每个scrub任务在注册时都会携带截止时间,只要OSD在该截止时间内执行scrub任务即可。Each scrub task carries a deadline when it is registered, as long as the OSD executes the scrub task within that deadline.

S103:根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数。S103: According to the process pressure of the cluster, adjust the number of objects in the scrub task to perform this scan task.

集群的进程压力会直接影响OSD执行scrub任务所花费的时间,OSD执行scrub任务期间会加pg锁。OSD执行scrub任务所花费的时间越长,则占用pg锁的时间就越长,相应的,对集群中前端业务的影响就越大。因此,在本发明实施例中,可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数。The process pressure of the cluster will directly affect the time it takes for the OSD to execute the scrub task. The OSD will add pg locks during the execution of the scrub task. The longer the OSD takes to execute the scrub task, the longer the pg lock is occupied, and accordingly, the greater the impact on the front-end services in the cluster. Therefore, in this embodiment of the present invention, the number of objects in the scrub task to perform this scan task can be adjusted according to the process pressure of the cluster.

当集群的进程压力较大时,可以适当的调小本次扫描任务的对象个数;当集群的进程压力较小时,可以适当的调大本次扫描任务的对象个数。When the process pressure of the cluster is high, the number of objects in this scan task can be appropriately reduced; when the process pressure of the cluster is low, the number of objects in this scan task can be appropriately increased.

在具体实现中,可以以对应关系列表的方式记载不同进程压力范围与对象个数的对应关系,当scrub状态机被触发之后,可以从预先建立的对应关系列表中查找与集群的进程压力相匹配的对象个数,并将对象个数作为scrub任务中执行本次扫描任务的对象个数。In a specific implementation, the correspondence between different process pressure ranges and the number of objects can be recorded in the form of a correspondence list. When the scrub state machine is triggered, a pre-established correspondence list can be used to search for a process pressure that matches the cluster's process pressure. The number of objects, and the number of objects is used as the number of objects in the scrub task to perform this scan task.

举例说明,可以将集群的进程压力划分为高压力、中压力和低压力三种级别,例如,当CPU的使用率或者磁盘的使用率大于50%时,说明集群的进程压力属于高压力;当CPU的使用率或者磁盘的使用率小于10%时,说明集群的进程压力属于低压力;当CPU的使用率或者磁盘的使用率在10%-50%之间时,说明集群的进程压力属于中压力。高压力下本次扫描任务的对象个数可以设置为2个;中压力下本次扫描任务的对象个数可以设置为5个;低压力下本次扫描任务的对象个数可以设置为10个。For example, the process pressure of the cluster can be divided into three levels: high pressure, medium pressure and low pressure. For example, when the CPU usage rate or the disk usage rate is greater than 50%, it means that the process pressure of the cluster belongs to high pressure; when When the CPU usage or disk usage is less than 10%, the process pressure of the cluster is low pressure; when the CPU usage or disk usage is between 10% and 50%, the cluster process pressure is medium pressure. The number of objects in this scan task under high pressure can be set to 2; the number of objects in this scan task under medium pressure can be set to 5; the number of objects in this scan task under low pressure can be set to 10 .

S104:依据对象个数执行本次扫描任务,每完成一次扫描任务则根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数,直至scrub任务包含的所有扫描任务全部完成,则结束操作。S104: Execute the current scan task according to the number of objects. After each scan task is completed, adjust the number of objects in the scrub task to perform the scan task according to the process pressure of the cluster until all the scan tasks included in the scrub task are completed. End the operation.

一个scrub任务中所需扫描的对象个数往往较多,一般需要执行多次扫描任务,因此每完成一次扫描任务则可以返回S103,根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数,直至完成scrub任务则结束操作。The number of objects to be scanned in a scrub task is often large. Generally, multiple scan tasks need to be performed. Therefore, each time a scan task is completed, you can return to S103 to adjust the number of objects in the scrub task to perform this scan task according to the process pressure of the cluster. The number of objects, until the scrub task is completed, the operation ends.

需要说明的是,在本发明实施例中,每次返回S103执行对象个数的调整时所依据的集群的进程压力都是指最新周期时间内集群的进程压力。It should be noted that, in the embodiment of the present invention, the process pressure of the cluster on which the adjustment of the number of objects is performed every time returning to S103 refers to the process pressure of the cluster within the latest cycle time.

由上述技术方案可以看出,获取集群的进程压力;依据集群的进程压力以及scrub任务的执行条件,触发scrub状态机。scrub状态机被触发后系统会自动对scrub任务进行加锁操作。为了降低本次加锁操作所占用的时长,可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数;依据对象个数执行本次扫描任务。一个scrub任务中所需扫描的对象个数往往较多,一般需要执行多次扫描任务,因此每完成一次扫描任务则可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数,直至scrub任务包含的所有扫描任务全部完成,则结束操作。在该技术方案中,可以根据集群的进程压力,自动调整当前scrub任务所需扫描的对象个数,在保证scrub任务能够顺利执行的情况下,有效的降低了scrub任务占用pg锁的时间,从而有效的降低了scrub任务对前端业务影响。It can be seen from the above technical solutions that the process pressure of the cluster is obtained; the scrub state machine is triggered according to the process pressure of the cluster and the execution conditions of the scrub task. After the scrub state machine is triggered, the system automatically locks the scrub task. In order to reduce the time occupied by this locking operation, you can adjust the number of objects in the scrub task to perform this scan task according to the process pressure of the cluster; perform this scan task according to the number of objects. The number of objects to be scanned in a scrub task is often large. Generally, multiple scan tasks need to be performed. Therefore, each time a scan task is completed, the number of objects to be scanned in the scrub task can be adjusted according to the process pressure of the cluster. , until all the scan tasks included in the scrub task are completed, the operation ends. In this technical solution, the number of objects to be scanned by the current scrub task can be automatically adjusted according to the process pressure of the cluster. Under the condition that the scrub task can be executed smoothly, the time that the scrub task occupies the pg lock can be effectively reduced, so that the Effectively reduce the impact of scrub tasks on front-end business.

在本发明实施例中,在依据对象个数执行本次扫描任务之后,可以返回S103重新调整下一次扫描任务所对应的对象个数。在执行两次扫描任务时可以存在间隔时间,因此,在本发明实施例中,为了进一步降低执行scrub任务对前端业务造成的影响,在依据对象个数完成本次扫描任务之后,在调整下一次扫描任务对应的对象个数之前,可以先判断集群的进程压力是否属于预设高压力范围。In this embodiment of the present invention, after the current scanning task is performed according to the number of objects, the process may return to S103 to re-adjust the number of objects corresponding to the next scanning task. There may be an interval between executing two scan tasks. Therefore, in this embodiment of the present invention, in order to further reduce the impact of executing the scrub task on the front-end business, after completing the current scan task according to the number of objects, adjust the next scan task according to the number of objects. Before scanning the number of objects corresponding to the task, you can first determine whether the process pressure of the cluster falls within the preset high pressure range.

当集群的进程压力不属于预设高压力范围时,则可以直接根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数的步骤。When the process pressure of the cluster is not within the preset high pressure range, you can directly adjust the steps of the number of objects to perform the scan task in the scrub task according to the process pressure of the cluster.

当集群的进程压力属于预设高压力范围时,则可以等待预设时间后再执行根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数的步骤。When the process pressure of the cluster falls within the preset high pressure range, you can wait for a preset time before executing the steps of adjusting the number of objects in the scrub task to perform the scan task according to the process pressure of the cluster.

其中,预设时间的取值可以根据实际需求设定,例如,预设时间可以设置为3秒。The value of the preset time can be set according to actual needs, for example, the preset time can be set to 3 seconds.

每执行完一次扫描任务则对集群的进程压力进行评估,可以在集群的进程压力较大时,等待预设时间再执行下一次扫描任务,可以有效的缓解集群的进程压力,从而进一步降低执行scrub任务对前端业务造成的影响。After each scan task is executed, the process pressure of the cluster is evaluated. When the process pressure of the cluster is high, it can wait for a preset time before executing the next scan task, which can effectively relieve the process pressure of the cluster and further reduce the execution of scrub The impact of the task on the front-end business.

在本发明实施例中,集群中的OSD可以包括主OSD和备用OSD。主OSD在执行完扫描任务之后,会将相应的扫描任务发送至备用OSD,备用OSD在完成扫描任务之后会向主OSD反馈对象数据。为了保证主OSD和备用OSD数据的一致性,主OSD在接收到备用OSD反馈的对象数据之后,可以判断执行本次扫描任务获取的对象数据与备用设备反馈的对象数据是否一致。In this embodiment of the present invention, the OSDs in the cluster may include a primary OSD and a backup OSD. After the primary OSD completes the scan task, it will send the corresponding scan task to the standby OSD, and the standby OSD will feed back object data to the primary OSD after completing the scan task. To ensure data consistency between the primary OSD and the backup OSD, after receiving the object data fed back by the backup OSD, the primary OSD can determine whether the object data obtained by executing this scan task is consistent with the object data fed back by the backup device.

当执行本次扫描任务获取的对象数据与备用设备反馈的对象数据不一致时,则可以将scrub任务标记为错误状态。When the object data obtained by executing this scan task is inconsistent with the object data fed back by the standby device, the scrub task can be marked as an error state.

通过对主OSD和备用OSD的对象数据进行比较,可以及时发现数据不一致的问题。将scrub任务标记为错误状态,可以便于管理人员直观的了解具体是哪个scrub任务出现了数据不一致的问题,从而有针对性的解决数据不一致的问题。By comparing the object data of the primary OSD and the backup OSD, data inconsistencies can be found in time. Marking a scrub task as an error state can help administrators to intuitively understand which scrub task has the data inconsistency problem, so as to solve the data inconsistency problem in a targeted manner.

图2为本发明实施例提供的一种scrub压力调整装置的结构示意图,包括获取单元21、触发单元22、调整单元23和执行单元24;2 is a schematic structural diagram of a scrub pressure adjustment device provided by an embodiment of the present invention, including an acquisition unit 21, a trigger unit 22, an adjustment unit 23, and an execution unit 24;

获取单元21,用于获取集群的进程压力;an obtaining unit 21 for obtaining the process pressure of the cluster;

触发单元22,用于依据集群的进程压力以及scrub任务的执行条件,触发scrub状态机;The triggering unit 22 is used to trigger the scrub state machine according to the process pressure of the cluster and the execution conditions of the scrub task;

调整单元23,用于根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数;The adjustment unit 23 is used to adjust the number of objects in the scrub task to perform this scan task according to the process pressure of the cluster;

执行单元24,用于依据对象个数执行本次扫描任务,每完成一次扫描任务则根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数,直至scrub任务包含的所有扫描任务全部完成,则结束操作。The execution unit 24 is configured to execute the scan task according to the number of objects, and adjust the number of objects to perform the scan task in the scrub task according to the process pressure of the cluster every time the scan task is completed, until all the scan tasks included in the scrub task When all are completed, the operation ends.

可选地,触发单元包括判断子单元、执行子单元和等待子单元;Optionally, the triggering unit includes a judging subunit, an executing subunit and a waiting subunit;

判断子单元,用于当PG处于任务执行状态并且当前时间满足scrub任务的执行时间时,判断集群的进程压力是否属于预设高压力范围;The judgment subunit is used to judge whether the process pressure of the cluster belongs to the preset high pressure range when the PG is in the task execution state and the current time meets the execution time of the scrub task;

执行子单元,用于当集群的进程压力不属于预设高压力范围,则触发scrub状态机;The execution subunit is used to trigger the scrub state machine when the process pressure of the cluster does not belong to the preset high pressure range;

等待子单元,用于当集群的进程压力属于预设高压力范围,则等待scrub任务达到截止时间时则触发scrub状态机。The waiting sub-unit is used to trigger the scrub state machine when the process pressure of the cluster falls within the preset high pressure range and wait for the scrub task to reach the deadline.

可选地,还包括压力判断单元和等待单元;Optionally, it also includes a pressure judging unit and a waiting unit;

压力判断单元,用于判断集群的进程压力是否属于预设高压力范围;The pressure judgment unit is used to judge whether the process pressure of the cluster belongs to the preset high pressure range;

等待单元,用于当集群的进程压力属于预设高压力范围时,则等待预设时间后再执行根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数的步骤。The waiting unit is used for, when the process pressure of the cluster falls within the preset high pressure range, wait for a preset time before executing the step of adjusting the number of objects in the scrub task to perform the scan task according to the process pressure of the cluster.

可选地,调整单元具体用于从预先建立的对应关系列表中查找与集群的进程压力相匹配的对象个数,并将对象个数作为scrub任务中执行本次扫描任务的对象个数;其中,对应关系列表中记载了不同进程压力范围与对象个数的对应关系。Optionally, the adjustment unit is specifically used to find the number of objects matching the process pressure of the cluster from the pre-established correspondence list, and use the number of objects as the number of objects to perform this scan task in the scrub task; wherein , the corresponding relationship between different process pressure ranges and the number of objects is recorded in the corresponding relationship list.

可选地,还包括数据判断单元和标记单元;Optionally, also include a data judging unit and a marking unit;

数据判断单元,用于判断执行本次扫描任务获取的对象数据与备用设备反馈的对象数据是否一致;A data judging unit for judging whether the object data obtained by executing this scanning task is consistent with the object data fed back by the standby device;

标记单元,用于当执行本次扫描任务获取的对象数据与备用设备反馈的对象数据不一致时,则将scrub任务标记为错误状态。The marking unit is used to mark the scrub task as an error state when the object data obtained by executing the current scan task is inconsistent with the object data fed back by the standby device.

图2所对应实施例中特征的说明可以参见图1所对应实施例的相关说明,这里不再一一赘述。For the description of the features in the embodiment corresponding to FIG. 2 , reference may be made to the relevant description of the embodiment corresponding to FIG. 1 , which will not be repeated here.

由上述技术方案可以看出,获取集群的进程压力;依据集群的进程压力以及scrub任务的执行条件,触发scrub状态机。scrub状态机被触发后系统会自动对scrub任务进行加锁操作。为了降低本次加锁操作所占用的时长,可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数;依据对象个数执行本次扫描任务。一个scrub任务中所需扫描的对象个数往往较多,一般需要执行多次扫描任务,因此每完成一次扫描任务则可以根据集群的进程压力,调整scrub任务中执行本次扫描任务的对象个数,直至scrub任务包含的所有扫描任务全部完成,则结束操作。在该技术方案中,可以根据集群的进程压力,自动调整当前scrub任务所需扫描的对象个数,在保证scrub任务能够顺利执行的情况下,有效的降低了scrub任务占用pg锁的时间,从而有效的降低了scrub任务对前端业务影响。It can be seen from the above technical solutions that the process pressure of the cluster is obtained; the scrub state machine is triggered according to the process pressure of the cluster and the execution conditions of the scrub task. After the scrub state machine is triggered, the system automatically locks the scrub task. In order to reduce the time occupied by this locking operation, you can adjust the number of objects in the scrub task to perform this scan task according to the process pressure of the cluster; perform this scan task according to the number of objects. The number of objects to be scanned in a scrub task is often large. Generally, multiple scan tasks need to be performed. Therefore, each time a scan task is completed, the number of objects to be scanned in the scrub task can be adjusted according to the process pressure of the cluster. , until all the scan tasks included in the scrub task are completed, the operation ends. In this technical solution, the number of objects to be scanned by the current scrub task can be automatically adjusted according to the process pressure of the cluster. Under the condition that the scrub task can be executed smoothly, the time that the scrub task occupies the pg lock can be effectively reduced, so that the Effectively reduce the impact of scrub tasks on front-end business.

图3为本发明实施例提供的一种scrub压力调整装置30的硬件结构示意图,包括:FIG. 3 is a schematic diagram of the hardware structure of a scrub pressure adjustment device 30 according to an embodiment of the present invention, including:

存储器31,用于存储计算机程序;memory 31 for storing computer programs;

处理器32,用于执行计算机程序以实现如上述任意实施例所述的scrub压力调整方法的步骤。The processor 32 is configured to execute a computer program to implement the steps of the scrub pressure adjustment method described in any of the above embodiments.

本发明实施例还提供了一种计算机可读存储介质,计算机可读存储介质上存储有计算机程序,计算机程序被处理器执行时实现如上述任实施例所述的scrub压力调整方法的步骤。Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the scrub pressure adjustment method described in any of the foregoing embodiments are implemented.

以上对本发明实施例所提供的一种scrub压力调整方法、装置和计算机可读存储介质进行了详细介绍。说明书中各个实施例采用递进的方式描述,每个实施例重点说明的都是与其他实施例的不同之处,各个实施例之间相同相似部分互相参见即可。对于实施例公开的装置而言,由于其与实施例公开的方法相对应,所以描述的比较简单,相关之处参见方法部分说明即可。应当指出,对于本技术领域的普通技术人员来说,在不脱离本发明原理的前提下,还可以对本发明进行若干改进和修饰,这些改进和修饰也落入本发明权利要求的保护范围内。The method, the device, and the computer-readable storage medium for adjusting the scrub pressure provided by the embodiments of the present invention have been described in detail above. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method. It should be pointed out that for those skilled in the art, without departing from the principle of the present invention, several improvements and modifications can also be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

专业人员还可以进一步意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本发明的范围。Professionals may further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two, in order to clearly illustrate the possibilities of hardware and software. Interchangeability, the above description has generally described the components and steps of each example in terms of functionality. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

结合本文中所公开的实施例描述的方法或算法的步骤可以直接用硬件、处理器执行的软件模块,或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。The steps of a method or algorithm described in conjunction with the embodiments disclosed herein may be directly implemented in hardware, a software module executed by a processor, or a combination of the two. A software module can be placed in random access memory (RAM), internal memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other in the technical field. in any other known form of storage medium.

Claims (8)

1. A scrub pressure adjustment method, comprising:
acquiring the process pressure of a cluster;
triggering a scrub state machine according to the process pressure of the cluster and the execution condition of the scrub task;
according to the process pressure of the cluster, adjusting the number of objects for executing the scanning task in the scrub task;
executing the scanning task according to the number of the objects, and adjusting the number of the objects executing the scanning task in the scrub task according to the process pressure of the cluster when the scanning task is completed once, until all the scanning tasks contained in the scrub task are completed, ending the operation;
the triggering the scrub state machine according to the process pressure of the cluster and the execution condition of the scrub task comprises:
when the PG is in a task execution state and the current time meets the execution time of a scrub task, judging whether the process pressure of the cluster belongs to a preset high pressure range;
when the process pressure of the cluster does not belong to a preset high pressure range, triggering a scrub state machine;
and when the process pressure of the cluster belongs to a preset high pressure range, triggering a scrub state machine when the scrub task reaches the cut-off time.
2. The scrub pressure adjustment method according to claim 1, further comprising, after the performing the scan task according to the number of the objects:
judging whether the process pressure of the cluster belongs to a preset high pressure range or not;
and when the process pressure of the cluster belongs to a preset high pressure range, waiting for a preset time and then executing the step of adjusting the number of objects for executing the scanning task in the scrub task according to the process pressure of the cluster.
3. The scrub pressure adjusting method according to claim 1, wherein the adjusting the number of the objects in the scrub task for executing the current scanning task according to the process pressure of the cluster comprises:
searching the number of objects matched with the process pressure of the cluster from a pre-established corresponding relation list, and taking the number of the objects as the number of the objects for executing the scanning task in the scrub task; wherein, the corresponding relation list records the corresponding relation between different process pressure ranges and the number of objects.
4. The scrub pressure adjustment method according to claim 1, further comprising, after the performing the scan task according to the number of the objects:
judging whether the object data acquired by executing the scanning task is consistent with the object data fed back by the standby equipment or not;
and when the object data acquired by executing the scanning task is inconsistent with the object data fed back by the standby equipment, marking the scrub task in an error state.
5. The scrub pressure adjusting device is characterized by comprising an acquisition unit, a trigger unit, an adjusting unit and an execution unit;
the acquiring unit is used for acquiring the process pressure of the cluster;
the triggering unit is used for triggering a scrub state machine according to the process pressure of the cluster and the execution condition of the scrub task;
the adjusting unit is configured to adjust the number of objects in the scrub task, which execute the current scanning task, according to the process pressure of the cluster;
the execution unit is configured to execute the scanning task according to the number of the objects, and adjust the number of the objects in the scrub task for executing the scanning task according to the process pressure of the cluster every time the scanning task is completed, and end the operation until all the scanning tasks included in the scrub task are completed;
the trigger unit comprises a judging subunit, an executing subunit and a waiting subunit;
the judging subunit is configured to, when the PG is in a task execution state and the current time meets the execution time of the scrub task, judge whether the process pressure of the cluster belongs to a preset high pressure range;
the execution subunit is used for triggering a scrub state machine when the process pressure of the cluster does not belong to a preset high pressure range;
and the waiting subunit is used for triggering the scrub state machine when the process pressure of the cluster belongs to a preset high pressure range and the scrub task is waited to reach the deadline time.
6. The scrub pressure adjustment device according to claim 5, further comprising a pressure judging unit and a waiting unit;
the pressure judging unit is used for judging whether the process pressure of the cluster belongs to a preset high pressure range or not;
and the waiting unit is used for waiting for a preset time and then executing the step of adjusting the number of objects for executing the scanning task in the scrub task according to the process pressure of the cluster when the process pressure of the cluster belongs to a preset high pressure range.
7. A scrub pressure adjustment device comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the scrub pressure adjustment method as claimed in any one of claims 1 to 4.
8. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the scrub pressure adjustment method as claimed in any one of claims 1 to 4.
CN202010821283.1A 2020-08-14 2020-08-14 Scrub pressure adjusting method, device and medium Active CN112000487B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010821283.1A CN112000487B (en) 2020-08-14 2020-08-14 Scrub pressure adjusting method, device and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010821283.1A CN112000487B (en) 2020-08-14 2020-08-14 Scrub pressure adjusting method, device and medium

Publications (2)

Publication Number Publication Date
CN112000487A CN112000487A (en) 2020-11-27
CN112000487B true CN112000487B (en) 2022-07-08

Family

ID=73472917

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010821283.1A Active CN112000487B (en) 2020-08-14 2020-08-14 Scrub pressure adjusting method, device and medium

Country Status (1)

Country Link
CN (1) CN112000487B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109710456A (en) * 2018-12-10 2019-05-03 新华三技术有限公司 A kind of data reconstruction method and device
CN110059068A (en) * 2019-04-11 2019-07-26 厦门网宿有限公司 Data verification method and data verification system in a kind of distributed memory system
CN111367926A (en) * 2020-02-27 2020-07-03 星辰天合(北京)数据科技有限公司 Data processing method and device for distributed system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9672122B1 (en) * 2014-09-29 2017-06-06 Amazon Technologies, Inc. Fault tolerant distributed tasks using distributed file systems
US10089023B2 (en) * 2015-06-23 2018-10-02 Western Digital Technologies, Inc. Data management for object based storage
US20170185454A1 (en) * 2015-12-25 2017-06-29 Le Holdings (Beijing) Co., Ltd. Method and Electronic Device for Determining Resource Consumption of Task
US10635485B2 (en) * 2018-03-23 2020-04-28 Intel Corporation Devices, systems, and methods for lockless distributed object input/output

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109710456A (en) * 2018-12-10 2019-05-03 新华三技术有限公司 A kind of data reconstruction method and device
CN110059068A (en) * 2019-04-11 2019-07-26 厦门网宿有限公司 Data verification method and data verification system in a kind of distributed memory system
CN111367926A (en) * 2020-02-27 2020-07-03 星辰天合(北京)数据科技有限公司 Data processing method and device for distributed system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Scalable, Efficient, and Policy-Aware Deduplication for Primary Distributed Storage Systems;H. Fingler et al.;《2019 31st International Symposium on Computer Architecture and High Performance Computing》;20191205;第180-187页 *
基于Bluestore的分布式存储Ceph集群QoS研究;袁猛;《中国优秀硕士学位论文全文数据库-信息科技辑》;20190215;第2019年卷(第2期);全文 *

Also Published As

Publication number Publication date
CN112000487A (en) 2020-11-27

Similar Documents

Publication Publication Date Title
CN101510167B (en) A kind of method of plug-in component operation, Apparatus and system
KR102072726B1 (en) Systems and methods for supporting inline delegation of middle-tier transaction logs to database
CN111177165B (en) Method, device and device for data consistency detection
WO2020232871A1 (en) Method and device for microservice dependency analysis
CN109213637B (en) Data recovery method, device and medium for cluster nodes of distributed file system
CN108768752A (en) fault locating method, device and system
WO2018072408A1 (en) Memory analysis method, device, system and computing device
CN110895484A (en) Task scheduling method and device
US20070214161A1 (en) System and method for resource lock acquisition and reclamation in a network file system environment
CN109766317B (en) File deletion method, device, equipment and storage medium
CN107465562B (en) A method, device, and device for self-defined allocation of virtual IP in CTDB
CN109981737B (en) Network request processing method, device, terminal and storage medium
CN110018996A (en) A kind of the snapshot rollback method and relevant apparatus of distributed memory system
CN107688489B (en) Method and system for scheduling tasks
CN107678972A (en) The appraisal procedure and relevant apparatus of a kind of test case
CN110895487A (en) Distributed task scheduling system
CN110895486A (en) Distributed Task Scheduling System
CN109960661A (en) An asset information management method, device, equipment and storage medium
US9170837B2 (en) Transaction concurrent execution control system, method and program for carrying out a control of concurrently executing a transaction, including measuring execution time from starting to ending of transaction execution
CN106021054A (en) Method and apparatus for testing upgrading and downgrading stability of BMC
CN108377268B (en) A method and system for adjusting task priority
CN111404730A (en) State synchronization method and device of virtual router, electronic equipment and storage medium
CN112000487B (en) Scrub pressure adjusting method, device and medium
CN109032874A (en) A kind of memory pressure test method, device, terminal and storage medium
CN111694734A (en) Software interface checking method and device and computer equipment

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