Method for testing concurrency property of cloud platform based on federated research

[0028] Specific embodiment one: the following combination figure 1 and figure 2 This embodiment will be described. The method for testing the concurrent performance of a cloud platform based on federated retrieval described in this embodiment is implemented based on the federated retrieval system constructed in the cloud platform environment. The federated retrieval system constructed in the cloud platform environment consists of From bottom to top, it includes physical resource layer, virtual resource layer, data access layer, external service layer, security link layer, business function layer and system presentation layer. The physical resource layer is implemented by physical resources in the cloud platform environment. It includes several servers, network devices and storage devices; the virtual resource layer is implemented by the cloud computing virtual resource pool in the cloud platform environment, and the cloud computing virtual resource pool is virtualized from the physical resources in the cloud platform environment; the data access layer, external The service layer, the security link layer and the business function layer are implemented by the software platform in the cloud platform environment;

[0029] This test method respectively tests the query transaction response time, the maximum number of concurrent users and the number of transactions per second of the query transaction of the cloud platform, and is used to evaluate the concurrent performance of the cloud platform. The details are as follows:

[0030] The test method for query transaction response time is: firstly, the load generating end initiates a retrieval request to the federated retrieval system constructed in the cloud platform environment, and records the initiation time t 1 , after receiving the retrieval request, the federated retrieval system performs corresponding calculations according to the request data of the load generating end, and then returns the calculation result as the retrieval result to the load generating end, and records the time t when the load generating end obtains the retrieval result 2 , calculate and obtain the current query transaction response time t 2 -t 1; Calculate the average value of the current query transaction response time within the preset time period, and use the average as the query transaction response time within the preset time period;

[0031] The test method for the maximum number of concurrent users is as follows: in the test scenario of the cloud platform, the number of concurrent users on the load-generating side is increased in a gradient manner, and m in each △t time period in turn, and the federated retrieval in the cloud platform environment is performed. The system initiates a stress test. During the test process after increasing the number of m concurrent users within the current △t time period, more than 5% of the keyword search transactions have a response time greater than 1s and continue for △t 1 △t 1 , then the number of all concurrent users in the current △t time period is taken as the maximum number of concurrent users of the cloud platform;

[0032]The test method for the number of transactions per second of query transactions is as follows: in the test scenario, the ratio of current keyword retrieval transactions to query transactions is 65%, and the number of current keyword retrieval transactions passed per second is counted as the number of query transactions per second.

[0033] In this embodiment, the overall architecture of the federated retrieval system is divided into seven levels, such as figure 1 As shown in the figure, the system presentation layer provides users with a unified retrieval entry. For this purpose, it is necessary to design a unified standard front-end interface for information retrieval and a retrieval result display page in a unified format; the business functions provided by the retrieval system for users mainly include information upload, federated Information retrieval, resource acquisition, resource download, etc. The access to the service layer uses the simple object access protocol SOAP of the secure link layer. The distributed retrieval Web service completes the retrieval of local index documents through the data access layer. Virtual machines and network infrastructure are located at the bottom layer, providing basic hardware support for the construction of the platform.

[0034] This embodiment builds a federated retrieval system in a cloud computing virtual environment, virtualizes traditional servers, pools existing computing resources, and integrates infrastructure resources, such as computing, memory, and disk, into virtual data The central resource pool enables users to request these resources on demand. It uses virtualization technology to virtualize a traditional single server into multiple virtual machines, but each virtual machine can independently provide services as a server.

[0035] The physical resource layer provides hardware resource support for the retrieval system. The cloud computing virtual resource pool includes virtual machines customized according to different needs. These virtual machines have the function of responding to traditional physical servers. The software platform can meet the needs of users for federated retrieval.

[0036] Definition of query transaction response time: This indicator refers to the time taken by a virtual user from initiating a query request to obtaining a query result, including the network communication time from the load generating end to the cloud computing platform. This indicator is used to evaluate the processing capability of the cloud computing platform to process query requests, and to evaluate the performance of the cloud computing platform under test from the perspective of response time.

[0037] Definition of the maximum number of concurrent users: This indicator performs stress testing on the cloud computing platform. When a certain percentage of query transactions have a response time greater than the predetermined indicator in the query transaction, the evaluation indicator is obtained. This indicator is used to evaluate the concurrency capability of the cloud computing platform.

[0038] Definition of the number of transactions per second for query transactions: This indicator represents the ability of the cloud computing platform under test to process query transactions. In the test scenario, the proportion of query transactions is certain. The transaction processing capability of the cloud computing platform under test is evaluated through statistics of this indicator.

[0039] In order to obtain the maximum performance of the cloud platform, the test is carried out by using multiple load simulation clients to access the cloud platform concurrently; at the same time, in order to avoid the limitation of the performance bottleneck of the test tool itself, a distributed data collection solution is used to build a load generation cluster, and Use Master-Slaves mode to manage the entire cluster. Namely: master-slave mode, that is: master controller-multiple load generators.

[0040] A corresponding test script should be created before the stress test, and all load-generating side Slaves execute the test script according to the corresponding rules. In the process of testing, the load generating end is responsible for collecting various test data during the test process, and after the test is over, it is sent to the master control computer Master, which analyzes and processes the test data, and obtains the final test result.

[0041] This test method is to evaluate the performance of the target cloud computing platform. The cloud computing platform manages the IT infrastructure by encapsulating the details of the underlying infrastructure, and realizes the service-oriented IT capabilities, which is the basis for the operation of cloud applications. As a typical application under the cloud computing platform, the federated retrieval system applies stress tests to the federated retrieval system and uses the above index system to measure the performance of the cloud computing platform.

[0042] Embodiment 2: This embodiment further describes Embodiment 1. The load generating end includes multiple load simulation clients, and the multiple load simulation clients exchange information with the cloud platform in a concurrent manner.

[0043] Specific embodiment three: the following combination figure 1 The present embodiment will be described, and the second embodiment will be further described in this embodiment. The processing method for the retrieval request by the federated retrieval system is as follows:

[0044] After the federated retrieval system receives the retrieval request, it first selects the retrieval service source from all the current data sources that can provide retrieval service according to the query keyword and retrieval data type of the retrieval request;

[0045] After invoking the Semantic Conflict Mediation Web Service to process the user's retrieval request, forward the retrieval request to the selected retrieval service source;

[0046] Each distributed retrieval Web service completes the information retrieval of a single node according to the local database and index documents, and returns part of the information of the retrieval results to the federated retrieval system;

[0047] The federated retrieval system sorts the result set returned by the distributed retrieval Web and displays it in a unified standard Web format.

[0048] The workflow of this embodiment is as follows: distributed heterogeneous data sources construct an inverted index for local data resources, publish it as a Web service, and complete service registration in the service management center. Specifically:

[0049] The user enters the query keyword, selects the retrieval data type, and selects the service source from all current data sources that can provide retrieval services; after calling the semantic conflict mediation Web service to process the user's query request, it forwards it to the retrieval service source specified by the user. ; Each distributed retrieval Web service completes the information retrieval of a single node based on the local database and index documents, and returns part of the retrieval result information; the platform sorts the result set returned by the distributed retrieval source and displays it in a unified standard Web format In front of the user; after the user clicks on a record of interest, the system obtains the detailed information of the corresponding record by calling the resource acquisition service; the user can preview this information online, or choose to download this information.