Message 336685 - Python tracker

Message336685

Author	methane
Recipients	desbma, giampaolo.rodola, methane
Date	2019-02-26.15:38:20
SpamBayes Score	-1.0
Marked as misclassified	Yes
Message-id	<1551195500.37.0.566234475573.issue36103@roundup.psfhosted.org>
In-reply-to

Content
Read this file too. http://git.savannah.gnu.org/cgit/coreutils.git/tree/src/ioblksize.h coreutils choose 128KiB for minimal buffer size to reduce syscall overhead. In case of shutil, we have Python interpreter overhead adding to syscall overhead. Who has deeper insights than coreutils author? I think 128KiB is the best, but I'm OK to 64KiB for conservative decision.

Content

Read this file too.
http://git.savannah.gnu.org/cgit/coreutils.git/tree/src/ioblksize.h

coreutils choose 128KiB for *minimal* buffer size to reduce syscall overhead.
In case of shutil, we have Python interpreter overhead adding to syscall overhead.
Who has deeper insights than coreutils author?

I think 128KiB is the best, but I'm OK to 64KiB for conservative decision.

History
Date	User	Action	Args
2019-02-26 15:38:20	methane	set	recipients: + methane, giampaolo.rodola, desbma
2019-02-26 15:38:20	methane	set	messageid: <1551195500.37.0.566234475573.issue36103@roundup.psfhosted.org>
2019-02-26 15:38:20	methane	link	issue36103 messages
2019-02-26 15:38:20	methane	create