From: Arjan van de Ven <arjan@linux.intel.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: Dave Airlie <airlied@redhat.com>,
linux-kernel@vger.kernel.org, tglx@linutronix.de,
mingo@redhat.com, thomas@tungstengraphics.com
Subject: Re: [PATCH] x86: create array based interface to change page attribute
Date: Mon, 31 Mar 2008 02:56:42 -0700 [thread overview]
Message-ID: <47F0B55A.4000607@linux.intel.com> (raw)
In-Reply-To: <87myof8ief.fsf@basil.nowhere.org>
Andi Kleen wrote:
> Also it is doubtful clflush really makes sense on a large array. Just
> doing wbinvd might be faster then.
wbinvd is rarely a good idea; think about it... it'll flush 12Mb of cache *per socket* in one instruction.
(on a modern Intel consumer grade CPU, more on the enterprise ones)
This doesn't only impact the current logical thread, but ALL of the threads in the system, since the cache
coherency needs to be preserved, all have to go empty at the same time.
Forget real time... this can take really long even for non-realtime users ;)
At least clflush breaks this up into smaller pieces so total latency won't suck entirely.
next prev parent reply other threads:[~2008-03-31 9:57 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-03-31 5:19 [PATCH] x86: create array based interface to change page attribute Dave Airlie
2008-03-31 6:54 ` Thomas Hellström
2008-03-31 9:33 ` Arjan van de Ven
2008-03-31 11:04 ` Thomas Hellström
2008-03-31 7:25 ` Andi Kleen
2008-03-31 7:55 ` Thomas Hellström
2008-03-31 8:38 ` Andi Kleen
2008-03-31 9:06 ` Thomas Hellström
2008-03-31 9:18 ` Andi Kleen
2008-03-31 11:10 ` Thomas Hellström
2008-03-31 16:08 ` Arjan van de Ven
2008-03-31 16:41 ` Thomas Hellström
2008-03-31 16:49 ` Arjan van de Ven
2008-03-31 17:26 ` Thomas Hellström
2008-04-01 20:58 ` Arjan van de Ven
2008-04-01 21:29 ` Thomas Hellström
2008-04-01 22:30 ` Arjan van de Ven
2008-04-02 6:30 ` Thomas Hellström
2008-04-02 6:35 ` Arjan van de Ven
2008-04-02 6:59 ` Thomas Hellström
2008-04-02 14:01 ` Arjan van de Ven
2008-04-02 17:57 ` Thomas Hellström
2008-04-07 18:23 ` Jesse Barnes
2008-04-07 19:51 ` Thomas Hellström
2008-04-07 19:59 ` Jesse Barnes
2008-04-07 20:46 ` Thomas Hellström
2008-04-07 20:57 ` Arjan van de Ven
2008-04-08 6:12 ` Thomas Hellström
2008-04-07 21:04 ` Jesse Barnes
2008-04-08 6:21 ` Thomas Hellström
2008-04-08 14:27 ` Jesse Barnes
2008-04-07 20:56 ` Arjan van de Ven
2008-04-07 21:02 ` Jesse Barnes
2008-04-07 21:09 ` Jesse Barnes
2008-03-31 9:56 ` Arjan van de Ven [this message]
2008-03-31 11:21 ` Dave Airlie
2008-03-31 11:46 ` Andi Kleen
2008-04-02 1:35 ` Dave Airlie
2008-04-01 18:20 ` Arjan van de Ven
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=47F0B55A.4000607@linux.intel.com \
--to=arjan@linux.intel.com \
--cc=airlied@redhat.com \
--cc=andi@firstfloor.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=tglx@linutronix.de \
--cc=thomas@tungstengraphics.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