#workload-generator #traffic

bin trawler

A workload generator that emulates the traffic to lobste.rs

26 releases

0.5.10 Apr 18, 2018
0.5.9 Apr 18, 2018
0.5.3 Mar 29, 2018
0.4.0 Mar 28, 2018
0.2.5 Mar 21, 2018

#7 in Profiling

Download history 32/week @ 2018-05-04 1/week @ 2018-05-11 26/week @ 2018-05-25 130/week @ 2018-06-01 1/week @ 2018-06-08 112/week @ 2018-06-15 29/week @ 2018-06-22 254/week @ 2018-06-29 303/week @ 2018-07-06 26/week @ 2018-07-13 78/week @ 2018-07-20 26/week @ 2018-07-27

197 downloads per month


Crates.io Documentation Build Status

This crate provides a workload generator that emulates the traffic to lobste.rs. It is a mostly open-loop benchmark similar to TailBench, but it also approximates the partly open-loop designed outlined in Open Versus Closed: A Cautionary Tale by having clients potentially issue more than one query per request.

The benchmarker has two main components: load generators and issuers. Load generators generate requests according to actual lobste.rs traffic patterns as reported in here, records the request time, and puts the request description into a queue. Issuers take requests from the queue and issues that request to the backend. When the backend responds, the issuer logs how long the request took to process, and how long the request took from when it was generated until it was satisfied (this is called the sojourn time).

Trawler is written so that it can either be run against an instance of the lobsters Rails app or directly against a backend by issuing queries. The former is done using the provided binary, whereas the latter is done by linking against this crate as a library an implementing the [LobstersClient] trait. The latter allows benchmarking a data storage backend without also incurring the overhead of the Rails frontend. Note that if you want to benchmark against the Rails application, you must apply the patches in lobsters.diff first.

MIT/Apache-2.0 license


  • build build.rs
  • build glob 0.2

Reverse deps