FlameGraph VS autocannon

We'll use async-profiler and flame graphs for profiling. To simplify the process, we'll run the code using JBang.

And flame graphs excel and this kind of thing

https://www.brendangregg.com/flamegraphs.html

which can output in a format understood by Brendan Gregg's flame frames (https://www.brendangregg.com/flamegraphs.html)

But that's not quite the kind of tracing you're talking about. We also built a printf-style interface to our recording files, which seems closer:

Strategies included discontinuing or resizing underutilized services, transitioning to more cost-effective solutions, reducing the current resources to the amount of resources that we need for our application, and conducting detailed analyses of computing resource utilization through tools like flamegraphs. This detailed scrutiny helped identify and rectify significant cost-driving areas, such as garbage collection and application configurations.

Flame Graphs by Brendan Gregg

Historically brendangregg's since AIUI he basically invented flamegraphs

https://www.brendangregg.com/flamegraphs.html

So if you can make your tool eat whatever https://github.com/brendangregg/FlameGraph is fed with you're going to support a lot of existing tooling across OSes and languages.

“Flame graphs are a visualization of hierarchical data, created to visualize stack traces of profiled software so that the most frequent code-paths to be identified quickly and accurately.”

SVGs are amazing for interactive visualisation too. Like Flamegraphs: https://www.brendangregg.com/flamegraphs.html

This may be a good example of the application of a flame graph but it is not a good demonstration of flame graphs; the graph is nearly incidental. The source has an actual explanation.

A profiling flame graph from Graphile Crystal (a precursor to Grafast) using GraphQL.js' executor (each tick is 1ms, total: 29ms). As we removed more and more responsibilities from GraphQL.js, we ended up only using it for output. Replacing this final responsibility with a custom implementation in Graphile Crystal itself, we reduced execution time for this query down to 15.5ms (effectively removing the majority of the yellow portion of the flame graph).

Autocannon GitHub Repository

To make things interesting, let’s send some requests to this server with autocannon:

Using autocannon, I did the following script to simulate 500 concurrent connections over 30 seconds:

We then used autocannon to measure the throughput (requests per second) of each runtime server-rendering our React app.

You could also use tools like autocannon to see how many requests/second you can achieve with various methods. : https://github.com/mcollina/autocannon

I used autocannon to test the function at 100 concurrent executions for 30 seconds. I also used Lambda Power Tuning to find the ideal memory configuration, which proved to be 512MB. All the results are available.

Moreover, if your blocking issue is appearing only on heavy load, you can easily test it using the very nice --autocannon CLI param (see it with clinic flame --help) where you can specificy autocannon options to generate some HTTP load on your web service.

I packaged them both with Docker and deployed them to an EC2 instance, each behind an Nginx reverse proxy I setup in docker-compose. I'm currently testing performance using autocannon from my laptop like this: `autocannon -a 5000 -w 10 URL` (5000 requests with 10 workers), and both apps complete in around 40 seconds. The EC2 instance is in Oregon and I'm testing from Toronto.

You can test it by yourself using console.time(). You can use autocannon to stress-test your http server to see what is really the best options.

When I test this with autocannon making three simultaneous requests (autocannon --connections 3 --amount 3 --timeout 10000 --no-progress http://localhost:5678/):