Eliminate the parallelization overhead when not needed

[xificurk]

The main target of this optimization is partial analysis run with a small number of files.

In my test runs with single file analyzed, it cuts down the total time almost in half (8.9 s -> 5.0 s).

Note this actually reverts commit 2159057 (Run the parallel worker even for a low number of files) - I am not sure, what the motivation has been then.

[phpstan-bot]

You've opened the pull request against the latest branch 2.2.x. PHPStan 2.2 is not going to be released for months. If your code is relevant on 2.1.x and you want it to be released sooner, please rebase your pull request and change its target to 2.1.x.

[ondrejmirtes]

The current code is important so that every analysis runs in a child worker. It means we will get a nice output even if the analysis in the worker crashes.

Addressing the root cause (the overhead you get for running a child worker) is really important here. It'd mean the analysis gets faster for everyone. Instead of working around it and run the analysis in the main thread. So if you're experiencing overhead, it'd be great to profile it with Blackfire or similar and make the code faster, or skip something that it doesn't have to do at all.

Again, to repeat my usual point, it's best to analyse the whole project instead of select files.

[xificurk]

Addressing the root cause (the overhead you get for running a child worker) is really important here. It'd mean the analysis gets faster for everyone. Instead of working around it and run the analysis in the main thread. So if you're experiencing overhead, it'd be great to profile it with Blackfire or similar and make the code faster, or skip something that it doesn't have to do at all.

I can try dig into this more, but the bottom line is that there will always be some cost for the orchestration of child workers - the subprocess management is not free and never will be. So, I wouldn't call this a workaround - when analyzing just a few files skipping the subprocess management falls exactly into the category "skip something that it doesn't have to do at all".

[xificurk]

@ondrejmirtes I did profile via SPX and the worker overhead comes almost all from the phpstan initialization - phar load, DI initialization...
That is why doing the analysis directly in the main process, instead of spinning up a worker, almost halfs the needed time - the bootup cost is paid only once, instead of twice.

[ondrejmirtes]

From your comment I understood this would take 4 seconds which seems weird to me and that something could definitely be cut there.

[ondrejmirtes]

Also - is this a graph of the worker process or the main process? My bet is on the worker process.

But the main process might be intersting too - maybe we can cut something from there. If we started to analyse small number of files in the main process, this optimization door would close.