Cal Paterson
Cal Paterson
I think "CPU core" is probably clearest in the first case? Googling, it seems that people sometimes use "hardware thread" to describe this concept but not sure that has popular...
Hi, I don't have good reason to think that Python was waiting for connections for very long (I'm using an external connection pooler, over a unix socket, and the query...
Hi, setting up all these benchmarks takes considerable time and I now consider it kind of done, so I'm not going to add any more frameworks and do it again....
Hi, thanks for taking the time to reproduce everything. I was surprised that so few people did that so you are one of the few - thanks for being interested...
Ok! I look forward to your blogpost!
Ah, I've just seen that you've already posted it. Thanks! Will have a look through when I get some time and perhaps continue the discussion here.
Hi Miguel. I'm sorry that I've only just gotten around to reading your article. I'm afraid I don't like it. One of the key bits of what I wrote was:...
> I just want people to be aware that the choices that you make can be used to make the test say whatever you want I think the problem for...
Are you getting at the fact that meinheld uses async io internally? This is true but I classified it as sync because it runs normal, sync Python (unlike Uvicorn that...
I'm am not able to replicate your results and I suspect the reason why is that you have the number of workers held too low for the gunicorn to operate...