headers
Raghu R. Arur | 1 Sep 2003 20:37

flushing tlb in try_to_swap_out

   I see that in try_to_swap_out() (linux 2.4.19), the page that is being
unmapped from a process is flushed out. But try_to_swap_out() is executed
in the context of kswapd. And also whenever a context switch takes place
the whole tlb is flushed out. So is this flushing done just becuase linux
uses lazy_tlb_flush during process context switch ?

 thanks a lot,
 Raghu
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo <at> kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart <at> kvack.org"> aart <at> kvack.org </a>
Permalink | Reply | 1 comment |
headers
Rik van Riel | 2 Sep 2003 04:13
Picon
Favicon

Re: flushing tlb in try_to_swap_out

On Mon, 1 Sep 2003, Raghu R. Arur wrote:

>    I see that in try_to_swap_out() (linux 2.4.19), the page that is being
> unmapped from a process is flushed out. But try_to_swap_out() is executed
> in the context of kswapd. And also whenever a context switch takes place
> the whole tlb is flushed out. So is this flushing done just becuase linux
> uses lazy_tlb_flush during process context switch ?

Think about SMP systems, where the task that's being swapped
out could be running simultaneously with the pageout code, on
another CPU.

--

-- 
"Debugging is twice as hard as writing the code in the first place.
Therefore, if you write the code as cleverly as possible, you are,
by definition, not smart enough to debug it." - Brian W. Kernighan

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo <at> kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart <at> kvack.org"> aart <at> kvack.org </a>
Permalink | Reply | 0 comments |
headers
Andrew Morton | 3 Sep 2003 08:18

2.6.0-test4-mm5

ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.0-test4/2.6.0-test4-mm5/

. Dropped out Con's CPU scheduler work, added Nick's.  This is to help us
  in evaluating the stability, efficacy and relative performance of Nick's
  work.

  We're looking for feedback on the subjective behaviour and on the usual
  server benchmarks please.

. Random other stuff.

Changes since 2.6.0-test4-mm4:

 linus.patch

 Latest from Linus

-handle-unreadable-dot-config.patch
-huge-net-update.patch
-disable-athlon-prefetch.patch
-sis900-atomicity-fix.patch
-x86_64-update-3.patch
-random-locking-fixes.patch
-random-accounting-and-sleeping-fixes.patch
-yenta-20030817-1-zv.patch
-yenta-20030817-2-override.patch
-yenta-20030817-3-sockinit.patch
-yenta-20030817-4-pm.patch
-yenta-20030817-5-pm2.patch
-yenta-20030817-6-init.patch
(Continue reading)

Permalink | Reply | 2 comments |
headers
Christian Axelsson | 3 Sep 2003 09:17
Picon
Gravatar

Re: 2.6.0-test4-mm5


How is the work on CPU scheduler selection coming along? It would be a
Good Thing (TM) to have in this one imho.

--
Christan Axelsson
smiler <at> lanil.mine.nu
Permalink | Reply | 0 comments |
headers
Raghu R. Arur | 3 Sep 2003 16:24

removing clean anonymous pages

 Hi,

   I see in try_to_swap_out() (linux 2.4.19), that when we remove a clean
anonymous page, we clear the pte entries. So when a page is swapped out to
the disk and then brought back to the memory. If that page is again
selected for removal during page replacement, then if we just clear the
pte entries wont we be losing the data. I think I have understood it
wrong. Can you please try to explain me this.

 Thanks,
 Raghu
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo <at> kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart <at> kvack.org"> aart <at> kvack.org </a>
Permalink | Reply | 0 comments |
headers
William Lee Irwin III | 3 Sep 2003 20:29

Re: 2.6.0-test4-mm5

On Wed, Sep 03, 2003 at 09:17:13AM +0200, Christian Axelsson wrote:
> How is the work on CPU scheduler selection coming along? It would be a
> Good Thing (TM) to have in this one imho.

No idea if anyone's doing it, but it should be relatively easy to do.

-- wli
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo <at> kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart <at> kvack.org"> aart <at> kvack.org </a>
Permalink | Reply | 0 comments |
headers
Sebastian Benoit | 4 Sep 2003 13:14
Picon

mm5 acpi compile error in pci_link.c:290


  CC      drivers/acpi/pci_link.o
drivers/acpi/pci_link.c: In function `acpi_pci_link_try_get_current':
drivers/acpi/pci_link.c:290: error: `_dbg' undeclared (first use in this
function)
drivers/acpi/pci_link.c:290: error: (Each undeclared identifier is reported
only once
drivers/acpi/pci_link.c:290: error: for each function it appears in.)
make[2]: *** [drivers/acpi/pci_link.o] Error 1
make[1]: *** [drivers/acpi] Error 2
make: *** [drivers] Error 2

from .config:

#
# ACPI (Advanced Configuration and Power Interface) Support
#
CONFIG_ACPI_HT=y
CONFIG_ACPI=y
CONFIG_ACPI_BOOT=y
CONFIG_ACPI_SLEEP=y
CONFIG_ACPI_SLEEP_PROC_FS=y
CONFIG_ACPI_AC=m
# CONFIG_ACPI_BATTERY is not set
CONFIG_ACPI_BUTTON=y
CONFIG_ACPI_FAN=y
CONFIG_ACPI_PROCESSOR=y
CONFIG_ACPI_THERMAL=y
# CONFIG_ACPI_ASUS is not set
# CONFIG_ACPI_TOSHIBA is not set
(Continue reading)

Permalink | Reply | 0 comments |
headers
Stephen Hemminger | 4 Sep 2003 21:21
X-Face

[PATCH] ikconfig cleanup

This applies after the ikconfig patch to gzip the config.

Simplify and cleanup the code:
	- use single interface to seq_file where possible
	- don't need to do as much of the /proc interface, only read
	- use copy_to_user to avoid char at a time copy
	- remove unneccesary globals
	- use const char[] rather than const char * where possible.

Didn't change the version since interface doesn't change.

diff -Nru a/kernel/configs.c b/kernel/configs.c
--- a/kernel/configs.c	Thu Sep  4 11:59:39 2003
+++ b/kernel/configs.c	Thu Sep  4 11:59:39 2003
 <at>  <at>  -27,6 +27,7  <at>  <at> 
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/compile.h>
 #include <linux/version.h>
 <at>  <at>  -46,112 +47,91  <at>  <at> 
 /**************************************************/
 /* globals and useful constants                   */

-static char *IKCONFIG_VERSION = "0.6";
-
-static struct proc_dir_entry *current_config, *build_info;
-
(Continue reading)

Permalink | Reply | 0 comments |
headers
Andrew Morton | 5 Sep 2003 10:59

2.6.0-test4-mm6


ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.0-test4/2.6.0-test4-mm6/

This is only faintly tested.  It's mainly a syncup with people..

. Initial support for kgdb-over-ethernet.  Mainly from Robert Walsh, based
  on work by San Mehat.

  It's pretty simple to use - read Documentation/i386/kgdb/kgdbeth.txt
  carefully.

  This uses the same ethernet driver hooks as netconsole, and is designed
  to work alongside netconsole.

  Currently it "supports" e100, eepro100, 3c59x, tlan and tulip.  Only e100
  has been tested.

. More preparation for the larger dev_t, from Al.

. Dropped out Nick's CPU scheduler changes, brought back Con's interactivity
  work.

  We didn't get many reports from this in -mm5.  I'd prefer to stick with
  Con's patches because they're tweaks, rather than fundamental changes and
  they have had more testing and are more widely understood.

  But the performance regressions with specjbb and volanomark are a
  problem.  We need to understand this and get it fixed up.

. The dev_t changes broke the feral driver.  The version in -mm is
(Continue reading)

Permalink | Reply | 0 comments |
headers
Michael Frank | 5 Sep 2003 11:32

Re: 2.6.0-test4-mm6

On Friday 05 September 2003 16:59, Andrew Morton wrote:
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.0-test4/2
>.6.0-test4-mm6/
>
>
> This is only faintly tested.  It's mainly a syncup with people..
>
> . Initial support for kgdb-over-ethernet.  Mainly from Robert Walsh, based
>   on work by San Mehat.
>
>   It's pretty simple to use - read Documentation/i386/kgdb/kgdbeth.txt
>   carefully.
>
>   This uses the same ethernet driver hooks as netconsole, and is designed
>   to work alongside netconsole.
>
>   Currently it "supports" e100, eepro100, 3c59x, tlan and tulip.  Only e100
>   has been tested.

This is cute, Nigel can then debug swsusp in 2.6 via the internet while I sleep...

Regards
Michael

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo <at> kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart <at> kvack.org"> aart <at> kvack.org </a>
(Continue reading)

Permalink | Reply | 0 comments |

Gmane