From: Anton Altaparmakov <aia21@cus.cam.ac.uk>
To: torvalds@transmeta.com
Cc: linux-kernel@vger.kernel.org, will_dyson@pobox.com
Subject: [PATCH] 2.4.14-pre7 Missing disk req queue unplugs
Date: Sat, 3 Nov 2001 15:30:32 +0000 (GMT) [thread overview]
Message-ID: <E1602ki-0001Uw-00@draco.cus.cam.ac.uk> (raw)
Linus,
Please apply below patch for your next -pre kernel.
This patch adds two disk request queue unplugs in mm/filemap.c which are
present in -ac kernels but not in -pre kernels.
Without this patch NTFS TNG will hang when it tries to read anything using
the page cache. Same for BeFS as reported by Will Dyson. The hangs would
"unhang" as soon as something else caused disk io to happen (e.g. doing
md5sum on an ext2 partition on a file that hasn't been accessed before
so it isn't in the page cache yet).
With this patch NTFS TNG no longer hangs. I haven't tried BeFS but I am
confident it will be fixed by this patch, too.
Thanks go to Andrew Morton for locating the problem causing the hangs.
Best regards,
Anton
--
Anton Altaparmakov <aia21 at cam.ac.uk> (replace at with @)
Linux NTFS maintainer / WWW: http://linux-ntfs.sf.net/
ICQ: 8561279 / WWW: http://www-stu.christs.cam.ac.uk/~aia21/
--- linux-2.4.14-pre7-unplug.diff ---
diff -u -urN linux-2.4.14-pre7-vanilla/mm/filemap.c linux-2.4.14-pre7-aia1/mm/filemap.c
--- linux-2.4.14-pre7-vanilla/mm/filemap.c Sat Nov 3 12:17:55 2001
+++ linux-2.4.14-pre7-aia1/mm/filemap.c Sat Nov 3 15:18:22 2001
@@ -769,6 +769,7 @@
if (!PageLocked(page))
break;
sync_page(page);
+ run_task_queue(&tq_disk);
schedule();
} while (PageLocked(page));
tsk->state = TASK_RUNNING;
@@ -800,7 +801,9 @@
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
if (PageLocked(page)) {
sync_page(page);
+ run_task_queue(&tq_disk);
schedule();
+ continue;
}
if (!TryLockPage(page))
break;
next reply other threads:[~2001-11-03 15:30 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-11-03 15:30 Anton Altaparmakov [this message]
2001-11-03 22:09 ` Anton Altaparmakov
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=E1602ki-0001Uw-00@draco.cus.cam.ac.uk \
--to=aia21@cus.cam.ac.uk \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@transmeta.com \
--cc=will_dyson@pobox.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 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®