WO2024160207A1 - Overload control method and device in object storage service system - Google Patents

Abstract

Embodiments of the present application relate to the technical field of object storage, and provide an overload control method and device in an object storage service system, which can effectively reduce the impact range of a connection flood attack and avoid affecting tenants of the entire cluster. The method is applied to a service node in an object storage service system, the service node is bound to a plurality of IP addresses, and each IP address in the plurality of IP addresses corresponds to one or more tenants. The method comprises: receiving an access request from a user equipment, wherein the access request is used for requesting to access a storage bucket of a target tenant, the access request comprises a target IP address, and the target IP address is one of the plurality of IP addresses; then determining the number of TCP connections corresponding to the target IP address in a TCP accept queue of the service node; and discarding the access request when the number of TCP connections corresponding to the target IP address is greater than a first preset threshold.

Description

Overload control method and device in object storage service system

This application claims priority to a Chinese patent application filed with the State Intellectual Property Office on January 31, 2023, with application number 202310064237.5 and application name “Overload Control Method and Device in Object Storage Service System”, the entire contents of which are incorporated by reference in this application.

Technical Field

The embodiments of the present application relate to the field of object storage technology, and more particularly to an overload control method and device in an object storage service system.

Background Art

Object storage service (OBS) can provide massive, secure, highly reliable, and low-cost data storage capabilities. Tenants can purchase storage resources of the object storage service to store various types of data.

Generally, the number of tenants in an object storage service system is nearly one million, and each of these nearly one million tenants corresponds to an IP address of the object storage service system. For a certain tenant, when there are too many access requests corresponding to the tenant, there are also too many connections established for data transmission in response to the access requests. In this case, the tenant is considered to be under a connection number attack or overloaded. When a tenant in the object storage service system is under a connection number attack, it will also affect the user's access to data corresponding to other tenants in the object storage service system.

Therefore, it is very important to control the number of connections (or overload control) of the object storage service system.

Summary of the invention

The embodiments of the present application provide an overload control method and device in an object storage service system, which can effectively reduce the impact range of connection number attacks and avoid affecting tenants of the entire cluster.

In order to achieve the above-mentioned purpose, the embodiment of the present application adopts the following technical solution:

In a first aspect, an embodiment of the present application provides an overload control method in an object storage service system, which is applied to a service node in the object storage service system, wherein the service node is bound to multiple IP addresses, and each of the multiple IP addresses corresponds to one or more tenants. The method includes: receiving an access request from a user device, wherein the access request is used to request access to a storage bucket of a target tenant, wherein the access request includes a target IP address, and the target IP address is one of multiple IP addresses; then, determining the number of TCP connections corresponding to the target IP address in a TCP full-connection queue of the service node; and discarding the access request when the number of TCP connections corresponding to the target IP address is greater than a first preset threshold.

In an embodiment of the present application, since each of the multiple IP addresses bound to the service node corresponds to one or more tenants, when the number of connections corresponding to the target IP address is overloaded, the service node discards the access request of the tenant corresponding to the target IP address, and the service node processes the access requests corresponding to other IP addresses normally. In this way, the impact range of the connection number attack can be effectively reduced to avoid affecting the tenants of the entire cluster.

In a possible implementation, the above-mentioned discarding of the access request when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold value includes: based on the user-mode protocol stack of DPDK, discarding the access request when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold value to alleviate the overload of the number of connections. It can be understood that DPDK is a software library for accelerating data packet processing at the network protocol transport layer. DPDK has efficient processing capabilities, and the user-mode protocol stack based on DPDK can efficiently control the overload of the number of connections.

When the number of TCP connections corresponding to the target IP address is greater than the first preset threshold, the service node only discards the current access request containing the target IP address, and the service node will not discard the access requests containing other IP addresses. In this way, the service node will not affect the services corresponding to other tenants during the process of controlling the number of connections overload.

In one possible implementation, the overload control method in the object storage service system provided in an embodiment of the present application also includes: when the number of TCP connections corresponding to the target IP address is less than or equal to a first preset threshold, establishing a TCP connection between the user device and the service node.

In the present application, if the number of TCP connections corresponding to the target IP address is less than or equal to the first preset threshold, it means that the number of TCP connections corresponding to the target IP is not overloaded, and the service node enters the TCP connection establishment process to establish a TCP connection between the user device and the service node, and places the TCP connection in the TCP full connection queue maintained by the service node, waiting for the application layer to process the access request corresponding to the TCP connection.

In a possible implementation, after establishing a TCP connection between the user device and the service node, the overload control method provided in the embodiment of the present application further includes: determining whether the length of the access request queue corresponding to the storage bucket of the target tenant is greater than a second preset threshold; if the length of the access request queue is greater than the second preset threshold, refusing to process the access request; if the length of the access request queue is less than or equal to When the second preset threshold is exceeded, the access request is processed.

In this application, for a tenant, each tenant corresponds to an access request queue, which includes all access requests for established TCP connections. After being processed by the above network transmission protocol layer, the service node receives the access request, establishes the TCP connection corresponding to the access request, and then processes the access request at the application layer.

For the target tenant, when the length of the access request queue corresponding to the storage bucket of the above target tenant is greater than the second preset threshold, it means that the target tenant is overloaded. At this time, the service node refuses to process the access request; when the length of the access request queue is less than or equal to the second preset threshold, it means that the target tenant is not overloaded. At this time, the service node processes the access request to ensure the service quality of the tenant.

In a possible implementation, the first preset threshold is half of the TCP full connection queue capacity. The first preset threshold can be determined based on the TCP full connection queue capacity (queue capacity can also be called queue depth), and the first preset threshold does not need to be adjusted with the processing capacity of the application layer.

In the second aspect, the embodiment of the present application provides a service node, which is bound to multiple IP addresses, each of which corresponds to one or more tenants, and the service node includes a receiving module, a determining module, and a processing module. Among them, the receiving module is used to receive an access request from a user device, the access request is used to request access to the storage bucket of the target tenant, and the access request includes a target IP address, which is one of the multiple IP addresses; the determining module is used to determine the number of TCP connections corresponding to the target IP address in the TCP full connection queue of the service node; the processing module is used to discard the access request when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold.

In a possible implementation, the processing module is specifically used for a user-mode protocol stack based on DPDK, and when the number of TCP connections corresponding to the target IP address is greater than a first preset threshold, the access request is discarded.

In a possible implementation, the processing module is further configured to establish a TCP connection between the user equipment and the service node when the number of TCP connections corresponding to the target IP address is less than or equal to a first preset threshold.

In one possible implementation, the above-mentioned determination module is also used to determine whether the length of the access request queue corresponding to the target tenant's storage bucket is greater than a second preset threshold; the processing module is also used to refuse to process the access request when the length of the access request queue is greater than the second preset threshold; and process the access request when the length of the access request queue is less than or equal to the second preset threshold.

In a possible implementation, the first preset threshold is half of the capacity of the TCP full connection queue.

In a third aspect, an embodiment of the present application provides a service node, comprising a memory and at least one processor connected to the memory, the memory being used to store computer program code, the computer program code comprising computer instructions, and when the computer instructions are executed by at least one processor, the computing device executes the method described in the first aspect and any one of its possible implementation methods.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing computer instructions, which, when executed on a computer, execute the method described in the first aspect and any one of its possible implementations.

In a fifth aspect, an embodiment of the present application provides a computer program product, which includes computer instructions. When the computer instructions are run on a computer, the method described in the first aspect and any one of its possible implementation methods is executed.

In a sixth aspect, an embodiment of the present application provides a chip, comprising a memory and a processor, the memory being used to store computer instructions, and the processor being used to call and run the computer instructions from the memory to execute the method described in the first aspect and any one of its possible implementation methods.

It should be understood that the beneficial effects achieved by the technical solutions of the second to sixth aspects of the present application and the corresponding possible implementation methods can be referred to the technical effects of the first aspect and its corresponding possible implementation methods mentioned above, and will not be repeated here.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of the architecture of a communication system provided in an embodiment of the present application;

FIG2 is a schematic diagram of the hardware structure of a service node provided in an embodiment of the present application;

3 is a schematic diagram of the correspondence between tenants and IP addresses in an object storage service system provided in an embodiment of the present application;

FIG4 is a schematic diagram of an overload control method in an object storage service system provided in an embodiment of the present application;

FIG5 is a second schematic diagram of an overload control method in an object storage service system provided by an embodiment of the present application;

FIG6 is one of the structural schematic diagrams of a service node provided in an embodiment of the present application;

FIG. 7 is a second schematic diagram of the structure of a service node provided in an embodiment of the present application.

DETAILED DESCRIPTION

The term "and/or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and/or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

The terms "first" and "second" in the description and claims of the embodiments of the present application are used to distinguish different objects, rather than to refer to different objects. Describes a specific order of objects.

In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more.

First, some concepts involved in the overload control method and device in the object storage service system provided in the embodiments of the present application are explained.

1. Some concepts about object storage service (OBS)

The basic components of the object storage service OBS are buckets and objects.

A bucket is a container for storing objects in OBS. Each bucket has attributes such as storage category, access permission, and region.

An object is the basic unit of data storage in OBS. An object includes the data of a file and its related attribute information, including key value (Key), metadata (Metadata), and data (Data). Among them, Key is the name of the object; Metadata is the description information of the object, including system metadata and user metadata; Data is the data content of the file.

2. Tenants of the Object Storage Service

Users who rent OBS resources are called tenants of the object storage service. Tenants can create buckets in OBS and configure bucket access policies through the OBS configuration interface or application programming interface (such as API), and then upload objects to the buckets through the Internet. Optionally, tenants can create one or more buckets.

After a tenant uploads an object in his bucket, other users (through their user devices) can access the tenant's bucket. Specifically, the user device can locate the bucket through the bucket's access domain name and then access the object in the bucket.

In the embodiment of the present application, tenants refer to the owners of buckets in OBS, and users refer to the visitors of the tenants' buckets.

The following introduces the architecture of a communication system for an object storage service in conjunction with Figure 1. As shown in Figure 1, the communication system includes a user device 101 (such as a mobile phone), a border router (BR) 102, and an OBS system 103, wherein the OBS system 103 may include multiple clusters (only one cluster is illustrated in Figure 1), and a cluster includes multiple service nodes, and the service nodes are responsible for creating buckets and managing buckets, etc.

The user holds a user device 101 , and the user device 101 can access the service node in the OBS system 103 through the Internet and the border router 102 , and obtain objects from the bucket created by the service node.

1, for a cluster in the OBS system 103, the cluster as a whole presents an IP address to the outside, and the IP address is a virtual IP address. Usually, one IP address carries nearly one million tenants, that is, all tenants of buckets on multiple service nodes in the OBS system 103 correspond to one IP address.

For a tenant, a user sends an access request through a user device. The access request is used to access objects in the bucket of the tenant. After receiving the access request, the service node establishes a communication connection (e.g., a transmission control protocol (TCP) connection) between the user device and the service node. Subsequently, the user device can communicate with the service node to transmit data. In some cases, there may be many users accessing the bucket of the tenant. When there are too many access requests corresponding to the tenant, there are too many connections established for data transmission in response to the access requests. At this time, it is considered that the tenant is under connection number attack or the tenant is overloaded.

Because all tenants in a cluster present the same IP address to the outside world, when a tenant is attacked by the number of connections, it will affect the access of all tenants in the entire cluster, that is, it will affect other users' access to other tenants in the cluster.

At present, one solution for handling connection number attacks is: after the administrator logs in to the service node, the access request of certain user devices is blocked by iptable technology. It should be understood that iptable is a firewall, and the service node blocks the source IP address (the source IP address is the IP address of the user device) by iptable in the kernel state. For more details about using iptable technology to block the access request of the user device, please refer to the existing technical materials, and the embodiments of this application will not be described in detail.

In the above solution of handling connection number attacks through iptable technology, since the tenant has been attacked by connection number, the processing efficiency of the service node is very low. At this time, the administrator may face the problem of being unable to log in to the service node, and therefore, cannot handle the connection number attack in a timely and effective manner.

Another solution to handle connection number attacks is to block the source IP address on the border router. In this solution, the source IP addresses are too scattered, for example, legitimate user access requests may be blocked, which will seriously affect the business and put the user's business at risk.

In view of the above problems, an embodiment of the present application provides an overload control method and device in an object storage service system. The method is applied to a service node in the object storage service system. The service node is bound to multiple IP addresses, each of which corresponds to one or more tenants. The overload control method includes: the service node receives an access request from a user device, and the access request is used to request Access the storage bucket of the target tenant, the access request includes the target IP address, and the target IP address is one of the above multiple IP addresses; then, the service node determines the number of TCP connections corresponding to the target IP address in the TCP full connection queue of the service node; and, if the number of TCP connections corresponding to the target IP address is greater than a first preset threshold, the access request of the user device is discarded. The technical solution provided by the embodiment of the present application can effectively reduce the impact range of the connection number attack and avoid affecting the tenants of the entire cluster.

In addition, compared with the above-mentioned method of overload control by administrators logging into the service node, the technical solution provided by the embodiment of the present application does not require the participation of administrators and can adaptively perform overload control. Compared with the above-mentioned solution of overload control through the border router, the technical solution provided by the embodiment of the present application controls the number of TCP connections corresponding to the tenant's IP address (the destination IP address), and no longer controls the number of connections by blocking the source IP address (the user's IP address), thereby reducing the impact on the user's business.

In the embodiment of the present application, the device for executing the above-mentioned overload control method is the service node of the OBS system shown in Figure 1. The scheduler can be a desktop computer, a portable computer, a personal digital assistant (PDA) and other devices, and the service node can also be one or more functional modules in the device, which can be either a component in a hardware device, or software running on dedicated hardware, or a combination of hardware and software. Optionally, the service node can be implemented by one device or multiple devices, and the embodiment of the present application does not specifically limit this.

Please refer to Figure 2 for an introduction to the hardware structure of the service node provided in the present application. The various components shown in Figure 2 may be implemented in hardware, software, or a combination of hardware and software including one or more signal processing and/or application-specific integrated circuits. As shown in Figure 2, the service node may include: a processor 201, a memory 202, and a communication interface 203. The processor 201, the memory 202, and the communication interface 203 may be connected via a bus 204, or may be connected to each other in other ways.

The processor 201 is the control center of the service node, and the processor 201 may be a general-purpose central processing unit (CPU) or other general-purpose processors, wherein the general-purpose processor may be a microprocessor or any conventional processor, etc. For example, the processor 201 may include an application processor (AP), a graphics processing unit (GPU), an image signal processor (ISP), a controller, etc.

The controller in the processor 201 is the nerve center and command center of the service node. The controller can generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. Optionally, a memory can also be set in the processor 201 to store instructions and data. Exemplarily, the processor 201 may include one or more CPUs, such as CPU 0 and CPU 1 shown in FIG. 2.

The memory 202 includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, or an optical memory, a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer. In the embodiment of the present application, the memory 202 can store information such as computer instructions.

In one possible implementation, the memory 202 may exist independently of the processor 201. The memory 202 may be connected to the processor 201 via the bus 204 and used to store data, instructions, or program codes. When the processor 201 calls and executes the instructions or program codes stored in the memory 202, the overload control method in the object storage service system provided in the embodiment of the present application can be implemented.

In another possible implementation, the memory 202 may also be integrated with the processor 201 .

The communication interface 203 may be a transceiver module for communicating with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (WLAN), etc. The communication interface 203 may receive instructions, messages, or data, etc. The transceiver module may be a device such as a transceiver or a transceiver. Optionally, the communication interface 203 may also be a transceiver circuit located in the processor 201, for realizing the signal input and signal output of the processor. The communication interface 203 may be a wired interface (port), such as a fiber distributed data interface (FDDI), a gigabit Ethernet (GE) interface, or the communication interface 203 may also be a wireless interface.

The bus 204 may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, FIG2 only uses one thick line, but does not mean that there is only one bus or one type of bus.

It should be noted that the service node shown in FIG. 2 is only an example of a service node, and the service node may have more or fewer components than those shown in FIG. 2 , may combine two or more components, or may have different component configurations.

The following describes an overload control method in an object storage service system provided by an embodiment of the present application with reference to the accompanying drawings. The method is applied to a service node in the object storage service system. The service node is bound to multiple IP addresses (the multiple IP addresses are virtual IP addresses), and each of the multiple IP addresses corresponds to one or more tenants. In the embodiment of the present application, the OBS system presents multiple IP addresses to the outside world. The multiple IP addresses are virtual IP addresses. The IP address is mounted on a single service node, that is, a service node is bound to multiple IP addresses. Moreover, each of the multiple IP addresses corresponds to one or more tenants, that is, multiple tenants are hashed on different IP addresses. For example, in Figure 3, tenants 1 and 2 correspond to IP address 1, tenants 3 and 4 correspond to IP address 2, ..., tenants 199 and 200 correspond to IP address 100.

As shown in FIG. 4 , the overload control method in the object storage service system provided in the embodiment of the present application may include the following steps:

S301: Receive an access request from a user device, where the access request includes a target IP address.

The above access request is used to request access to the target tenant's storage bucket (the storage bucket is a bucket created by the target tenant and contains objects). The target IP address in the access request is one of the multiple IP addresses bound to the service node.

It should be understood that the specific process of the service node receiving the access request from the user equipment includes S1-S3:

S1. The user device sends an access request to the domain name server, where the access request includes the domain name of the bucket of the target tenant.

The domain name of a bucket can be recorded as bucket1.region1.com, where bucket1 is the identifier of the bucket and region1 indicates the region where the bucket is located. The domain name of a bucket is unique, and each bucket corresponds to a tenant, so the domain name of the bucket also has tenant attributes.

S2. The domain name server sends the target IP address to the user device based on the domain name of the target tenant's bucket.

The domain name server stores the correspondence between the bucket identifier and the IP address. The domain name server can determine the target IP address corresponding to the bucket according to the domain name of the bucket of the target tenant in the access request, and then return the target IP address to the user device. It can be understood that the bucket in the OBS system can be accessed according to the target IP address.

S3. The user equipment sends an access request including the target IP address to the service node. Correspondingly, the service node receives the access request from the user equipment.

S302: Determine the number of TCP connections corresponding to the target IP address in the TCP full connection queue of the service node.

It can be understood that, usually, after the service node receives the access request of the user device, at the network transmission protocol layer, the service node enters the process of establishing a TCP connection, for example, establishing a TCP connection with the user device through a three-way handshake process. For the process of establishing a TCP connection, reference can be made to the prior art. After the service node completes the process of establishing a TCP connection, the service node places the TCP connection into a TCP full-connection queue maintained by the service node, and then the service node processes (or consumes) the access request corresponding to the TCP connection in the TCP full-connection queue at the application layer. In an embodiment of the present application, after the service node receives the access request of the user device, the service node does not directly enter the process of establishing a TCP connection, but first determines the number of TCP connections corresponding to the target IP address in the TCP full-connection queue in the service node based on the target IP address in the access request, and determines whether a connection number attack occurs based on the number of TCP connections.

S303: When the number of TCP connections corresponding to the target IP address is greater than a first preset threshold, discard the access request.

The above service node controls the number of connections corresponding to the target IP address at the network protocol transport layer. If the number of TCP connections corresponding to the target IP address is greater than the first preset threshold, it means that the number of TCP connections corresponding to the target IP is overloaded, so the service node discards the access request (also known as rejecting the access request) to alleviate the overload of the number of connections. For example, in conjunction with Figure 4 above, assuming that the target IP address is IP address 1, and IP address 1 corresponds to tenant 1 and tenant 2, if the number of TCP connections corresponding to IP address 1 is overloaded, it indicates that tenant 1 and/or tenant 2 are under attack by the number of connections.

The first preset threshold can be determined based on the TCP full connection queue capacity (queue capacity can also be called queue depth), and the first preset threshold does not need to be adjusted with the processing capacity of the application layer. Optionally, the TCP full connection queue capacity refers to the maximum number of TCP connections that the TCP full connection queue can accommodate. Optionally, the first preset threshold is one-half of the TCP full connection queue capacity. For example, the capacity of the TCP full connection queue can be 60,000, and the first preset threshold is 30,000.

In one implementation, the above S303 is specifically implemented through S3031.

S3031. A user-mode protocol stack based on the Intel data plane development kit (DPDK) discards an access request when the number of TCP connections corresponding to the target IP address is greater than a first preset threshold.

It can be understood that DPDK is a software library used to accelerate data packet processing. DPDK has efficient processing capabilities, and the user-mode protocol stack based on DPDK can efficiently control the number of connections overload.

S304: When the number of TCP connections corresponding to the target IP address is less than or equal to a first preset threshold, establish a TCP connection between the user equipment and the service node.

In an embodiment of the present application, if the number of TCP connections corresponding to the target IP address is less than or equal to the first preset threshold, it means that the number of TCP connections corresponding to the target IP is not overloaded, and the service node enters the TCP connection establishment process to establish a TCP connection between the user device and the service node, and places the TCP connection in the TCP full connection queue maintained by the service node, waiting for the application layer to process the access request corresponding to the TCP connection. For example, in conjunction with Figure 4 above, assuming that the target IP address is IP address 2, and IP address 2 corresponds to tenants 3 and 4, if the number of TCP connections corresponding to IP address 2 is not overloaded, it means that tenants 3 and 4 are not attacked by the number of connections, and the service node can process the access requests of tenants 3 and 4 normally.

In summary, when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold, the service node only discards the current access request containing the target IP address, and the service node will not discard the access request containing other IP addresses. In this way, the service node will not affect the services corresponding to other tenants during the process of controlling the number of connections overload. Exemplarily, referring to Figure 4, if the target IP address is IP address 1, when the number of TCP connections corresponding to IP address 1 is greater than the first preset threshold, the service node discards the access request for the storage bucket of tenant 1 and/or tenant 2, and the service node normally processes the access request for accessing the storage bucket of other tenants, such as the service node will normally process the service requests of tenants 3 to tenant 200, that is, in the process of controlling the number of TCP connections overload, the service node minimizes the impact range of the connection number attack to avoid affecting the tenants of the entire cluster, so that the tenants do not interfere with each other.

In combination with FIG. 4 , as shown in FIG. 5 , after the TCP connection between the user device and the service node is established, the overload control method in the object storage service system provided by the embodiment of the present application further includes:

S305: Determine whether the length of the access request queue corresponding to the storage bucket of the target tenant is greater than a second preset threshold.

S306: When the length of the access request queue is greater than a second preset threshold, refuse to process the access request.

S307: When the length of the access request queue is less than or equal to the second preset threshold, process the access request.

It should be noted that the above S305-S307 are actions performed by the service node at the application layer.

In the embodiment of the present application, for a tenant, each tenant corresponds to an access request queue, and the access request queue includes all access requests for which TCP connections have been established. After being processed by the above network transmission protocol layer, the service node receives the access request, establishes the TCP connection corresponding to the access request, and then processes the access request at the application layer.

For the target tenant, when the length of the access request queue corresponding to the storage bucket of the above target tenant is greater than the second preset threshold, it means that the target tenant is overloaded. At this time, the service node refuses to process the access request; when the length of the access request queue is less than or equal to the second preset threshold, it means that the target tenant is not overloaded. At this time, the service node processes the access request to ensure the service quality of the tenant.

Based on the above, the overload control method in the object storage system provided by the embodiment of the present application is that the service node receives an access request including a target IP address from a user device, the access request is used to request access to the storage bucket of the target tenant, the service node is bound to multiple IP addresses, each of the multiple IP addresses corresponds to one or more tenants, and the above target IP address is one of the above multiple IP addresses; then, the service node determines the number of TCP connections corresponding to the target IP address in the TCP full connection queue of the service node; and, when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold, the access request of the user device is discarded. Since each of the multiple IP addresses bound to the service node corresponds to one or more tenants, when the number of connections corresponding to the target IP address is overloaded, the service node discards the access request of the tenant corresponding to the target IP address, and the service node normally processes the access requests corresponding to other IP addresses, so that the impact range of the connection number attack can be effectively reduced to avoid affecting the tenants of the entire cluster.

Accordingly, an embodiment of the present application provides a service node. In an embodiment of the present application, the service node can be divided into functional modules according to the above method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

In the case of dividing each functional module according to each function, FIG6 shows a possible structural diagram of the service node involved in the above embodiment, and the service node is bound to multiple IP addresses, and each of the multiple IP addresses corresponds to one or more tenants. As shown in FIG6, the service node includes a receiving module 601, a determining module 602, and a processing module 603. Among them, the receiving module 601 is used to receive an access request from a user device, and the access request is used to request access to the storage bucket of the target tenant. The access request includes a target IP address, and the target IP address is one of the multiple IP addresses, for example, executing S301 in the above method embodiment. The determining module 602 is used to determine the number of TCP connections corresponding to the target IP address in the TCP full connection queue of the service node, for example, executing S302 in the above method embodiment. The processing module 603 is used to discard the access request when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold, for example, executing S303 in the above method embodiment.

Optionally, the processing module 603 is specifically used for discarding the access request based on the user-mode protocol stack of DPDK when the number of TCP connections corresponding to the target IP address is greater than a first preset threshold, such as executing S3031 in the above method embodiment. The processing module 603 is also used to establish a TCP connection between the user device and the service node when the number of TCP connections corresponding to the target IP address is less than or equal to the first preset threshold, such as executing S304 in the above method embodiment. The determination module 602 is also used to determine whether the length of the access request queue corresponding to the storage bucket of the target tenant is greater than a second preset threshold, such as executing S305 in the above method embodiment; the processing module 603 is also used to refuse to process the access request when the length of the access request queue is greater than the second preset threshold, and to process the access request when the length of the access request queue is less than or equal to the second preset threshold, such as executing S306-S307 in the above method embodiment.

The modules of the service node described above can also be used to perform other actions in the method embodiment described above. All relevant contents of the steps can be referred to the functional description of the corresponding functional modules and will not be repeated here.

In the case of adopting an integrated unit, FIG. 7 shows another possible structural diagram of the service node involved in the above embodiment. As shown in FIG. 7, the service node provided in the embodiment of the present application may include: a processing module 701 and a communication module 702. The processing module 701 can be used to control and manage the actions of the service node. For example, the processing module 701 can be used to support the service node to perform S302, S303 (including S3031), S304-S307 in the above method embodiment, and/or other processes for the technology described herein. The communication module 702 can be used to support the communication between the service node and other network entities, for example, to support the service node to communicate with a computing node. For example, the communication module 702 can be used to support the service node to perform S301 in the above method embodiment. Optionally, as shown in FIG. 7, the service node may also include a storage module 703 for storing computer instructions and data.

Wherein, the processing module 701 may be a processor or a controller (for example, the processor 201 as shown in FIG. 2 ), and the processor may also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 702 may be a communication interface (for example, the communication interface 203 as shown in FIG. 2 ). The storage module 703 may be a memory (for example, the memory 202 as shown in FIG. 2 ). When the processing module 701 is a processor, the communication module 702 is a communication interface, and the storage module 703 is a memory, the processor, the transceiver, and the memory may be connected via a bus.

For more details on how the modules included in the service node implement the above functions, please refer to the descriptions in the previous method embodiments, which will not be repeated here. Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments.

In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function in accordance with the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., floppy disks, magnetic disks, tapes), an optical medium (e.g., digital video discs (DVD)), or a semiconductor medium (e.g., solid state drives (SSD)), etc.

Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: flash memory, mobile hard disk, read-only memory, random access memory, disk or optical disk and other media that can store program codes.

The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (12)

An overload control method in an object storage service system, characterized in that it is applied to a service node in the object storage service system, the service node is bound to multiple IP addresses, each of the multiple IP addresses corresponds to one or more tenants, and the method includes: Receive an access request from a user device; wherein the access request is used to request access to a storage bucket of a target tenant, and the access request includes a target IP address, and the target IP address is one of the multiple IP addresses; Determine the number of TCP connections corresponding to the target IP address in the Transmission Control Protocol TCP full connection queue of the service node; When the number of TCP connections corresponding to the target IP address is greater than a first preset threshold, the access request is discarded. The method according to claim 1, characterized in that, when the number of TCP connections corresponding to the target IP address is greater than a first preset threshold, discarding the access request comprises: Based on the user mode protocol stack of the data plane development kit DPDK, when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold, the access request is discarded. The method according to claim 1 or 2, characterized in that the method further comprises: When the number of TCP connections corresponding to the target IP address is less than or equal to the first preset threshold, a TCP connection is established between the user equipment and the service node. The method according to claim 3, characterized in that after establishing a TCP connection between the user equipment and the service node, the method further comprises: Determine whether the length of the access request queue corresponding to the storage bucket of the target tenant is greater than a second preset threshold; If the length of the access request queue is greater than the second preset threshold, refusing to process the access request; When the length of the access request queue is less than or equal to the second preset threshold, the access request is processed. The method according to any one of claims 1 to 4, characterized in that The first preset threshold is half of the TCP full connection queue capacity. A service node, characterized in that the service node is bound to multiple IP addresses, each of the multiple IP addresses corresponds to one or more tenants, and the service node includes a receiving module, a determining module, and a processing module; The receiving module is used to receive an access request from a user device; wherein the access request is used to request access to a storage bucket of a target tenant, and the access request includes a target IP address, and the target IP address is one of the multiple IP addresses; The determining module is used to determine the number of TCP connections corresponding to the target IP address in the Transmission Control Protocol TCP full connection queue of the service node; The processing module is configured to discard the access request when the number of TCP connections corresponding to the target IP address is greater than a first preset threshold. The service node according to claim 6, characterized in that The processing module is specifically used to discard the access request based on the user mode protocol stack of the data plane development kit DPDK when the number of TCP connections corresponding to the target IP address is greater than the first preset threshold. The service node according to claim 6 or 7, characterized in that: The processing module is further configured to establish a TCP connection between the user equipment and the service node when the number of TCP connections corresponding to the target IP address is less than or equal to the first preset threshold. The service node according to claim 8, characterized in that The determination module is further configured to determine whether the length of the access request queue corresponding to the storage bucket of the target tenant is greater than a second preset threshold; The processing module is further configured to refuse to process the access request when the length of the access request queue is greater than the second preset threshold; and to process the access request when the length of the access request queue is less than or equal to the second preset threshold. The service node according to any one of claims 6 to 9, characterized in that: The first preset threshold is half of the TCP full connection queue capacity. A service node, characterized in that it comprises a memory and at least one processor connected to the memory, the memory is used to store computer program code, the computer program code comprises computer instructions, and when the computer instructions are executed by the at least one processor, the computing device executes the method according to any one of claims 1 to 5. A computer-readable storage medium, characterized in that computer instructions are stored therein, and when the computer instructions are run on a computer, the method according to any one of claims 1 to 5 is executed.