From 8361fefab79dd2355c5f990b70a256644b26ec8c Mon Sep 17 00:00:00 2001 From: Svyatoslav Date: Sun, 24 Dec 2023 13:31:11 +0300 Subject: [PATCH] Made better performance experiments --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f6e06f9..c55d5e0 100644 --- a/README.md +++ b/README.md @@ -259,7 +259,7 @@ and the approximate CPU usage by the container with the model for `concurrency = 1. The queue consumpts a lot of time compared to the model. 2. Increasing the models count from $1$ to $N$ for `concurrency == 5` results in - $\approx 150\% \cdot N$ CPU usage, $\approx 800 \cdot N$ throughput and dividing + $`\approx 150\% \cdot N`$ CPU usage, $`\approx 800 \cdot N`$ throughput and dividing queue's latency by some $k > 1$. #### Dynamic batching