public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Andi Kleen <ak@muc.de>
To: Andrew Morton <akpm@osdl.org>
Cc: linux-kernel@vger.kernel.org
Subject: Re: Fw: potential /dev/urandom scalability improvement
Date: Sat, 27 Mar 2004 02:29:12 +0100	[thread overview]
Message-ID: <m3fzbvqdqv.fsf@averell.firstfloor.org> (raw)
In-Reply-To: <1E4IT-7f3-21@gated-at.bofh.it> (Andrew Morton's message of "Fri, 26 Mar 2004 20:00:15 +0100")

Andrew Morton <akpm@osdl.org> writes:
>
> I think this gets it right, but I probably screwed something up.
>
> static inline void prefetch_range(void *addr, size_t len)
> {
> #ifdef ARCH_HAS_PREFETCH
> 	char *cp;
> 	unsigned long end;
>
> 	end = ((unsigned long)addr + len + PREFETCH_STRIDE - 1);
> 	end &= ~(PREFETCH_STRIDE - 1);
>
> 	for (cp = addr; cp < (char *)end; cp += PREFETCH_STRIDE)
> 		prefetch(cp);
> #endif
> }

The memory/bus controller usually only has a limited queue of
outstanding transactions and for a big buffer you will likely overflow
it. Also usually on modern CPUs it is enough to do prefetch for 2-3
cache lines at the beginning, then an automatic hardware prefetcher
will kick in and take care of the rest.

-Andi


       reply	other threads:[~2004-03-27  6:11 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <1DLZM-8aK-67@gated-at.bofh.it>
     [not found] ` <1DLZM-8aK-65@gated-at.bofh.it>
     [not found]   ` <1DOE1-20o-17@gated-at.bofh.it>
     [not found]     ` <1DOXn-2k7-5@gated-at.bofh.it>
     [not found]       ` <1DXxI-Z7-39@gated-at.bofh.it>
     [not found]         ` <1E467-6KK-17@gated-at.bofh.it>
     [not found]           ` <1E4IT-7f3-21@gated-at.bofh.it>
2004-03-27  1:29             ` Andi Kleen [this message]
2004-03-27 15:48               ` Fw: potential /dev/urandom scalability improvement Matt Mackall
     [not found] <20040325141923.7080c6f0.akpm@osdl.org>
2004-03-25 22:47 ` Matt Mackall
2004-03-26  1:45   ` David Mosberger
2004-03-26  2:00     ` Andrew Morton
2004-03-26  2:10       ` David Mosberger
2004-03-26  4:07       ` Matt Mackall
2004-03-26  4:19       ` Matt Mackall
2004-03-26  4:51         ` David Mosberger
2004-03-26  5:15           ` Matt Mackall
2004-03-26  5:24             ` David Mosberger
2004-03-26 11:06       ` Dave Jones
2004-03-26 18:08         ` David Mosberger
2004-03-26 18:23           ` Dave Jones
2004-03-26 21:31             ` David Mosberger
2004-03-26 18:49           ` Andrew Morton
2004-03-26 20:25             ` David Mosberger
2004-03-26 20:33               ` Andrew Morton
2004-03-26 20:45                 ` Arjan van de Ven
2004-03-26 21:17                   ` Andrew Morton
2004-03-27  7:44                     ` Arjan van de Ven
2004-03-26 21:12                 ` David Mosberger

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=m3fzbvqdqv.fsf@averell.firstfloor.org \
    --to=ak@muc.de \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.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