From: Dor Laor <dor.laor-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: Ingo Molnar <mingo-X9Un+BFzKDI@public.gmane.org>
Cc: kvm-devel
<kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org>,
Linux Kernel Mailing List
<linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Re: Performance overhead of get_cycles_sync
Date: Tue, 11 Dec 2007 16:14:39 +0200 [thread overview]
Message-ID: <475E9B4F.2090008@qumranet.com> (raw)
In-Reply-To: <20071211133738.GA8150-X9Un+BFzKDI@public.gmane.org>
Ingo Molnar wrote:
>
> * Dor Laor <dor.laor-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:
>
> > Hi Ingo, Thomas,
> >
> > In the latest kernel (2.6.24-rc3) I noticed a drastic performance
> > decrease for KVM networking. The reason is many vmexit (exit reason is
> > cpuid instruction) caused by calls to gettimeofday that uses tsc
> > sourceclock. read_tsc calls get_cycles_sync which might call cpuid in
> > order to serialize the cpu.
> >
> > Can you explain why the cpu needs to be serialized for every gettime
> > call? Do we need to be that accurate? (It will also slightly improve
> > physical hosts). I believe you have a reason and the answer is yes. In
> > that case can you replace the serializing instruction with an
> > instruction that does not trigger vmexit? Maybe use 'ltr' for example?
>
> hm, where exactly does it call CPUID?
>
> Ingo
>
Here, commented out [include/asm-x86/tsc.h]:
/* Like get_cycles, but make sure the CPU is synchronized. */
static __always_inline cycles_t get_cycles_sync(void)
{
unsigned long long ret;
unsigned eax, edx;
/*
* Use RDTSCP if possible; it is guaranteed to be synchronous
* and doesn't cause a VMEXIT on Hypervisors
*/
alternative_io(ASM_NOP3, ".byte 0x0f,0x01,0xf9", X86_FEATURE_RDTSCP,
ASM_OUTPUT2("=a" (eax), "=d" (edx)),
"a" (0U), "d" (0U) : "ecx", "memory");
ret = (((unsigned long long)edx) << 32) | ((unsigned long long)eax);
if (ret)
return ret;
/*
* Don't do an additional sync on CPUs where we know
* RDTSC is already synchronous:
*/
// alternative_io("cpuid", ASM_NOP2, X86_FEATURE_SYNC_RDTSC,
// "=a" (eax), "0" (1) : "ebx","ecx","edx","memory");
rdtscll(ret);
return ret;
}
-------------------------------------------------------------------------
SF.Net email is sponsored by:
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://sourceforge.net/services/buy/index.php
prev parent reply other threads:[~2007-12-11 14:14 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-11 13:11 Performance overhead of get_cycles_sync Dor Laor
2007-12-11 13:37 ` Ingo Molnar
[not found] ` <20071211133738.GA8150-X9Un+BFzKDI@public.gmane.org>
2007-12-11 14:11 ` Dor Laor
[not found] ` <475E9A92.4030001-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-12-11 14:27 ` Ingo Molnar
[not found] ` <20071211142717.GA15903-X9Un+BFzKDI@public.gmane.org>
2007-12-11 15:03 ` Dor Laor
2007-12-11 21:26 ` Joerg Roedel
[not found] ` <20071211212628.GB6537-5C7GfCeVMHo@public.gmane.org>
2007-12-12 0:19 ` Dor Laor
2007-12-11 16:35 ` Arjan van de Ven
[not found] ` <20071211083513.56c2a385-NIQFrBLA1CpScpXdPBN83iCwEArCW2h5@public.gmane.org>
2007-12-11 17:03 ` Ingo Molnar
[not found] ` <p73abohno0u.fsf@bingen.suse.de>
[not found] ` <20071211201930.GB22397@elte.hu>
[not found] ` <20071211201930.GB22397-X9Un+BFzKDI@public.gmane.org>
2007-12-11 20:29 ` Ingo Molnar
2007-12-11 14:14 ` Dor Laor [this message]
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=475E9B4F.2090008@qumranet.com \
--to=dor.laor-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
--cc=dor.laor-atKUWr5tajBWk0Htik3J/w@public.gmane.org \
--cc=kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=mingo-X9Un+BFzKDI@public.gmane.org \
/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