Author benjamin.peterson
Recipients amaury.forgeotdarc, benjamin.peterson, neologix, pitrou, rosslagerwall
Date 2011-07-30.14:15:16
SpamBayes Score 7.2397e-05
Marked as misclassified No
Message-id <CAPZV6o_RU4vQ2qN2N1ZbggzSk_2bJ0G=Y5xDwS6K+MPa7xyP3w@mail.gmail.com>
In-reply-to <CAH_1eM0TMVODcCB71F1Waq69iCz7id=BY1RKEsSHWtN0tdj+Mg@mail.gmail.com>
Content
2011/7/30 Charles-Fran├žois Natali <report@bugs.python.org>:
>
> Charles-Fran├žois Natali <neologix@free.fr> added the comment:
>
>> I actually implemented this because I wanted to confine a Python process to a cpu to prevent keep it from being tossed from core to core. It made sense to bring the other scheduling functions along for the ride.
>
> Why didn't you use something like:
>
> $ taskset <cpu mask> python myscript.py

Because I didn't want to type that every time I ran the script.

>
> By the way, binding a multi-threaded Python process to a single core
> is often a simple way to improve performance, because with the GIL the
> threads are actually serialized, so you have almost no contention, and
> your threads get hot cache.

Indeed, that's what I was doing.
History
Date User Action Args
2011-07-30 14:15:17benjamin.petersonsetrecipients: + benjamin.peterson, amaury.forgeotdarc, pitrou, neologix, rosslagerwall
2011-07-30 14:15:17benjamin.petersonlinkissue12655 messages
2011-07-30 14:15:16benjamin.petersoncreate