A, QPS: Queries per Second
QPS: Queries Per Second means "query per second rate", is a server capable of the appropriate number of queries per second, is a measure of a particular query server within the specified time how much of the processing flow.
Internet, as the performance of the domain name system server machine is often used to measure queries per second rate.
Two, TPS: transactions per second
TPS: Transactions Per Second is the abbreviation, which is the number of transactions / second . It is the unit of measurement software test results. A transaction is the process of a client sends a request to the server and then the server to respond. The client requests the transmission start timing, end timing after receiving the server response, in order to calculate the time of use and the number of transactions completed.
QPS vs TPS: QPS substantially similar to the TPS, but the difference is that for the first visit to a page, form a TPS; but once the page request may result in multiple requests to the server, the server for these requests can be counted. " QPS "being. For example, to access a page server will request 2 times, once visited, resulting in a "T", produced two "Q".
Three, RT: Response time
Response time: the implementation of a request last received overall time it takes to respond to data from the beginning to that initiated the request to receive server response time results from the client.
Response Time RT (Response-time), is the most important indicator of a system that directly reflects the value of the size of the system speed.
Fourth, the number of concurrent
Is the number of concurrent refers to the number of simultaneous requests that the system can handle , this is the load capacity of the reaction system.
V. throughput
System throughput (pressure capacity) closely associated with the request CPU consumption, external interface, IO and so on. The higher the consumption of a single request to the CPU, the slower external system interface, the IO speed, the lower the system throughput, whereas higher.
System throughput several important parameters: QPS (TPS), concurrent, response time.
QPS (TPS) :( Query Per Second) per request / number of transactions
Concurrent: request system simultaneously processed / number of transactions
After generally the average response time to understand the meaning of the above three elements,: response time
Sixth, calculated relationship
QPS (TPS) = number of concurrent / average response time
Concurrent average response time = QPS *
Seven, the best: the number of threads, QPS, RT
1, single-threaded QPS formula: QPS = 1000ms / RT
For the same system, the more the number of threads supported by the higher QPS. RT is assumed that a 80ms, can be easily calculated from QPS, QPS = 1000/80 = 12.5 multithreaded scenario, if the number of threads to enhance the server 2, then the entire system was QPS 2 * (1000/80) = 25, with the increase of the thread visible QPS and linear growth, it can not go on QPS plus thread chant, sounds reasonable, the company also said that through, but the reality is often not the case.