From: Andrea Arcangeli <andrea@suse.de>
To: Andrew Morton <akpm@osdl.org>
Cc: wli@holomorphy.com, nickpiggin@yahoo.com.au, tiwai@suse.de,
ak@suse.de, ak@muc.de, tripperda@nvidia.com, discuss@x86-64.org,
linux-kernel@vger.kernel.org
Subject: Re: [discuss] Re: 32-bit dma allocations on 64-bit platforms
Date: Fri, 25 Jun 2004 01:09:19 +0200 [thread overview]
Message-ID: <20040624230919.GB30687@dualathlon.random> (raw)
In-Reply-To: <20040624151130.4a444973.akpm@osdl.org>
On Thu, Jun 24, 2004 at 03:11:30PM -0700, Andrew Morton wrote:
> After setting lower_zone_protection to 10:
>
> Active:111515 inactive:65009 dirty:116 writeback:0 unstable:0 free:3290 slab:75489 mapped:52247 pagetables:446
> DMA free:4172kB min:16kB low:32kB high:48kB active:0kB inactive:0kB present:16384kB
> protections[]: 8 5156 5860
> Normal free:8736kB min:936kB low:1872kB high:2808kB active:352780kB inactive:224972kB present:901120kB
> protections[]: 0 468 1172
> HighMem free:252kB min:128kB low:256kB high:384kB active:93280kB inactive:35064kB present:130516kB
> protections[]: 0 0 64
>
> It's a bit complex, and perhaps the relative levels of the various
> thresholds could be tightened up.
this is the algorithm I added to 2.4 to produce good protection levels (with
lower_zone_reserve_ratio supposedly tunable at boot time):
static int lower_zone_reserve_ratio[MAX_NR_ZONES-1] = { 256, 32 };
zone->watermarks[j].min = mask;
zone->watermarks[j].low = mask*2;
zone->watermarks[j].high = mask*3;
/* now set the watermarks of the lower zones in the "j" classzone */
for (idx = j-1; idx >= 0; idx--) {
zone_t * lower_zone = pgdat->node_zones + idx;
unsigned long lower_zone_reserve;
if (!lower_zone->size)
continue;
mask = lower_zone->watermarks[idx].min;
lower_zone->watermarks[j].min = mask;
lower_zone->watermarks[j].low = mask*2;
lower_zone->watermarks[j].high = mask*3;
/* now the brainer part */
lower_zone_reserve = realsize / lower_zone_reserve_ratio[idx];
lower_zone->watermarks[j].min += lower_zone_reserve;
lower_zone->watermarks[j].low += lower_zone_reserve;
lower_zone->watermarks[j].high += lower_zone_reserve;
realsize += lower_zone->realsize;
}
Your code must be inferior since it doesn't even allow to tune each zone
differently (you seems not to have a lower_zone_reserve_ratio[idx]). Not sure
why you dont' simply forward port the code from 2.4 instead of reinventing it.
next prev parent reply other threads:[~2004-06-24 23:09 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <m3acyu6pwd.fsf@averell.firstfloor.org>
[not found] ` <20040623213643.GB32456@hygelac>
2004-06-23 23:46 ` 32-bit dma allocations on 64-bit platforms Andi Kleen
2004-06-24 11:13 ` Takashi Iwai
2004-06-24 11:29 ` [discuss] " Andi Kleen
2004-06-24 14:36 ` Takashi Iwai
2004-06-24 14:42 ` Andi Kleen
2004-06-24 14:58 ` Takashi Iwai
2004-06-24 15:29 ` Andrea Arcangeli
2004-06-24 15:48 ` Nick Piggin
2004-06-24 16:52 ` Andrea Arcangeli
2004-06-24 16:56 ` William Lee Irwin III
2004-06-24 17:32 ` Andrea Arcangeli
2004-06-24 17:38 ` William Lee Irwin III
2004-06-24 18:02 ` Andrea Arcangeli
2004-06-24 18:13 ` William Lee Irwin III
2004-06-24 18:27 ` Andrea Arcangeli
2004-06-24 18:50 ` William Lee Irwin III
2004-06-24 21:54 ` Andrew Morton
2004-06-24 22:08 ` William Lee Irwin III
2004-06-24 22:45 ` Andrea Arcangeli
2004-06-24 22:51 ` William Lee Irwin III
2004-06-24 23:09 ` Andrew Morton
2004-06-24 23:15 ` William Lee Irwin III
2004-06-25 6:16 ` William Lee Irwin III
2004-06-25 2:39 ` Andrea Arcangeli
2004-06-25 2:47 ` Andrew Morton
2004-06-25 3:19 ` Andrea Arcangeli
2004-06-24 22:11 ` Andrew Morton
2004-06-24 23:09 ` Andrea Arcangeli [this message]
2004-06-25 1:17 ` Nick Piggin
2004-06-25 3:11 ` Andrea Arcangeli
2004-06-24 22:21 ` Andrea Arcangeli
2004-06-24 22:36 ` Andrew Morton
2004-06-24 23:15 ` Andrea Arcangeli
2004-06-24 22:37 ` William Lee Irwin III
2004-06-24 22:40 ` William Lee Irwin III
2004-06-24 23:21 ` Andrea Arcangeli
2004-06-24 23:45 ` William Lee Irwin III
2004-06-24 17:39 ` Andrea Arcangeli
2004-06-24 17:53 ` William Lee Irwin III
2004-06-24 18:07 ` Andrea Arcangeli
2004-06-24 18:29 ` William Lee Irwin III
2004-06-24 16:04 ` Takashi Iwai
2004-06-24 17:16 ` Andrea Arcangeli
2004-06-24 18:33 ` Takashi Iwai
2004-06-24 18:44 ` Andrea Arcangeli
2004-06-25 15:50 ` Takashi Iwai
2004-06-25 17:30 ` Andrea Arcangeli
2004-06-25 17:39 ` Takashi Iwai
2004-06-25 17:45 ` Andrea Arcangeli
2004-06-24 14:45 ` Terence Ripperda
2004-06-24 15:41 ` Andrea Arcangeli
2004-06-24 15:44 ` Terence Ripperda
2004-06-24 16:15 ` [discuss] " Andi Kleen
2004-06-24 17:22 ` Andrea Arcangeli
2004-06-24 22:28 ` Terence Ripperda
2004-06-24 18:51 ` Andi Kleen
2004-06-26 4:58 ` David Mosberger
2004-06-24 13:48 Jesse Barnes
2004-06-24 14:39 ` Terence Ripperda
2004-06-24 15:01 ` [discuss] " 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=20040624230919.GB30687@dualathlon.random \
--to=andrea@suse.de \
--cc=ak@muc.de \
--cc=ak@suse.de \
--cc=akpm@osdl.org \
--cc=discuss@x86-64.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=tiwai@suse.de \
--cc=tripperda@nvidia.com \
--cc=wli@holomorphy.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.