News for hackers. Stuff that matters.

A comment on Memory efficiency of parallel IO operations in Python. Parent comment

Re:Memory efficiency of parallel IO operations in Python by dekhn on Tuesday March 13, 2018 @12:56PM (#16577572)
You're probably thinking of Linux's older thread system, LinuxThreads, which didn't scale at all. It was replaced with NPTL, which scales far better. I think also the kernel scheduler got much better.

I'm not aware of any system that manages millions of threads well- it's also not clear what the usecase for this would be.

[ Parent | on HN ]
Re:Memory efficiency of parallel IO operations in Python by akvadrako on Tuesday March 13, 2018 @01:04PM (#16577629)
I'm not thinking of LinuxThreads, but internally Linux still treats threads and processes as one. So each thread is assigned a PID.

As per the top post, millions of threads means there is no need to implement your own scheduling system with async IO, which can handle millions of idle connections.

[ Parent | on HN ]