You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Sean McBride
fe35e90bb1
|
4 years ago | |
---|---|---|
.. | ||
.gitignore | 4 years ago | |
README.md | 4 years ago | |
debug.sh | 4 years ago | |
latency.gnuplot | 4 years ago | |
run.sh | 4 years ago | |
spec.json | 4 years ago | |
success.gnuplot | 4 years ago | |
throughput.gnuplot | 4 years ago |
README.md
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 theempty.so
test workload
To Execute
- Run
./run.sh
- View the results in the newest timestamped directory in
./res
To Debug
- Run
./debug.sh
in a tab - 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