Knowledge Maxxing← Back to topic library
Dev MaxxingAdvancedPerformance75 sec
Throughput
Throughput is the total amount of work a system can complete in a given period, such as the number of requests it can handle per second.
Prerequisite: Latency
What matters
A system can have excellent latency for one request at a time but still have limited throughput, which becomes the bottleneck once many users arrive at once.
Example
A server that responds to a single request instantly might still only handle 100 requests per second total before it starts falling behind under heavier load.
Common misconception
Improving one request's latency does not automatically improve a system's overall throughput under heavy concurrent load; the two require different kinds of optimization.
Recall question
Why can a system with fast individual responses still struggle under many simultaneous users?
Keywords and related concepts
throughputcapacityperformancelatency