Message 364469 - Python tracker

➜

This issue tracker has been migrated to GitHub , and is currently read-only.
For more information, see the GitHub FAQs in the Python's Developer Guide.

In-reply-to
Author	larry
Recipients	Mark.Shannon, eric.snow, jeremy.kloth, jkloth, larry, maciej.szulik, nanjekyejoannah, ncoghlan, phsilva, rhettinger, shihai1991, vstinner
Date	2020年03月17日.18:17:23
SpamBayes Score	-1.0
Marked as misclassified	Yes
Message-id	<1584469043.32.0.622554823246.issue39511@roundup.psfhosted.org>

Content
> The problem with having a single immortal `None`, is that it will > cause data cache thrashing as two different CPUs modify the > refcount on the shared `None` object. That's a very reasonable theory. Personally, I find modern CPU architecture bewildering and unpredictable. So I'd prefer it if somebody tests such performance claims, rather than simply asserting them and having that be the final design.

Content

> The problem with having a single immortal `None`, is that it will
> cause data cache thrashing as two different CPUs modify the
> refcount on the shared `None` object.
That's a very reasonable theory. Personally, I find modern CPU architecture bewildering and unpredictable. So I'd prefer it if somebody tests such performance claims, rather than simply asserting them and having that be the final design.

History
Date	User	Action	Args
2020年03月17日 18:17:23	larry	set	recipients: + larry, rhettinger, ncoghlan, vstinner, jkloth, phsilva, jeremy.kloth, Mark.Shannon, eric.snow, maciej.szulik, nanjekyejoannah, shihai1991
2020年03月17日 18:17:23	larry	set	messageid: <1584469043.32.0.622554823246.issue39511@roundup.psfhosted.org>
2020年03月17日 18:17:23	larry	link	issue39511 messages
2020年03月17日 18:17:23	larry	create

homepage