Latency

What is Latency?

Latency refers to the delay or waiting time (time lag) that happens when a request or operation is initiated within an application and when a response is received. It is the time taken for data to travel from the source to the destination, including any processing time in between.

Monitoring latency helps ensure that a system or service responds quickly and doesn't keep users waiting, which is especially crucial for applications where real-time updates matter, like online gaming, online transactions, etc.

What is the p99 latency metric?

When measuring latency, the p99 refers to the 99th percentile of the latency metric. For instance, if a service is required to have a P99 latency of 100 milliseconds, it means that atleast 99% of the requests need to be completed in 100 milliseconds or less, but 1% of requests may take longer than 100 milliseconds.