Comments on Majek's technical blog: GNU pth instead of pthread: hardcore python tuning...

> I was browsing the Python source to
> s...

2008-08-30T12:01:00.000+02:00

> I was browsing the Python source to
> see if system call mapping is
> enabled, because if it isn't then
> any I/O will block the entire
> process.

I only tried to avoid the futex() overhead. I never really thought about wrapping read(). But it's

So I know this post is old, but I am very intrigue...

2008-08-30T04:28:00.000+02:00

So I know this post is old, but I am very intrigued by this idea. Seems like a big win for Python and a very logical choice.

I was browsing the Python source to see if system call mapping is enabled, because if it isn't then any I/O will block the entire process.

It doesn't

Didn't worked for me either.

2007-10-23T18:52:00.000+02:00

Didn't worked for me either.

LD_PRELOAD didn't worked ;)

2007-10-23T17:52:00.000+02:00

LD_PRELOAD didn't worked ;)

you might try something like this:
LD_PRELOAD=/...

2007-10-23T14:04:00.000+02:00

you might try something like this:
LD_PRELOAD=/path/to/pth.so ./single_threaded_python_script.py
Since the api is supposed to be the same, it should be possible to substitute libraries at startup-time

Comments on Majek's technical blog: GNU pth instead of pthread: hardcore python tuning...

> I was browsing the Python source to> s...

So I know this post is old, but I am very intrigue...

Didn't worked for me either.

LD_PRELOAD didn't worked ;)

you might try something like this:LD_PRELOAD=/...

> I was browsing the Python source to
> s...

you might try something like this:
LD_PRELOAD=/...