From: Linus Torvalds <torvalds@osdl.org>
To: Andi Kleen <ak@suse.de>
Cc: Benjamin LaHaise <bcrl@kvack.org>,
Zachary Amsden <zach@vmware.com>,
Chuck Ebbert <76306.1226@compuserve.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [rfc patch] i386: don't save eflags on task switch
Date: Sun, 5 Nov 2006 09:20:12 -0800 (PST) [thread overview]
Message-ID: <Pine.LNX.4.64.0611050914030.25218@g5.osdl.org> (raw)
In-Reply-To: <200611051754.11982.ak@suse.de>
On Sun, 5 Nov 2006, Andi Kleen wrote:
>
> > - mispredicted branches on a P4 are potentially worse than
> > the popf cost.
>
> They are far less than 48 cycles. The P4 is not _that_ bad in this
> area.
You wanna bet? Use the newer P4 cores. A branch mispredict is over 20
cycles, and I bet the "sti" isn't cheap either.
In other words, I suspect the difference between "popfl" and "conditional
jump over sti" is basically zero - exactly because the sti isn't exactly a
no-op.
(Enabling interrupts is actually much more complex than you'd expect.
Interrupt delivery in a HT core is not simple in itself, and "sti" in many
ways is actually more complex than "popf", because it has the additional
"single-cycle interrupt shadow", ie the interrupt isn't actually enabled
after the sti, it's enabled after the _next_ instruction after the sti. So
from a uarch standpoint, "popf" is actually somewhat simpler.)
Anyway, what both you and Chuck seem to be missing is that trying to save
a couple of CPU cycles is NOT WORTH IT, if it makes the code harder and
more fragile. The "save eflags over context switch" that we do now is
_obvious_ code. That's worth a lot in itself. And the costs of context
switching isn't actually a couple of cycles - the real costs are all
elsewhere.
Linus
next prev parent reply other threads:[~2006-11-05 17:20 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-11-04 6:56 Chuck Ebbert
2006-11-04 19:09 ` Zachary Amsden
2006-11-04 19:35 ` Linus Torvalds
2006-11-05 3:55 ` Benjamin LaHaise
2006-11-05 4:13 ` Linus Torvalds
2006-11-05 5:41 ` Andi Kleen
2006-11-05 8:01 ` Zachary Amsden
2006-11-05 17:01 ` Andi Kleen
2006-11-05 17:26 ` Linus Torvalds
2006-11-05 17:34 ` Arjan van de Ven
2006-11-05 17:51 ` Linus Torvalds
2006-11-05 22:48 ` Zachary Amsden
2006-11-05 18:52 ` Andi Kleen
2006-11-05 16:12 ` Linus Torvalds
2006-11-05 16:54 ` Andi Kleen
2006-11-05 17:20 ` Linus Torvalds [this message]
2006-11-05 4:17 ` Zachary Amsden
2006-11-05 20:10 ` H. Peter Anvin
-- strict thread matches above, loose matches on Subject: below --
2006-11-04 0:00 Chuck Ebbert
2006-11-04 0:46 ` Linus Torvalds
2006-11-04 1:36 ` Andi Kleen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=Pine.LNX.4.64.0611050914030.25218@g5.osdl.org \
--to=torvalds@osdl.org \
--cc=76306.1226@compuserve.com \
--cc=ak@suse.de \
--cc=bcrl@kvack.org \
--cc=linux-kernel@vger.kernel.org \
--cc=zach@vmware.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®