haiwan
/
sledge
0
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity
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.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '86b1a274e9'
${ noResults }
sledge/runtime/experiments/concurrency/README.md

1.1 KiB
Raw Blame History

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