lkml.org 
[lkml]   [2010]   [Nov]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectRe: Free memory never fully used, swapping
Date
Hi

> On Tue, Nov 23, 2010 at 12:35:31AM -0800, Dave Hansen wrote:
>
> > I wish. :) The best thing to do is to watch stuff like /proc/vmstat
> > along with its friends like /proc/{buddy,meminfo,slabinfo}. Could you
> > post some samples of those with some indication of where the bad
> > behavior was seen?
> >
> > I've definitely seen swapping in the face of lots of free memory, but
> > only in cases where I was being a bit unfair about the numbers of
> > hugetlbfs pages I was trying to reserve.
>
> So, Dave and I spent quite some time today figuring out was going on
> here. Once load picked up during the day, kswapd actually never slept
> until late in the afternoon. During the evening now, it's still waking
> up in bursts, and still keeping way too much memory free:
>
> http://0x.ca/sim/ref/2.6.36/memory_tonight.png
>
> (NOTE: we did swapoff -a to keep /dev/sda from overloading)
>
> We have a much better idea on what is happening here, but more questions.
>
> This x86_64 box has 4 GB of RAM; zones are set up as follows:
>
> [ 0.000000] Zone PFN ranges:
> [ 0.000000] DMA 0x00000001 -> 0x00001000
> [ 0.000000] DMA32 0x00001000 -> 0x00100000
> [ 0.000000] Normal 0x00100000 -> 0x00130000
> ...
> [ 0.000000] On node 0 totalpages: 1047279
> [ 0.000000] DMA zone: 56 pages used for memmap
> [ 0.000000] DMA zone: 0 pages reserved
> [ 0.000000] DMA zone: 3943 pages, LIFO batch:0
> [ 0.000000] DMA32 zone: 14280 pages used for memmap
> [ 0.000000] DMA32 zone: 832392 pages, LIFO batch:31
> [ 0.000000] Normal zone: 2688 pages used for memmap
> [ 0.000000] Normal zone: 193920 pages, LIFO batch:31

This machine's zone size are

DMA32: 3250MB
NORMAL: 750MB

This inbalance zone size is one of root cause of the strange swapping
issue. I'm sure we certinally need to fix our VM heuristics. However
there is no perfect heuristics in the real world and we can't make it.
Also, I guess a bug reporter need practical workaround.

Then, I wrote following patch.

if you pass a following boot parameter, zone division change to
dma32=1G + normal=3G.

in grub.conf

kernel /boot/vmlinuz ro root=foobar .... zone_dma32_size=1G


I bet this one reduce your head pain a lot. Can you please try this?
Of cource, this is only workaround. not truth fix.


From 1446c915fd59a5f123c2619d1f1f3b4e1bd0c648 Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Thu, 23 Dec 2010 08:57:27 +0900
Subject: [PATCH] x86: implement zone_dma32_size boot parameter

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
---
Documentation/kernel-parameters.txt | 5 +++++
arch/x86/mm/init_64.c | 17 ++++++++++++++++-
2 files changed, 21 insertions(+), 1 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a5966c0..25b4a53 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2686,6 +2686,11 @@ and is between 256 and 4096 characters. It is defined in the file
Format:
<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

+ zone_dma32_size=nn[KMG] [KNL,BOOT,X86-64]
+ forces the dma32 zone to have an exact size of <nn>.
+ This works to reduce dma32 zone (In other word, to
+ increase normal zone) size.
+
______________________________________________________________________

TODO:
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 71a5929..12d813d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -95,6 +95,21 @@ static int __init nonx32_setup(char *str)
}
__setup("noexec32=", nonx32_setup);

+static unsigned long max_dma32_pfn = MAX_DMA32_PFN;
+static int __init parse_zone_dma32_size(char *arg)
+{
+ unsigned long dma32_pages;
+
+ if (!arg)
+ return -EINVAL;
+
+ dma32_pages = memparse(arg, &arg) >> PAGE_SHIFT;
+ max_dma32_pfn = min(MAX_DMA_PFN + dma32_pages, MAX_DMA32_PFN);
+
+ return 0;
+}
+early_param("zone_dma32_size", parse_zone_dma32_size);
+
/*
* When memory was added/removed make sure all the processes MM have
* suitable PGD entries in the local PGD level page.
@@ -625,7 +640,7 @@ void __init paging_init(void)

memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
- max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
+ max_zone_pfns[ZONE_DMA32] = max_dma32_pfn;
max_zone_pfns[ZONE_NORMAL] = max_pfn;

sparse_memory_present_with_active_regions(MAX_NUMNODES);
--
1.6.5.2





\
 
 \ /
  Last update: 2010-11-29 10:33    [W:0.070 / U:8.920 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site