From: Chuck Ebbert <76306.1226@compuserve.com>
To: Chris Friesen <cfriesen@nortelnetworks.com>
Cc: linux-kernel <linux-kernel@vger.kernel.org>,
Chris Ross <chris@tebibyte.org>,
Alan Cox <alan@lxorguk.ukuu.org.uk>
Subject: Re: Linux 2.6.9-ac16
Date: Tue, 21 Dec 2004 18:49:13 -0500 [thread overview]
Message-ID: <200412211850_MC3-1-916E-59A6@compuserve.com> (raw)
Chuck Ebbert wrote:
> I backported this patch to 2.6.9 but haven't tested it yet. It requires the
> 'spurious oomkill' patch I posted earlier in this thread. Early reports
> are that it stops the freezes during heavy paging.
OK here's one that actually compiles. (3AM was not a good time to be
making patches.)
# mm_swap_token_disable.patch
# include/linux/swap.h -0 +1
# mm/rmap.c -0 +3
# mm/thrash.c -1 +4
#
# NOTE: On 2.6.9 there is no sysctl to change
# swap_token_default_timeout.
#
# Based on a patch by Con Kolivas for 2.6.10
# Backported to 2.6.9 by Chuck Ebbert <76306.1226@compuserve.com>
#
--- 2.6.9.1/include/linux/swap.h
+++ 2.6.9.2/include/linux/swap.h
@@ -230,6 +230,7 @@
/* linux/mm/thrash.c */
extern struct mm_struct * swap_token_mm;
+extern unsigned long swap_token_default_timeout;
extern void grab_swap_token(void);
extern void __put_swap_token(struct mm_struct *);
--- 2.6.9.1/mm/rmap.c
+++ 2.6.9.2/mm/rmap.c
@@ -394,6 +394,9 @@ int page_referenced(struct page *page, i
{
int referenced = 0;
+ if (!swap_token_default_timeout)
+ ignore_token = 1;
+
if (page_test_and_clear_young(page))
referenced++;
--- 2.6.9.1/mm/thrash.c
+++ 2.6.9.2/mm/thrash.c
@@ -19,7 +19,11 @@ unsigned long swap_token_check;
struct mm_struct * swap_token_mm = &init_mm;
#define SWAP_TOKEN_CHECK_INTERVAL (HZ * 2)
-#define SWAP_TOKEN_TIMEOUT (HZ * 300)
+#define SWAP_TOKEN_TIMEOUT 0
+/*
+ * Currently disabled; Needs further code to work at HZ * 300.
+ */
+unsigned long swap_token_default_timeout = SWAP_TOKEN_TIMEOUT;
/*
* Take the token away if the process had no page faults
_
--
Please take it as a sign of my infinite respect for you,
that I insist on you doing all the work.
-- Rusty Russell
next reply other threads:[~2004-12-21 23:51 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-12-21 23:49 Chuck Ebbert [this message]
2004-12-21 23:58 ` Nick Piggin
2004-12-22 2:49 ` Con Kolivas
-- strict thread matches above, loose matches on Subject: below --
2004-12-22 6:44 Chuck Ebbert
2004-12-21 9:11 Chuck Ebbert
2004-12-17 23:35 Chuck Ebbert
2004-12-20 17:27 ` Chris Friesen
2004-12-16 18:43 Alan Cox
2004-12-17 11:23 ` Arjan van de Ven
2004-12-17 18:54 ` Francois Romieu
2004-12-17 13:08 ` Chris Ross
2004-12-17 14:51 ` Chris Friesen
2004-12-17 15:45 ` Chris Ross
2004-12-18 6:01 ` Thomas Gleixner
2004-12-18 15:11 ` Bill Davidsen
2004-12-18 15:06 ` Jan Engelhardt
2004-12-18 16:01 ` Chris Ross
2004-12-20 14:48 ` Alan Cox
2004-12-20 16:19 ` Chris Ross
2004-12-20 19:54 ` Alan Cox
2004-12-19 16:22 ` Thomas Gleixner
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=200412211850_MC3-1-916E-59A6@compuserve.com \
--to=76306.1226@compuserve.com \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=cfriesen@nortelnetworks.com \
--cc=chris@tebibyte.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
all inboxes | Powered by JetHome®