qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Anthony Liguori <anthony@codemonkey.ws>
To: Aurelien Jarno <aurelien@aurel32.net>
Cc: kwolf@redhat.com, Alexander Graf <agraf@suse.de>,
	hch@lst.de, Paul Brook <paul@codesourcery.com>,
	qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] Re: [PATCH] Add cache=volatile parameter to -drive
Date: Wed, 26 May 2010 09:19:35 -0500	[thread overview]
Message-ID: <4BFD2DF7.6020806@codemonkey.ws> (raw)
In-Reply-To: <4BFD2C57.4050606@aurel32.net>

On 05/26/2010 09:12 AM, Aurelien Jarno wrote:
>> It's hard for me to consider this a performance regression because
>> ultimately, you're getting greater than bare metal performance (because
>> of extremely aggressive caching).  It might be a regression from the
>> previous performance, but that was at the cost of safety.
>>      
> For people who don't care about safety it's still a regression. And it
> is a common usage of QEMU.
>    

It's not a functional change.  It's a change in performance.  There are 
tons of changes in performance characteristics of qemu from version to 
version.  It's not even a massive one.

>> We might get 100 bug reports about this "regression" but they concern
>> much less than 1 bug report of image corruption because of power
>> failure/host crash.  A reputation of being unsafe is very difficult to
>> get rid of and is something that I hear concerns about frequently.
>>
>> I'm not suggesting that the compile option should be disabled by default
>> upstream.  But the option should be there for distributions because I
>> hope that any enterprise distro disables it.
>>
>>      
> Which basically means those distro don't care about some use cases of
> QEMU, that were for most of them the original uses cases. It's sad.
>    

This isn't a feature.  This is a change in performance.  No one is not 
able to satisfy their use case from this behavior.

> Sometimes I really whishes that KVM never tried to reintegrate code into
> QEMU, it doesn't bring only good things.
>    

I highly doubt that this is even visible on benchmarks without using 
KVM.  The improvement on a microbenchmark was relatively small and the 
cost from TCG would almost certainly dwarf it.

Also, remember before KVM, we had single threaded IO and posix-aio 
(which is still single threaded).  If KVM never happened, block 
performance would be far, far worse than it is today with cache=writeback.

Regards,

Anthony Liguori

  reply	other threads:[~2010-05-26 14:19 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-05-17 10:14 [Qemu-devel] [PATCH] Add cache=volatile parameter to -drive Alexander Graf
2010-05-17 10:42 ` [Qemu-devel] " Kevin Wolf
2010-05-17 12:58 ` Anthony Liguori
2010-05-17 13:02   ` Alexander Graf
2010-05-17 13:09     ` Anthony Liguori
2010-05-17 13:17       ` Alexander Graf
2010-05-17 13:26         ` Anthony Liguori
2010-05-17 14:04           ` Alexander Graf
2010-05-17 14:22             ` Alexander Graf
2010-05-17 15:16             ` Anthony Liguori
2010-05-17 16:23               ` Paul Brook
2010-05-17 16:26                 ` Anthony Liguori
2010-05-17 16:28                   ` Alexander Graf
2010-05-17 20:07                     ` Jamie Lokier
2010-05-18  7:42                       ` Kevin Wolf
2010-05-25 17:59                   ` Alexander Graf
2010-05-25 18:48                     ` Anthony Liguori
2010-05-25 19:01                       ` Alexander Graf
2010-05-26 13:09                       ` Avi Kivity
2010-05-25 21:01                     ` Aurelien Jarno
2010-05-26  1:31                       ` Anthony Liguori
2010-05-26  8:43                         ` Kevin Wolf
2010-05-26 13:42                           ` Anthony Liguori
2010-05-26 14:03                             ` Kevin Wolf
2010-05-26 14:08                               ` Anthony Liguori
2010-05-26 14:26                                 ` Kevin Wolf
2010-05-26 14:13                               ` Aurelien Jarno
2010-05-26  8:52                         ` Aurelien Jarno
2010-05-26  9:16                           ` Kevin Wolf
2010-05-26 13:48                           ` Anthony Liguori
2010-05-26 14:12                             ` Aurelien Jarno
2010-05-26 14:19                               ` Anthony Liguori [this message]
2010-05-26 15:40                                 ` Aurelien Jarno
2010-05-26 16:11                                   ` Anthony Liguori
2010-05-26 14:27                             ` Paolo Bonzini
2010-05-26 13:06   ` Avi Kivity
2010-05-26 13:50     ` Anthony Liguori
2010-05-26 15:13       ` Avi Kivity
2010-05-17 15:11 ` Anthony Liguori

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=4BFD2DF7.6020806@codemonkey.ws \
    --to=anthony@codemonkey.ws \
    --cc=agraf@suse.de \
    --cc=aurelien@aurel32.net \
    --cc=hch@lst.de \
    --cc=kwolf@redhat.com \
    --cc=paul@codesourcery.com \
    --cc=qemu-devel@nongnu.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;
as well as URLs for NNTP newsgroup(s).