LoadRunner analysis graph and Data Type Translation

Transactions (User transaction analysis) User transaction analysis is a basic performance analysis from the user's perspective. 1. transation sunmmary (transaction summary) Comprehensive analysis of transactions is the first step in performance analysis. By analyzing the success and failure of user transactions during the test period, you can directly determine whether the system is running normally. 2. Average transaciton response time (average Transaction Response Time) The "average Transaction Response Time" shows the average transaction execution time per second during the test scenario. It can be used to analyze the performance trend of the application system during the test scenario. For example, as the test time changes, the transaction processing speed of the system gradually slows down. This shows that the overall performance of the application system will decrease as the production time changes. 3. transactions per second (number of transactions per second/TPS) The number of transactions per second/TPS is displayed every second of the scenario. The number of transactions that pass, fail, and stop makes the system performance an important parameter. It can be used to determine the transaction load of the system at any given time point. The analysis TPS mainly refers to the performance trend of the curve. Compare it with the average transaction response time to analyze the impact of the number of transactions on the execution time. For example, when the pressure increases, if the click rate/TPS curve changes slowly or has a flat trend, it is likely that the server begins to experience a bottleneck. 4. Total transactions per second (number of transactions passed per second) "Number of transactions passed per second" shows the total number of transactions passed in each second, the total number of failed transactions, and the total number of stopped transactions in the scenario. 5. Transaction performance sunmmary (transaction performance summary) The "transaction performance summary" shows the minimum, maximum, and average execution time of all transactions in the solution. It can directly determine whether the response time meets the user's requirements. Focus on the average and maximum execution time of transactions. If the scope is not within the acceptable time range, analyze the cause. 6. Transaction Response Time under load (Transaction Response Time and load) The "Transaction Response Time and load" is a combination of the "running Virtual users" diagram and the "Average Response transaction time" diagram, it can be seen from the relationship between the transaction response time and the number of users at any point in time, so as to master the performance data of the system in terms of user concurrency and provide a reference for expanding the user system. This figure shows the overall impact of virtual user load on execution time and is useful for analysis of test scenarios with gradient load. 7. Transaction Response Time (percentile) (Transaction Response Time (percentage )) The "transaction response time (percentage)" is a comprehensive analysis chart based on the test results, that is, a chart indirectly obtained by the tool through some statistical analysis methods. It can be used to analyze the percentage of transactions that can be executed within a given transaction response time range. 8. Transaction Response Time (distribution) (Transaction Response Time (distribution )) The "transaction response time (distribution)" shows the distribution of the time used for transaction execution during the scenario. It can be used to understand the number of transactions with different response times during the test. If the system pre-defines the minimum and maximum Transaction Response Time acceptable to the relevant transaction, you can use this figure to determine whether the server performance is within the acceptable range. Web Resources) Web Resource Analysis analyzes the performance of web servers from the perspective of servers. 1. hits per second (clicks per second) "Number of clicks per second", even if the number of HTTP requests that virtual users submit to the Web server per second during the running scenario. It can be used to evaluate the workload generated by virtual users. For example, you can compare it with the "average Transaction Response Time" graph to see the impact of the number of clicks on transaction performance. You can check the number of clicks per second to determine whether the system is stable. The decrease in the system click rate usually indicates that the server's response speed is slowing down. Further analysis is required to find out the bottleneck of the system. 2. throughput (throughput) The "throughput" shows the server throughput per second during the scenario. The measurement unit is byte, indicating the amount of data that is virtualized for any given second from the server. The workload generated by virtual users can be evaluated based on the server throughput, as well as the processing capacity of the server in terms of traffic and whether there are bottlenecks. Differences between the "throughput" and "click rate" charts: The "throughput" diagram shows the number of HTTP requests processed by the server per second. The "click rate" chart shows the total data volume that the client obtains from the server per second. 3. Http status code Summary (HTTP status code overview) The "HTTP status code overview" shows the number of HTTP status codes returned from the Web server during the scenario or session step. This figure is grouped by code. The HTTP status code indicates the status of the HTTP request. 4. HTTP responses per second (number of HTTP responses per second) "HTTP responses per second" shows the number of different HTTP status codes returned from the Web server per second during the running scenario. It also returns information about other status codes. By analyzing the status codes, you can determine the running status of the server under pressure, or you can group the results shown in the figure to locate the code scripts that generate errors. 5. Pages downloader per second (number of download pages per second) "Number of pages downloaded per second" shows the number of webpages downloaded from the server per second during the scenario or session step. Use this figure to calculate the load generated by the vuser based on the number of pages downloaded. Like the throughput chart, the number of page downloads per second icon is the volume of data that a vuser receives from the server within any given second. However, the throughput of each resource is extremely large (for example, the size of each GIF file and the size of each webpage ). The number of pages downloaded per second is only the number of pages. Note: To view the page views downloaded per second, you must set the number of pages per second (HTML mode only) in the R-T-S )". 6. retries per second (number of retries per second) "Number of retries per second" indicates the number of connections tried by the server in the scenario or session step. The server connection will be retried in the following cases: A. The initial connection is unauthorized. B. Proxy Server authentication is required C. The server closes the initial connection. D. The initial connection cannot connect to the server. E. The server cannot parse the IP address of the Server Load balancer. 7. retries Summary (Summary of retries) The "retry count summary" displays the number of connections tried by the server during the scenario or session step, which is grouped by the retry reason. Using this diagram with the number of retries per second graph can determine the time at which the server retries during the scenario or session step. 8. Connections (connections) "Connections" shows the number of TCP/IP connections opened at each time point during the scenario or session step. With this figure, you can know when to add other connections. For example, when the number of connections reaches a stable state and the transaction response time increases rapidly, adding a connection greatly improves the performance (the Transaction Response time decreases ). 9. Connections per second (number of connections per second) "Connections per second" shows the number of TCP/IP connections established per second during the running process. Ideally, many HTTP requests should use the same connection, instead of opening a new connection for each request. The number of connections per second graph shows the processing status of the server, indicating that the server performance is gradually decreasing. 10. SSLS per second (number of SSL connections per second) "Number of SSL connections per second" shows the number of new and re-used SSL connections opened per second during the scenario or session step. When a TCP/IP connection is enabled to the security server, the browser opens the SSL connection. Web page breakdown (page element segmentation) "Webpage element segmentation" is used to assess whether the page content affects the response time of transactions. It can be used to analyze problematic elements such as those on the website that download slow graphics or interrupt connections. 1. Web page breakdown (page breakdown overview) "Page breakdown" shows the response of a specific transaction in the test process, and then analyzes whether the related transaction runs normally. The page breakdown chart can be further subdivided in the following four ways: 1) download time breaddown (download time subdivision) The "download time subdivision" graph shows the download time of different elements on the web page. You can also split the time according to the download process, different colors are used to display the proportion of DNS resolution time, connection establishment time, and first buffer time. 2) component breakdown (over time) (Component subdivision (changed over time )) The "component segmentation" chart shows the page components of the selected webpage that change over time. The figure shows which elements have unstable download time during the test. This figure is especially suitable for pages with many controls to be downloaded from the client. By analyzing the response time of the control, it is easy to find the unstable or time-consuming controls. 3) download time breakdown (over time) (download time subdivision (changed with time )) The "download time subdivision (changed over time)" graph shows the page element download time subdivision (changed over time) of the selected page, it clearly shows the download of each element on the page during the stress test. The "download time subdivision" graph shows the time statistical analysis result of the element response on the entire test process page, and the "download time subdivision (changed over time) "displays the statistical results of page element response time in every second during the scenario running. The two analyze the download time of page elements from both the macro and micro perspectives. 4), time to first buffer breakdown (over time) (first buffer time subdivision (changed with time )) The "first buffer time segment (varies with time)" graph shows the time before the first buffer is successfully received from the web server, the server time and network time (in seconds) of each web page component in each second of a scenario or session step ). You can use this figure to determine the time when a server or network problem occurs during the scenario or session step. First buffer time: after the client establishes a connection with the server, the system starts timing when the server sends the first data packet. Data is transmitted to the client over the network, the time when the browser receives the first buffer. 2. Page component breakdown (page component subdivision) The "Page component subdivision" graph shows the average download time (in seconds) of each webpage and its components ). You can sort the chart columns based on the average number of seconds used to download the component. This helps isolate problematic components. 3. Page component breakdown (over time) (page Component Decomposition (changed over time )) The "Page Component Decomposition (changes with time)" chart shows the average response time (in seconds) of each webpage and its components during the running of the solution ). 4. page download time breakdown (page download time subdivision) The page download time breakdown graph shows the breakdown of the download time of each page component. You can determine whether the slow Transaction Response Time is caused by a network error or a server error during the download. The "page download time subdivision" Graph describes the DNS resolution time, connection time, first buffer time, SSL handshake time, receipt time, FTP verification time, client time, and error time for each component. the download process is subdivided. 5. page download time breakdown (over time) (page download time subdivision (changed over time )) The "page download time subdivision (changed with time)" graph shows the breakdown of the download time of each page component in each second during the running of the solution. Use this figure to determine the time point at which the network or server encountered a problem during the execution of the solution. The "Page component segmentation (change with time)" chart and the "page download time subdivision (change with time)" chart are usually combined for analysis: first, determine the problematic component, analyze the download process and locate the cause. 6. Time to first buffer breakdown (first buffer time subdivision) The "first buffer time subdivision" graph shows the server/network time of each page component before the first buffer is successfully received from the web server. If the component has been downloaded for a long time, you can use this figure to determine whether the problem is related to the server or the network. Network Time: the average time that begins at the moment of the first HTTP request until it is confirmed. Server time: it is defined as the average time from receiving the initial HTTP request confirmation until the Web server receives a buffer successfully. 7. Time to first buffer breakdown (over time) (first buffer time subdivision (changed with time )) The "first buffer time segment (varies with time)" graph shows the period before the first buffer is successfully received from the web server, the server time and network time of each web page component in each second of a scenario. You can use this figure to determine the time when a server or network problem occurs during the running of the scenario. 8. downloader component size (Kb) (size of downloaded components) The downloaded component size graph shows the size of each downloaded webpage. It can be seen which components are relatively large and need further optimization to improve performance.