Multi-tenant traffic scheduling method and device, medium, electronic equipment and program product

By building a scheduler tree on the storage nodes of the storage cluster, dynamically scheduling and controlling traffic, the problem of insufficient real-time and flexibility in multi-tenant IO quality management is solved, efficient tenant isolation and performance allocation are achieved, and burst load is reduced jitter.

CN119030933APending Publication Date: 2024-11-26BEIJING VOLCANO ENGINE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411155625.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing multi-tenant IO quality management method lacks real-time and flexibility in the elastic block storage system of the public cloud, and cannot effectively manage sub-second IO quality. System administrators need to manually mark priority, resulting in high management complexity. .

Method used

By receiving the tenant list sent by the control node in the storage node of the storage cluster, a scheduler tree is built based on the tenant weight, including priority schedulers, tenant-level schedulers and first-in-first-out schedulers, to dynamically schedule and control traffic, and realize between tenants by realizing the inter-tenant weights isolation and performance allocation.

Benefits of technology

It realizes flexible allocation and isolation of tenant service performance in a multi-tenant environment, reduces the jitter of burst load, and reduces the intervention effect time from seconds to 100 microseconds, improving the real-time and resource utilization of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119030933A_ABST
    Figure CN119030933A_ABST
Patent Text Reader

Abstract

The invention relates to a multi-tenant traffic scheduling method and device, a medium, electronic equipment and a program product, belongs to the field of cloud storage, and can realize real-time performance and flexibility of multi-tenant traffic scheduling. A multi-tenant traffic scheduling method based on elastic block storage comprises the steps that a tenant list sent by a management and control node in a storage cluster is received through a storage node in the storage cluster, the tenant list is used for maintaining a tenant name and a tenant weight, and the tenant weight represents the proportion of storage service capability enjoyed by a corresponding tenant; a scheduler tree is determined based on a tenant list through a storage node, the scheduler tree comprises a priority scheduler, a tenant-level scheduler and a first-in first-out scheduler, the priority scheduler is used for scheduling flow in tenants and a storage cluster according to service priorities, the tenant-level scheduler is used for scheduling flow among multiple tenants, and the first-in first-out scheduler is used for scheduling flow among the tenants. The first-in first-out scheduler is used for scheduling access of flow; and controlling access of traffic in the storage cluster based on the scheduler tree.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of cloud storage, and in particular, to a multi-tenant traffic scheduling method, device, medium, electronic device and program product. Background Art

[0002] In the public cloud's Elastic Block Storage (EBS) system, a single EBS cluster will be shared by a certain number of tenants. In this multi-tenant architecture, the EBS system needs to have multi-tenant IO (Input / Output) quality management capabilities.

[0003] In related technologies, multi-tenant IO quality management methods are usually implemented in the following ways: (1) The management and control nodes regularly collect feedback from storage nodes, make decisions based on the feedback from storage nodes, allocate resources, and push them to storage nodes.

[0004] (2) Storage nodes have basic real-time IO quality management capabilities, such as current limiting and fixed-priority IO scheduling. Current limiting refers to limiting the use of IO performance at the cloud disk level. Fixed-priority IO scheduling refers to rearranging the order of IO based on priority marking when IO is queued, so as to serve high-priority IO as soon as possible.

[0005] This multi-tenant IO quality management method does not have real-time and flexibility. Summary of the invention

[0006] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] In a first aspect, the present disclosure provides a multi-tenant traffic scheduling method based on elastic block storage, comprising: receiving a tenant list sent by a management node in the storage cluster through a storage node in the storage cluster, the tenant list is used to maintain tenant names and tenant weights, and the tenant weights represent the proportion of storage service capabilities enjoyed by corresponding tenants; determining a scheduler tree based on the tenant list through the storage node, the scheduler tree includes a priority scheduler, a tenant-level scheduler, and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule tenants and traffic within the storage cluster according to business priorities, the tenant-level scheduler is used to schedule traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the entry and exit of the traffic; controlling the entry and exit of the traffic in the storage cluster based on the scheduler tree.

[0008] In a second aspect, the present disclosure provides a multi-tenant traffic scheduling device based on elastic block storage, comprising a receiving module, a determining module and a control module located on a storage node in a storage cluster, wherein: the receiving module is used to receive a tenant list sent by a management and control node in the storage cluster, the tenant list is used to maintain tenant names and tenant weights, and the tenant weights represent the proportion of storage service capabilities enjoyed by corresponding tenants; the determining module is used to determine a scheduler tree based on the tenant list, the scheduler tree includes a priority scheduler, a tenant-level scheduler and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule tenants and traffic within the storage cluster according to business priorities, the tenant-level scheduler is used to schedule traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the entry and exit of the traffic; the control module is used to control the entry and exit of the traffic in the storage cluster based on the scheduler tree.

[0009] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which implements the steps of any one of the methods described in the first aspect when the computer program is executed by a processing device.

[0010] In a fourth aspect, the present disclosure provides an electronic device, including: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of any one of the methods in the first aspect.

[0011] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0012] By adopting the above technical solution, the storage node in the storage cluster can receive the tenant list sent by the management node in the storage cluster, the tenant list is used to maintain the tenant name and tenant weight, the tenant weight represents the proportion of storage service capacity enjoyed by the corresponding tenant, and then the storage node determines the scheduler tree based on the tenant list, the scheduler tree includes a priority scheduler, a tenant-level scheduler and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the tenant and the traffic within the storage cluster according to the business priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, the first-in-first-out scheduler is used to schedule the entry and exit of the traffic, and then the entry and exit of the traffic in the storage cluster is controlled based on the scheduler tree. Therefore, in terms of the flexibility of multi-tenant traffic scheduling, it can not only allocate the service performance allocation of tenants, but also provide isolation between multiple tenants. For example, when the EBS cluster is highly loaded, the delay increase of tenants that do not cause high load is only at the level of ten microseconds, which effectively provides tenant isolation. In terms of the real-time performance of multi-tenant traffic scheduling, by executing multi-tenant traffic scheduling on storage nodes, the intervention and effectiveness time of multi-tenant traffic scheduling can be reduced from the seconds and tens of seconds of the industry's mainstream solutions to hundreds of microseconds, effectively reducing the jitter of sudden load scenarios.

[0013] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings: Figure 1 The present invention is a flowchart of a multi-tenant traffic scheduling method based on elastic block storage according to an embodiment of the present invention.

[0015] Figure 2 is a schematic diagram of a tenant list according to an embodiment of the present disclosure.

[0016] Figure 3 is a schematic diagram of a scheduler tree according to an embodiment of the present disclosure.

[0017] Figure 4 It is a schematic diagram of fair round-robin scheduling according to an embodiment of the present disclosure.

[0018] Figure 5 This is another schematic diagram of fair round-robin scheduling according to an embodiment of the present disclosure.

[0019] Figure 6It is a schematic block diagram of a multi-tenant traffic scheduling device based on elastic block storage according to an embodiment of the present disclosure.

[0020] Figure 7 A schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0022] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0023] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0030] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] At the same time, it is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0032] In the public cloud's EBS system, a single EBS cluster will be shared by a certain number of tenants and the EBS internal system. The tenants here refer to customer tenants outside the EBS internal system. In this multi-tenant architecture, the EBS system needs to have multi-tenant IO quality management capabilities to achieve the following goals: (1) Allocate service performance for heterogeneous tenants. Different tenants have obvious heterogeneity in their requirements for storage IO quality. Different tenants may have different expectations and requirements in terms of business importance, latency sensitivity, and other dimensions. The EBS system needs to recognize and adapt to these differences. For example, some tenants' key business applications have strict requirements on IO performance, and they expect stable and low-latency IO quality to ensure the tenant experience; while the EBS internal system has lower requirements for IO performance, for example, it can tolerate a certain degree of performance jitter, and can accept elastic concessions during the off-peak period of key business to improve resource utilization.

[0033] (2) Provide isolation between tenants. When managing such shared resources, the isolation of tenants should be ensured to avoid the problem of "disturb neighbors". In other words, isolation means that tenants are not aware of each other, as if they have exclusive use of the EBS cluster. For example, in a scenario where a tenant causes a high load on the EBS cluster, the EBS system should ensure that the impact of the high load on IO quality is only borne by the tenant who causes the high load, while other tenants are hardly affected.

[0034] In related technologies, multi-tenant IO quality management methods are usually implemented in the following ways: (1) The management and control nodes regularly collect feedback from storage nodes, make decisions based on the feedback from storage nodes, allocate resources, and push them to storage nodes.

[0035] (2) Storage nodes have basic real-time IO quality management capabilities, such as current limiting and fixed-priority IO scheduling. Current limiting refers to limiting the use of IO performance at the cloud disk level. Fixed-priority IO scheduling refers to rearranging the order of IO based on priority marking when IO is queued, so as to serve high-priority IO as soon as possible.

[0036] The above multi-tenant IO quality management method adopts the approach of "focusing on the control plane and neglecting the data plane", which has obvious defects, mainly including the following problems: (1) Real-time issues. The feedback collection, decision-making, and push paths of the control node are too long, resulting in performance allocation and tenant isolation taking effect usually in seconds or tens of seconds. Therefore, the real-time performance is insufficient and it is impossible to effectively manage sub-second IO quality. For example, if a tenant generates a large amount of burst load within 1 second, causing the EBS system to overload, all other tenants will be impacted and jitter will occur before the decision of the control node takes effect (the effective time is in seconds or tens of seconds).

[0037] (2) Flexibility issues. The real-time IO quality management capabilities of storage nodes are too simple (mainly including current limiting and IO scheduling based on fixed priorities), and are unable to perceive specific tenant characteristics in a fine-grained manner. IO scheduling based on fixed priorities requires system administrators to prioritize a large number of tenants in advance and mark them to a fixed number of priorities. This places too high a demand on the manual decision-making of system administrators and is not flexible enough.

[0038] Figure 1 1 is a flow chart of a multi-tenant traffic scheduling method based on elastic block storage according to an embodiment of the present disclosure. The multi-tenant traffic scheduling method based on elastic block storage can be applied to various multi-tenant traffic scheduling scenarios, such as in an EBS system. Figure 1 As shown, the multi-tenant traffic scheduling method based on elastic block storage may include steps S11 to S13.

[0039] In step S11, a tenant list sent by a management and control node in the storage cluster is received by a storage node in the storage cluster, wherein the tenant list is used to maintain tenant names and tenant weights, and the tenant weights represent the proportion of storage service capabilities enjoyed by the corresponding tenants.

[0040] Storage nodes and management nodes can be deployed in a storage cluster. Storage nodes refer to nodes that implement data storage, such as nodes that implement data reading and writing. Management nodes refer to nodes used to implement storage management.

[0041] For example, the management and control node may periodically push a tenant list to the storage node.

[0042] Figure 2 FIG. 1 is a schematic diagram of a tenant list according to an embodiment of the present disclosure. Figure 2 As shown in the figure, the management node regularly pushes a tenant list to each storage node. The tenant list includes the tenant name and tenant weight. For example, the tenant weight of tenant 1 is 15, the tenant weight of tenant 2 is 8, the tenant weight of tenant 3 is 20, and so on. It should be noted that Figure 2 In the embodiment, the number of management and control nodes and storage nodes, the number of tenants, and the tenant weights are exemplary and do not constitute a limitation to the present disclosure.

[0043] In step S12, a scheduler tree is determined by the storage node based on the tenant list, and the scheduler tree includes a priority scheduler, a tenant-level scheduler, and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule tenants and traffic within the storage cluster according to business priority, the tenant-level scheduler is used to schedule traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the entry and exit of the traffic.

[0044] In step S13, the flow in and out of the storage cluster is controlled based on the scheduler tree.

[0045] By adopting the above technical solution, the storage node in the storage cluster can receive the tenant list sent by the management node in the storage cluster, the tenant list is used to maintain the tenant name and tenant weight, the tenant weight represents the proportion of storage service capacity enjoyed by the corresponding tenant, and then the storage node determines the scheduler tree based on the tenant list, the scheduler tree includes a priority scheduler, a tenant-level scheduler and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the tenant and the traffic within the storage cluster according to the business priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, the first-in-first-out scheduler is used to schedule the entry and exit of the traffic, and then the entry and exit of the traffic in the storage cluster is controlled based on the scheduler tree. Therefore, in terms of the flexibility of multi-tenant traffic scheduling, it can not only allocate the service performance allocation of tenants, but also provide isolation between multiple tenants. For example, when the EBS cluster is highly loaded, the delay increase of tenants that do not cause high load is only at the level of ten microseconds, which effectively provides tenant isolation. In terms of the real-time performance of multi-tenant traffic scheduling, by executing multi-tenant traffic scheduling on storage nodes, the intervention and effectiveness time of multi-tenant traffic scheduling can be reduced from the seconds and tens of seconds of the industry's mainstream solutions to hundreds of microseconds, effectively reducing the jitter of sudden load scenarios.

[0046] In some embodiments, determining the scheduler tree based on the tenant list through the storage node as described in step S12 may include: initially constructing or updating a three-layer tree-structured scheduler tree based on the tenant list through the storage node, wherein the first layer of the scheduler tree is the priority scheduler, the second layer is the tenant-level scheduler, and the third layer is the first-in-first-out scheduler, wherein the priority scheduler is used to fairly rotate and schedule traffic among the business priorities based on the service weights of the business priorities, the tenant-level scheduler is used to fairly rotate and schedule traffic among multiple tenants based on the tenant weights, and the first-in-first-out scheduler is used to schedule traffic based on the first-in-first-out principle.

[0047] After the storage node obtains the tenant list from the control node for the first time, the scheduler tree can be initially constructed. After the storage node obtains the tenant list from the control node again, the previously constructed scheduler tree can be updated.

[0048] By way of example, the priority scheduler is configured with multiple priorities, each priority is assigned an independent queue, each priority is configured with a corresponding service weight, and isolation and service performance allocation are performed based on the service weight, wherein each priority corresponds to a sub-priority scheduler for serving traffic scheduling of the corresponding priority business, wherein the sub-priority scheduler of the first priority is used to serve the traffic of tenants on the storage cluster, and the sub-priority schedulers of other priorities are used to serve the traffic within the storage cluster, and the service weight corresponding to the first priority is greater than the service weights corresponding to other priorities.

[0049] For example, the priority scheduler is configured with multiple priorities, wherein each priority corresponds to a sub-priority scheduler for serving the traffic scheduling of the corresponding priority business. Each sub-priority scheduler performs traffic scheduling of the corresponding priority based on the fair round-robin scheduling principle, and supports flexible transfer to other priorities when the service capacity corresponding to any priority is not exhausted.

[0050] For example, the tenant-level scheduler serves as a sublayer of the priority scheduler, allocates an independent queue for each tenant, and configures a sub-tenant-level scheduler for each tenant for isolation and service performance allocation according to the tenant weight. The sub-tenant-level schedulers schedule multi-tenant traffic based on the principle of fair round-robin scheduling.

[0051] For example, the tenant-level scheduler configures a sub-tenant-level scheduler for each tenant to serve the traffic scheduling of the corresponding tenant, and supports elastic transfer to other tenants when the service capacity configured for any tenant is not exhausted.

[0052] Figure 3 1 is a schematic diagram of a scheduler tree according to an embodiment of the present disclosure. The scheduler tree is used in a storage node.

[0053] like Figure 3 As shown, the scheduler tree according to the embodiment of the present disclosure includes 3 levels.

[0054] The first level is the priority scheduler, which is divided into multiple sub-priority schedulers according to service priorities.

[0055] Each priority level corresponds to a sub-priority scheduler, and the higher the priority level, the higher the service capacity of the corresponding sub-priority scheduler. Figure 3 The priority of the first priority sub-priority scheduler is the highest, and then the priority is reduced in turn, and the priority of the nth priority sub-priority scheduler is the lowest. The specific value of n can be set according to actual needs, for example, it can be 5.

[0056] The highest priority sub-priority scheduler (i.e. Figure 3The first priority sub-priority scheduler in the scheduler can be used to serve the tenant's IO, and the sub-priority schedulers of other priorities (for example, the fourth priority sub-priority scheduler) can be used to serve the IO of the internal system of the storage cluster (for example, the EBS cluster). Compared with the internal system of the storage cluster, tenants usually have more IO requirements, so configuring the highest priority sub-priority scheduler for tenants can ensure the IO quality of tenants.

[0057] Fair round-robin scheduling can be performed between sub-priority schedulers of all priorities (details will be introduced below). Fair round-robin scheduling refers to a traffic scheduling strategy, that is, fair round-robin scheduling between IO queues. Fairness means that all IO queues have service capabilities guaranteed by weight ratios; fair round-robin scheduling can be driven by virtual time.

[0058] The service capacity ratio between each sub-priority scheduler can be preset. Taking the first level including a total of 5 priorities as an example, the service capacity ratio (that is, service weight) between the highest priority sub-priority scheduler to the lowest priority sub-priority scheduler can be preset to 16:8:4:2:1. When performing fair round-robin scheduling, fair rotation can be performed according to the service capacity ratio between each sub-priority scheduler. For example, the sub-priority scheduler that is currently being fairly rotated can be determined based on the service capacity ratio between each sub-priority scheduler. Through fair round-robin scheduling, both the isolation of traffic scheduling and the performance allocation of traffic scheduling can be ensured.

[0059] If the service capacity of a sub-priority scheduler of any priority level is not fully utilized, the excess service capacity of the sub-priority scheduler can be flexibly transferred to sub-priority schedulers of other priorities. For example, if the service capacity of a sub-priority scheduler is not fully utilized and the sub-priority scheduler is currently being fairly rotated, the sub-priority scheduler can transfer the current IO scheduling opportunity to other sub-priority schedulers that are busy with IO scheduling. By transferring service capacity, resource utilization can be improved.

[0060] In addition, the IO queues scheduled by each sub-priority scheduler are independent, thus providing performance allocation capabilities for tenants and internal system traffic of the storage cluster.

[0061] The second level is the tenant-level scheduler, which is a sub-level of the priority scheduler.

[0062] Tenant-level schedulers may exist under all sub-priority schedulers, or under some sub-priority schedulers. Preferably, tenant-level schedulers exist only under the highest-priority sub-priority scheduler to serve the tenant's IO. By making the highest-priority sub-priority scheduler serve the tenant's IO and having tenant-level schedulers only under the highest-priority sub-priority scheduler, the structure of the scheduler tree can be simplified on the one hand, and the IO quality management requirements of the tenant (such as isolation, real-time performance, flexibility, etc.) can be met with the help of the scheduler tree on the other hand.

[0063] The number of tenant-level schedulers under the corresponding sub-priority scheduler corresponds to the number of tenants under the priority level. Each tenant corresponds to a sub-tenant-level scheduler, thereby providing isolation for the tenants.

[0064] Fair round-robin scheduling can be performed between sub-tenant-level schedulers under the same sub-priority scheduler (details will be introduced below). Fair round-robin scheduling refers to a traffic scheduling strategy, that is, fair round-robin scheduling between IO queues. Fairness means that all IO queues have a service capacity guaranteed by the weight ratio. Fair round-robin scheduling can be driven by virtual time.

[0065] The service capacity ratio between sub-tenant-level schedulers under the same sub-priority scheduler is determined by the tenant weight of the tenant under the sub-priority scheduler. When performing fair round-robin scheduling, fair round-robin can be performed according to the service capacity ratio between sub-tenant-level schedulers. For example, the sub-tenant-level scheduler currently being fairly rotated can be determined based on the service capacity ratio between each sub-tenant-level scheduler. Through fair round-robin scheduling, both the isolation of traffic scheduling and the performance distribution of traffic scheduling can be ensured.

[0066] In addition, if the service capacity of any subtenant-level scheduler is not fully utilized, the excess service capacity of the subtenant-level scheduler can be flexibly transferred to other subtenant-level schedulers. For example, if the service capacity of a subtenant-level scheduler is not currently fully utilized, and the subtenant-level scheduler is currently being fairly rotated, then the subtenant-level scheduler can give the current IO scheduling opportunity to other subtenant-level schedulers that are busy with IO scheduling. By transferring service capacity, resource utilization can be improved.

[0067] The third level is the FIFO scheduler, which is a sub-level of the tenant-level scheduler. The FIFO scheduler is used to carry out actual IO enqueue and dequeue operations. If a sub-tenant-level scheduler exists under the corresponding sub-priority scheduler, then there is a sub-FIFO scheduler under each sub-tenant-level scheduler; since one tenant corresponds to one sub-tenant-level scheduler, one tenant also corresponds to one sub-FIFO scheduler, thereby achieving tenant isolation. If there is no sub-tenant-level scheduler under the corresponding sub-priority scheduler, then there is a sub-FIFO scheduler directly under the sub-priority scheduler.

[0068] By using a scheduler tree according to an embodiment of the present disclosure, the multi-tenant traffic scheduling (i.e., IO quality management) capability of the storage node is expanded, so that the storage node can directly support the allocation of service performance for heterogeneous tenants and directly provide isolation between tenants. With the help of the scheduler tree used in the storage node, the core capability of multi-tenant traffic scheduling can be "unloaded" from the control node to the storage node, and the resource allocation problem of the control node can be converted into a traffic scheduling problem of the storage node, which greatly improves the flexibility and real-time performance of multi-tenant traffic scheduling. In the present disclosure, IO quality can include IO latency, jitter, performance capability, etc.

[0069] In some embodiments, the step S13 of controlling the flow in and out of the storage cluster based on the scheduler tree may include: Determine a corresponding first target first-in-first-out scheduler based on the tenant or priority to which the ingress traffic belongs, and perform traffic enqueuing based on the first target first-in-first-out scheduler; or Determine the corresponding second target first-in-first-out scheduler based on the tenant and priority to which the export traffic belongs, and execute traffic dequeue based on the second target first-in-first-out scheduler; or, determine the corresponding third target first-in-first-out scheduler based on the priority to which the export traffic belongs, and execute traffic dequeue based on the third target first-in-first-out scheduler.

[0070] For example, if the sub-priority scheduler to which the IO to be queued belongs is the sub-priority scheduler of the first priority, and the sub-tenant-level scheduler to which it belongs is the first sub-tenant-level scheduler under the sub-priority scheduler of the first priority, then the first target FIFO scheduler of the leaf node in the scheduler tree can be found accordingly, and the first target FIFO scheduler will execute the IO queueing. In this way, the IO can be queued quickly.

[0071] For another example, in the scenario of IO dequeue, if in some branches of the scheduler tree, there is no sub-tenant-level scheduler under the sub-priority scheduler, but only a sub-FIFO scheduler, then in this case, if the sub-priority scheduler of the branch is fairly rotated, the sub-FIFO scheduler under the sub-priority scheduler that is fairly rotated will schedule IO dequeue for the corresponding tenant.

[0072] For another example, in the scenario of IO dequeue, you can first determine the sub-priority scheduler that is currently being fairly rotated, and then determine the sub-tenant-level scheduler that is currently being fairly rotated under the sub-priority scheduler that is currently being fairly rotated, and then, the sub-first-in-first-out scheduler under the sub-tenant-level scheduler that is currently being fairly rotated will schedule IO dequeue.

[0073] By adopting the above technical solution, the real-time and flexibility of traffic scheduling can be achieved on the storage node through fair round-robin scheduling of each sub-priority scheduler and each sub-tenant-level scheduler. That is, each time an IO is dequeued from the scheduler tree, the appropriate scheduler at each level is determined according to the fair round-robin scheduling, and so on recursively downward until the first-in-first-out scheduler of the leaf node is reached, and the IO can be dequeued. In terms of flexibility, it can not only allocate the performance allocation of tenants, but also provide isolation between tenants. For example, when the storage cluster is highly loaded, the delay increase of tenants who do not cause high load is only in the tens of microseconds, which effectively provides tenant isolation. In terms of real-time performance, the intervention and effectiveness time of multi-tenant traffic scheduling is reduced from the seconds and tens of seconds of the mainstream solutions in the industry to hundreds of microseconds, effectively reducing the jitter in burst load scenarios. For example, for burst response time, the mainstream solutions in the industry can achieve an effect of 1s~10s level, while the multi-tenant traffic scheduling method according to the present invention can achieve an effect of 100μs level; for burst jitter, the mainstream solutions in the industry can achieve an effect of increasing the delay by more than 10ms, while the multi-tenant traffic scheduling method according to the present invention can achieve an effect of increasing the delay to up to 100μs.

[0074] Figure 4 It is a schematic diagram of fair round-robin scheduling according to an embodiment of the present disclosure. Figure 4 The sub-scheduler 1 and sub-scheduler 2 in can be sub-priority schedulers or sub-tenant-level schedulers.

[0075] like Figure 4 As shown, IO is dequeued in turn among the sub-schedulers.

[0076] If a sub-scheduler (for example, Figure 4If the sub-scheduler 2) in the fair round-robin scheduling does not fully utilize the performance allocated by the fair round-robin scheduling, its IO will hardly be queued, forming an isolation effect between sub-schedulers. Among them, the sub-priority schedulers can achieve the corresponding isolation effect according to their preset service capacity ratio; the sub-tenant-level schedulers can achieve the corresponding isolation effect according to the corresponding tenant weights.

[0077] For example, if sub-scheduler 1 schedules the IO of tenant 1 that causes high load, and sub-scheduler 2 schedules the IO of other tenant 2, then through fair round-robin scheduling, tenant 2 will not feel the queuing delay caused by the high load of tenant 1, that is, isolation is provided between tenant 1 and tenant 2, and the impact of high load on IO quality is only borne by tenant 1 that causes high load (for example, Figure 4 Neutron Scheduler 1 has a queueing delay of 50ms), while Tenant 2 is not affected by this (e.g. Figure 4 The queuing delay of Neutron Scheduler 2 is 1ms). It should be noted that Figure 4 The specific queuing delay values ​​are only used to illustrate that the impact of high load on IO quality is only borne by the tenant causing the high load, while other tenants are hardly affected by it, and do not constitute a limitation of the present disclosure.

[0078] By adopting the above fair round-robin scheduling, it is possible to provide isolation capabilities between tenants.

[0079] Figure 5 This is another schematic diagram of fair round-robin scheduling according to an embodiment of the present disclosure. Figure 5 The sub-scheduler 1 and sub-scheduler 2 in can be sub-priority schedulers or sub-tenant-level schedulers.

[0080] like Figure 5 As shown, IO is dequeued in turn between each sub-scheduler. The frequency of IO dequeuing of each sub-scheduler is proportional to its service capacity. For the sub-priority scheduler, its IO dequeuing frequency is proportional to its preset service capacity ratio. For the sub-tenant-level scheduler, its IO dequeuing frequency is proportional to the tenant weight. The frequency of IO dequeuing can be expressed by the number of I / O operations performed per second (Input / Output Operations Per Second, IOPS). For example, Figure 5 The total IOPS is 300. Since the tenant weight of the tenant scheduled by sub-scheduler 1 is 2 and the tenant weight of the tenant scheduled by sub-scheduler 2 is 1, the IOPS of sub-scheduler 1 is 200 and the IOPS of sub-scheduler 2 is 100, which is proportional to their tenant weights. Figure 5 The IOPS values, tenant weight values, etc. are all examples and do not constitute a limitation to the present disclosure.

[0081] Through the above fair round-robin scheduling, the performance allocation of IO scheduling can be achieved.

[0082] Figure 6 is a schematic block diagram of a multi-tenant traffic scheduling device based on elastic block storage according to an embodiment of the present disclosure. Figure 6 As shown, the multi-tenant traffic scheduling device based on elastic block storage may include a receiving module 61, a determining module 62 and a control module 63 located on a storage node in a storage cluster, wherein: The receiving module 61 is used to receive a tenant list sent by the management and control node in the storage cluster, where the tenant list is used to maintain tenant names and tenant weights, where the tenant weights represent the proportion of storage service capabilities enjoyed by the corresponding tenants; The determination module 62 is used to determine a scheduler tree based on the tenant list, the scheduler tree includes a priority scheduler, a tenant-level scheduler and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the traffic within the tenant and the storage cluster according to the business priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the ingress and egress of the traffic; The control module 63 is used to control the flow in and out of the storage cluster based on the scheduler tree.

[0083] By adopting the above technical solution, the storage node in the storage cluster can receive the tenant list sent by the management node in the storage cluster, the tenant list is used to maintain the tenant name and tenant weight, the tenant weight represents the proportion of storage service capacity enjoyed by the corresponding tenant, and then the storage node determines the scheduler tree based on the tenant list, the scheduler tree includes a priority scheduler, a tenant-level scheduler and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the tenant and the traffic within the storage cluster according to the business priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, the first-in-first-out scheduler is used to schedule the entry and exit of the traffic, and then the entry and exit of the traffic in the storage cluster is controlled based on the scheduler tree. Therefore, in terms of the flexibility of multi-tenant traffic scheduling, it can not only allocate the service performance allocation of tenants, but also provide isolation between multiple tenants. For example, when the EBS cluster is highly loaded, the delay increase of tenants that do not cause high load is only at the level of ten microseconds, which effectively provides tenant isolation. In terms of the real-time performance of multi-tenant traffic scheduling, by executing multi-tenant traffic scheduling on storage nodes, the intervention and effectiveness time of multi-tenant traffic scheduling can be reduced from the seconds and tens of seconds of the industry's mainstream solutions to hundreds of microseconds, effectively reducing the jitter of sudden load scenarios.

[0084] Optionally, the determining module 62 determines the scheduler tree based on the tenant list through the storage node, including: A three-layer tree-structured scheduler tree is initially constructed or updated through the storage node based on the tenant list, wherein the first layer of the scheduler tree is the priority scheduler, the second layer is the tenant-level scheduler, and the third layer is the first-in-first-out scheduler, wherein the priority scheduler is used to fairly rotate and schedule traffic among the business priorities based on the service weights of the business priorities, the tenant-level scheduler is used to fairly rotate and schedule traffic among multiple tenants based on the tenant weights, and the first-in-first-out scheduler is used to schedule traffic based on the first-in-first-out principle.

[0085] Optionally, the priority scheduler is configured with multiple priorities, each priority is assigned an independent queue, and each priority is configured with a corresponding service weight, and isolation and service performance allocation are performed based on the service weight, wherein each priority corresponds to a sub-priority scheduler, which is used to serve the traffic scheduling of the corresponding priority business, wherein the sub-priority scheduler of the first priority is used to serve the traffic of tenants on the storage cluster, and the sub-priority schedulers of other priorities are used to serve the traffic within the storage cluster, and the service weight corresponding to the first priority is greater than the service weights corresponding to other priorities.

[0086] Optionally, the priority scheduler is configured with multiple priorities, wherein each priority corresponds to a sub-priority scheduler for serving the traffic scheduling of the corresponding priority business, and each sub-priority scheduler performs traffic scheduling of the corresponding priority based on the fair round-robin scheduling principle, and supports flexible transfer to other priorities when the service capacity corresponding to any priority is not exhausted.

[0087] Optionally, the tenant-level scheduler serves as a sublayer of the priority scheduler, allocates an independent queue for each tenant, and configures a sub-tenant-level scheduler for each tenant for isolation and service performance allocation according to the tenant weight. The sub-tenant-level schedulers schedule multi-tenant traffic based on the principle of fair round-robin scheduling.

[0088] Optionally, the tenant-level scheduler configures a sub-tenant-level scheduler for each tenant to serve the traffic scheduling of the corresponding tenant, and supports elastic transfer to other tenants when the service capacity configured for any tenant is not exhausted.

[0089] Optionally, the control module 63 controls the flow in and out of the storage cluster based on the scheduler tree, including: Determine a corresponding first target first-in-first-out scheduler based on the tenant or priority to which the ingress traffic belongs, and perform traffic enqueuing based on the first target first-in-first-out scheduler; or Determine the corresponding second target first-in-first-out scheduler based on the tenant and priority to which the export traffic belongs, and execute traffic dequeue based on the second target first-in-first-out scheduler; or, determine the corresponding third target first-in-first-out scheduler based on the priority to which the export traffic belongs, and execute traffic dequeue based on the third target first-in-first-out scheduler.

[0090] The specific implementation methods of the operations performed by each module in the multi-tenant traffic scheduling device based on elastic block storage according to the embodiment of the present disclosure have been described in detail in the multi-tenant traffic scheduling method based on elastic block storage, and will not be repeated here.

[0091] The present disclosure also provides a computer-readable medium having a computer program stored thereon, and when the computer program is executed by a processing device, the steps of any method described in the present disclosure are implemented.

[0092] The present disclosure also provides an electronic device, comprising: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of any method described in the present disclosure.

[0093] The present disclosure also provides a computer program product, comprising a computer program, which implements the steps of any one of the methods of the present disclosure when executed by a processor.

[0094] Reference below Figure 7 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0095] like Figure 7As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0096] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0097] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0098] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0099] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0100] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0101] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: receives a tenant list sent by a management node in the storage cluster through a storage node in the storage cluster, wherein the tenant list is used to maintain tenant names and tenant weights, and the tenant weights represent the proportion of storage service capabilities enjoyed by corresponding tenants; determines a scheduler tree based on the tenant list through the storage node, and the scheduler tree includes a priority scheduler, a tenant-level scheduler, and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule tenants and traffic within the storage cluster according to business priorities, the tenant-level scheduler is used to schedule traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the entry and exit of the traffic; and controls the entry and exit of the traffic in the storage cluster based on the scheduler tree.

[0102] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0103] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0104] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the receiving module may also be described as "a module for receiving a tenant list sent by a management and control node in the storage cluster".

[0105] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0106] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0107] According to one or more embodiments of the present disclosure, Example 1 provides a multi-tenant traffic scheduling method based on elastic block storage, including: A tenant list sent by a management and control node in the storage cluster is received through a storage node in the storage cluster, where the tenant list is used to maintain tenant names and tenant weights, where the tenant weights represent the proportion of storage service capabilities enjoyed by the corresponding tenants; Determining a scheduler tree based on the tenant list by the storage node, the scheduler tree including a priority scheduler, a tenant-level scheduler, and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the traffic within the tenant and the storage cluster according to the service priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the ingress and egress of the traffic; The entry and exit of the traffic in the storage cluster is controlled based on the scheduler tree.

[0108] According to one or more embodiments of the present disclosure, Example 2 provides the multi-tenant traffic scheduling method based on elastic block storage of Example 1, wherein the determining the scheduler tree based on the tenant list by the storage node includes: A three-layer tree-structured scheduler tree is initially constructed or updated through the storage node based on the tenant list, wherein the first layer of the scheduler tree is the priority scheduler, the second layer is the tenant-level scheduler, and the third layer is the first-in-first-out scheduler, wherein the priority scheduler is used to fairly rotate and schedule traffic among the business priorities based on the service weights of the business priorities, the tenant-level scheduler is used to fairly rotate and schedule traffic among multiple tenants based on the tenant weights, and the first-in-first-out scheduler is used to schedule traffic based on the first-in-first-out principle.

[0109] According to one or more embodiments of the present disclosure, Example 3 provides a multi-tenant traffic scheduling method based on elastic block storage of Example 1 or 2, wherein the priority scheduler is configured with multiple priorities, each priority is assigned an independent queue, each priority is configured with a corresponding service weight, isolation and service performance allocation are performed based on the service weight, wherein each priority corresponds to a sub-priority scheduler for serving traffic scheduling of the corresponding priority business, wherein the sub-priority scheduler of the first priority is used to serve the traffic of tenants on the storage cluster, and the sub-priority schedulers of other priorities are used to serve the traffic within the storage cluster, and the service weight corresponding to the first priority is greater than the service weights corresponding to other priorities.

[0110] According to one or more embodiments of the present disclosure, Example 4 provides a multi-tenant traffic scheduling method based on elastic block storage of Example 1 or 2, wherein the priority scheduler is configured with multiple priorities, wherein each priority corresponds to a sub-priority scheduler for serving traffic scheduling of the corresponding priority business, and each of the sub-priority schedulers performs traffic scheduling of the corresponding priority based on the fair round-robin scheduling principle, and supports elastic transfer to other priorities when the service capacity corresponding to any priority is not exhausted.

[0111] According to one or more embodiments of the present disclosure, Example 5 provides a multi-tenant traffic scheduling method based on elastic block storage of Example 1 or 2, wherein the tenant-level scheduler serves as a sublayer of the priority scheduler, allocates an independent queue for each tenant, and configures a sub-tenant-level scheduler for each tenant for isolation and service performance allocation according to the tenant weight, and the sub-tenant-level schedulers schedule multi-tenant traffic based on the principle of fair round-robin scheduling.

[0112] According to one or more embodiments of the present disclosure, Example 6 provides a multi-tenant traffic scheduling method based on elastic block storage of Example 1 or 2, wherein the tenant-level scheduler configures a sub-tenant-level scheduler for each tenant to serve the traffic scheduling of the corresponding tenant, and supports elastic transfer to other tenants when the service capacity configured for any tenant is not exhausted.

[0113] According to one or more embodiments of the present disclosure, Example 7 provides a multi-tenant traffic scheduling method based on elastic block storage of Example 1 or 2, wherein the controlling the entry and exit of the traffic in the storage cluster based on the scheduler tree includes: Determine a corresponding first target first-in-first-out scheduler based on the tenant or priority to which the ingress traffic belongs, and perform traffic enqueuing based on the first target first-in-first-out scheduler; or Determine the corresponding second target first-in-first-out scheduler based on the tenant and priority to which the export traffic belongs, and execute traffic dequeue based on the second target first-in-first-out scheduler; or, determine the corresponding third target first-in-first-out scheduler based on the priority to which the export traffic belongs, and execute traffic dequeue based on the third target first-in-first-out scheduler.

[0114] According to one or more embodiments of the present disclosure, Example 8 provides a multi-tenant traffic scheduling device based on elastic block storage, including a receiving module, a determining module, and a control module located on a storage node in a storage cluster, wherein: The receiving module is used to receive a tenant list sent by the management and control node in the storage cluster, wherein the tenant list is used to maintain tenant names and tenant weights, and the tenant weights represent the proportion of storage service capabilities enjoyed by the corresponding tenants; The determination module is used to determine a scheduler tree based on the tenant list, the scheduler tree includes a priority scheduler, a tenant-level scheduler and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the traffic within the tenant and the storage cluster according to the business priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the ingress and egress of the traffic; The control module is used to control the entry and exit of the traffic in the storage cluster based on the scheduler tree.

[0115] According to one or more embodiments of the present disclosure, Example 9 provides a computer-readable medium having a computer program stored thereon, which implements the steps of any of the methods described in Examples 1-7 when executed by a processing device.

[0116] According to one or more embodiments of the present disclosure, Example 10 provides an electronic device, including: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of any one of the methods described in Examples 1-7.

[0117] According to one or more embodiments of the present disclosure, Example 11 provides a computer program product, including a computer program, which implements the steps of any one of the methods of Examples 1 to 7 when executed by a processor.

[0118] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0119] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0120] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A multi-tenant traffic scheduling method based on elastic block storage, It is characterized in that include: A tenant list sent by a management and control node in the storage cluster is received through a storage node in the storage cluster, where the tenant list is used to maintain tenant names and tenant weights, where the tenant weights represent the proportion of storage service capabilities enjoyed by the corresponding tenants; Determining a scheduler tree based on the tenant list by the storage node, the scheduler tree including a priority scheduler, a tenant-level scheduler, and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the traffic within the tenant and the storage cluster according to the service priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the ingress and egress of the traffic; The entry and exit of the traffic in the storage cluster is controlled based on the scheduler tree.

2. The multi-tenant traffic scheduling method based on elastic block storage according to claim 1, It is characterized in that The determining a scheduler tree based on the tenant list by the storage node includes: A three-layer tree-structured scheduler tree is initially constructed or updated through the storage node based on the tenant list, wherein the first layer of the scheduler tree is the priority scheduler, the second layer is the tenant-level scheduler, and the third layer is the first-in-first-out scheduler, wherein the priority scheduler is used to fairly rotate and schedule traffic among the business priorities based on the service weights of the business priorities, the tenant-level scheduler is used to fairly rotate and schedule traffic among multiple tenants based on the tenant weights, and the first-in-first-out scheduler is used to schedule traffic based on the first-in-first-out principle.

3. The multi-tenant traffic scheduling method based on elastic block storage according to claim 1 or 2, It is characterized in that The priority scheduler is configured with multiple priorities, each priority is assigned an independent queue, and each priority is configured with a corresponding service weight. Isolation and service performance allocation are performed based on the service weight, wherein each priority corresponds to a sub-priority scheduler for serving the traffic scheduling of the corresponding priority business, wherein the sub-priority scheduler of the first priority is used to serve the traffic of tenants on the storage cluster, and the sub-priority schedulers of other priorities are used to serve the traffic within the storage cluster, and the service weight corresponding to the first priority is greater than the service weights corresponding to other priorities.

4. The multi-tenant traffic scheduling method based on elastic block storage according to claim 1 or 2, It is characterized in that The priority scheduler is configured with multiple priorities, wherein each priority corresponds to a sub-priority scheduler for serving the traffic scheduling of the corresponding priority business. Each sub-priority scheduler performs traffic scheduling of the corresponding priority based on the fair round-robin scheduling principle, and supports flexible transfer to other priorities when the service capacity corresponding to any priority is not exhausted.

5. The multi-tenant traffic scheduling method based on elastic block storage according to claim 1 or 2, It is characterized in that The tenant-level scheduler serves as a sublayer of the priority scheduler, allocates an independent queue for each tenant, and configures a sub-tenant-level scheduler for each tenant for isolation and service performance allocation according to the tenant weight. The sub-tenant-level schedulers schedule multi-tenant traffic based on the principle of fair round-robin scheduling.

6. The multi-tenant traffic scheduling method based on elastic block storage according to claim 1 or 2, It is characterized in that The tenant-level scheduler configures a sub-tenant-level scheduler for each tenant to serve the traffic scheduling of the corresponding tenant, and supports flexible transfer to other tenants when the service capacity configured for any tenant is not exhausted.

7. The multi-tenant traffic scheduling method based on elastic block storage according to claim 1 or 2, It is characterized in that The controlling the flow in and out of the storage cluster based on the scheduler tree includes: Determine a corresponding first target first-in-first-out scheduler based on the tenant or priority to which the ingress traffic belongs, and perform traffic enqueuing based on the first target first-in-first-out scheduler; or Determine the corresponding second target first-in-first-out scheduler based on the tenant and priority to which the export traffic belongs, and execute traffic dequeue based on the second target first-in-first-out scheduler; or, determine the corresponding third target first-in-first-out scheduler based on the priority to which the export traffic belongs, and execute traffic dequeue based on the third target first-in-first-out scheduler.

8. A multi-tenant traffic scheduling device based on elastic block storage, It is characterized in that The system comprises a receiving module, a determining module and a controlling module located on a storage node in a storage cluster, wherein: The receiving module is used to receive a tenant list sent by the management and control node in the storage cluster, wherein the tenant list is used to maintain tenant names and tenant weights, and the tenant weights represent the proportion of storage service capabilities enjoyed by the corresponding tenants; The determination module is used to determine a scheduler tree based on the tenant list, the scheduler tree includes a priority scheduler, a tenant-level scheduler and a first-in-first-out scheduler, wherein the priority scheduler is used to schedule the traffic within the tenant and the storage cluster according to the business priority, the tenant-level scheduler is used to schedule the traffic between multiple tenants, and the first-in-first-out scheduler is used to schedule the ingress and egress of the traffic; The control module is used to control the entry and exit of the traffic in the storage cluster based on the scheduler tree.

9. A computer readable medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processing device, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, It is characterized in that include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.