From fe35e90bb1ec522e89b235b888f4b5cbbfbdb391 Mon Sep 17 00:00:00 2001 From: Sean McBride Date: Sat, 3 Oct 2020 19:50:18 -0400 Subject: [PATCH] docs: add documentation for concurrency experiment --- runtime/experiments/concurrency/README.md | 36 +++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 runtime/experiments/concurrency/README.md diff --git a/runtime/experiments/concurrency/README.md b/runtime/experiments/concurrency/README.md new file mode 100644 index 0000000..2b89042 --- /dev/null +++ b/runtime/experiments/concurrency/README.md @@ -0,0 +1,36 @@ +# Concurrency + +## Question + +_How does increasing levels of concurrent client requests affect tail latency, throughput, and the success/error rate of sandbox execution?_ + +## Independent Variable + +- The number of concurrent client requests made at a given time + +## Dependent Variables + +- p50, p90, p99, and p100 latency measured in ms +- throughput measures in requests/second +- success rate, measures in % of requests that return a 200 + +## Assumptions about test environment + +- You have a modern bash shell. My Linux environment shows version 4.4.20(1)-release +- `hey` (https://github.com/rakyll/hey) is available in your PATH +- You have compiled `sledgert` and the `empty.so` test workload + +## To Execute + +1. Run `./run.sh` +2. View the results in the newest timestamped directory in `./res` + +## To Debug + +1. Run `./debug.sh` in a tab +2. Run `./run.sh -d` in a second tab + +## TODO + +- Harden scripts to validate assumptions +- Improve error handling in scripts. If `sledgrt` crashes, this charges forward until it hits a divide by error when attempting to clean data that doesn't exist